Titulaer 2011 DELTA-P for SCLC association in Lambert-Eaton myasthenic syndrome. One point each, at or within 3 months of LEMS onset: bulbar weakness (dysarthria/dysphagia/chewing/neck weakness); erectile dysfunction if male (always 0 if female); weight loss ≥5%; smoking at onset; age ≥50; Karnofsky <70. Max 6. Bands low 0-1, intermediate 2, high 3-6. Published SCLC percents for scores 0, 1, 3-6; none for score 2. Not a LEMS diagnosis, not SOX1, and not an SCLC screen.

Modified Denver BCVI (Cothren 2005). Positive if any sign (arterial hemorrhage; cervical bruit age <50; expanding cervical hematoma; focal deficit; neuro exam incongruous with head CT; stroke on secondary CT) or any risk factor (LeFort II/III; C-spine subluxation, transverse foramen, or C1-C3; basilar skull with carotid canal; DAI with GCS <6; near hanging with anoxia). Imaging indicated when positive. Not Biffl grade, expanded Denver, NEXUS, or Canadian C-spine. magent does not read CTA.

Levine 2015 DHAKA Dehydration Score (Table 3, not the Tree): appearance 0/2/4, respirations 0/2, skin pinch 0/2/4, tears 0/1/2. Max 12. Bands 0-1 / 2-3 / ≥4. Derived in children <5 with acute diarrhea. magent does not examine the child or order fluids. Not a WHO IMCI clone. Not a medical device.

Haukoos 2012 Table 2 FULL Denver HIV score (not abbreviated). Age bands, sex, ethnicity, and five caller-assigned flags (sm vi rai idu pht). Range -14 to 81. Caller-assigned. Not a diagnosis.

Passamonti 2010 DIPSS for primary myelofibrosis: age >65 (1), WBC >25×10^9/L (1), hemoglobin <10 g/dL (2), peripheral-blood blasts ≥1% (1), constitutional symptoms (1); max 6. Low 0, intermediate_1 1–2, intermediate_2 3–4, high 5–6. Not DIPSS Plus or aaDIPSS. magent does not read a smear; constitutional symptoms are caller-assigned.

Belgrade 2006 DIRE score: Diagnosis, Intractability, and Efficacy each caller-assigned 1-3; Risk is the sum of Psychological, Chemical, Reliability, and Social support (each 1-3, so Risk 4-12). Total 7-21. Scores 14-21 are more suitable for long-term opioid maintenance; 7-13 less suitable. Caller assigns the integers. magent does not take a pain history or write an opioid prescription or taper. Not a medical device.

Hohol 1995 Disease Steps: caller-assigned integer 0-6 (normal; mild disability, mild symptoms or signs; moderate disability, visible abnormality of gait; early cane, intermittent use of cane; late cane, cane-dependent; bilateral support; confined to wheelchair). Not 0.5 half-steps, not later Disease Steps Plus, and not EDSS. magent does not examine gait. Not a medical device and not an MS diagnosis.

Efstathiou 2002 DKA-MPM. Six caller-assigned flags: severe coexisting disease at presentation (+6), pH <7.0 at presentation (+4), regular insulin >50 IU in the first 12 h (+4), glucose >16.7 mmol/L after 12 h (+4), depressed mental state after 24 h (+4), fever after 24 h (+3). Max 25. Published in-hospital death 0.86% for scores 0–14 and 93.3% for 19–25; scores 15–18 return the total only. magent does not assay pH or glucose. Not a DKA treatment or insulin-dose order. Not a medical device.

Shi 2020 donor whole-blood liters to process for a CD3+ DLI target: (recipient_weight_kg × cd3_target_per_kg × num_infusions) / (0.6 × donor_alc_per_ul × collection_efficiency × 1e6). Estimates CD3 as 60% of donor ALC. Caller assigns collection_efficiency in (0,1]; the paper used first-quartile 0.57. Deterministic published arithmetic with citation. Not an apheresis order; magent does not run a device or the paper's CD34 HPC algorithm.

