ESC 2024 CHA2DS2-VA stroke-risk score from age and discrete flags (CHF, hypertension, diabetes, prior stroke/TIA, vascular disease). No sex category (not CHA2DS2-VASc). Score 0 none, 1 consider OAC, ≥2 OAC recommended. Deterministic published arithmetic with citation; not an anticoagulation order.

Cited Lip 2010 CHA2DS2-VASc stroke-risk score. Agents must not invent CHA2DS2-VASc from model memory; pay per request with x402 USDC on Base. Deterministic published score with citation. Not a treatment recommendation.

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.

CCS 2014 CHADS-65 algorithm for nonvalvular AF/AFL stroke-prevention discussion. Oral anticoagulant if age ≥65 or CHF, hypertension, diabetes, or prior stroke/TIA. Else aspirin if coronary, aortic, or peripheral arterial disease. Else none. Not CHADS2, not CHA2DS2-VASc, not HAS-BLED, and not an anticoagulation order. magent does not examine the patient.

CHALICE (Dunning 2006). CT required in children 0-15 if any history, exam, or mechanism criterion is present; else low risk. GCS <14, or GCS <15 if age <1 year. Bruise/swelling/laceration >5 cm only if age <1 year. Mechanism is caller-assigned (paper: high-speed RTA >40 mph as occupant/pedestrian/cyclist; fall >3 m; high-speed projectile or object). NAI is caller-assigned. Not PECARN, CATCH, or Canadian CT Head. magent does not examine the child. Not a diagnosis or medical device.

Charlson 1987 original weighted comorbidity index. Nineteen caller-assigned flags with published weights 1, 2, 3, or 6 (max 37). 1-year mortality groups: 0, 1–2, 3–4, ≥5. Flags are independent (overlapping pairs are not dropped). Not a diagnosis, not Deyo or Quan ICD mapping, not age-adjusted Charlson. LACE takes the integer this tool returns. magent does not diagnose.

McGrath 1985 CHEOPS from six caller-assigned observational categories (cry 1-3; facial 0-2; child_verbal 0-2; torso, touch, and legs 1-2). magent sums only (published range 4-13) and does not observe the child. No invented analgesic cutoffs. Not a pain diagnosis or analgesic order. Not FLACC. Not BOPS.

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.

Smits 2007 CHIP rule (adults ≥16, GCS 13-15). CT if ≥1 major (pedestrian/cyclist vs vehicle, ejected, vomiting, PTA ≥4 h, skull-fracture signs, GCS <15, GCS drop ≥2 at 1 h, anticoagulants, posttraumatic seizure, age ≥60) or ≥2 minor (fall from elevation, persistent anterograde amnesia, PTA 2 to <4 h, skull contusion, neurologic deficit, LOC, GCS drop of 1 at 1 h, age 40-60). Not a diagnosis; not Canadian CT Head, NEXUS, PECARN, or 2022 CHIP. magent does not examine the patient.

Bharamgoudar 2018 CholeS Table 3 score for elective laparoscopic cholecystectomy duration. Age, sex, indication, BMI, CBD diameter, gallbladder wall, pre-op CT, planned IOC, prior surgical admissions, ASA class. Max 20. Numeric total only; no duration bands. Not a booking, not Nassar, not Tokyo. magent does not image the gallbladder.

Levine 2020 CHOSEN (COVID Home Safely Now): age 18-45 +5, 46-59 +2, 60-73 +1, >73 +0; SpO2 <94 +0, 94-96 +9, 97-98 +14, >98 +21; albumin g/dL <2.8 +0, 2.8-3.3 +5, 3.4-3.7 +15, >3.7 +29. Score 0-55. Cutpoint 30 (derivation sensitivity 83%, specificity 82%). Higher score favored event-free status in the paper. Not a discharge order.

Garibaldi 2020 CIRC day-2/4/7 probability of severe disease or death from admission age, nursing-home residence, caller-assigned race term, Charlson CCI, BMI, symptoms, vitals, and listed laboratories. Appendix Table 1 coefficients on the printed reference cumulative incidences. Not a diagnosis, triage order, or the death-only Appendix Table 2 model.

