# IMPACT TBI prognostic score IMPACT Status: LIVE Price: $0.005 USDC `GET /api/calc/impact` HTML: https://magentlab.com/docs/impact Markdown: https://magentlab.com/docs/impact.md Not a medical device. Not a diagnosis, dose, or listing recommendation. ## What it computes Compute the Steyerberg 2008 IMPACT points and 6-month mortality and unfavorable-outcome probabilities from the printed Figure 1 score chart and logistic LPs. model is required (core, extended, or lab). ## When to use When an agent already has admission age, GCS motor, and pupils (and CT / hypoxia / hypotension / labs when using those models) and needs the published IMPACT probabilities. Not MRC CRASH, not a GCS conversion, and not a diagnosis. ## When not to use - Not a medical device. Not a diagnosis, triage, ICU, or withdrawal-of-care decision. - Not MRC CRASH (Perel 2008). magent crash is Extermann 2012 chemotherapy CRASH. - Age, motor, pupils, hypoxia, hypotension, Marshall CT, tSAH, EDH, glucose, and hemoglobin are caller-assigned. magent does not examine the patient, read the scan, or assay labs. - Motor 9 is the published untestable/missing token. magent does not infer motor from a narrative. ## Formula ``` IMPACT (Steyerberg 2008 Fig 1): core = age(<=30:0, 31-39:1, 40-49:2, 50-59:3, 60-69:4, >=70:5) + motor(1-2:6, 3:4, 4:2, 5-6:0, 9:3) + pupils(both:0, one:2, none:4); extended = core + hypoxia(yes/suspected:1) + hypotension(yes/suspected:2) + marshall(I:-2, II:0, III-VI:2) + tSAH(yes:2) + EDH(yes:-2); lab = extended + glucose_mmol_l(<6:0, 6-8.9:1, 9-11.9:2, 12-14.9:3, >=15:4) + hb_g_dl(<9:3, 9-11.9:2, 12-14.9:1, >=15:0); p = 1/(1+e^(-LP)); LPcore mort=-2.55+0.275*sum; LPcore unfav=-1.62+0.299*sum; LPext mort=-2.98+0.256*sum; LPext unfav=-2.10+0.276*sum; LPlab mort=-3.42+0.216*sum; LPlab unfav=-2.82+0.257*sum; 6-month percent 1 decimal; not MRC CRASH ``` ## Citation [Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics](https://doi.org/10.1371/journal.pmed.0050165) Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, Murray GD, Marmarou A, Roberts I, Habbema JDF, Maas AIR PLoS Med. 2008;5(8):e165 DOI: [10.1371/journal.pmed.0050165](https://doi.org/10.1371/journal.pmed.0050165) ## Worked example ### Paper core example: age 35, motor 3, both pupils Given: `age=35, model=core, motor_score=3, pupillary_reactivity=both` 1. age 35 → 1; motor 3 → 4; pupils both → 0 2. core sum = 5 3. LPmort = -2.55 + 0.275 × 5 = -1.175 → 23.6% 4. LPunfav = -1.62 + 0.299 × 5 = -0.125 ### Same patient extended: hypoxia, Marshall V, tSAH, no hypotension or EDH Given: `age=35, edh=false, hypotension=false, hypoxia=true, marshall_ct=V, model=extended, motor_score=3, pupillary_reactivity=both, tsah=true` 1. core 5 + hypoxia 1 + hypotension 0 + Marshall V 2 + tSAH 2 + EDH 0 2. extended sum = 10 ### Same patient lab: glucose 10 mmol/L, Hb 11 g/dL Given: `age=35, edh=false, glucose_mmol_l=10, hemoglobin_g_dl=11, hypotension=false, hypoxia=true, marshall_ct=V, model=lab, motor_score=3, pupillary_reactivity=both, tsah=true` 1. extended 10 + glucose 10 → 2 + Hb 11 → 2 2. lab sum = 14 ## Also searched as - IMPACT score - IMPACT TBI - Steyerberg IMPACT - traumatic brain injury prognosis - IMPACT core model - IMPACT extended model - IMPACT lab model - 6-month TBI outcome - Marshall CT IMPACT - International Mission for Prognosis ## Parameters - `model` (string, required): Steyerberg 2008 IMPACT model. core uses age, motor, and pupils. extended adds hypoxia, hypotension, Marshall CT, tSAH, and EDH. lab adds glucose mmol/L and hemoglobin g/dL. Required; magent does not pick a model. - `age` (integer, required): Age in years (integer 14-90). Steyerberg 2008 Figure 1: ≤30 → 0; 31–39 → 1; 40–49 → 2; 50–59 → 3; 60–69 → 4; ≥70 → 5. Chart label 30–39 is the decade after ≤30 (age 30 scores 0). - `motor_score` (integer, required): GCS motor integer 1-6 or 9 (untestable/missing) as in Steyerberg 2008. 