Aggarwal 2023 DOAC Score (Circulation Table 2) for AF on DOACs: age 65-69 2 / 70-74 3 / 75-79 4 / >=80 5 (<65 0); CrCl/eGFR 30-60 inclusive 1, <30 2; underweight caller BMI <18.5 flag 1; stroke/TIA/embolism 1; diabetes 1; hypertension 1; antiplatelet none 0, aspirin 2, dual 3; NSAID 1; bleeding history 3; liver disease 2. Score min(raw, 10). Bands 0-3 very_low, 4-5 low, 6-7 moderate, 8-9 high, 10 very_high. Not HAS-BLED. Not DOAC dosing. Not warfarin.

DRAGON (Strbian 2012 Neurology) for 3-month outcome after IV thrombolysis. CT hyperdense artery or early infarct 0/1/2, prestroke mRS >1 (1), age <65/65-79/>=80 (0/1/2), glucose >8 mmol/L (mg/dL /18) (1), onset-to-treatment >90 min (1), NIHSS 0-4/5-9/10-15/>15 (0/1/2/3); max 10. Tabulated mRS 0-2 and mRS 5-6 percents for scores 0-1, 2, 3, 8, and 9-10 only. Not a tPA decision. Not studied in basilar occlusion. magent does not read CT or assign NIHSS.

Webb 2016 DRIP (drug resistance in pneumonia): ten caller-assigned flags, four major at 2 points and six minor at 1, max 14. high_risk if score >= 4. Deterministic published score with citation; not a medical device, not an antibiotic order, and not HCAP. magent does not classify the facility or compute Karnofsky.

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.

du Bois 2011 abbreviated four-predictor IPF score from age (<60 → 0, 60–69 → 4, ≥70 → 8), 24-week respiratory hospitalization (true → 14), FVC % predicted (<50 → 18, 51–65 → 13, 66–79 → 8, >80 → 0; 50 and 80 unpublished), and 24-week FVC % change (≤ −10 → 21, > −10 and < −4.9 → 10, ≥ −4.9 → 0). Returns a 0–61 total only. Does not interpolate Table 4 risk percents. Not GAP and not a transplant listing.

Durack 1994 original Duke criteria for infective endocarditis. Definite if pathologic_definite or clinical_definite (2 major, or 1 major plus 3 minor, or 5 minor); else rejected if any rejected flag; else possible. Suggestive echo and suggestive micro are not double-counted with the matching major. Caller assigns flags. magent does not examine the patient, read an echocardiogram, or interpret cultures. Not Li 2000 modified Duke. Not ISCVID 2023. Not a diagnosis.

2023 Duke-ISCVID (Fowler) IE criteria. Definite if pathologic_definite or clinical_definite (2 major, or 1 major plus 3 minor, or 5 minor). Possible if 1 major plus 1 minor or 3 minor. Rejected if neither, or if a rejected flag is true and definite does not hold. Majors are caller-assigned microbiologic, imaging, and surgical domains. minor_microbiologic is not counted when major_microbiologic is true. magent does not read echo, PET, or cultures. Not Durack 1994. Not Li 2000. Not a diagnosis.

Mark 1991 Duke treadmill score: duke_treadmill_score = exercise_min - (5 * st_deviation_mm) - (4 * angina_index), 1 decimal. Angina index 0 none, 1 nonlimiting, 2 exercise-limiting. High if score < -10, moderate -10 to 4, low >= 5. Not a catheterization order, CAD diagnosis, or Bruce-protocol prescription. magent does not read the ECG.

Dutch Lipid Clinic Network (Nordestgaard 2013 Table 1) familial hypercholesterolaemia score. One LDL (mmol/L or mg/dL / 38.67) plus family, clinical, physical, and DNA groups; per group only the highest. Max 26. Definite >8, probable 6-8, possible 3-5, unlikely 0-2. Score 8 (mutation alone) is probable. Adult Table 1 only; not Simon Broome, not MEDPED, not homozygous FH. magent does not assay lipids, examine tendons or arcus, or sequence genes. Not a medical device and not a diagnosis of FH.