Miller 1992 CIRS-G from 14 caller-assigned organ-system integers 0-4 (heart, vascular, hematopoietic, respiratory, EENT, upper GI, lower GI, liver, renal, genitourinary, musculoskeletal, neurologic, endocrine-metabolic, psychiatric). magent does not examine the patient. Total 0-56 plus count of categories rated ≥3. No total-score class. Not Charlson. Not a diagnosis.

Carmona-Bayonas 2015 CISNE: ECOG ≥2 (2), stress hyperglycemia (2), COPD (1), chronic cardiovascular disease (1), NCI CTC mucositis ≥2 (1), monocytes <200/µL (1). Max 8. Low 0, intermediate 1–2, high ≥3. Seemingly stable adult solid-tumor febrile neutropenia only. Deterministic published score with citation; not MASCC; not an outpatient-chemotherapy or discharge order. magent does not assign ECOG, assay glucose, diagnose COPD, read an echocardiogram, grade mucositis, or count monocytes.

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.

Busto 1989 CIWA-B: twenty caller-assigned 0-4 items summed (max 80). Optional hours of sleep and minutes to fall asleep are recorded only and are not in the total. magent does not observe the patient and does not apply later mild-to-very-severe manuals. Not a benzodiazepine prescription and not a medical device.

CKiD U25 eGFR (Pierce 2021) for ages 1-25: age- and sex-dependent K times height in meters over creatinine (mg/dL), or K over cystatin C (mg/L), or the average of both when both markers are given. Height may be cm or inches; creatinine may be mg/dL or µmol/L. Not the Schwartz 2009 bedside 0.413 formula, not a drug dose, and not a CKD stage. Not a medical device.

Jalan 2014 CLIF-C ACLF (CANONIC) from caller-assigned CLIF-C OF (integer 6-18), age, and WBC in 10^9/L. Score = 10 × (0.33 × CLIF-C OF + 0.04 × age + 0.63 × ln(WBC) − 2), rounded to 1 decimal then clamped 0-100. magent does not score the six organs or compute CLIF-C OF. Not MELD, MELD-Na, Child-Pugh, CLIF-SOFA, or a transplant listing protocol. Not a medical device.

CLL-IPI 2016 for chronic lymphocytic leukaemia: TP53 abnormality (del(17p) and/or TP53 mutation) 4, unmutated IGHV 2, beta-2 microglobulin >3.5 mg/L 2, advanced stage (Binet B/C or Rai I–IV) 1, age >65 1; max 10. Low 0–1, intermediate 2–3, high 4–6, very_high 7–10. Deterministic published score with citation; not a CLL diagnosis; not Shipp IPI; not MIPI. magent does not assay TP53, IGHV, or beta-2 microglobulin.

Schmitz 2016 CNS-IPI: Shipp IPI factors (age >60, ECOG ≥2, LDH > ULN, Ann Arbor III or IV, extranodal sites >1) plus kidney and/or adrenal involvement; 1 point each, max 6. Low 0–1, intermediate 2–3, high 4–6. CNS relapse risk after R-CHOP in DLBCL. Deterministic published score; not a CNS prophylaxis or LP order; not NCCN-IPI; not R-IPI; not a DLBCL diagnosis. magent does not stage lymphoma or image kidneys.

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

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.

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.

Gupta 2024 Figure 2 simple CP-AKI score after first IV cisplatin: age, hypertension, diabetes, current or former smoking, hemoglobin g/L, WBC, albumin g/L, magnesium mmol/L, and cisplatin dose mg. Max 22.5. Low / moderate / high / very_high. Not a diagnosis or chemo order. magent does not assay labs or dose cisplatin.