1 or 2 (none/extension) → 6; 3 (abnormal flexion) → 4; 4 (normal flexion) → 2; 5 or 6 (localizes/obeys) → 0; 9 → 3. - `pupillary_reactivity` (string, required): Pupillary reactivity (Steyerberg 2008). both → 0; one → 2; none → 4. Caller-assigned. magent does not examine pupils. - `hypoxia` (boolean, optional): Hypoxia yes or suspected (Steyerberg 2008). Required when model is extended or lab. true adds 1; false adds 0. Ignored on model=core. - `hypotension` (boolean, optional): Hypotension yes or suspected (Steyerberg 2008). Required when model is extended or lab. true adds 2; false adds 0. Ignored on model=core. - `marshall_ct` (string, optional): Marshall CT class I–VI (Steyerberg 2008). Required when model is extended or lab. I → −2; II → 0; III, IV, V, or VI → 2. Ignored on model=core. magent does not read the scan. - `tsah` (boolean, optional): Traumatic subarachnoid hemorrhage (Steyerberg 2008). Required when model is extended or lab. true adds 2; false adds 0. Ignored on model=core. - `edh` (boolean, optional): Epidural hematoma (Steyerberg 2008). Required when model is extended or lab. true adds −2; false adds 0. Ignored on model=core. - `glucose_mmol_l` (number, optional): Admission glucose in mmol/L (2.8-55.5). Required when model is lab. Steyerberg 2008: <6 → 0; 6–8.9 → 1; 9–11.9 → 2; 12–14.9 → 3; ≥15 → 4. Ignored on core and extended. magent does not assay glucose. - `hemoglobin_g_dl` (number, optional): Admission hemoglobin in g/dL (3-22). Required when model is lab. Steyerberg 2008: <9 → 3; 9–11.9 → 2; 12–14.9 → 1; ≥15 → 0. Ignored on core and extended. magent does not assay hemoglobin. ## 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/impact` 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": [ { "age": "35", "model": "core", "motor_score": "3", "pupillary_reactivity": "both" }, { "age": "35", "model": "core", "motor_score": "3", "pupillary_reactivity": "both" } ] } ``` Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/impact Example 200: ```json { "count": 2, "path": "/api/calc/impact", "items": [ { "components": [ { "value": 35, "factor": "age", "points": 1, "present": true }, { "value": 3, "factor": "motor_score", "points": 4, "present": true }, { "value": "both", "factor": "pupillary_reactivity", "points": 0, "present": false } ], "age": 35, "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": "Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, Murray GD, Marmarou A, Roberts I, Habbema JDF, Maas AIR", "doi": "10.1371/journal.pmed.0050165", "id": "steyerberg-2008-impact", "pmid": "18640954", "source": "PLoS Med. 2008;5(8):e165", "title": "Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics" }, "formula": "impact", "formula_expression": "IMPACT (Steyerberg 2008 Fig 1): core = age(<=30:0, 31-39:1, 40-49:2, 50-59:3, 60-69:4, >=70:5) + motor(1-2:6, 3:4, 4:2, 5-6:0, 9:3) + pupils(both:0, one:2, none:4); extended = core + hypoxia(yes/suspected:1) + hypotension(yes/suspected:2) + marshall(I:-2, II:0, III-VI:2) + tSAH(yes:2) + EDH(yes:-2); lab = extended + glucose_mmol_l(<6:0, 6-8.9:1, 9-11.9:2, 12-14.9:3, >=15:4) + hb_g_dl(<9:3, 9-11.9:2, 12-14.9:1, >=15:0); p = 1/(1+e^(-LP)); LPcore mort=-2.55+0.275*sum; LPcore unfav=-1.62+0.299*sum; LPext mort=-2.98+0.256*sum; LPext unfav=-2.10+0.276*sum; LPlab