Struck 2017 2HELPS2B: BIRDs 2 points; LPD or LRDA or BIPD, prior seizure, sporadic epileptiform discharges, frequency >2.0 Hz, and plus features 1 point each. Max 7. Published probable seizure risk: 0→5%, 1→12%, 2→27%, 3→50%, 4→73%, 5→88%, 6–7→>95%. Not a seizure diagnosis or monitoring-duration protocol. magent does not read EEG.

4AT (Bellelli 2014): alertness (normal 0, abnormal 4) + AMT4 mistake count 0/1/2 + attention 0/1/2 + acute change or fluctuation (false 0, true 4). Max 12. Band 0 unlikely, 1–3 possible cognitive impairment, ≥4 possible delirium. Not a delirium or dementia diagnosis. magent does not examine the patient. AMT4 is the caller-assigned mistake count only; this API does not collect age, date of birth, place, or year.

Knight 2020 ISARIC 4C Mortality Score: age (<50→0, 50–59→2, 60–69→4, 70–79→6, ≥80→7) + male 1 + comorbidity_count (0/1/≥2 → 0/1/2; caller-assigned Charlson-plus-obesity count) + RR (<20→0, 20–29→1, ≥30→2) + room-air SpO2 (<92→2) + GCS (<15→2) + urea (<7→0, 7–14→1, >14→3 mmol/L; or BUN/2.8) + CRP (<50→0, 50–99→1, ≥100→2). Max 21. Table 5: low 0–3, intermediate 4–8, high 9–14, very high ≥15. Not a COVID-19 diagnosis or treatment order.

Roy 2021 4PEPS Table 3: age <50 −2, 50–64 −1, ≥65 0; chronic respiratory disease −1; HR <80 −1; chest pain and acute dyspnea +1; male +2; estrogen treatment +2; prior VTE +2; syncope +2; 4-week immobility +2; SpO2 <95% +3; calf pain or unilateral edema +3; PE most likely +5. Max 22. Bands: very_low <0, low 0–5, moderate 6–12, high ≥13. Not imaging or D-dimer. magent does not examine the patient or decide PE most likely.

Enright 1998 predicted six-minute walk distance (meters) from sex, age 40-80, height_cm, and weight_kg (Table 3 height/weight: male 7.57H−5.02age−1.76W−309; female 2.11H−2.29W−5.78age+667). Reports predicted_m and lln_m (minus 153 m men or 139 m women). Optional walked_m (0-1500) yields percent_predicted. Not a timed walk, BMI-equation path, or 80%/400 m class. Not a medical device.

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

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.

AAP 2017 Flynn Table 3 pediatric BP category (normal, elevated, stage_1, stage_2) from age 1-17 and cuff mm Hg. Age ≥13 uses adult-aligned 120/80, 130/80, and 140/90 cutoffs. Age 1-12 needs caller 90th/95th mm Hg (magent does not interpolate height/sex tables). Category is the more severe limb. magent does not measure BP. Not a device, not a hypertension diagnosis, not the 2004 Fourth Report, and not ACC/AHA 2017 for age <13.

AAP 2022 Kemper KAS 10 intensive phototherapy threshold from Supplemental Tables 1 and 2 by completed GA, age in hours, TSB, and caller-assigned extra neurotoxicity risk factors. Linear interpolation between tabulated hours. Do not subtract conjugated bilirubin. Not a phototherapy order. magent does not assay TSB.

Abbey 2004 observational pain scale from six caller-assigned 0-3 items (vocalization, facial_expression, change_in_body_language, behavioural_change, physiological_change, physical_changes) using that paper's absent/mild/moderate/severe descriptors. magent sums only (max 18) and returns Abbey 2004 bands: 0-2 none, 3-7 mild, 8-13 moderate, 14+ severe. magent does not observe the patient. Not a pain diagnosis or analgesic order. Not PAINAD.

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.

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.

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.

Berend 2014 physiological acid-base assessment. Labels acidemia or alkalemia, primary metabolic vs respiratory process, anion gap (Na-Cl-HCO3), optional albumin-corrected gap, and printed delta-delta. Not a diagnosis, ventilator order, bicarbonate dose, or blood-gas assay.

Dominguez 2008 ABIC score from age, bilirubin, creatinine, and INR. ABIC = (age * 0.1) + (bilirubin_mg_dl * 0.08) + (creatinine_mg_dl * 0.3) + (inr * 0.8). Low <6.71, intermediate 6.71–9.0, high >9.0. Not a diagnosis of alcoholic hepatitis and not a steroid or transplant order.

2013 ACCF/AHA heart-failure stages (Yancy) from four caller flags: high risk for HF, structural heart disease, prior or current HF symptoms, and refractory specialized care. Returns hf_stage A, B, C, D, or not_staged. Progressive and inviolate: D first, then C, B, A, else not_staged. Not NYHA class and not a diagnosis. magent does not examine the patient or read an echocardiogram.

