magentlab

Apgar score from five 0-2 newborn signs (appearance, pulse, grimace, activity, respiration). Deterministic published score with citation; not a diagnosis.

Convert a glucocorticoid milligram dose among hydrocortisone, prednisone, and dexamethasone using Meikle 1977 equivalent doses (20 : 5 : 0.75). Not a taper, stress-dose protocol, or regimen recommendation; mineralocorticoid activity is not converted. Deterministic published table with citation.

CDC 2022 morphine milligram equivalents from a published opioid key and dose (mg/day, or mcg/hr for fentanyl_transdermal). Estimates only; do not use MME to convert one opioid to another. Not a taper protocol or OUD dosing tool.

4Ts score (Lo 2006) for heparin-induced thrombocytopenia pretest probability. Four caller-assigned integers 0-2 (thrombocytopenia, timing, thrombosis, other causes) using the published table; magent sums only (max 8). Bands 0-3 low, 4-5 intermediate, and 6-8 high pretest probability. Not a diagnosis of HIT, not the HEP score, and not an antibody result. magent does not grade platelet counts or day of onset.

Absolute neutrophil count from WBC and neutrophil plus band percents. Bodey 1966 granulocyte bands. Deterministic published arithmetic with citation; not a diagnosis.

Kothari 1996 ABC/2 ellipsoid ICH volume: (a_cm × b_cm × c_cm) / 2, rounded to one decimal milliliter. A is the largest diameter, B the perpendicular diameter, and C slice count times thickness; the caller supplies all three in cm. Volume estimate only; not the ICH Score. magent does not read imaging or choose A/B/C on the scan. Not a diagnosis.

Hemphill 2001 ICH Score from caller-assigned GCS, age, infratentorial origin, ICH volume (mL), and IVH; max 6. GCS 3-4 scores 2, 5-12 scores 1, 13-15 scores 0; age ≥80, volume ≥30 mL, infratentorial origin, and IVH score 1 each. Deterministic published score with citation; not a diagnosis or withdrawal-of-care protocol. magent does not read CT. Not FUNC and not ICH-GS.

ABCD2 (Johnston 2007) early stroke-risk score after TIA from age, blood pressure, caller-assigned clinical features, symptom duration, and diabetes (max 7). Bands 0-3, 4-5, and 6-7. Deterministic published score with citation; not a diagnosis or admit protocol. magent does not examine the patient. Not ABCD (Rothwell 2005) and not ABCD3-I.

Glasgow Coma Scale from eye, verbal, and motor integers. edition=1974 (motor 1-5, max 14) or edition=1976 (motor 1-6, max 15) is required; magent does not pick one. Deterministic published score with citation; not a diagnosis.

Ottawa SAH Rule (Perry 2013 JAMA). Investigate when any of six findings is present: age 40 or older, neck pain or stiffness, witnessed loss of consciousness, onset during exertion, thunderclap headache (instantly peaking pain), or limited neck flexion on examination. Not a diagnosis of SAH, not Hunt-Hess, and not Fisher grade. For alert, neurologically intact adults with nontraumatic headache peaking within 1 hour as published. magent does not examine the neck.

New Orleans Head CT Rule (Haydel 2000). CT is indicated if any of seven findings: headache, vomiting, age over 60, drug or alcohol intoxication, short-term memory deficit (anterograde amnesia), physical evidence of trauma above the clavicles, or seizure. Published for GCS 15 minor head injury in adults; magent does not take GCS or examine the patient. Not a diagnosis, not the Canadian CT Head Rule, not PECARN, and not pediatric.

PECARN pediatric head CT (Kuppermann 2009). Two age trees (under 2 vs 2-17). High if any age-applicable high-risk factor (GCS <=14 or altered mental status in both; palpable skull fracture if under 2; signs of basilar skull fracture if 2 or older), else intermediate if any age-applicable intermediate factor, else low. CT recommended only when high. Not a diagnosis. Not Canadian CT Head, CATCH, CHALICE, NEXUS, or PECARN IAI/febrile/c-spine. magent does not examine the patient.

Canadian CT Head Rule (Stiell 2001). CT is indicated if any high-risk factor (GCS <15 at 2 hours, suspected open or depressed skull fracture, any sign of basal skull fracture, vomiting 2 or more times, or age 65 or older) or any medium-risk factor (amnesia before impact >30 min, or dangerous mechanism as assigned by the caller). Not a diagnosis, not NEXUS, not PECARN, not CATCH, and not pediatric. magent does not examine the patient.

Canadian C-spine rule (Stiell 2001). Cervical radiography is indicated if any high-risk factor is present (age ≥65, dangerous mechanism, or paresthesias in the extremities). If none, radiography is indicated unless at least one low-risk factor allows safe range-of-motion assessment and the patient can rotate the neck 45° left and right. Not a diagnosis, not NEXUS, and not pediatric. For alert, stable blunt-trauma adults with GCS 15. magent does not examine the neck.

NEXUS C-spine rule (Hoffman 2000). The patient is NEXUS low-risk, and imaging is not indicated by this rule, only when all five hold: no posterior midline cervical-spine tenderness, no focal neurologic deficit, normal alertness, no intoxication, and no painful distracting injury. Any failed criterion means x-ray is indicated. Not a diagnosis, not the Canadian C-spine rule, and not NEXUS chest. Blunt-trauma adults as published. magent does not examine the patient.

Ottawa knee rule (Stiell 1995). Knee x-ray is indicated when any of: age 55 or older, bone tenderness at the fibular head, isolated patellar tenderness (caller-applied), inability to flex to 90 degrees, or inability to bear weight both immediately after injury and in the emergency department (four steps). One weight-bearing failure alone is not enough. Not a diagnosis of fracture, not the Ottawa ankle or foot rule, and not the Pittsburgh knee rule. magent does not examine the knee.

Ottawa ankle rule (Stiell 1992). Ankle x-ray is indicated when there is malleolar-zone pain and any of: bone tenderness at the posterior edge or tip of the lateral or medial malleolus, or inability to bear weight both immediately after injury and in the emergency department (four steps). One weight-bearing failure alone is not enough. Not a diagnosis of fracture, not the Ottawa foot rule, and not the Pittsburgh knee rule. magent does not examine the ankle.

San Francisco Syncope Rule (CHESS) from history of CHF, hematocrit, abnormal ECG, shortness of breath, and systolic BP. Returns a 0-5 criterion count and rule-positive if any CHESS item is present. Deterministic published score with citation; not a disposition protocol.

SIRS from Bone 1992 ACCP/SCCM: four binary criteria (temperature >38 or <36 °C, heart rate >90, respiratory rate >20 or PaCO2 <32 mm Hg, WBC >12000 or <4000 per µL or bands >10%); present when ≥2 of 4. Deterministic published criteria with citation; not a diagnosis, not Sepsis-3, not qSOFA or SOFA.

Khorana 2008 Blood predictive model for chemotherapy-associated thrombosis: very_high site (stomach or pancreas) 2, high (lung, lymphoma, gynecologic, bladder, testicular) 1, other 0; platelets >=350 1; hemoglobin <10 g/dL or ESA 1 (once); WBC >11 x10^9/L 1; BMI>=35 caller flag 1. Max 6. 0 low; 1-2 intermediate; >=3 high. Not a diagnosis. Not Padua or Caprini. Caller assigns cancer site; magent does not compute BMI.

Barbar 2010 Padua Prediction Score for hospitalized medical patients: cancer 3, previous VTE 3, reduced mobility 3, thrombophilia 3, recent trauma/surgery 2, age >=70 1, heart/respiratory failure 1, acute MI/stroke 1, infection/rheumatologic 1, obesity (BMI>=30) 1, hormonal treatment 1. Max 20. <4 low; >=4 high. Not a diagnosis. Not Caprini, IMPROVE, or Khorana.

Revised Geneva score (Le Gal 2006) for suspected PE in the emergency department: age >65 (1), previous DVT or PE (3), surgery or lower-limb fracture within 1 month (2), active malignancy (2), unilateral lower-limb pain (3), hemoptysis (2), heart rate 75-94 (3) or >=95 (5), pain on deep-vein palpation and unilateral edema (4). Max 22. Bands 0-3, 4-10, and 11-22. Not a diagnosis, not simplified Geneva, and not Wells.

Hestia criteria (Zondag 2011). Outpatient PE is eligible only when none of 11 caller-assigned exclusions hold: hemodynamic instability, thrombolysis or embolectomy, high bleeding risk, oxygen >24 h, PE on anticoagulation, IV pain medication >24 h, medical or social admission, CrCl <30, severe liver impairment, pregnancy, or documented HIT. Any yes excludes home treatment. Not a diagnosis, not PESI, not sPESI.

PESI (Pulmonary Embolism Severity Index) from Aujesky 2005: age in years plus male sex (+10), cancer (+30), heart failure (+10), chronic lung disease (+10), heart rate >=110 (+20), SBP <100 mm Hg (+30), respiratory rate >=30 (+20), temperature <36 C (+20), altered mental status (+60), and SpO2 <90% (+20). Classes I (<=65) through V (>125). Only for already diagnosed PE. Not a diagnosis, not an outpatient protocol, not sPESI, and not the 17-variable laboratory model.

sPESI (simplified Pulmonary Embolism Severity Index) from Jiménez 2010: 1 point each for age >80, cancer, chronic cardiopulmonary disease (one combined item), heart rate ≥110, systolic BP <100 mm Hg, and SpO2 <90%; max 6. Score 0 is low risk; ≥1 is high risk. Only for already diagnosed acute PE as in the paper. Not a diagnosis, not an outpatient-treatment protocol, and not original PESI classes.

