All services

Maxwell 2008 Nottingham hip fracture score: age <=65 0, 66-85 3, >=86 4; male 1; hemoglobin <=10 g/dL 1 (g/L / 10); caller-assigned AMTS <=6, lives in institution, >=2 comorbidities, and malignancy 1 each. Max 10. Integer score only; no predicted 30-day mortality percent. magent does not administer AMTS or clear a patient for surgery. Not the 2012 or 2015 recalibrations.

Tavaglione 2023 fibrotic NASH index (FNI) from AST, HbA1c, and HDL cholesterol. FNI = e^x/(1+e^x) with x = -10.33 + 2.54*ln(AST) + 3.86*ln(HbA1c) - 1.66*ln(HDL mg/dL). HDL may be mg/dL or mmol/L (×38.67). Rule-out ≤0.10; indeterminate between 0.10 and 0.33; rule-in ≥0.33. Not a biopsy, not FIB-4, not the NAFLD fibrosis score, not SAFE, and not BARD.

Thieblemont 2017 MALT-IPI (IELSG-19): age ≥70, Ann Arbor III or IV, LDH > ULN; 1 point each, max 3. Low 0, intermediate 1, high ≥2. Deterministic published score with citation; not a lymphoma diagnosis or treatment choice; original MALT-IPI, not Revised MALT-IPI (no MMS; age is ≥70 not >60), not Shipp IPI. magent does not stage lymphoma or assay LDH.

Grossman 2007 Boston Syncope from eight caller-assigned flags: ACS signs/symptoms, conduction disease, worrisome cardiac history, valvular heart disease, family history of sudden death, persistent abnormal ED vitals, volume depletion, and primary CNS event. high_risk (Boston-positive) iff any is true; low_risk iff none. Adult (enrolled 18+). Not a disposition or admission order. magent does not examine the patient or interpret ECG/hematocrit. Not San Francisco Syncope, EGSYS, ROSE, or OESIL.

Spyropoulos 2011 7-factor associative IMPROVE VTE score during hospitalization: previous VTE 3, known thrombophilia 2, lower-limb paralysis 2, current cancer 2, immobilized >=7 days 1, ICU/CCU stay 1, age >60 1. Max 12. Bands: 0-1; 2-3 (observed VTE 1.5%); >=4 (observed VTE 5.7%). Not a VTE diagnosis or prophylaxis order. Not the 4-factor admission predictive model. Not IMPROVEDD. magent does not examine the patient.

Thompson 1999 Rome II IBS. rome_ii_ibs is true iff at least 12 weeks (need not be consecutive) in the preceding 12 months of abdominal discomfort or pain and at least two of: relieved with defecation, onset associated with a change in stool frequency, and onset associated with a change in stool form. supporting_features_met is 0-3. Caller assigns four flags. magent does not examine the patient. Not a diagnosis, not Rome III, not Rome IV, not Manning, not IBS subtype.

Berlin Definition of ARDS (Ranieri 2012). berlin_ards iff clinical box (onset within 1 week, bilateral opacities not fully explained, origin not fully HF or fluid) and severity mild, moderate, or severe. Severe: PF<=100 with PEEP>=5. Moderate: 100<PF<=200 with PEEP>=5. Mild: 200<PF<=300 with PEEP or CPAP>=5. Caller assigns flags and pf_ratio. magent does not read radiographs or echo, diagnose ARDS, or set ventilator mode. Not AECC 1994, not Kigali, not the oxygenation index.

Stratton 2004 Malnutrition Universal Screening Tool (MUST) for adults. Three additive scores, max 6: BMI (>20 → 0, 18.5–20 → 1 including 20.0, <18.5 → 2); unplanned weight loss % last 3–6 months (<5 → 0, 5–10 → 1 including 10%, >10 → 2); acute disease no nutritional intake >5 days → 2. Risk 0 low, 1 medium, ≥2 high. Caller supplies BMI and weight-loss percent. Not a malnutrition diagnosis, diet order, or MUAC. magent does not weigh 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.

Stanghellini 2016 Rome IV B1 FD. rome_iv_fd is true iff last-3-months criteria with 6-month onset, no structural disease likely to explain symptoms, and PDS (B1a) and/or EPS (B1b). pds iff fullness and/or early satiation >=3 days/week. eps iff epigastric pain and/or burning >=1 day/week. Overlap allowed. Caller assigns six flags. magent does not examine the patient. Not a diagnosis, not Rome III dyspepsia, not Rome IV IBS.

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.

EconDash economic data API (M2M)

RFC 5322 syntax check, live MX resolution and a disposable-provider check for one email address, in a single call.

Live, policy-filtered Taskmarket opportunities suitable for autonomous work agents.

Search Google Jobs by role and location. Returns job ID/title, employer, location, source/application URL, salary when present, contract type, posting time and rank. For job-search and recruiting agents.

Crypto fear & greed index (current + previous reading). JSON.

POST /api/scan — agent-readiness scan for a domain (~$0.01 USDC per call)

No description provided.

Search Services

USD Coin

Chen 2013 kinetic eGFR (KeGFR) from two plasma creatinines, hours between them, caller-assigned steady-state creatinine and corresponding eGFR/CrCl, and required max_delta_pcr_mg_dl_day (Chen usual default 1.5). KeGFR = (SSPCr * CrCl / MeanPCr) * (1 - 24*dPCr / (dTime_hours * MaxdPCr/Day)), clamped at 0 when that (1 - ratio) term is negative. Creatinine mg/dL only. Not a CKD-EPI result. Not a dialysis prescription. magent does not compute MDRD or CKD-EPI.

Kleiner 2005 NAFLD activity score (NAS): caller-assigned steatosis 0-3 (<5% / 5–33% / >33–66% / >66%), lobular_inflammation 0-3 (none / <2 foci per 200× / 2–4 / >4), ballooning 0-2 (none / few / many or prominent). magent sums only (max 8). Fibrosis is not in NAS. Kleiner 2005 reported NAS ≥5 correlated with NASH in that study; that is not a diagnostic algorithm. magent does not read histology and does not return NASH bands.

Live prediction-market odds (Polymarket) — search active markets by keyword and get each outcome's implied probability + 24h volume. For trading, research and forecasting agents.

Gibson 2017 IMPROVEDD VTE score: Spyropoulos 2011 7-factor IMPROVE items (previous VTE 3, known thrombophilia 2, lower-limb paralysis 2, current cancer 2, immobilized >=7 days 1, ICU/CCU 1, age >60 1) plus 2 if caller-assigned D-dimer >=2x ULN. Max 14. low 0-1 vs high >=2 (heightened VTE through 77 days when >=2). Not a VTE diagnosis or prophylaxis order. Not the 4-factor admission model. Not Padua or Caprini. magent does not assay D-dimer.