Duval 2010 AML Table 5 (not ALL): PIF or CR1 >6 mo 0 / CR1 <6 mo 1; ECOG/SWOG cyto good/intermediate 0, poor 1; HLA sibling or well/partially matched unrelated 0, mismatched unrelated 1, related other 2; circulating blasts 1; KPS/Lansky <90 1; max 6. Groups 0, 1, 2, ≥3. Caller assigns categories; magent does not karyotype. Not a transplant listing.

Hanifin 2001 EASI from four regions. Each region: area 0-6 and erythema, edema/papulation, excoriation, and lichenification 0-3. Region score = (sum of signs) × area × adult weight (head/neck 0.1, upper extremities 0.2, trunk 0.3, lower extremities 0.4). Total max 72. Adult weights only. magent does not examine the skin. No IGA or later severity bands. Not a diagnosis.

Grossman 2018 Eat, Sleep, Console functional assessment. well_managed iff eat ≥1 oz per feed or breastfeed well, sleep undisturbed ≥1 hour, and console within 10 minutes if crying. needs_increased_treatment iff not well_managed (boolean only; not a morphine dose). Not modified Finnegan. Not the later ESC Care Tool item list. magent does not examine the infant. Not a diagnosis or medical device.

Oken 1982 ECOG performance status: caller-assigned integer 0-4 (fully active; restricted strenuous activity, ambulatory, light work; ambulatory, all self-care, unable to work, up >50% waking hours; limited self-care, bed/chair >50% waking hours; completely disabled, no self-care, totally bed/chair). Grade 5 (dead) is not scored. Returns score, max 4, and a stable label. Not a performance-status assignment and not Karnofsky; magent does not observe the patient.

ED-initiated buprenorphine milligrams from D'Onofrio 2015 (JAMA; PMID 25919527): dose_mg is 8 on protocol day 1 and 16 on days 2 and 3. Take-home schedule only. Not a home-induction decision tree, not COWS scoring, and not a prescription or X-waiver. magent does not score withdrawal.

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.

Cited race-free CKD-EPI 2021 creatinine eGFR. Agents must not invent eGFR from model memory; pay per request with x402 USDC on Base. Deterministic published formula with citation. Not a treatment recommendation.

El-Ganzouri 1996 simplified airway risk index (0/1/2): mouth opening >4 cm=0, <=4=1; thyromental >6.5 cm=0, 6.0-6.5=1, <6.0=2; original Mallampati 1/2/3 = 0/1/2 (class 4 not used); neck >90 deg=0, 80-90=1, <80=2; can prognath true=0, false=1; weight <90 kg=0, 90-110=1, >110=2; intubation history none/questionable/definite = 0/1/2. Max 12. High risk if score >=4. Not an intubation order; magent does not examine the airway.

Del Rosso 2008 EGSYS: palpitations +4, abnormal ECG or heart disease +3, syncope during effort +3, syncope while supine +2, absence of autonomic prodromes −1, absence of predisposing and/or precipitating factors −1. Range −2 to 12. Discriminator is score ≥3 versus <3 (cardiac-syncope triage). Caller assigns six flags. Not a medical device, not a cardiac-syncope diagnosis, and magent does not take a history.

Brindle 2021 Edinburgh gastric ulcer score (human gastric ulcer at index OGD): age <68 → 0, 68-79 → 1, ≥80 → 2; size <1.25 cm → 0, 1.25-2.99 cm → 2, ≥3.00 cm → 3 (no 1-point size band); antral 0, non-antral 1. Total 0-6. higher_malignancy_risk iff score ≥ 3. Use only with macroscopically benign appearance and ≥6 negative biopsies. magent does not read endoscopy images. Not equine EGUS. Not a medical device.