Alvarado 1986 MANTRELS score from caller-assigned findings, temperature, WBC, and neutrophil percent (max 10). Bands 0-4, 5-6, and 7-10. Deterministic published score with citation; not a diagnosis or operating-room protocol. magent does not examine the abdomen.

qSOFA from Seymour 2016: respiratory rate ≥22, caller-assigned altered mentation, and systolic BP ≤100 mm Hg; 1 point each, max 3. Deterministic published score with citation; not a diagnosis of sepsis.

SOFA (Sepsis-related Organ Failure Assessment) from Vincent 1996 Table 3: six organs 0-4, max 24, from PaO2/FiO2 with a ventilation gate, platelets, bilirubin, MAP and adrenergic agents, caller-assigned GCS, and creatinine or urine output. Deterministic published score with citation; not a Sepsis-3 diagnosis.

Age-adjusted D-dimer cutoff (Righini 2014 ADJUST-PE). PE excluded only when D-dimer (ng/mL FEU) is strictly below 500 if age <50 or age×10 if age ≥50. Equality is not excluded. FEU only, not DDU; magent does not convert units. Not a diagnosis, not YEARS, not Wells.

YEARS algorithm (van der Hulle 2017 Lancet). Count three caller-assigned items (clinical signs of DVT, hemoptysis, PE most likely) and exclude PE only when D-dimer (ng/mL FEU) is strictly below 1000 with 0 items or 500 with 1-3 items. Equality is not excluded. Not a diagnosis, not Wells, not PERC. magent does not decide PE most likely. The 2017 cohort excluded pregnancy.

Eight-factor pulmonary embolism rule-out criteria (Kline 2004). PERC-negative only when all eight hold: age <50, pulse <100, SaO2 >94%, and no unilateral leg swelling, hemoptysis, recent trauma or surgery, prior PE or DVT, or hormone use. Caller must already have low pretest probability as in the paper. Not a diagnosis, not a D-dimer protocol, and not altitude-adjusted PERC.

Centor or McIsaac (age-modified) score for streptococcal pharyngitis from four caller-assigned findings. edition=centor (max 4) or edition=mcisaac (age 3-14 +1, 15-44 0, >=45 -1, max 5) is required; magent does not pick one. Deterministic published score with citation; not a test-or-treat protocol.

Wells deep-vein thrombosis probability from discrete clinical flags. Returns three-tier and two-tier bands. Deterministic published score with citation; not a diagnosis.

Wells pulmonary-embolism probability from discrete clinical flags. Returns three-tier and two-tier bands. Deterministic published score with citation; not a diagnosis.

Lim 2003 CRB-65 for community-acquired pneumonia: confusion, respiratory rate ≥30/min, low blood pressure (SBP <90 or DBP ≤60), and age ≥65; 1 point each, max 4. No urea. Score only; no mortality percentages or site-of-care bands. Not a diagnosis. Not CURB-65. Caller assigns the C, R, and B flags; magent does not convert BUN or take BP numbers.

CURB-65 pneumonia severity from age and discrete clinical flags. Deterministic published score with citation; not a treatment recommendation.

Heart-rate-corrected QT (Bazett or Fridericia). formula is required; magent does not pick one silently. Deterministic published correction with citation.

Friedewald estimated LDL-C from total cholesterol, HDL, and triglycerides. One unit system (mg/dL or mmol/L). Deterministic published equation with citation; not a diagnosis or statin order.

Eherer–Fordtran 1992 fecal osmotic gap: stool osmolality minus 2×(stool Na + stool K). Assumed stool osm 290 mOsm/kg when measured osm is omitted. Deterministic published arithmetic with citation; not a diagnosis of osmotic versus secretory diarrhea.

Serum anion gap from sodium, chloride, and bicarbonate, with or without potassium. formula=without_k or formula=with_k is required; magent does not pick one. Deterministic Emmett–Narins 1977 arithmetic with citation. Not a diagnosis, albumin-corrected gap (Figge/Fencl), or delta gap.

Winters' formula for expected PCO2 in metabolic acidosis: 1.5 × bicarbonate + 8 mm Hg, with a published ±2 mm Hg range. Optional comparison of measured PaCO2 to that band. Deterministic Albert–Winters 1967 arithmetic with citation; not a treatment target or a metabolic alkalosis formula.

Free water deficit from weight, sex, and measured Na using Adrogué–Madias TBW (0.6 male / 0.5 female). Deterministic published arithmetic with citation; not a water-replacement infusion protocol.

Sodium deficit from weight, sex, and measured Na using Adrogué–Madias TBW (0.6 male / 0.5 female). Deterministic published arithmetic with citation; not a sodium infusion protocol.

Worthley 1987 calculated serum osmolality: 2×Na + glucose/18 + BUN/2.8. Optional osmolar gap when a measured osm is supplied. Deterministic published arithmetic with citation; not a measured freezing-point osmometer or a diagnosis.

Sodium correction for hyperglycemia (Katz 1.6 or Hillier 2.4). formula is required; magent does not pick one silently. Deterministic published correction with citation; not a treatment recommendation.

Bicarbonate deficit from weight and measured HCO3 using Adrogué–Madias 50 percent body-weight space. Deterministic published arithmetic with citation; not a dosing protocol.

HOMA-IR as (fasting glucose in mmol/L × insulin in µU/mL) / 22.5 (Matthews et al. 1985). Provide glucose_mg_dl (50–1000) or glucose_mmol_l (2.8–55.5), not both; mg/dL converts as mmol/L = mg/dL / 18. Returns the approximation rounded to two decimals. Not HOMA-B, not the HOMA2 computer model, not a diabetes diagnosis, and not an insulin-resistance cutoff.

Payne albumin-corrected calcium from total calcium and albumin. Deterministic published formula with citation; not a treatment recommendation.

Wu 2008 BISAP for early mortality prediction in acute pancreatitis: BUN >25 mg/dL, caller-assigned impaired mental status, caller-assigned SIRS, age >60, and caller-assigned pleural effusion; 1 point each, max 5. BUN 25.0 and age 60 do not score. Score only; no mortality percentages. Not a diagnosis. Not Ranson, APACHE II, or CTSI. magent does not recompute SIRS, assign mental status, or read imaging.

Rockall 1996 pre-endoscopy (admission) score after acute upper GI haemorrhage: age <60 0, 60-79 1, >=80 2; shock SBP<100 2 (hypotension; tachycardia not added), else HR>=100 1, else 0; comorbidity none 0, cardiac (failure, IHD, or any major) 2, renal/liver/metastatic 3. Max 7. Not complete Rockall, AIMS65, or GBS. Caller assigns comorbidity.

Saltzman 2011 AIMS65 for in-hospital mortality in acute upper GI bleeding: albumin <3.0 g/dL, INR >1.5, caller-assigned altered mental status, systolic BP <=90 mm Hg, and age >65; 1 point each, max 5. Albumin 3.0, INR 1.5, and age 65 do not score; SBP 90 does. Score only; no mortality percentages. Not a diagnosis. Not Glasgow-Blatchford or Rockall. magent does not assess mental status. Albumin g/dL or g/L.

Glasgow-Blatchford score (Blatchford 2000) for need for treatment after upper-gastrointestinal haemorrhage. Points from urea, haemoglobin (sex-specific), systolic BP, heart rate ≥100, melena, syncope, hepatic disease, and cardiac failure; max 23. Score 0 is the published low-risk screen; magent does not invent other GBS bands. Not a diagnosis, not Rockall, and not AIMS65. Urea may be mmol/L or BUN mg/dL; haemoglobin g/L or g/dL.

Wai 2003 AST to platelet ratio index (APRI) from AST, laboratory AST ULN, and platelet count. Returns APRI to two decimals plus published training-set cut-offs for significant fibrosis (Ishak ≥3) and cirrhosis. ULN is required; magent does not assume 40 U/L. Not a diagnosis, not FIB-4, and not a biopsy.

McDiarmid 2002 PELD from bilirubin, INR, albumin, age under 1 year, and growth failure. Deterministic published listing arithmetic with citation; not a transplant listing recommendation.

Runyon 1992 SAAG as serum albumin minus ascites albumin in g/dL, rounded to one decimal. portal_hypertension_physiology is true when SAAG >= 1.1 g/dL. Gradient only; not Light-style exudate/transudate criteria for ascites. Not a diagnosis. magent does not diagnose portal hypertension or peritonitis. Serum and ascites albumin as g/dL or g/L.

Child–Pugh (Child–Turcotte–Pugh) cirrhosis severity from bilirubin, albumin, INR, caller-assigned encephalopathy, and ascites. Deterministic published score with citation; not a transplant listing protocol.

Maddrey discriminant function (1978) from patient and control prothrombin time in seconds plus bilirubin. Deterministic published formula with citation; not a diagnosis or steroid order.

OPTN/UNOS 2016 MELD-Na from creatinine, bilirubin, INR, sodium, and dialysis. Deterministic published score with citation; not a listing recommendation.

