# HIT Expert Probability (HEP) score HEP score Status: LIVE Price: $0.005 USDC `GET /api/calc/hep` HTML: https://magentlab.com/docs/hep Markdown: https://magentlab.com/docs/hep.md Not a medical device. Not a diagnosis, dose, or listing recommendation. ## What it computes Sum the Cuker 2010 HIT Expert Probability (HEP) eight clinical features with published signed integer weights and return the 2010 cutoff-2 and cutoff-5 operating points. ## When to use When an agent has already applied the Cuker 2010 HEP table and needs the published signed total, not a 4Ts score, HIT antibody result, SRA, or ELISA. ## When not to use - Not a medical device. Not a diagnosis of HIT. - This is the Cuker 2010 HEP score, not the 4Ts score (Lo 2006) and not a HIT antibody, SRA, or ELISA result. - Items are caller-assigned from the published 2010 table. magent does not grade platelet counts, day of onset, or assay SRA/ELISA. - Cutoff 2 (100% sensitive / 60% specific vs expert panel) and cutoff 5 (86% / 88%) are 2010 operating-characteristic points, not a HIT diagnosis. ## Formula ``` HEP = magnitude (lt_30 -1, 30_to_50 1, gt_50 3) + timing (typical_lt_4 -2, typical_day_4 2, typical_5_10 3, typical_11_14 2, typical_gt_14 -1; rapid_lt_48h 2, rapid_gt_48h -1) + nadir (le_20 -2, gt_20 2) + thrombosis select at most one (none 0; typical_new_ge_4d 3, typical_progression 2; rapid_new 3, rapid_progression 2) + skin_necrosis 3 + systemic_reaction 2 + bleeding -1 + other causes select all (chronic_thrombocytopenia -1, new_drug_thrombocytopenia -2, severe_infection -2, overt_dic -2, intra_arterial_device -2, cpb_96h -1, no_other_cause 3 mutually exclusive with other causes); Cuker 2010; range -16 to 19; cutoff 2 was 100% sensitive / 60% specific vs expert panel; cutoff 5 was 86% sensitive / 88% specific ``` ## Citation [The HIT Expert Probability (HEP) Score: a novel pre-test probability model for heparin-induced thrombocytopenia based on broad expert opinion](https://doi.org/10.1111/j.1538-7836.2010.04059.x) Cuker A, Arepally G, Crowther MA, Rice L, Datko F, Hook K, Propert KJ, Kuter DJ, Ortel TL, Konkle BA, Cines DB J Thromb Haemost. 2010;8(12):2642-2650 DOI: [10.1111/j.1538-7836.2010.04059.x](https://doi.org/10.1111/j.1538-7836.2010.04059.x) ## Worked example ### Typical-onset high features, no other cause Given: `bleeding=false, chronic_thrombocytopenia=false, cpb_96h=false, intra_arterial_device=false, magnitude=gt_50, nadir=gt_20, new_drug_thrombocytopenia=false, no_other_cause=true, overt_dic=false, severe_infection=false, skin_necrosis=false, systemic_reaction=false, thrombosis=typical_new_ge_4d, timing=typical_5_10` 1. magnitude gt_50 +3; typical_5_10 +3; nadir gt_20 +2; typical_new_ge_4d +3 2. skin_necrosis 0; systemic_reaction 0; bleeding 0; no_other_cause +3 3. Score = 14 (max 19); score_ge_2 true; score_ge_5 true ## Also searched as - HIT Expert Probability - HEP score - Cuker HEP - heparin-induced thrombocytopenia HEP - HEP pretest HIT - Cuker 2010 HEP - HIT expert score ## Parameters - `magnitude` (string, required): Caller-assigned Cuker 2010 magnitude of platelet fall (peak to nadir since heparin exposure). lt_30 (<30%) scores -1; 30_to_50 (30-50%) scores 1; gt_50 (>50%) scores 3. magent does not grade platelet counts. - `timing` (string, required): Caller-assigned Cuker 2010 timing. Typical-onset: typical_lt_4 (fall begins <4 days) -2; typical_day_4 (day 4) 2; typical_5_10 (days 5-10) 3; typical_11_14 (days 11-14) 2; typical_gt_14 (>14 days) -1. Rapid-onset after re-exposure within 100 days: rapid_lt_48h (<48 h) 2; rapid_gt_48h (>48 h) -1. magent does not infer day of onset. - `nadir` (string, required): Caller-assigned Cuker 2010 nadir platelet count. le_20 (≤20 ×10^9/L) scores -2; gt_20 (>20 ×10^9/L) scores 2. magent does not take a raw platelet count. - `thrombosis` (string, required): Caller-assigned Cuker 2010 thrombosis (select at most one). none scores 0. Typical-onset: typical_new_ge_4d (new VTE or ATE ≥4 days after heparin) 3; typical_progression (progression of preexisting VTE or ATE while receiving heparin) 2. Rapid-onset: rapid_new (new VTE or ATE after heparin) 3; rapid_progression 2. - `skin_necrosis` (boolean, required): Skin necrosis at subcutaneous heparin injection sites (Cuker 2010). true scores 3; false scores 0. magent does not examine the skin. - `systemic_reaction` (boolean, required): Acute systemic reaction after intravenous heparin bolus (Cuker 2010). true scores 2; false scores 0. - `bleeding` (boolean, required): Presence of bleeding, petechiae, or extensive bruising (Cuker 2010). true scores -1; false scores 0. - `chronic_thrombocytopenia` (boolean, required): Presence of a chronic thrombocytopenic disorder (Cuker 2010 other causes; select all that apply). true scores -1. Mutually exclusive with no_other_cause true. - `new_drug_thrombocytopenia` (boolean, required): Newly initiated non-heparin medication known to cause thrombocytopenia (Cuker 2010). true scores -2. Mutually exclusive with no_other_cause true. - `severe_infection` (boolean, required): Severe infection as an other cause of thrombocytopenia (Cuker 2010). true scores -2. Mutually exclusive with no_other_cause true. - `overt_dic` (boolean, required): Overt DIC as assigned by the caller (Cuker 2010: fibrinogen <100 mg/dL and D-dimer >5.0 μg/mL). true scores -2. magent does not assay fibrinogen or D-dimer. Mutually exclusive with no_other_cause true. - `intra_arterial_device` (boolean, required): Indwelling intra-arterial device (Cuker 2010 examples: IABP, VAD, ECMO). true scores -2. Mutually exclusive with no_other_cause true. - `cpb_96h` (boolean, required): Cardiopulmonary bypass within the previous 96 hours (Cuker 2010). true scores -1. Mutually exclusive with no_other_cause true. - `no_other_cause` (boolean, required): No other apparent cause of thrombocytopenia (Cuker 2010). true scores 3. Must be false if any other-cause flag is true. ## Bulk (POST) POST the same path with a JSON items array. The first item is the GET unit; each additional item is $0.002. Invalid items return HTTP 400 before settlement. Method: `POST /api/calc/hep` Max items: 25 Price: unit_amount + extra_item_amount * (n - 1) (unit 5000 atomic, extra 2000 atomic) Status: PREVIEW - 1 to 25 items. Each item uses the same keys as the GET query parameters. - POST of 1 item costs the same as GET. Lists longer than 25: chunk into multiple POSTs. Extra items still execute; do not pad dummy rows. - The first invalid item fails the whole request (index in the 400 JSON). You are not charged. - HTTP 200 is {count, path, items}. Each items[i] is the GET 200 body for that row. - Catalog misses (empty matches, found=false) stay paid 200s inside that slot. - x402 resource URL is this path plus n and body_sha256. Browsers that prefer text/html get the same paywall as GET; Pay retries POST with the same items. Example request: ```json { "items": [ { "bleeding": "false", "chronic_thrombocytopenia": "false", "cpb_96h": "false", "intra_arterial_device": "false", "magnitude": "gt_50", "nadir": "gt_20", "new_drug_thrombocytopenia": "false", "no_other_cause": "true", "overt_dic": "false", "severe_infection": "false", "skin_necrosis": "false", "systemic_reaction": "false", "thrombosis": "typical_new_ge_4d", "timing": "typical_5_10" }, { "bleeding": "false", "chronic_thrombocytopenia": "false", "cpb_96h": "false", "intra_arterial_device": "false", "magnitude": "gt_50", "nadir": "gt_20", "new_drug_thrombocytopenia": "false", "no_other_cause": "true", "overt_dic": "false", "severe_infection": "false", "skin_necrosis": "false", "systemic_reaction": "false", "thrombosis": "typical_new_ge_4d", "timing": "typical_5_10" } ] } ``` Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/hep Example 200: ```json { "count": 2, "path": "/api/calc/hep", "items": [ { "components": [ { "value": "gt_50", "factor": "magnitude", "points": 3, "present": true }, { "value": "typical_5_10", "factor": "timing", "points": 3, "present": true }, { "value": "gt_20", "factor": "nadir", "points": 2, "present": true }, { "value": "typical_new_ge_4d", "factor": "thrombosis", "points": 3, "present": true }, { "factor": "skin_necrosis", "points": 0, "present": false }, { "factor": "systemic_reaction", "points": 0, "present": false }, { "factor": "bleeding", "points": 0, "present": false }, { "factor": "chronic_thrombocytopenia", "points": 0, "present": false }, { "factor": "new_drug_thrombocytopenia", "points": 0, "present": false }, { "factor": "severe_infection", "points": 0, "present": false }, { "factor": "overt_dic", "points": 0, "present": false }, { "factor": "intra_arterial_device", "points": 0, "present": false }, { "factor": "cpb_96h", "points": 0, "present": false }, { "factor": "no_other_cause", "points": 3, "present": true } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Cuker A, Arepally G, Crowther MA, Rice L, Datko F, Hook K, Propert KJ, Kuter DJ, Ortel TL, Konkle BA, Cines DB", "doi": "10.1111/j.1538-7836.2010.04059.x", "id": "cuker-2010", "pmid": "20854372", "source": "J Thromb Haemost. 2010;8(12):2642-2650", "title": "The HIT Expert Probability (HEP) Score: a novel pre-test probability model for heparin-induced thrombocytopenia based on broad expert opinion" }, "formula": "hep", "formula_expression": "HEP = magnitude (lt_30 -1, 30_to_50 1, gt_50 3) + timing (typical_lt_4 -2, typical_day_4 2, typical_5_10 3, typical_11_14 2, typical_gt_14 -1; rapid_lt_48h 2, rapid_gt_48h -1) + nadir (le_20 -2, gt_20 2) + thrombosis select at most one (none 0; typical_new_ge_4d 3, typical_progression 2; rapid_new 3, rapid_progression 2) + skin_necrosis 3 + systemic_reaction 2 + bleeding -1 + other causes select all (chronic_thrombocytopenia -1, new_drug_thrombocytopenia -2, severe_infection -2, overt_dic -2, intra_arterial_device -2, cpb_96h -1, no_other_cause 3 mutually exclusive with other causes); Cuker 2010; range -16 to 19; cutoff 2 was 100% sensitive / 60% specific vs expert panel; cutoff 5 was 86% sensitive / 88% specific", "max_score": 19, "score": 14, "score_ge_2": true, "score_ge_5": true }, { "components": [ { "value": "gt_50", "factor": "magnitude", "points": 3, "present": true }, { "value": "typical_5_10", "factor": "timing", "points": 3, "present": true }, { "value": "gt_20", "factor": "nadir", "points": 2, "present": true }, { "value": "typical_new_ge_4d", "factor": "thrombosis", "points": 3, "present": true }, { "factor": "skin_necrosis", "points": 0, "present": false }, { "factor": "systemic_reaction", "points": 0, "present": false }, { "factor": "bleeding", "points": 0, "present": false }, { "factor": "chronic_thrombocytopenia", "points": 0, "present": false }, { "factor": "new_drug_thrombocytopenia", "points": 0, "present": false }, { "factor": "severe_infection", "points": 0, "present": false }, { "factor": "overt_dic", "points": 0, "present": false }, { "factor": "intra_arterial_device", "points": 0, "present": false }, { "factor": "cpb_96h", "points": 0, "present": false }, { "factor": "no_other_cause", "points": 3, "present": true } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Cuker A, Arepally G, Crowther MA, Rice L, Datko F, Hook K, Propert KJ, Kuter DJ, Ortel TL, Konkle BA, Cines DB", "doi": "10.1111/j.1538-7836.2010.04059.x", "id": "cuker-2010", "pmid": "20854372", "source": "J Thromb Haemost. 