Felitti 1998 ACE Study: seven caller-assigned exposure categories (psychological abuse, physical abuse, sexual abuse, mother treated violently, household substance abuse, household mental illness, household incarceration), 1 point each, max 7. Returns ace_band 0, 1, 2, 3, or ge_4 (score ≥4). A category count, not a diagnosis, trauma inventory, or 10-item ACE-Q. magent does not interpret the items.

Ranucci 2018 ACEF II for cardiac surgery: ACEF II = age/EF + 2.0 if serum creatinine > 2.0 mg/dL + 3.0 if emergency surgery + 0.2 × (hematocrit points below 36%). Hematocrit ≥ 36% contributes 0. Returns the published score only (4 decimals). Not original ACEF 2009, not a predicted-mortality percent, and not an operative clearance.

Intravenous acetylcysteine milligrams from weight (Prescott 1979). load_mg = weight_kg * 150 over 15 minutes; infusion_4h_mg = weight_kg * 50 over 4 hours; infusion_16h_mg = weight_kg * 100 over 16 hours; total_mg = weight_kg * 300 over 20.25 hours. For acetaminophen (paracetamol) poisoning. Not a prescription, not a Rumack–Matthew nomogram, and not a plasma acetaminophen interpretation.

ACR/EULAR 2015 gout classification (Neogi). MSU crystals classify without score ≥8; else score ≥8 (max 23). Pattern 0/1/2, characteristics 0–3, time course 0/1/2, tophus 4, urate −4 to 4, MSU-negative −2, imaging 4+4. Not a diagnosis. Not Janssens 2010. magent does not examine joints or polarizing microscopy.

ACR/EULAR 2012 PMR classification (Dasgupta Table 4). Required: age 50–120, bilateral shoulder aching, abnormal CRP or ESR. Score morning stiffness >45 min 2, hip pain or limited ROM 1, RF or ACPA absent 2, other joint pain absent 1. Without ultrasound: max 6, classified iff ≥4. With ultrasound: add shoulder-and-hip 1 and both shoulders 1; max 8, classified iff ≥5. Not a diagnosis (not meant for diagnostic purposes). magent does not assay CRP/ESR/RF/ACPA or perform ultrasound.

ACR/EULAR 2010 RA classification (Aletaha Table 3). Required: clinical_synovitis true. Score: joint involvement 0/1/2/3/5 + serology 0/2/3 + abnormal CRP or ESR 1 + duration ≥6 weeks 1; max 10. classified false if another disease better explains synovitis; else true if typical RA erosions or score ≥6. Not a diagnosis. Not 1987 ACR RA. Not SDAI. magent does not examine joints or titer RF/ACPA.

ACR/EULAR 2016 primary Sjögren classification (Shiboski Table 3). Required: inclusion_met true (AECG dryness or ESSDAI domain) and exclusion_present false (no radiation, HCV, AIDS, sarcoid, amyloid, GVHD, IgG4-RD). Score: labial biopsy FS ≥1 3, anti-SSA/Ro 3, ocular staining 1, Schirmer 1, UWS 1; max 9; classified iff ≥4. Not a diagnosis. Not AECG 2002. Not 2012 ACR-only. magent does not stain eyes, measure saliva, or read biopsies.

Fanaroff 2018 ACTION ICU integer score (Table 3) for initially hemodynamically stable NSTEMI. Points from age, creatinine, heart rate, systolic BP (lower SBP scores more), troponin × ULN, HF signs, ST depression, absence of prior revascularization, and chronic lung disease. Returns integer score 0–19. Not a medical device or triage order; magent does not read an ECG or assay labs.

Bang 2009 Table 2 development screening score for undiagnosed diabetes. Age (<40 → 0, 40–49 → 1, 50–59 → 2, ≥60 → 3); male 1; family history of diabetes 1; hypertension 1; BMI (≥40 extremely obese 3; 30–<40 obese 2; 25–<30 overweight 1; else 0); physically active −1. Returns score and high_risk (true iff score ≥ 5). BMI-only, no waist. Not Appendix ARIC/CHS, not a diagnosis.

Than 2012 ADAPT 2-hour accelerated diagnostic protocol for emergency chest pain. low_risk is true only when the caller-assigned TIMI UA/NSTEMI score is 0, new ischemic ECG changes are absent, and both 0-hour and 2-hour (not 3-hour) troponin flags are not elevated. magent does not assign TIMI items, read an ECG, or assay troponin. Not HEART Pathway. Not a discharge order, ACS diagnosis, or stress-test order. Not a medical device.

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.

Fonarow 2005 ADHERE CART bedside tree from admission BUN, systolic BP, and serum creatinine. high: BUN>=43, SBP<115, Cr>=2.75; intermediate_1: BUN>=43, SBP<115, Cr<2.75; intermediate_2: BUN>=43, SBP>=115; intermediate_3: BUN<43, SBP<115; low: BUN<43, SBP>=115. Creatinine consulted only when BUN>=43 and SBP<115. CART tree only, not the logistic model or GWTG-HF. Not a heart-failure diagnosis or treatment/ICU 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.