FIB-4 fibrosis index from age, AST, ALT, and platelets. Use for MASH/NASH prior-auth arithmetic. Deterministic published index with citation; not a diagnosis.

HEART score for emergency chest pain from age and caller-assigned history, ECG, risk factors, and troponin (each 0-2, max 10). Bands 0-3, 4-6, and 7-10 from Six 2008. Deterministic published score with citation; not a diagnosis or discharge protocol. magent does not read an ECG.

TIMI risk score for unstable angina / NSTEMI from age and six caller-assigned flags. Returns the 0-7 point total and components. Deterministic published score with citation; not an invasive-strategy protocol.

TIMI risk score for ST-elevation MI from age, diabetes/hypertension/angina, systolic BP, heart rate, Killip class, weight, anterior STE or LBBB, and time to treatment. Returns a 0-14 point total with components. Deterministic published score with citation; not a reperfusion or fibrinolytic protocol.

Map a natural-language drug, diagnosis, or lab phrase to a current RxNorm, ICD-10-CM, or LOINC code. Use when an agent must not hallucinate or invent a billing/pharmacy code.

qSOFA from Seymour 2016: respiratory rate ≥22, caller-assigned altered mentation, and systolic BP ≤100 mm Hg; 1 point each, max 3. Deterministic published score with citation; not a diagnosis of sepsis.

SOFA (Sepsis-related Organ Failure Assessment) from Vincent 1996 Table 3: six organs 0-4, max 24, from PaO2/FiO2 with a ventilation gate, platelets, bilirubin, MAP and adrenergic agents, caller-assigned GCS, and creatinine or urine output. Deterministic published score with citation; not a Sepsis-3 diagnosis.

Age-adjusted D-dimer cutoff (Righini 2014 ADJUST-PE). PE excluded only when D-dimer (ng/mL FEU) is strictly below 500 if age <50 or age×10 if age ≥50. Equality is not excluded. FEU only, not DDU; magent does not convert units. Not a diagnosis, not YEARS, not Wells.

Tosetto 2012 DASH (D-dimer, Age, Sex, Hormonal therapy) after a first unprovoked VTE: abnormal D-dimer after stopping anticoagulation +2, age <50 +1 (age 50 does not score), male +1, hormone use at the initial VTE in women -2. Score -2 to 4. Returns published recurrence bands <=1, 2, and >=3 without percents. Not a medical device and not a duration-of-anticoagulation order.

YEARS algorithm (van der Hulle 2017 Lancet). Count three caller-assigned items (clinical signs of DVT, hemoptysis, PE most likely) and exclude PE only when D-dimer (ng/mL FEU) is strictly below 1000 with 0 items or 500 with 1-3 items. Equality is not excluded. Not a diagnosis, not Wells, not PERC. magent does not decide PE most likely. The 2017 cohort excluded pregnancy.

Eight-factor pulmonary embolism rule-out criteria (Kline 2004). PERC-negative only when all eight hold: age <50, pulse <100, SaO2 >94%, and no unilateral leg swelling, hemoptysis, recent trauma or surgery, prior PE or DVT, or hormone use. Caller must already have low pretest probability as in the paper. Not a diagnosis, not a D-dimer protocol, and not altitude-adjusted PERC.

FeverPAIN from Little 2013 (PRISM): five caller-assigned flags (fever in past 24 hours, purulent tonsils, attendance within 3 days, severely inflamed tonsils, no cough or coryza), 1 point each, max 5. Returns published score groups 0-1 / 2-3 / 4-5. Deterministic published score with citation; not a medical device, not a test-or-treat order, and not a diagnosis of streptococcal pharyngitis. magent does not examine the throat.

Centor or McIsaac (age-modified) score for streptococcal pharyngitis from four caller-assigned findings. edition=centor (max 4) or edition=mcisaac (age 3-14 +1, 15-44 0, >=45 -1, max 5) is required; magent does not pick one. Deterministic published score with citation; not a test-or-treat protocol.

Wells deep-vein thrombosis probability from discrete clinical flags. Returns three-tier and two-tier bands. Deterministic published score with citation; not a diagnosis.

Wells pulmonary-embolism probability from discrete clinical flags. Returns three-tier and two-tier bands. Deterministic published score with citation; not a diagnosis.

Charles 2008 SMART-COP for intensive respiratory or vasopressor support in community-acquired pneumonia: SBP <90 (2), multilobar CXR (1), albumin <3.5 g/dL (1), age-adjusted RR (1), HR >=125 (1), new confusion (1), age-adjusted low oxygen (2), arterial pH <7.35 (2; omitted pH scores 0). Max 11. IRVS 0-2 low, 3-4 moderate, 5-6 high, >=7 very high. Not a site-of-care protocol. Albumin g/dL or g/L. Exactly one of PaO2, SpO2, or P/F.

Fine 1997 Pneumonia Severity Index (PSI/PORT): Class I if age ≤50 and no neoplastic, liver, CHF, cerebrovascular, or renal disease, no AMS, HR <125, RR <30, SBP >=90, and temperature 35 to <40 C. Otherwise Table 2 points (age, or age-10 if female, plus comorbidity, vital-sign, and laboratory weights) map to classes II-V. Always returns the Table 2 total. Not a medical device and not a site-of-care decision.

Lim 2003 CRB-65 for community-acquired pneumonia: confusion, respiratory rate ≥30/min, low blood pressure (SBP <90 or DBP ≤60), and age ≥65; 1 point each, max 4. No urea. Score only; no mortality percentages or site-of-care bands. Not a diagnosis. Not CURB-65. Caller assigns the C, R, and B flags; magent does not convert BUN or take BP numbers.

CURB-65 pneumonia severity from age and discrete clinical flags. Deterministic published score with citation; not a treatment recommendation.

Tisdale 2013 QT prolongation risk score (Table 5): age ≥68 (1), female (1), loop diuretic (1), potassium ≤3.5 mmol/L (2), admission QTc ≥450 ms (2), acute MI (2), sepsis (3), heart failure (3), one QTc-prolonging drug (3) plus ≥2 drugs (3 stacked; max 21). Returns bands 0-6 / 7-10 / ≥11. Deterministic published arithmetic with citation; not a medical device, not a drug-stop protocol, and not a TdP diagnosis.

Heart-rate-corrected QT (Bazett or Fridericia). formula is required; magent does not pick one silently. Deterministic published correction with citation.

Sampson 2020 estimated LDL-C from total cholesterol, HDL, and triglycerides (valid through 800 mg/dL). One unit system (mg/dL or mmol/L). Deterministic published equation with citation; not Friedewald, not a diagnosis or statin order.

Friedewald estimated LDL-C from total cholesterol, HDL, and triglycerides. One unit system (mg/dL or mmol/L). Deterministic published equation with citation; not a diagnosis or statin order.

Adrogué–Madias change in serum sodium after 1 L of infusate from TBW (child 0.6; adult male 0.6; adult female 0.5; elderly male 0.5; elderly female 0.45) and infusate Na plus K. Deterministic published arithmetic with citation; not a correction-rate order or infusion protocol.

Urine anion gap from urine sodium, potassium, and chloride (Na + K − Cl). Batlle 1988 interpretive band: negative suggests increased NH4+ (GI bicarbonate loss); positive suggests impaired NH4+ (RTA). Deterministic published arithmetic with citation; not a diagnosis.

Eherer–Fordtran 1992 fecal osmotic gap: stool osmolality minus 2×(stool Na + stool K). Assumed stool osm 290 mOsm/kg when measured osm is omitted. Deterministic published arithmetic with citation; not a diagnosis of osmotic versus secretory diarrhea.

Serum anion gap from sodium, chloride, and bicarbonate, with or without potassium. formula=without_k or formula=with_k is required; magent does not pick one. Deterministic Emmett–Narins 1977 arithmetic with citation. Not a diagnosis, albumin-corrected gap (Figge/Fencl), or delta gap.

Winters' formula for expected PCO2 in metabolic acidosis: 1.5 × bicarbonate + 8 mm Hg, with a published ±2 mm Hg range. Optional comparison of measured PaCO2 to that band. Deterministic Albert–Winters 1967 arithmetic with citation; not a treatment target or a metabolic alkalosis formula.

Free water deficit from weight, sex, and measured Na using Adrogué–Madias TBW (0.6 male / 0.5 female). Deterministic published arithmetic with citation; not a water-replacement infusion protocol.

Sodium deficit from weight, sex, and measured Na using Adrogué–Madias TBW (0.6 male / 0.5 female). Deterministic published arithmetic with citation; not a sodium infusion protocol.

Worthley 1987 calculated serum osmolality: 2×Na + glucose/18 + BUN/2.8. Optional osmolar gap when a measured osm is supplied. Deterministic published arithmetic with citation; not a measured freezing-point osmometer or a diagnosis.

Sodium correction for hyperglycemia (Katz 1.6 or Hillier 2.4). formula is required; magent does not pick one silently. Deterministic published correction with citation; not a treatment recommendation.

Bicarbonate deficit from weight and measured HCO3 using Adrogué–Madias 50 percent body-weight space. Deterministic published arithmetic with citation; not a dosing protocol.