Bangalore 2023 composite PE shock score for intermediate-risk PE. Six equally weighted caller-assigned flags (elevated troponin per local assay, elevated BNP, moderate or severe RV dysfunction, saddle PE, concomitant DVT, tachycardia ≥100 beats/min), 1 point each, max 6. Integer 0–6 score only; no named bands. magent does not invent biomarker cutoffs, read echo, or take raw heart rate. Not a shock diagnosis, not sPESI/Bova/PESI, not hypotensive PE, and not a medical device.

Pugin 1991 clinical pulmonary infection score (CPIS, max 12) from temperature, leukocytes and band forms, tracheal secretions, PaO2/FiO2 with ARDS, chest radiograph, and tracheal-aspirate culture. Band CPIS>6 follows the 1991 derivation correlation. Not a VAP diagnosis or Singh modified CPIS.

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.

Gélinas 2006 CPOT from four caller-assigned 0-2 items (facial_expression, body_movements, muscle_tension, plus ventilator_compliance when intubated or vocalization when extubated) using that paper's 0/1/2 descriptors. magent sums only (max 8) and does not observe the patient. No later intensity cutoffs. Not a pain diagnosis or analgesic order. Not PAINAD.

Cerebral perfusion pressure from caller-supplied MAP and ICP in mm Hg: CPP = MAP − ICP, rounded to 1 decimal. Returns cpp_ge_70 when CPP is at least 70 mm Hg (Rosner 1995 protocol minimum). magent does not measure MAP or ICP and is not an invasive monitor. Not a medical device and not a treatment protocol.

Saisho 2011 CPR index: serum C-peptide (ng/mL) / plasma glucose (mg/dL) * 100, two decimals. timing fasting or postprandial (same formula; required label). below_best_cutoff true iff cpri < 2.02 (ROC for later insulin therapy; 80.8% sensitivity, 63.3% specificity). Glucose mg/dL only. Not HOMA-IR, not a diabetes diagnosis, not C-peptide alone, and not an insulin order.

Katz 2015 Cincinnati Prehospital Stroke Severity Scale (CP-SSS): gaze deviation 2 if present else 0 + abnormal LOC 1 + arm cannot hold 10 s 1. Max 4. severe_stroke_suggested iff score ≥ 2. Not the 3-item CPSS facial/arm/speech screen, not NIHSS, not a tPA decision. magent does not examine the patient.

Knight 2002 CRAFFT: six caller-assigned yes/no flags (car, relax, alone, forget, friends, trouble), 1 point each, max 6. Screen-positive when score ≥2 (optimal cutoff in Knight 2002 for any problem / any disorder / dependence). Deterministic published score with citation; not a diagnosis of a substance use disorder and not a medical device. magent does not interview the patient. Not CAGE and not CRAFFT 2.1 / 2.0 quantity questions.

Extermann 2012 CRASH chemotherapy toxicity score (not trauma CRASH): diastolic BP, IADL, LDH versus ULN, caller-assigned MAX2 Chemotox, ECOG, Mini-Mental Status, Mini-Nutritional Assessment. Hematologic 0–6, nonhematologic 0–8, combined 0–12 counting Chemotox once. Four-level low/medium_low/medium_high/high bands with derivation incidences. Not a chemotherapy order and not CARG-TT. magent does not look up regimens.

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.

Cited Cockcroft–Gault creatinine clearance. Agents must not invent CrCl from model memory; pay per request with x402 USDC on Base. Deterministic published formula with citation. Not a treatment recommendation.

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.

Cryoprecipitate bag estimate from the AABB Technical Manual calculation as reprinted in Nascimento 2011: 70 mL/kg blood volume, 250 mg fibrinogen per bag, bags = ceil(mg_fibrinogen / 250). Deterministic published arithmetic with citation. Not a transfusion order or major-haemorrhage protocol. The paper notes 100% recovery is likely false and fibrinogen per bag varies. magent does not choose a product or ABO group.

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.

Static respiratory-system compliance (Cstat) as in ARDS Network 2000 methods: Cstat (mL/cm H2O) = tidal_volume_ml / (pplat_cm_h2o - peep_cm_h2o). Caller supplies the three measured terms. Rejects Pplat less than or equal to PEEP. Does not invent ARDS severity bands from Cstat (Murray 1988 compliance bands are a different tool). Not a ventilator order or medical device. magent does not read the ventilator.