Lee 2012 EHMRG 7-day ED model (Table 3 integer score): 2*age + 60 if EMS transport - min(SBP,160) + clamp(HR,80-120) - 2*min(SpO2,92) + 20*creatinine_mg_dl + K (<=3.9: +5; 4.0-4.5: 0; >=4.6: +30) + 60 if troponin>ULN + 45 if active cancer + 60 if home metolazone + 12. Groups 1/2/3/4/5a/5b. Dialysis-dependent excluded. Not EHMRG30-ST, not ADHERE CART, not a discharge or admission order.

2023 emergency medical decision making from AMA CPT Table 1 as reprinted by ACEP. Caller assigns problems, data, and risk as straightforward, low, moderate, or high. Overall MDM is the highest level at which at least 2 of 3 elements are met or exceeded. Not a bill or CPT assignment. magent does not code the chart.

Sharma 2009 Edmonton Obesity Staging System (EOSS). Caller-assigned stage 0-4 with the published clinical-picture wording. magent does not assign stage from BMI or from separate medical, functional, or psychological domain scores. Not WHO BMI class. Not a diagnosis. Not a surgical-eligibility gate. magent does not examine the patient. Not a medical device.

Cox 1987 EPDS: 10 caller-assigned integers 0-3 (past 7 days). laugh, enjoyment, and anxious are reverse-scored in that paper; the caller assigns the published 0-3 (0 = least symptomatic pole after that reverse key). Total 0-30. This paper's threshold is 12/13 (at or above iff score ≥13). magent does not interview, apply later ≥10 community cuts, PHQ-9, QIDS, or MDI. Not a diagnosis.

Carmona-Bayonas 2017 EPIPHANY CHAID tree for cancer-associated PE. Hestia-like CDR any vs none, then ECOG-PS, SaO2, PE symptoms, tumour response, and primary resection as in Figure 2. Returns low, intermediate, or high with 15-day complication rates 1.6/9.4/30.6% and mortality 0.3/6.1/17.1%. Caller assigns the six covariates. Not a diagnosis or anticoagulation order. magent does not examine the patient.

Hirano 2013 modified EREFS: caller-assigned edema (absent 0, present 1), rings (none 0, mild 1, moderate 2, severe 3), exudates (none 0, mild_lt_10pct 1, severe_gt_10pct 2), furrows (absent 0, present 1; original 0-2 collapsed), stricture (absent 0, present 1). magent sums only (max 8; not later 0-9). No activity bands, inflammatory/fibrostenotic subscores, crepe-paper, or narrow-calibre. magent does not perform endoscopy. Not a diagnosis.

Watanabe 2011 ESAS-r from nine caller-assigned integers 0-10 (pain, tiredness, drowsiness, nausea, lack of appetite, shortness of breath, depression, anxiety, wellbeing; now; 0 none/best, 10 worst). magent does not administer the form. Sum 0-90. Watanabe 2011 published no severity classes for that sum. Not Bruera 1991 ESAS, not ESAS-r Renal (itch is not a core item), not a diagnosis or treatment order, and not a medical device.

Fasting Watson 1981 theoretical Co from ingested ethanol grams and sex-specific Watson 1980 total body water. Blood-water fraction 0.80; absorbed fraction 1. Fasting Widmark-type estimate only. Ethanol only; not a medicolegal BAC or treatment dose.

ESUS (Hart 2014). True iff all five caller-assigned flags hold: non-lacunar infarct on CT/MRI; no ≥50% stenosis supplying the ischaemia; no major-risk cardioembolic source; no other specific cause; and Panel 3 minimum workup (brain CT/MRI, 12-lead ECG, precordial echo, ≥24 h automated rhythm monitoring (not telemetry), extra- and intracranial arterial imaging). Incomplete workup is not ESUS. Not a stroke diagnosis, not TOAST cryptogenic, not anticoagulation. magent does not read imaging.

Soliman 2018 EUROMACS 9.5-point right-sided heart failure score after continuous-flow LVAD. Five caller-assigned flags: RA/PCWP >0.54 (2), hemoglobin ≤10 g/dL (1), multiple IV inotropes (2.5), INTERMACS class 1-3 (2), severe RV dysfunction (2). Max 9.5; half-points not integer-rounded. Bands: low 0-2, intermediate >2 to 4, high >4. Not a device indication. Not Michigan RV-failure score. Not CRITT. magent does not catheterize or echo.