HOMA-IR as (fasting glucose in mmol/L × insulin in µU/mL) / 22.5 (Matthews et al. 1985). Provide glucose_mg_dl (50–1000) or glucose_mmol_l (2.8–55.5), not both; mg/dL converts as mmol/L = mg/dL / 18. Returns the approximation rounded to two decimals. Not HOMA-B, not the HOMA2 computer model, not a diabetes diagnosis, and not an insulin-resistance cutoff.

Nathan/ADAG A1C to estimated average glucose conversion, or the reverse. Provide exactly one of a1c_percent or eAG. Deterministic published equation with citation.

Payne albumin-corrected calcium from total calcium and albumin. Deterministic published formula with citation; not a treatment recommendation.

Blamey 1984 Glasgow-Imrie eight-factor pancreatitis score: age >55, WBC >15 ×10^9/L, glucose >10 mmol/L, urea >16 mmol/L, PaO2 <60 mm Hg, calcium <2.0 mmol/L, albumin <32 g/L, LDH >600 U/L; 1 point each, max 8. Severe predicted if score ≥3. Caller-assigned flags; magent does not convert units. Not a diagnosis. Not Ranson. Transaminases omitted as in the paper.

Ranson 1974 pancreatitis score from eleven published signs (five at admission, six at 48 hours) as boolean flags. Returns points 0-11 and mortality band 0-2 / 3-4 / 5-6 / 7-11. Deterministic published arithmetic with citation; not an ICU order.

Wu 2008 BISAP for early mortality prediction in acute pancreatitis: BUN >25 mg/dL, caller-assigned impaired mental status, caller-assigned SIRS, age >60, and caller-assigned pleural effusion; 1 point each, max 5. BUN 25.0 and age 60 do not score. Score only; no mortality percentages. Not a diagnosis. Not Ranson, APACHE II, or CTSI. magent does not recompute SIRS, assign mental status, or read imaging.

Rockall 1996 complete (post-endoscopy) score after acute upper GI haemorrhage: age <60 0, 60-79 1, >=80 2; shock SBP<100 2 (hypotension; tachycardia not added), else HR>=100 1, else 0; comorbidity none 0, cardiac 2, renal/liver/metastatic 3; diagnosis none or mallory_weiss 0, other 1, malignancy 2; stigmata none_or_spot 0, blood_clot_vessel 2. Max 11. Not pre-endoscopy-only Rockall, AIMS65, or GBS. Caller assigns comorbidity, diagnosis, and stigmata.

Rockall 1996 pre-endoscopy (admission) score after acute upper GI haemorrhage: age <60 0, 60-79 1, >=80 2; shock SBP<100 2 (hypotension; tachycardia not added), else HR>=100 1, else 0; comorbidity none 0, cardiac (failure, IHD, or any major) 2, renal/liver/metastatic 3. Max 7. Not complete Rockall, AIMS65, or GBS. Caller assigns comorbidity.

Saltzman 2011 AIMS65 for in-hospital mortality in acute upper GI bleeding: albumin <3.0 g/dL, INR >1.5, caller-assigned altered mental status, systolic BP <=90 mm Hg, and age >65; 1 point each, max 5. Albumin 3.0, INR 1.5, and age 65 do not score; SBP 90 does. Score only; no mortality percentages. Not a diagnosis. Not Glasgow-Blatchford or Rockall. magent does not assess mental status. Albumin g/dL or g/L.

Glasgow-Blatchford score (Blatchford 2000) for need for treatment after upper-gastrointestinal haemorrhage. Points from urea, haemoglobin (sex-specific), systolic BP, heart rate ≥100, melena, syncope, hepatic disease, and cardiac failure; max 23. Score 0 is the published low-risk screen; magent does not invent other GBS bands. Not a diagnosis, not Rockall, and not AIMS65. Urea may be mmol/L or BUN mg/dL; haemoglobin g/L or g/dL.

King's College criteria (O'Grady 1989) for poor prognosis in fulminant hepatic failure. Acetaminophen: arterial pH <7.30, or PT >100 s plus creatinine >300 umol/L plus grade III/IV encephalopathy. Non-acetaminophen: PT >100 s, or any 3 of age <11 or >40, unfavorable etiology (non-A non-B or drug reaction), jaundice-to-encephalopathy >7 days, bilirubin >300 umol/L, PT >50 s. PT seconds, not INR. Not a transplant listing order.

Lille model (Louvet 2007) from age, albumin, bilirubin at day 0 and day 7, creatinine, and PT seconds or INR. formula=pt or formula=inr is required; magent does not swap them. Score 0-1 with the published 0.45 cutoff. Deterministic published arithmetic with citation; not a medical device or a steroid order.

West Haven / Conn hepatic encephalopathy grade 0-4 (Conn 1977). Deterministic published grade with citation. Not a diagnosis; magent does not examine the patient or apply ISHEN covert/overt or psychometric minimal-HE tests.

Angulo 2007 NAFLD fibrosis score from age, BMI, IFG/diabetes, AST, ALT, platelets, and albumin. Deterministic published equation with citation. Not a biopsy or diagnosis. Not FIB-4, APRI, or BARD.

Forrest 2005 Glasgow alcoholic hepatitis score from age, WBC, urea, PT ratio, and bilirubin (range 5-12) with the published ≥9 band. Deterministic published arithmetic with citation; not a steroid order.

Wai 2003 AST to platelet ratio index (APRI) from AST, laboratory AST ULN, and platelet count. Returns APRI to two decimals plus published training-set cut-offs for significant fibrosis (Ishak ≥3) and cirrhosis. ULN is required; magent does not assume 40 U/L. Not a diagnosis, not FIB-4, and not a biopsy.

McDiarmid 2002 PELD from bilirubin, INR, albumin, age under 1 year, and growth failure. Deterministic published listing arithmetic with citation; not a transplant listing recommendation.

Runyon 1992 SAAG as serum albumin minus ascites albumin in g/dL, rounded to one decimal. portal_hypertension_physiology is true when SAAG >= 1.1 g/dL. Gradient only; not Light-style exudate/transudate criteria for ascites. Not a diagnosis. magent does not diagnose portal hypertension or peritonitis. Serum and ascites albumin as g/dL or g/L.

Johnson 2015 albumin-bilirubin (ALBI) grade from total bilirubin and albumin. xb = 0.66*log10(bilirubin umol/L) + albumin_g_l*(-0.085). Grade 1 if xb <= -2.60, grade 2 if xb <= -1.39, else 3. Returns albi_score (4 decimals) and albi_grade. Not a listing protocol, Child-Pugh, survival estimate, mALBI, PALBI, or EZ-ALBI.

Child–Pugh (Child–Turcotte–Pugh) cirrhosis severity from bilirubin, albumin, INR, caller-assigned encephalopathy, and ascites. Deterministic published score with citation; not a transplant listing protocol.

Maddrey discriminant function (1978) from patient and control prothrombin time in seconds plus bilirubin. Deterministic published formula with citation; not a diagnosis or steroid order.

OPTN/UNOS 2016 MELD-Na from creatinine, bilirubin, INR, sodium, and dialysis. Deterministic published score with citation; not a listing recommendation.

FIB-4 fibrosis index from age, AST, ALT, and platelets. Use for MASH/NASH prior-auth arithmetic. Deterministic published index with citation; not a diagnosis.

Rogers 2011 aortic dissection detection risk score (ADD-RS). One point per high-risk category with any marker (conditions, pain features, exam features); two markers in the same category still add only 1; max 3. Bands 0 / 1 / 2-3. Deterministic published score with citation. Not an imaging order, not ADvISED D-dimer rule-out; score 0 does not exclude dissection.

Killip and Kimball 1967 myocardial-infarction heart-failure class 1-4 as assigned by the caller. Returns the published class, description (no heart failure; S3 and basilar rales; pulmonary edema; cardiogenic shock), and 1967 CCU hospital mortality (6%, 17%, 38%, 81%). Not a diagnosis; magent does not examine the patient. Not GRACE or contemporary registry mortality.

Than 2014 EDACS from age bands, male sex, known CAD or three risk factors (age 18-50 only), diaphoresis, radiation, inspiration (−4), and palpation (−6). Returns the point total (may be negative) and whether the score is <16. The paper ADP also requires ECG and 0/2h troponin, which magent does not take. Not a diagnosis or discharge order. Deterministic published arithmetic with citation.

Sgarbossa 1996 GUSTO-1 criteria for evolving AMI in left bundle-branch block: caller-assigned concordant ST elevation ≥1 mm (5), concordant ST depression ≥1 mm in V1–V3 (3), and discordant ST elevation ≥5 mm (2). Max 10. Score ≥3 had ~90% specificity in the derivation. Deterministic published score with citation; not a diagnosis, not the Smith modification, and magent does not read the tracing.

Morrow InTIME-II TIMI risk index: heart rate × (age/10)^2 / systolic BP, with the five published groups (≤12.5, >12.5–17.5, >17.5–22.5, >22.5–30, >30). Deterministic published arithmetic with citation; not a reperfusion decision.

HEART score for emergency chest pain from age and caller-assigned history, ECG, risk factors, and troponin (each 0-2, max 10). Bands 0-3, 4-6, and 7-10 from Six 2008. Deterministic published score with citation; not a diagnosis or discharge protocol. magent does not read an ECG.

TIMI risk score for unstable angina / NSTEMI from age and six caller-assigned flags. Returns the 0-7 point total and components. Deterministic published score with citation; not an invasive-strategy protocol.