Graham 2006 CTS-6 from six caller-assigned booleans with published discrete weights (median-territory numbness 3.5, nocturnal numbness 4, thenar atrophy or weakness 5, Phalen 5, two-point discrimination loss 4.5, Tinel 4; max 26). Score >5 is associated with ≈25% probability of CTS; score >12 with ≈80%. magent does not examine the patient. Deterministic published arithmetic with citation; not a CTS diagnosis, not an EMG order, not a Boston questionnaire, and not a medical device.

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

Mocroft 2015 D:A:D full CKD risk score (Table 2 integer points only): IDU, hepatitis C, age, caller-assigned eGFR >60, sex, nadir CD4, hypertension, prior CVD, and diabetes. Bands low <0, medium 0–4, high ≥5. Not the short score, not the Poisson probability model, not NNTH, and not an ART start order. Race is not an input.

D'Amico 1998 JAMA clinically localized prostate-cancer groups from caller-assigned T (t1c, t2a, t2b, t2c), Gleason 2-10, and PSA ng/mL (0.1-200). Returns low, intermediate, or high. High if T2c or PSA > 20 or Gleason ≥ 8; else intermediate if T2b or Gleason 7 or PSA > 10 and ≤ 20; else low if T1c/T2a and PSA ≤ 10 and Gleason ≤ 6. Not CAPRA. Not NCCN. magent does not assay PSA or assign Gleason. Not a diagnosis. Not a medical device.

Yeh 2016 DAPT prediction rule after PCI: exclusive age (<65: 0; 65 to younger than 75: -1; 75 or older: -2) plus MI at presentation, prior MI or PCI, diabetes, stent diameter <3 mm, smoking (current or within past year), and paclitaxel-eluting stent (1 each); CHF or LVEF <30% and vein-graft intervention (2 each). Max 10. Score >=2 high, <2 low. Not a duration order. Not a diagnosis.

Wells 2009 DAS28(CRP): 0.56*sqrt(TJC28)+0.28*sqrt(SJC28)+0.014*GH+0.36*ln(CRP+1)+0.96. CRP is mg/L, not SDAI mg/dL. GH is 0-100 mm VAS, not 0-10. The +0.96 constant is required. Remission is DAS28<2.6 as stated in that paper. magent does not count joints or assay CRP. Not DAS28-ESR, SDAI, or CDAI. Not a rheumatoid arthritis diagnosis.

Prevoo 1995 DAS28-ESR: 0.56*sqrt(tjc28) + 0.28*sqrt(sjc28) + 0.70*ln(esr_mm_h) + 0.014*gh (0-100 mm VAS, not 0-10 CDAI/SDAI). Caller-assigned 28-joint counts 0-28; ESR strictly >0 (typical 1-150). magent does not count joints or assay ESR. Score only; Prevoo 1995 does not publish later EULAR 2.6/3.2/5.1 cutoffs. Not SDAI, not CDAI, not DAS28-CRP. Not a rheumatoid arthritis diagnosis.

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.

Hlatky 1989 Duke Activity Status Index. Twelve caller-assigned yes/no items (self-care through strenuous sports); Yes adds the Table I weight, No adds 0. Light housework is 2.70. DASI is the sum (0-58.2). Estimated peak VO2 mL/kg/min = 0.43 x DASI + 9.6. magent does not observe the patient. Not a functional-capacity assignment or exercise-test replacement.

Skinner 1982 10-item Drug Abuse Screening Test (DAST-10). Caller-assigned yes/no items; score is the count of answers in the problem direction (able_to_stop scores 1 if false; the other nine score 1 if true), max 10. Degree-of-problems bands 0 no problems, 1-2 low, 3-5 moderate, 6-8 substantial, 9-10 severe. Not a diagnosis, not a toxicology panel, not DAST-20, and not DAST-28. magent does not interpret the items.

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.