mort=-3.42+0.216*sum; LPlab unfav=-2.82+0.257*sum; 6-month percent 1 decimal; not MRC CRASH", "max_score": 15, "score": 5, "linear_predictor_mortality": -1.175, "linear_predictor_unfavorable": -0.125, "model": "core", "mortality_6_month_percent": 23.6, "motor_score": 3, "pupillary_reactivity": "both", "sum_core": 5, "unfavorable_6_month_percent": 46.9 }, { "components": [ { "value": 35, "factor": "age", "points": 1, "present": true }, { "value": 3, "factor": "motor_score", "points": 4, "present": true }, { "value": "both", "factor": "pupillary_reactivity", "points": 0, "present": false } ], "age": 35, "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": "Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, Murray GD, Marmarou A, Roberts I, Habbema JDF, Maas AIR", "doi": "10.1371/journal.pmed.0050165", "id": "steyerberg-2008-impact", "pmid": "18640954", "source": "PLoS Med. 2008;5(8):e165", "title": "Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics" }, "formula": "impact", "formula_expression": "IMPACT (Steyerberg 2008 Fig 1): core = age(<=30:0, 31-39:1, 40-49:2, 50-59:3, 60-69:4, >=70:5) + motor(1-2:6, 3:4, 4:2, 5-6:0, 9:3) + pupils(both:0, one:2, none:4); extended = core + hypoxia(yes/suspected:1) + hypotension(yes/suspected:2) + marshall(I:-2, II:0, III-VI:2) + tSAH(yes:2) + EDH(yes:-2); lab = extended + glucose_mmol_l(<6:0, 6-8.9:1, 9-11.9:2, 12-14.9:3, >=15:4) + hb_g_dl(<9:3, 9-11.9:2, 12-14.9:1, >=15:0); p = 1/(1+e^(-LP)); LPcore mort=-2.55+0.275*sum; LPcore unfav=-1.62+0.299*sum; LPext mort=-2.98+0.256*sum; LPext unfav=-2.10+0.276*sum; LPlab mort=-3.42+0.216*sum; LPlab unfav=-2.82+0.257*sum; 6-month percent 1 decimal; not MRC CRASH", "max_score": 15, "score": 5, "linear_predictor_mortality": -1.175, "linear_predictor_unfavorable": -0.125, "model": "core", "mortality_6_month_percent": 23.6, "motor_score": 3, "pupillary_reactivity": "both", "sum_core": 5, "unfavorable_6_month_percent": 46.9 } ] } ``` ## Response fields - `formula` (string): impact - `formula_expression` (string): Exact expression used - `model` (string): core, extended, or lab - `age` (integer): Input age in years - `motor_score` (integer): Input GCS motor 1-6 or 9 - `pupillary_reactivity` (string): Input pupils both, one, or none - `score` (integer): Model sum (core, core+CT, or core+CT+lab) - `sum_core` (integer): Age + motor + pupils points - `subscore_ct` (integer): Extended CT subscore. Present when model is extended or lab. - `subscore_lab` (integer): Lab subscore (glucose + Hb). Present when model is lab. - `hypoxia` (boolean): Hypoxia flag used when model is extended or lab - `hypotension` (boolean): Hypotension flag used when model is extended or lab - `marshall_ct` (string): Marshall class used when model is extended or lab - `tsah` (boolean): tSAH flag used when model is extended or lab - `edh` (boolean): EDH flag used when model is extended or lab - `glucose_mmol_l` (number): Glucose used when model is lab - `hemoglobin_g_dl` (number): Hemoglobin used when model is lab - `max_score` (integer): 15 core, 22 extended, 29 lab - `components` (array): Per-factor points - `linear_predictor_mortality` (number): Printed Steyerberg 2008 mortality LP, 3 decimals - `linear_predictor_unfavorable` (number): Printed Steyerberg 2008 unfavorable LP, 3 decimals - `mortality_6_month_percent` (number): 6-month mortality percent, 1 decimal - `unfavorable_6_month_percent` (number): 6-month unfavorable-outcome percent, 1 decimal - `citation` (object): Steyerberg et al. PLoS Med 2008 citation - `disclaimer` (string): Not-a-device notice ## Example JSON