TIMI risk score for ST-elevation MI from age, diabetes/hypertension/angina, systolic BP, heart rate, Killip class, weight, anterior STE or LBBB, and time to treatment. Returns a 0-14 point total with components. Deterministic published score with citation; not a reperfusion or fibrinolytic protocol.

Gage 2006 HEMORR2HAGES (NRAF) AF major-bleed score: prior bleed 2; hepatic or renal, ethanol, malignancy, age >75, reduced platelet count or function, uncontrolled hypertension, anemia, genetic factors, excessive fall risk, and stroke each 1. Max 12. Warfarin major bleed per 100 patient-years: 0→1.9, 1→2.5, 2→5.3, 3→8.4, 4→10.4, ≥5→12.3. Not a medical device. Not a decision to start or stop anticoagulation. Not HAS-BLED, ORBIT, or ATRIA.

Fang 2011 ATRIA hemorrhage score: anemia caller flag 3 (paper Hb <13 g/dL men or <12 g/dL women); severe renal disease (eGFR <30 or dialysis) caller flag 3; age >=75 scores 2; prior hemorrhage 1; diagnosed hypertension 1. Max 10. Score 0-3 low, 4 intermediate, 5-10 high. Not a diagnosis. Not a warfarin order. Not HAS-BLED. magent does not measure hemoglobin or compute eGFR.

CHADS2 score from discrete clinical flags. Use for the 2001 Gage atrial-fibrillation stroke-risk arithmetic. Deterministic published score with citation; not an anticoagulation order.

ORBIT 2015 (O'Brien) AF bleeding score: age >=75 scores 1; anemia caller flag 2; bleeding history 2; insufficient kidney (paper eGFR <60) caller flag 1; antiplatelet 1. Max 7. Score 0-2 low, 3 intermediate, >=4 high. Not a diagnosis. Not HAS-BLED. magent does not take hemoglobin or compute eGFR.

HAS-BLED score from discrete clinical flags. Use for bleeding-risk arithmetic in atrial fibrillation. Deterministic published score with citation.

CHA2DS2-VASc score from discrete clinical flags. Use for stroke-risk stratification arithmetic in atrial fibrillation. Deterministic published score with citation.

Schwartz 2009 bedside eGFR for children with CKD (CKiD): 0.413 × height in cm divided by serum creatinine in mg/dL, rounded to one decimal as mL/min/1.73m2. Height may be centimeters or inches; creatinine may be mg/dL or µmol/L. Not a dosing recommendation, not CKD-EPI, not Cockcroft–Gault, and not the 1976 Schwartz k=0.55 formula. Does not assign CKD stages.

Fractional excretion of urea (FEUN) from BUN, urine urea nitrogen, and plasma/urine creatinine (Carvounis 2002). Use when diuretics make FENa unhelpful. Deterministic published formula with citation; not a diagnosis.

Fractional excretion of sodium (FENa) from plasma and urine sodium and creatinine. Espinel 1976 oliguric ARF strata. Deterministic published formula with citation; not a diagnosis.

Cockcroft-Gault creatinine clearance from age, sex, total body weight, and creatinine. Use when a label still doses on CrCl rather than CKD-EPI eGFR. Deterministic published formula with citation; not a dosing recommendation.

CKD-EPI 2021 creatinine eGFR (race-free). Use when an agent must not guess kidney function from a language model. Deterministic published formula with citation.

Chung 2008 Appendix 2 STOP-Bang OSA screen. Four caller-assigned STOP flags (loud snoring heard through closed doors, daytime tiredness, observed stop-breathing, hypertension) plus computed BANG: BMI >35, age >50, neck >40 cm, male; each 1; max 8. BMI 35, age 50, and neck 40 cm do not score. Returns bands 0-2 and >=3. Not Chung 2012 three-tier, not a medical device, and not a sleep-study order.

Steer 2012 DECAF: eMRCD 1-4 → 0, 5a → 1, 5b → 2; eosinophils <0.05 ×10^9/L → 1 (0.05 does not score); caller-assigned consolidation → 1; arterial pH <7.30 → 1 (7.30 does not score); atrial fibrillation → 1. Returns a 0–6 total and band 0-1 / 2 / 3-6. Deterministic published points with citation. Not an early-discharge or escalation protocol and not a medical device.

Ley 2012 GAP index (points) from sex (male 1), age (≤60 → 0, 61–65 → 1, >65 → 2), FVC % predicted (>75 → 0, 50–75 → 1, <50 → 2), and DLCO % predicted (>55 → 0, 36–55 → 1, ≤35 → 2; cannot perform → 3). Returns a 0–8 total and stage 1–3 (0–3 / 4–5 / 6–8). Deterministic published points with citation. Not a transplant listing and not a continuous GAP calculator.

Celli 2004 BODE index from BMI (≤21 → 1), FEV1 % predicted (0–3), MMRC dyspnea (0–3), and 6-minute walk in meters (0–3). Returns a 0–10 total and quartile 1–4 (0–2 / 3–4 / 5–6 / 7–10). Deterministic published points with citation. Not a GOLD stage and not a transplant listing.

Nunn and Gregg 1989 predicted adult peak expiratory flow (L/min) from age, sex, and height. Sex-specific ln(PEF) regressions as published. Deterministic published arithmetic with citation; not a personal-best or action-plan zone.

Light 1972 pleural fluid criteria: exudate if protein ratio > 0.5, LDH ratio > 0.6, or pleural LDH > two-thirds the laboratory LDH ULN. ULN is required; magent does not assume 200 U/L. Strictly greater than those cutoffs. Deterministic published arithmetic with citation; not a diagnosis of cause, not Heffner's abbreviated criteria, and not a chest x-ray interpretation.

SpO2/FiO2 (S/F) ratio as pulse-oximetry SpO2 percent divided by inspired oxygen as a fraction (0.21–1.0) (Rice 2007). Returns the ratio rounded to one decimal. Magent does not apply ARDS or Berlin bands. This is not the PaO2/FiO2 (P/F) ratio and not the ROX index.

ROX index as (SpO2 percent / FiO2) / respiratory rate in breaths/min (Roca 2016). Returns the index rounded to two decimals. Not a ventilation order. This is not the PaO2/FiO2 (P/F) ratio and not RSBI (respiratory rate / tidal volume).

Rapid shallow breathing index (RSBI) as respiratory rate in breaths/min divided by tidal volume in liters (Yang and Tobin 1991). Provide tidal_volume_ml (50–2000) or tidal_volume_l (0.05–2.0), not both. Returns f/VT rounded to one decimal and whether that ratio is greater than 105 breaths/min/L. Not a wean order; magent does not perform a spontaneous breathing trial (SBT).

PaO2/FiO2 ratio as arterial PO2 in mm Hg divided by inspired oxygen as a fraction (0.21–1.0). Returns the ratio rounded to one decimal. Magent does not apply ARDS severity cutoffs, and this is not the oxygenation index (FiO2 × MAP × 100 / PaO2).

Oxygenation index from FiO2 as a fraction (0.21–1.0), mean airway pressure in cm H2O, and PaO2: FiO2 × MAP × 100 / PaO2. Deterministic published arithmetic with citation; not a diagnosis or an ECMO-initiation protocol.

Alveolar–arterial oxygen gradient from FiO2, barometric pressure, PaCO2, PaO2, and RQ using the simplified alveolar-gas equation (PH2O 47 mm Hg). Deterministic published arithmetic with citation; not a diagnosis.

Korabathina 2012 pulmonary artery pulsatility index from PA systolic (mm Hg), PA diastolic (mm Hg), and RAP (mm Hg): PAPi = (PAS − PAD) / RAP. Returns papi to two decimals and the paper ROC band (<=0.9 or >0.9) from the unrounded ratio. Equality at 0.9 is <=0.9. RAP 0 is invalid (no RAP=1 substitution). Not a medical device, RV-failure diagnosis, or device threshold.

Diastolic shock index as heart rate in bpm divided by cuff diastolic pressure in mm Hg (Ospina-Tascón 2020). Returns the ratio rounded to two decimals. Not a shock diagnosis, treatment target, or cutoff. Distinct from Allgöwer–Burri HR/SBP shock index. The 2020 cohort had no normal-subject control group, so a DSI cutoff to identify abnormality could be misleading.

Fincke 2004 cardiac power output from MAP (mm Hg) and cardiac output (L/min): CPO = MAP × CO / 451. Returns cpo_watts to two decimals and the paper ROC band (<=0.53 or >0.53) from the unrounded value. Equality at 0.53 W is <=0.53. MAP is caller-supplied (Fincke used diastolic + (systolic−diastolic)/3); this tool does not take SBP/DBP or compute cardiac power index. Not a medical device, shock diagnosis, or treatment target.

Shock index as heart rate in bpm divided by cuff systolic pressure in mm Hg (Allgöwer and Burri 1967). Returns the original ratio rounded to two decimals. Not a shock diagnosis, treatment target, or cutoff, and does not use MAP or diastolic pressure.

Mean arterial pressure from cuff systolic and diastolic BP using diastolic + pulse pressure / 3. Conventional 1/3 estimate, not an invasive aortic mean. Deterministic published arithmetic with citation; not a treatment target.

Adult Parkland crystalloid volume: 4 mL × kg × %TBSA for 24 hours, half in the first 8 hours from the time of injury. Baxter 1974. Deterministic published arithmetic with citation; not a treatment order, IV prescription, or urine-output titration.