2010;8(12):2642-2650", "title": "The HIT Expert Probability (HEP) Score: a novel pre-test probability model for heparin-induced thrombocytopenia based on broad expert opinion" }, "formula": "hep", "formula_expression": "HEP = magnitude (lt_30 -1, 30_to_50 1, gt_50 3) + timing (typical_lt_4 -2, typical_day_4 2, typical_5_10 3, typical_11_14 2, typical_gt_14 -1; rapid_lt_48h 2, rapid_gt_48h -1) + nadir (le_20 -2, gt_20 2) + thrombosis select at most one (none 0; typical_new_ge_4d 3, typical_progression 2; rapid_new 3, rapid_progression 2) + skin_necrosis 3 + systemic_reaction 2 + bleeding -1 + other causes select all (chronic_thrombocytopenia -1, new_drug_thrombocytopenia -2, severe_infection -2, overt_dic -2, intra_arterial_device -2, cpb_96h -1, no_other_cause 3 mutually exclusive with other causes); Cuker 2010; range -16 to 19; cutoff 2 was 100% sensitive / 60% specific vs expert panel; cutoff 5 was 86% sensitive / 88% specific", "max_score": 19, "score": 14, "score_ge_2": true, "score_ge_5": true } ] } ``` ## Response fields - `formula` (string): hep - `formula_expression` (string): Exact expression used - `score` (integer): HEP points (signed; published range -16 to 19) - `max_score` (integer): 19 - `score_ge_2` (boolean): true iff score ≥ 2 (Cuker 2010 cutoff 2: 100% sensitive / 60% specific vs expert panel). Not a HIT diagnosis. - `score_ge_5` (boolean): true iff score ≥ 5 (Cuker 2010 cutoff 5: 86% sensitive / 88% specific). Not a HIT diagnosis. - `components` (array): Per-feature signed points - `citation` (object): Cuker 2010 citation - `disclaimer` (string): Not-a-device notice ## Example JSON Frozen fixture. Not a live lookup. ```json { "components": [ { "value": "gt_50", "factor": "magnitude", "points": 3, "present": true }, { "value": "typical_5_10", "factor": "timing", "points": 3, "present": true }, { "value": "gt_20", "factor": "nadir", "points": 2, "present": true }, { "value": "typical_new_ge_4d", "factor": "thrombosis", "points": 3, "present": true }, { "factor": "skin_necrosis", "points": 0, "present": false }, { "factor": "systemic_reaction", "points": 0, "present": false }, { "factor": "bleeding", "points": 0, "present": false }, { "factor": "chronic_thrombocytopenia", "points": 0, "present": false }, { "factor": "new_drug_thrombocytopenia", "points": 0, "present": false }, { "factor": "severe_infection", "points": 0, "present": false }, { "factor": "overt_dic", "points": 0, "present": false }, { "factor": "intra_arterial_device", "points": 0, "present": false }, { "factor": "cpb_96h", "points": 0, "present": false }, { "factor": "no_other_cause", "points": 3, "present": true } ], "disclaimer": "Not a medical device. Deterministic published-formula or published-code output for autonomous agents. A licensed clinician remains responsible for patient care and billing submissions.", "citation": { "authors": "Cuker A, Arepally G, Crowther MA, Rice L, Datko F, Hook K, Propert KJ, Kuter DJ, Ortel TL, Konkle BA, Cines DB", "doi": "10.1111/j.1538-7836.2010.04059.x", "id": "cuker-2010", "pmid": "20854372", "source": "J Thromb Haemost. 2010;8(12):2642-2650", "title": "The HIT Expert Probability (HEP) Score: a novel pre-test probability model for heparin-induced thrombocytopenia based on broad expert opinion" }, "formula": "hep", "formula_expression": "HEP = magnitude (lt_30 -1, 30_to_50 1, gt_50 3) + timing (typical_lt_4 -2, typical_day_4 2, typical_5_10 3, typical_11_14 2, typical_gt_14 -1; rapid_lt_48h 2, rapid_gt_48h -1) + nadir (le_20 -2, gt_20 2) + thrombosis select at most one (none 0; typical_new_ge_4d 3, typical_progression 2; rapid_new 3, rapid_progression 2) + skin_necrosis 3 + systemic_reaction 2 + bleeding -1 + other causes select all (chronic_thrombocytopenia -1, new_drug_thrombocytopenia -2, severe_infection -2, overt_dic -2, intra_arterial_device -2, cpb_96h -1, no_other_cause 3 mutually exclusive with other causes); Cuker 2010; range -16 to 19; cutoff 2 was 100% sensitive / 60% specific vs expert panel; cutoff 5 was 86% sensitive / 88% specific", "max_score": 19, "score": 14, "score_ge_2": true, "score_ge_5": true } ``` ## Errors - HTTP 400 `invalid_hep`: HEP items must use Cuker 2010 Table point values (signed integers as published; not the 4Ts score). Returned before settlement; you are not charged. - HTTP 400 `invalid_items`: POST body must be a JSON object with only an items array Returned before settlement; you are not charged. - HTTP 400 `invalid_item_count`: items must be an array of 1 to 25 objects Returned before settlement; you are not charged. - HTTP 400 `invalid_item`: each items entry must be a JSON object Returned before settlement; you are not charged. Shared HTTP 402 and 503: https://magentlab.com/docs/payments ## Related tools - [4Ts score](https://magentlab.com/docs/four-ts) — Compute the Lo 2006 4Ts score as the sum of four caller-assigned integers 0-2 (thrombocytopenia, timing, thrombosis, other causes). - [PLASMIC score](https://magentlab.com/docs/plasmic) — Sum the seven Bendapudi 2017 PLASMIC items and return the published 0-4 / 5 / 6-7 pretest band for severe ADAMTS13 deficiency. - [ISTH overt DIC](https://magentlab.com/docs/isth-dic) — Sum the four Taylor 2001 ISTH SSC overt DIC laboratory items (platelets, fibrin-related marker, PT prolongation, fibrinogen) and return the published <5 / >=5 band. ## Payment Unpaid requests return HTTP 402 even if query parameters or POST items are missing or invalid, so CDP and agents can index the path. After a PAYMENT-SIGNATURE, invalid params return HTTP 400 JSON before settlement. magent does not charge. Fix the params, then request a new 402 quote for that complete URL. Catalog misses (empty matches, found=false) are valid paid 200s. - GET the tool with Accept: application/json (do not send Accept: text/html unless you want the human paywall). - HTTP 402 means you have not paid. Decode the base64 PAYMENT-REQUIRED header. HTTP 503 is not a new quote. - Sign accepts[0] (exact, EIP-3009) with validBefore = now + maxTimeoutSeconds (600 seconds), or accepts[1] (batch-settlement deposit/voucher) on product GET. Ping and POST {items} stay exact. Magent retries transient facilitator 429/5xx before answering. - Retry the same URL with PAYMENT-SIGNATURE (base64 JSON of accepted and payload). Magent attaches canonical extensions.bazaar on CDP verify/settle; echoing 402 bazaar is optional. - Success is HTTP 200 JSON plus PAYMENT-RESPONSE. exact settles before the tool. batch-settlement verifies (and deposit-settles) before the tool and commits the charge after HTTP 2xx. HTTP 503: retry the same PAYMENT-SIGNATURE. Mint a new exact nonce only after a new HTTP 402. - offered `exact` on eip155:8453: Fixed-price USDC on Base. The buyer authorizes the advertised amount (EIP-3009). magent settles before the tool runs (paymentFlow upfront). extra.assetTransferMethod=eip3009 extra.paymentFlow=upfront. - offered `batch-settlement` on eip155:8453: Payment-channel vouchers claimed later in batches. Exact stays accepts[0]. Same-path POST {items} is still exact. extra.assetTransferMethod=eip3009 extra.paymentFlow=authorization. - not offered `upto`: Not offered. Usage-based: buyer authorizes a ceiling, seller settles the actual amount after work. Reserved for a future metered tool. Not for current calculators or code search. Same-path POST {items} is still scheme exact: one EIP-3009 authorization for GET unit plus $0.002 per extra item. That is not x402 batch-settlement (payment channels / vouchers). Shared HTTP 402 and 503 table: https://magentlab.com/docs/payments Stdio MCP (one process per host): https://magentlab.com/docs/mcp ## Guarantees - HTTP 402 is unpaid, including a missing query. After PAYMENT-SIGNATURE, invalid parameters return HTTP 400 before settlement. You are not charged. HTTP 402 never includes the tool JSON. - exact: settlement finishes before the tool (paymentFlow upfront). batch-settlement: verify/deposit before the tool; chargedCumulativeAmount commits after HTTP 2xx. Uncertain or failed settlement fails closed (HTTP 503). Retry the same PAYMENT-SIGNATURE. - HTTP 402 is unpaid only. Do not sign a second authorization because of a 503. - Execution is timeout-bounded and concurrency-capped. - Calculator inputs are stored encrypted for allowlisted operators (Magent Console). They are not in public logs, SSH lookups, catalog, or rollups. Request logs store path without query.