Nashef 2012 EuroSCORE II Table 6 logistic in-hospital mortality after adult cardiac surgery. Age Xi is 1 if age <= 60, else age - 59. Renal function is a caller-assigned creatinine-clearance band or dialysis; magent does not run Cockcroft-Gault. Returns logit and estimated_probability_percent from the unrounded logit. Not additive EuroSCORE I, not a medical device, and Nashef 2012 publishes no low/intermediate/high percent cuts.

Hasford 2011 EUTOS score for baseline untreated chronic myeloid leukemia (CML). eutos_score = 4 * spleen_cm + 7 * basophils_percent, rounded to 1 decimal. Low if score ≤ 87; high if score > 87. spleen_cm is centimetres below the costal margin (0-40); basophils_percent is peripheral-blood basophils (0-100). Not a CML diagnosis and not a TKI choice.

Dong 2019 EVendo score for screening high-risk esophageal varices. A = (8.5 * INR) + (AST/35); B = (platelets/150) + (BUN/20) + (hemoglobin/15); score = A/B + 1 if ascites. US conventional units. Round to 2 decimals. Published cutoff strictly below 3.90. magent clamps: INR 0.8-4.0, AST 5-4000 U/L, platelets 10-800 k/uL, BUN 2-150 mg/dL, hemoglobin 4-20 g/dL. Not a varices diagnosis or endoscopy order. magent does not assay labs. Not a medical device.

McEntire 2025 FACE DROPS: seven caller-assigned flags for acute Lyme disease-associated facial palsy versus Bell palsy. Fever +8, aches (arthralgia/myalgia) +6, cephalalgia +3, exhaustion +4, dermatomal or radicular pattern +4, otalgia or postauricular pain −1, stiff neck +3. Score −1 to 28. Scores ≤4 favor Bell palsy; ≥7 favor LDFP; 5–6 indeterminate. Not a Lyme test, diagnosis, serology order, or stroke FACE-DROPS mimic score. magent does not examine the face.

Scalea 1999 FAST four Ps (pericardial, perihepatic, perisplenic, pelvic). Each window is a caller-assigned boolean for free intraperitoneal fluid (perihepatic/Morison, perisplenic, pelvic) or pericardial fluid. positive is true if any window is positive and false only if all four are negative. Sequence is not required. Not eFAST pleural views. Not Huang or McKenney scoring. Not a laparotomy order. magent does not scan or interpret ultrasound. Not a medical device.

Lima 2016 FAST-ED (Field Assessment Stroke Triage for Emergency Destination): facial_palsy 0-1 + arm_weakness 0-2 + speech 0-2 + eye_deviation 0-2 + neglect 0-2. Max 9. lvo_suggested iff score ≥4. Bands 0_to_1 / 2_to_3 / gte_4. Time is documented for decision making (0 points, not scored). Not a stroke diagnosis or transfer order. magent does not examine the patient.

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.

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.

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.

Boer 1984 estimated lean body mass from sex, height_cm, and weight_kg (male 0.407W+0.267H-19.2; female 0.252W+0.473H-48.3). Reports lbm_kg (paper term) with ffm_kg as the same alias. Height 100-220 cm and weight 20-300 kg are magent clamps, not Boer bands. Not a dosing weight, James/Hume formula, or measured body composition. magent does not measure the patient.

Cited Sterling 2006 FIB-4 fibrosis index. Agents must not invent FIB-4 from model memory; pay per request with x402 USDC on Base. Deterministic published index with citation. Not a treatment recommendation.

Fick 1870 cardiac output: CO (L/min) = VO2 (ml/min) / (CaO2 - CvO2) with contents in ml/L (ml/dL x10). Caller supplies the three measured terms. Does not estimate VO2 from BSA or apply Hufner Hb factors. Rejects CaO2 <= CvO2. Not a catheter order, shock diagnosis, or medical device. magent does not sample blood.