Holliday–Segar 1957 daily maintenance water from weight: 100 mL/kg for the first 10 kg, 50 mL/kg for the next 10 kg, 20 mL/kg thereafter. Returns daily and hourly milliliters. Deterministic published arithmetic with citation; not a treatment order or IV prescription.

Nadler 1962 predicted blood volume in liters from height, weight, and sex (separate male and female equations). Deterministic published arithmetic with citation. For adults as published; this tool does not take age. Not a transfusion order, Lemmens–Bernstein–Brodsky estimate, or 70 mL/kg rule of thumb.

Harris–Benedict 1919 basal energy expenditure (kcal/day) from height, weight, age, and sex. Deterministic published formula with citation; not a nutrition prescription.

Devine ideal body weight and 0.4 adjusted body weight from height, sex, and actual weight. Deterministic published formula with citation; not a dosing recommendation.

Mosteller body surface area from height and weight. Use for oncology dosing arithmetic. Deterministic published formula with citation; not a dosing recommendation.

Body-mass index from height and weight (Keys/Quetelet). Use for GLP-1 and bariatric prior-auth arithmetic. Deterministic published index with citation; not a diagnosis.

Look up a current RxNorm, ICD-10-CM, or LOINC display from an exact code. Use when an agent already has a code and must not invent the preferred term.

CAM-ICU (Ely 2001). Delirium is present iff Feature 1 (acute onset or fluctuating course) and Feature 2 (inattention) both hold, and Feature 3 (disorganized thinking) or Feature 4 (altered level of consciousness) also holds. The caller assigns each feature as already determined. magent does not observe the patient, administer RASS, or run the attention screening exam. Not a diagnosis and not a medical device.

THRIVE (Totaled Health Risks in Vascular Events; Flint 2010 AJNR) from trichotomized age (<=59 0, 60-79 1, >=80 2), trichotomized NIHSS (<=10 0, 11-20 2, >=21 4), and chronic disease scale (hypertension, diabetes, atrial fibrillation; 1 each). Score 0-9; bands low 0-2, moderate 3-5, high 6-9 with published 90-day mRS 0-2 and mortality percents. Not a treatment recommendation. magent does not examine the patient or assign NIHSS.

CRUSADE in-hospital major bleeding score (Subherwal 2009 Table 4) for NSTE-ACS / NSTEMI. Points from hematocrit, caller-assigned Cockcroft–Gault CrCl, heart rate, sex, CHF, prior vascular disease, diabetes, and systolic BP. Returns integer score (max 96), quintile band, and published in-hospital major-bleeding percent. Not a medical device; magent does not compute CrCl or examine the patient.

Yücel 2006 TASH (Trauma Associated Severe Hemorrhage): seven independent nested less-than point bands for arrival SBP, hemoglobin, intra-abdominal fluid, complex long-bone/pelvic fracture AIS, heart rate, base excess, and male sex; max 28. Highest matching band only (do not stack). Deterministic published arithmetic with citation; not a transfusion or MTP order; not ABC (assessment of blood consumption). Caller assigns FAST and AIS; magent does not read imaging.

NEXUS Chest (Rodriguez 2011). Chest radiography is not indicated by this instrument only when all seven caller-assigned findings are absent: chest pain, distracting injury, chest-wall tenderness, intoxication, age >60, rapid deceleration, and altered mental status. Any one present means chest x-ray is indicated. Not a diagnosis, not Hoffman 2000 NEXUS C-spine, and not a NEXUS Chest CT instrument. Derivation enrolled blunt trauma age >14. magent does not examine the patient.

Apgar score from five 0-2 newborn signs (appearance, pulse, grimace, activity, respiration). Deterministic published score with citation; not a diagnosis.

Sheiner–Tozer / Winter–Tozer albumin-adjusted total phenytoin: Ccorr = Cobs / ((0.2 or 0.1) × albumin_g_dl + 0.1). Renal factor 0.1 when renal_impairment is true. Deterministic published arithmetic with citation; not a free phenytoin level or a dose.

Convert a glucocorticoid milligram dose among hydrocortisone, prednisone, and dexamethasone using Meikle 1977 equivalent doses (20 : 5 : 0.75). Not a taper, stress-dose protocol, or regimen recommendation; mineralocorticoid activity is not converted. Deterministic published table with citation.

CDC 2022 morphine milligram equivalents from a published opioid key and dose (mg/day, or mcg/hr for fentanyl_transdermal). Estimates only; do not use MME to convert one opioid to another. Not a taper protocol or OUD dosing tool.

Gross 1983 dilution-corrected allowable blood loss from caller-supplied estimated blood volume and initial versus target hematocrit. Deterministic published arithmetic with citation. Not a transfusion trigger or order. Does not compute Nadler EBV; does not use the uncorrected EBV*(Hi-Hf)/Hi form.

Ganzoni 1970 iron deficit: weight_kg * (target_hemoglobin_g_dl - hemoglobin_g_dl) * 2.4 + iron_stores_mg. Deterministic published arithmetic with citation. Not an IV iron product dose or order; magent does not pick target Hb or depot iron, and this is not a diagnosis of iron deficiency.

Neutrophil-to-lymphocyte ratio from relative neutrophil and lymphocyte percents (Zahorec 2001). Deterministic published arithmetic with citation. Not a sepsis diagnosis; magent does not apply later oncology cutoffs that are not in that paper.

Corrected reticulocyte count (retic% × Hct/45), Hillman 1969 maturation-shift reticulocyte index, and optional absolute reticulocyte count. Deterministic published arithmetic with citation; not a marrow diagnosis.

Taylor 2001 ISTH SSC overt DIC (four lab items; max 8). Platelets >=100=0, 50-<100=1, <50=2. fibrin_related_marker none/moderate/strong = 0/2/3 (caller-assigned; magent does not grade D-dimer). PT sec above ULN <3=0, >=3 and <6=1, >=6=2. Fibrinogen >=1.0 g/L=0, <1.0=1 (XOR g/L or mg/dL÷100). Band <5 not compatible with overt DIC; >=5 compatible. Not a diagnosis. Not the non-overt serial score.

Bendapudi 2017 PLASMIC: seven 1-point items (platelets <30×10^9/L, caller-assigned hemolysis, no active cancer, no solid-organ or stem-cell transplant, MCV <90 fL, INR <1.5, creatinine <2.0 mg/dL), max 7. Bands 0-4 / 5 / 6-7 are pretest groups for severe ADAMTS13 deficiency, not percents or a plasma-exchange order. magent does not assay hemolysis. Cutoffs 30, 90, 1.5, and 2.0 do not score.

4Ts score (Lo 2006) for heparin-induced thrombocytopenia pretest probability. Four caller-assigned integers 0-2 (thrombocytopenia, timing, thrombosis, other causes) using the published table; magent sums only (max 8). Bands 0-3 low, 4-5 intermediate, and 6-8 high pretest probability. Not a diagnosis of HIT, not the HEP score, and not an antibody result. magent does not grade platelet counts or day of onset.

Mentzer index as MCV in fL divided by RBC count in millions per µL (Mentzer 1973 Lancet letter). Quotient <13 favors β-thalassaemia trait; >13 favors iron deficiency; 13 is indeterminate. Deterministic published arithmetic with citation. Not a diagnosis of thalassemia or iron deficiency; magent does not apply later cutoffs that are not in that letter.

Absolute neutrophil count from WBC and neutrophil plus band percents. Bodey 1966 granulocyte bands. Deterministic published arithmetic with citation; not a diagnosis.

FOUR score (Wijdicks 2005) from caller-assigned eye, motor, brainstem, and respiration integers 0-4; magent sums only (max 16) and does not pick a component from a narrative. Eye 4 tracking/blink to command to 0 closed to pain; motor 4 thumbs-up/fist/peace to 0 none or myoclonus status; brainstem 4 pupil and corneal present to 0 pupil, corneal, and cough absent; respiration 4 not intubated regular to 0 ventilator rate or apnea. Not a diagnosis and not a GCS conversion.

Fisher 1980 original CT groups 1-4 for subarachnoid hemorrhage as assigned from CT by the caller. Returns the published group and description. Group 3 (thick SAH) was the high-vasospasm group; group 4 is ICH/IVH without thick SAH, not a worse grade than 3. Not modified Fisher 2006. Not a diagnosis; magent does not read the CT.

Kothari 1996 ABC/2 ellipsoid ICH volume: (a_cm × b_cm × c_cm) / 2, rounded to one decimal milliliter. A is the largest diameter, B the perpendicular diameter, and C slice count times thickness; the caller supplies all three in cm. Volume estimate only; not the ICH Score. magent does not read imaging or choose A/B/C on the scan. Not a diagnosis.

Hunt and Hess 1968 SAH surgical-risk grade from a caller-assigned grade 1-5. Serious systemic disease (as assigned by the caller) places the patient in the next less favorable category, capped at 5. Deterministic published grade with citation. Not a diagnosis; not WFNS; not Hunt-Kosnik 1974 grade 0/1a.

Modified Rankin handicap grade 0-5 (van Swieten 1988) as assigned by the caller. Returns the published wording (no symptoms at all through severe disability: bedridden, incontinent, constant nursing). This 1988 scale has six grades 0-5 and does not include a dead grade. Not a diagnosis or discharge/disability-benefit protocol; magent does not interview the patient.