Frozen fixture. Not a live lookup. ```json { "components": [ { "value": 35, "factor": "age", "points": 1, "present": true }, { "value": 3, "factor": "motor_score", "points": 4, "present": true }, { "value": "both", "factor": "pupillary_reactivity", "points": 0, "present": false } ], "age": 35, "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": "Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, Murray GD, Marmarou A, Roberts I, Habbema JDF, Maas AIR", "doi": "10.1371/journal.pmed.0050165", "id": "steyerberg-2008-impact", "pmid": "18640954", "source": "PLoS Med. 2008;5(8):e165", "title": "Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics" }, "formula": "impact", "formula_expression": "IMPACT (Steyerberg 2008 Fig 1): core = age(<=30:0, 31-39:1, 40-49:2, 50-59:3, 60-69:4, >=70:5) + motor(1-2:6, 3:4, 4:2, 5-6:0, 9:3) + pupils(both:0, one:2, none:4); extended = core + hypoxia(yes/suspected:1) + hypotension(yes/suspected:2) + marshall(I:-2, II:0, III-VI:2) + tSAH(yes:2) + EDH(yes:-2); lab = extended + glucose_mmol_l(<6:0, 6-8.9:1, 9-11.9:2, 12-14.9:3, >=15:4) + hb_g_dl(<9:3, 9-11.9:2, 12-14.9:1, >=15:0); p = 1/(1+e^(-LP)); LPcore mort=-2.55+0.275*sum; LPcore unfav=-1.62+0.299*sum; LPext mort=-2.98+0.256*sum; LPext unfav=-2.10+0.276*sum; LPlab mort=-3.42+0.216*sum; LPlab unfav=-2.82+0.257*sum; 6-month percent 1 decimal; not MRC CRASH", "max_score": 15, "score": 5, "linear_predictor_mortality": -1.175, "linear_predictor_unfavorable": -0.125, "model": "core", "mortality_6_month_percent": 23.6, "motor_score": 3, "pupillary_reactivity": "both", "sum_core": 5, "unfavorable_6_month_percent": 46.9 } ``` ## Errors - HTTP 400 `invalid_impact`: IMPACT model inputs must match Steyerberg 2008 (age, motor score, pupils; extended and lab add hypoxia, hypotension, CT, glucose, Hb). Returned before settlement; you are not charged. - HTTP 400 `invalid_impact_model`: model must be core, extended, or lab as in Steyerberg 2008. Returned before settlement; you are not charged. - HTTP 400 `invalid_age`: age must be an integer from 18 to 120 Returned before settlement; you are not charged. - HTTP 400 `invalid_motor_score`: motor_score must be 1-6 or 9 (untestable) as in Steyerberg 2008 IMPACT. Returned before settlement; you are not charged. - HTTP 400 `invalid_pupillary`: pupillary_reactivity must be both, one, or none as in Steyerberg 2008. Returned before settlement; you are not charged. - HTTP 400 `invalid_flag`: boolean clinical flags must be true or false Returned before settlement; you are not charged. - HTTP 400 `invalid_marshall_ct`: marshall_ct must be I, II, III, IV, V, or VI as in Steyerberg 2008. Returned before settlement; you are not charged. - HTTP 400 `invalid_glucose`: glucose_mg_dl (50-1000) or glucose_mmol_l (2.8-55.5) is required Returned before settlement; you are not charged. - HTTP 400 `invalid_hemoglobin`: hemoglobin_g_l (30-220) or hemoglobin_g_dl (3-22) is required, not both. 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 - [Glasgow Coma Scale](https://magentlab.com/docs/gcs) — Compute the Glasgow Coma Scale as the sum of caller-assigned eye, verbal, and motor integers. The 1974 or 1976 edition is required. - [GCS-Pupils](https://magentlab.com/docs/gcs-pupils) — Return the Brennan 2018 GCS-Pupils index as caller-assigned total GCS 3-15 minus pupil reactivity score (unreactive pupils 0, 1, or 2). - [FOUR score](https://magentlab.com/docs/four-score) — Compute the FOUR score as the sum of caller-assigned eye, motor, brainstem, and respiration integers 0-4. ## 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.