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.

Alvarez 1999 revised original IAIHG AIH score, not Hennes 2008 simplified. Caller-assigned sex, ALP:AST/ALT ratio, globulin/IgG, ANA/SMA/LKM titer, AMA, viral markers, drugs, alcohol, additive histology, other autoimmune disease; optional HLA/other autoantibodies if seronegative and treatment response. Pretreatment definite >15 / probable 10-15; posttreatment definite >17 / probable 12-17. magent does not read histology. Not a diagnosis or immunosuppression order.

Guy 1976 Abnormal Involuntary Movement Scale (AIMS): seven 0-4 movement items summed (max 28). Rate highest severity observed. Items 8-12 (overall severity, incapacitation, awareness, dental problems, dentures) are required and returned, not added to the total. No activation subtraction. Not a tardive dyskinesia diagnosis. magent does not examine the patient. Not a medical device.

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.

Moledina 2022 development-model logistic probability of biopsy-proven acute interstitial nephritis from serum creatinine, BUN:creatinine ratio, urine dipstick specific gravity, and dipstick protein (0 or 1+ versus 2+ or higher, caller-assigned). Returns logit and estimated_probability_percent. Not a medical device, not a diagnosis, and not a kidney biopsy. Does not include urine IL-9 or TNF-α. Moledina 2022 publishes no named low/high cutoff.

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.

Endorf 2007 bronchoscopic AIS inhalation injury grade 0-4 as assigned by the caller. Returns ais_grade, the published bronchoscopic description, and high_grade (true when grade is 2-4; those grades had worse survival than 0-1, P = .03). magent does not perform bronchoscopy. Not a diagnosis. Not ISS body-region AIS. Not RADS CT smoke score. Not a medical device.

AKIN 2007 (Mehta Table 2) stage 0-3 from baseline and current creatinine in mg/dL and a caller-assigned urine-output category. Stage is the worse of the two limbs; RRT is stage 3. magent does not assay creatinine, measure urine, or collect weight. Not a medical device, not a diagnosis, not KDIGO 2012, and not RIFLE.

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.

Absolute lymphocyte count from WBC and lymphocyte percent (Shapiro 1998). ALC < 1000 cells/mm3 predicts CD4 < 200; ALC >= 2000 predicts CD4 >= 200. Deterministic published arithmetic with citation. Not a CD4 measurement or HIV diagnosis. magent does not measure the CBC.

Aldrete 1970 postanesthetic recovery score from five caller-assigned 0-2 signs (activity, respiration, circulation, consciousness, color), summed to 0-10. Returns 0_to_7 (close observation), 8_to_9 (acceptable for recovery-room discharge to the ward), or 10 (ideal). Deterministic published score with citation; not the 1995 SpO2 revision; not PADSS; not a discharge order.

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.

Cedarbaum 1999 ALSFRS-R: twelve caller-assigned integers 0-4 (speech, salivation, swallowing, handwriting, cutting_food, dressing_hygiene, turning_in_bed, walking, climbing_stairs, dyspnea, orthopnea, respiratory_insufficiency). One cutting_food slot for with or without gastrostomy. Sum 0-48. magent does not examine. Cedarbaum 1999 printed no total-score severity bands. Not a diagnosis, not original 10-item ALSFRS, not Karnofsky or ECOG, and not a medical device.

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.

NINDS 1995 IV alteplase milligram arithmetic from weight: total_mg = min(0.9 × weight_kg, 90), 10% bolus, 90% infusion over 60 minutes. Reports milligrams and whether the 90 mg cap applied. Not a medical device, not a prescription, not an eligibility screen, and not tenecteplase.

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.

AMT-10 (Hodkinson 1972): ten caller-assigned correct/incorrect flags. Each correct item scores 1; max 10. Score is the 0–10 sum only. Hodkinson 1972 did not publish a diagnostic cutoff. Flags only; magent does not interview the patient or collect age, date of birth, place, year, address, or monarch name. Not a dementia diagnosis, not a medical device, and not Swain 1997 AMT-4.

AMT-4 (Swain 1997): four caller-assigned flags for age, date of birth, place, and year. Each correct item scores 1; max 4. Impaired cognition is indicated when the score is less than 4 (0–3 impaired; 4 not impaired). Flags only; magent does not interview the patient or collect a date of birth, age, place name, or year. Not a dementia diagnosis and not a medical device. Not Hodkinson 1972 AMT-10.

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

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.

Jin 2018 ED model for early diagnosis of acute pancreatitis when lipase is at least 3x ULN. Integer points: prior episodes 0/1/2/3/4, cholelithiasis +2, abdominal surgery in 2 months -2, epigastric pain +2, worsening pain +1, pain duration >=5 days -1, severity mild 0 / moderate +2 / severe +3, lipase fold +0/+1/+2. Score max 14; jin2018_high_ppv if score>=8; jin2024_accuracy_cut if score>=6. Not a diagnosis. Not an imaging order. Not Ranson, BISAP, or Glasgow-Imrie.