Rost 2008 FUNC score (0-11) after primary ICH from caller-assigned volume, age, location (lobar/deep/infratentorial), GCS, and pre-ICH cognitive impairment. Volume <30 mL scores 4, 30-60 scores 2, >60 scores 0; age <70 scores 2, 70-79 scores 1, >=80 scores 0; lobar 2, deep 1, infratentorial 0; GCS >=9 scores 2, <=8 scores 0; cognitive impairment absent scores 1. Companion to the Hemphill ICH Score, not a replacement. Not a diagnosis or withdrawal-of-care protocol. magent does not read CT.

Hemphill 2001 ICH Score from caller-assigned GCS, age, infratentorial origin, ICH volume (mL), and IVH; max 6. GCS 3-4 scores 2, 5-12 scores 1, 13-15 scores 0; age ≥80, volume ≥30 mL, infratentorial origin, and IVH score 1 each. Deterministic published score with citation; not a diagnosis or withdrawal-of-care protocol. magent does not read CT. Not FUNC and not ICH-GS.

ABCD2 (Johnston 2007) early stroke-risk score after TIA from age, blood pressure, caller-assigned clinical features, symptom duration, and diabetes (max 7). Bands 0-3, 4-5, and 6-7. Deterministic published score with citation; not a diagnosis or admit protocol. magent does not examine the patient. Not ABCD (Rothwell 2005) and not ABCD3-I.

Glasgow Coma Scale from eye, verbal, and motor integers. edition=1974 (motor 1-5, max 14) or edition=1976 (motor 1-6, max 15) is required; magent does not pick one. Deterministic published score with citation; not a diagnosis.

Thiruganasambandamoorthy 2016 Canadian Syncope Risk Score: vasovagal predisposition −1, heart disease +1, any ED SBP <90 or >180 +2, troponin above the 99th percentile +2, QRS axis < −30° or >100° +1, QRS duration >130 ms +1, QTc >480 ms +2, ED vasovagal diagnosis −2, ED cardiac diagnosis +2. Score −3 to 11. Caller assigns flags and ECG numbers. Not a medical device, not a syncope diagnosis, and not a disposition protocol.

Apfel 1999 simplified PONV risk score. Four caller-assigned predictors, 1 each, max 4: female sex, history of motion sickness or PONV, nonsmoking, postoperative opioids. Male and smokers score 0 on those items. Returns the integer score as bands 0-4. Apfel 1999 reported incidences by score; this tool returns the integer score without those percents. Not a medical device, not a prophylaxis order, not a diagnosis of PONV. Caller assigns history and opioid plan; magent does not take an anesthetic.

Johansen 1990 Mangled Extremity Severity Score (MESS): caller-assigned skeletal/soft-tissue energy 1-4, limb ischemia 1-3 (doubled if ischemia time >6 hours), shock 0-2, and age points (<30 → 0, 30-50 → 1, >50 → 2). Max 14. MESS ≥7 predicted amputation with 100% accuracy in that series (mess_band 0-6 or >=7). Deterministic published arithmetic with citation. Not an amputation or limb-salvage protocol; magent does not examine the limb. Not later papers' cutoff of 8.

Gill 2005 Simplified Motor Score (SMS) from one caller-assigned motor category: obeys (2, obeys commands), localizes (1, localizes pain), or withdrawal_or_less (0, withdrawal to pain or less). Companion to GCS, not a replacement protocol and not a triage or intubation order. magent does not examine the patient. Deterministic published score with citation.

Wesson 2003 Clinical Opiate Withdrawal Scale (COWS). Eleven caller-assigned appendix integers (pulse 0/1/2/4, GI 0/1/2/3/5, sweating 0-4, tremor 0/1/2/4, restlessness 0/1/3/5, yawning 0/1/2/4, pupils 0/1/2/5, anxiety 0/1/2/4, aches 0/1/2/4, gooseflesh 0/3/5, rhinorrhea/tearing 0/1/4). Max 48. Severity 5-12 mild, 13-24 moderate, 25-36 moderately severe, >36 severe; 0-4 below mild (none). magent does not observe the patient. Not a buprenorphine induction protocol.

Sullivan 1989 CIWA-Ar (revised Clinical Institute Withdrawal Assessment for Alcohol). Ten caller-assigned integers: nausea/vomiting, tremor, paroxysmal sweats, anxiety, agitation, tactile, auditory, visual, and headache each 0-7; orientation 0-4 (not 0-7). Max 67. magent sums only and does not observe the patient or apply later protocol treatment cutoffs such as benzodiazepine orders. Not a diagnosis and not a medical device.

Intraoperative Surgical Apgar (Gawande 2007 Table 1) from estimated blood loss, lowest mean arterial pressure, and lowest heart rate, summed to a 0–10 total. Returns score_le_4 because scores ≤4 were associated with 58.6% 30-day death or major complication in the validation cohort (9–10 associated with 3.6%). Deterministic published arithmetic with citation; not Virginia Apgar; not operative clearance.

Samuel 2002 pediatric appendicitis score from eight caller-assigned findings, ages 4-15, max 10. Cough/percussion/hopping RLQ and RIF tenderness score 2; anorexia, pyrexia, nausea/emesis, leukocytosis, neutrophilia, and migration score 1. Fever and labs are flags, not unpublished cutoffs. Not Alvarado (MANTRELS). Not a diagnosis or operating-room protocol. magent does not examine the abdomen.

Kocher 1999 four predictors for children with irritable hip: history of fever (oral temperature >38.5 C), non-weight-bearing, ESR >=40 mm/h, and serum WBC >12000/uL; 1 point each, max 4. Returns published predicted probability of septic arthritis vs transient synovitis. Deterministic published score with citation; not a diagnosis, not Caird CRP, not adults, and not an aspiration order.

NEWS from RCP 2012 Chart 1: respiratory rate, SpO2, supplemental oxygen, temperature (°C), systolic BP, heart rate, and caller-assigned AVPU (alert 0; voice, pain, or unresponsive 3 each) summed to a 0–20 total. Returns Chart 2 clinical_risk (low/medium/high) and red_score when any parameter scores 3. Deterministic published arithmetic with citation; not NEWS2; not an ICU-admission order.

MEWS from Subbe 2001 Table 1: systolic BP, heart rate, respiratory rate, temperature (°C), and caller-assigned AVPU (alert/voice/pain/unresponsive) summed to a 0–14 total. Returns score_ge_5 because scores ≥5 were associated with increased risk of death or ICU/HDU. Deterministic published arithmetic with citation; not NEWS2; not an ICU-admission order.

Nunez 2009 ABC (assessment of blood consumption): penetrating mechanism, arrival SBP ≤90 mm Hg, arrival HR ≥120 bpm, and positive FAST; 1 point each, max 4. score_ge_2 is the published ≥2 cutoff (75% sensitive / 86% specific for massive transfusion in that paper). Deterministic published arithmetic with citation; not a transfusion or MTP order; not TASH; not ABC/2 ICH volume.

Revised Trauma Score (Champion 1989): coded GCS, SBP, and respiratory rate (0-4 each), T-RTS as their sum (0-12), and weighted RTS = 0.9368·GCS + 0.7326·SBP + 0.2908·RR. Deterministic published arithmetic with citation. Not a triage order; not ISS; not the 1981 Trauma Score.

Injury Severity Score (Baker 1974): ISS is the sum of squares of the three highest caller-assigned AIS body-region grades (head, face, chest, abdomen, extremity, external; each 0-6). Any AIS 6 (unsurvivable) is ISS 75. Deterministic published arithmetic with citation; not a triage order and not NISS (which squares the three worst injuries regardless of region).

Bush 1998 AUDIT-C from three caller-assigned integers 0-4 (frequency, typical drinks, binge frequency); magent does not map drink-count categories. Total 0-12. This paper reported ≥3 as sensitive and ≥4 as more specific for heavy drinking / active abuse or dependence in VA outpatients (mostly men). Returns screen_ge_3 and screen_ge_4. Not later sex-specific VA primary-care cutoffs, not the full 10-item AUDIT, and not CIWA-Ar. Not a diagnosis.

Ewing 1984 CAGE questionnaire: four caller-assigned yes/no items (cut down, annoyed, guilty, eye-opener), 1 point each, max 4. Screen-positive when two or more answers are affirmative (score ≥2). Deterministic published score with citation; not a diagnosis of alcohol use disorder, not CIWA-Ar, and not AUDIT. magent does not interpret individual items.

Westley 1978 croup score from five caller-assigned signs (consciousness 0/5, cyanosis 0/4/5, stridor 0-2, air entry 0-2, retractions 0-3; max 17). Deterministic published score with citation. Not a diagnosis; magent does not invent total-score severity bands.

Cole 1957 uncuffed pediatric endotracheal tube internal diameter: age_years/4 + 4 millimetres. Deterministic published arithmetic with citation; not a device-selection order or length-based tape.

Lee 1999 revised cardiac risk index: six 1-point factors (high-risk surgery, ischemic heart disease, heart failure, cerebrovascular disease, insulin diabetes, creatinine >2.0 mg/dL) and class I–IV. Deterministic published arithmetic with citation; not operative clearance.

Ottawa SAH Rule (Perry 2013 JAMA). Investigate when any of six findings is present: age 40 or older, neck pain or stiffness, witnessed loss of consciousness, onset during exertion, thunderclap headache (instantly peaking pain), or limited neck flexion on examination. Not a diagnosis of SAH, not Hunt-Hess, and not Fisher grade. For alert, neurologically intact adults with nontraumatic headache peaking within 1 hour as published. magent does not examine the neck.

New Orleans Head CT Rule (Haydel 2000). CT is indicated if any of seven findings: headache, vomiting, age over 60, drug or alcohol intoxication, short-term memory deficit (anterograde amnesia), physical evidence of trauma above the clavicles, or seizure. Published for GCS 15 minor head injury in adults; magent does not take GCS or examine the patient. Not a diagnosis, not the Canadian CT Head Rule, not PECARN, and not pediatric.

PECARN pediatric head CT (Kuppermann 2009). Two age trees (under 2 vs 2-17). High if any age-applicable high-risk factor (GCS <=14 or altered mental status in both; palpable skull fracture if under 2; signs of basilar skull fracture if 2 or older), else intermediate if any age-applicable intermediate factor, else low. CT recommended only when high. Not a diagnosis. Not Canadian CT Head, CATCH, CHALICE, NEXUS, or PECARN IAI/febrile/c-spine. magent does not examine the patient.

Canadian CT Head Rule (Stiell 2001). CT is indicated if any high-risk factor (GCS <15 at 2 hours, suspected open or depressed skull fracture, any sign of basal skull fracture, vomiting 2 or more times, or age 65 or older) or any medium-risk factor (amnesia before impact >30 min, or dangerous mechanism as assigned by the caller). Not a diagnosis, not NEXUS, not PECARN, not CATCH, and not pediatric. magent does not examine the patient.

Canadian C-spine rule (Stiell 2001). Cervical radiography is indicated if any high-risk factor is present (age ≥65, dangerous mechanism, or paresthesias in the extremities). If none, radiography is indicated unless at least one low-risk factor allows safe range-of-motion assessment and the patient can rotate the neck 45° left and right. Not a diagnosis, not NEXUS, and not pediatric. For alert, stable blunt-trauma adults with GCS 15. magent does not examine the neck.

NEXUS C-spine rule (Hoffman 2000). The patient is NEXUS low-risk, and imaging is not indicated by this rule, only when all five hold: no posterior midline cervical-spine tenderness, no focal neurologic deficit, normal alertness, no intoxication, and no painful distracting injury. Any failed criterion means x-ray is indicated. Not a diagnosis, not the Canadian C-spine rule, and not NEXUS chest. Blunt-trauma adults as published. magent does not examine the patient.

Pittsburgh knee rule (Seaberg 1994): after fall or blunt trauma, a knee radiograph is indicated if the patient cannot walk four weight-bearing steps or is younger than 12 or older than 50. Deterministic published rule with citation. Not a diagnosis; not the Ottawa knee rule.

Ottawa knee rule (Stiell 1995). Knee x-ray is indicated when any of: age 55 or older, bone tenderness at the fibular head, isolated patellar tenderness (caller-applied), inability to flex to 90 degrees, or inability to bear weight both immediately after injury and in the emergency department (four steps). One weight-bearing failure alone is not enough. Not a diagnosis of fracture, not the Ottawa ankle or foot rule, and not the Pittsburgh knee rule. magent does not examine the knee.

Ottawa ankle rule (Stiell 1992). Ankle x-ray is indicated when there is malleolar-zone pain and any of: bone tenderness at the posterior edge or tip of the lateral or medial malleolus, or inability to bear weight both immediately after injury and in the emergency department (four steps). One weight-bearing failure alone is not enough. Not a diagnosis of fracture, not the Ottawa foot rule, and not the Pittsburgh knee rule. magent does not examine the ankle.

San Francisco Syncope Rule (CHESS) from history of CHF, hematocrit, abnormal ECG, shortness of breath, and systolic BP. Returns a 0-5 criterion count and rule-positive if any CHESS item is present. Deterministic published score with citation; not a disposition protocol.

Raff 2017 ALT-70 for lower-extremity cellulitis vs pseudocellulitis. Caller-assigned unilateral involvement (3), WBC ≥10,000/µL (1), heart rate ≥90 (1), age ≥70 (2); max 7. Bands 0-2 (pseudocellulitis-leaning), 3-4 (indeterminate), and ≥5 (cellulitis-leaning). Deterministic published score with citation; not a medical device, not a cellulitis diagnosis, and not an antibiotic order. magent does not examine the limb.

LRINEC (Wong 2004): CRP ≥150 mg/L (4), WBC k/µL (<15 0, 15–25 1, >25 2), hemoglobin g/dL (>13.5 0, 11–13.5 1, <11 2), sodium <135 mmol/L (2), creatinine >141 µmol/L (2), glucose >10 mmol/L (1); max 13; cutoff ≥6. Deterministic published laboratory score with citation; not a diagnosis of necrotizing fasciitis and not an operative decision. A score below cutoff does not exclude disease.

SIRS from Bone 1992 ACCP/SCCM: four binary criteria (temperature >38 or <36 °C, heart rate >90, respiratory rate >20 or PaCO2 <32 mm Hg, WBC >12000 or <4000 per µL or bands >10%); present when ≥2 of 4. Deterministic published criteria with citation; not a diagnosis, not Sepsis-3, not qSOFA or SOFA.

Khorana 2008 Blood predictive model for chemotherapy-associated thrombosis: very_high site (stomach or pancreas) 2, high (lung, lymphoma, gynecologic, bladder, testicular) 1, other 0; platelets >=350 1; hemoglobin <10 g/dL or ESA 1 (once); WBC >11 x10^9/L 1; BMI>=35 caller flag 1. Max 6. 0 low; 1-2 intermediate; >=3 high. Not a diagnosis. Not Padua or Caprini. Caller assigns cancer site; magent does not compute BMI.

Barbar 2010 Padua Prediction Score for hospitalized medical patients: cancer 3, previous VTE 3, reduced mobility 3, thrombophilia 3, recent trauma/surgery 2, age >=70 1, heart/respiratory failure 1, acute MI/stroke 1, infection/rheumatologic 1, obesity (BMI>=30) 1, hormonal treatment 1. Max 20. <4 low; >=4 high. Not a diagnosis. Not Caprini, IMPROVE, or Khorana.

Revised Geneva score (Le Gal 2006) for suspected PE in the emergency department: age >65 (1), previous DVT or PE (3), surgery or lower-limb fracture within 1 month (2), active malignancy (2), unilateral lower-limb pain (3), hemoptysis (2), heart rate 75-94 (3) or >=95 (5), pain on deep-vein palpation and unilateral edema (4). Max 22. Bands 0-3, 4-10, and 11-22. Not a diagnosis, not simplified Geneva, and not Wells.

Hestia criteria (Zondag 2011). Outpatient PE is eligible only when none of 11 caller-assigned exclusions hold: hemodynamic instability, thrombolysis or embolectomy, high bleeding risk, oxygen >24 h, PE on anticoagulation, IV pain medication >24 h, medical or social admission, CrCl <30, severe liver impairment, pregnancy, or documented HIT. Any yes excludes home treatment. Not a diagnosis, not PESI, not sPESI.

Bova 2014 seven-point index for confirmed acute PE that is not hypotensive: SBP 90–100 mm Hg +2 (SBP 100 scores; 101 does not; SBP <90 rejected), elevated troponin +2 (caller-assigned lab cutoff; magent does not grade assays), RV dysfunction on echo or CT +2, heart rate ≥110 +1 (110 scores; 109 does not). Max 7. Returns bands 0-2 / 3-4 / >4 (stages I–III) without mortality percents. Not a medical device and not a thrombolysis order.

PESI (Pulmonary Embolism Severity Index) from Aujesky 2005: age in years plus male sex (+10), cancer (+30), heart failure (+10), chronic lung disease (+10), heart rate >=110 (+20), SBP <100 mm Hg (+30), respiratory rate >=30 (+20), temperature <36 C (+20), altered mental status (+60), and SpO2 <90% (+20). Classes I (<=65) through V (>125). Only for already diagnosed PE. Not a diagnosis, not an outpatient protocol, not sPESI, and not the 17-variable laboratory model.

sPESI (simplified Pulmonary Embolism Severity Index) from Jiménez 2010: 1 point each for age >80, cancer, chronic cardiopulmonary disease (one combined item), heart rate ≥110, systolic BP <100 mm Hg, and SpO2 <90%; max 6. Score 0 is low risk; ≥1 is high risk. Only for already diagnosed acute PE as in the paper. Not a diagnosis, not an outpatient-treatment protocol, and not original PESI classes.

Andersson 2008 appendicitis inflammatory response (AIR) score from caller-assigned vomiting, right-iliac-fossa pain, rebound or guarding (none/light/medium/strong), temperature, WBC, neutrophil percent, and CRP in mg/L (max 12). Bands 0-4, 5-8, and 9-12. Deterministic published score with citation; not a diagnosis or operating-room protocol. magent does not examine the abdomen.

Alvarado 1986 MANTRELS score from caller-assigned findings, temperature, WBC, and neutrophil percent (max 10). Bands 0-4, 5-6, and 7-10. Deterministic published score with citation; not a diagnosis or operating-room protocol. magent does not examine the abdomen.