Neurology · LIVE
IMPACT TBI prognostic score
IMPACT
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).
Markdown: /docs/impact.md · Canonical: https://magentlab.com/docs/impact
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
- Authors
- Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, Murray GD, Marmarou A, Roberts I, Habbema JDF, Maas AIR
- Source
- PLoS Med. 2008;5(8):e165
Worked example
Paper core example: age 35, motor 3, both pupils
Given:
age=35model=coremotor_score=3pupillary_reactivity=both
- age 35 → 1; motor 3 → 4; pupils both → 0
- core sum = 5
- LPmort = -2.55 + 0.275 × 5 = -1.175 → 23.6%
- LPunfav = -1.62 + 0.299 × 5 = -0.125
Same patient extended: hypoxia, Marshall V, tSAH, no hypotension or EDH
Given:
age=35edh=falsehypotension=falsehypoxia=truemarshall_ct=Vmodel=extendedmotor_score=3pupillary_reactivity=bothtsah=true
- core 5 + hypoxia 1 + hypotension 0 + Marshall V 2 + tSAH 2 + EDH 0
- extended sum = 10
Same patient lab: glucose 10 mmol/L, Hb 11 g/dL
Given:
age=35edh=falseglucose_mmol_l=10hemoglobin_g_dl=11hypotension=falsehypoxia=truemarshall_ct=Vmodel=labmotor_score=3pupillary_reactivity=bothtsah=true
- extended 10 + glucose 10 → 2 + Hb 11 → 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
Try
Opens the live endpoint. Unpaid browser requests show the paywall; agents should send Accept: application/json.
/api/calc/impact?age=35&motor_score=3&pupillary_reactivity=both&model=core
Full URL: https://api.magentlab.com/api/calc/impact?age=35&motor_score=3&pupillary_reactivity=both&model=core
Call
Expect HTTP 402 until you retry with PAYMENT-SIGNATURE. Incomplete query params
return HTTP 400 before any quote or charge.
curl -i -H "Accept: application/json" "https://api.magentlab.com/api/calc/impact?age=35&motor_score=3&pupillary_reactivity=both&model=core"
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
model |
string | required · core, extended, lab | 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 · both, one, none | 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 · I, II, III, IV, V, VI | 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.
- 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 (fixture)
{
"items": [
{
"age": "35",
"model": "core",
"motor_score": "3",
"pupillary_reactivity": "both"
},
{
"age": "35",
"model": "core",
"motor_score": "3",
"pupillary_reactivity": "both"
}
]
}
Opens a two-item fixture on the API host. Unpaid browsers get the same MetaMask paywall as GET; Pay retries POST with those items.
Example 200 (fixture)
{
"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
| Field | Type | Description |
|---|---|---|
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
Machine form of the same example. Frozen fixture. Not a live lookup.
{
"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
}
Client errors (HTTP 400)
Invalid params return 400 without charge. Shared HTTP 402 and 503 meanings: Payments.
| HTTP | Code | When |
|---|---|---|
| 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. |
| 400 | invalid_impact_model |
model must be core, extended, or lab as in Steyerberg 2008. Returned before settlement; you are not charged. |
| 400 | invalid_age |
age must be an integer from 18 to 120 Returned before settlement; you are not charged. |
| 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. |
| 400 | invalid_pupillary |
pupillary_reactivity must be both, one, or none as in Steyerberg 2008. Returned before settlement; you are not charged. |
| 400 | invalid_flag |
boolean clinical flags must be true or false Returned before settlement; you are not charged. |
| 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. |
| 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. |
| 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. |
| 400 | invalid_items |
POST body must be a JSON object with only an items array Returned before settlement; you are not charged. |
| 400 | invalid_item_count |
items must be an array of 1 to 25 objects Returned before settlement; you are not charged. |
| 400 | invalid_item |
each items entry must be a JSON object Returned before settlement; you are not charged. |
Related tools
- Glasgow Coma Scale — 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 — 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 — 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. Unpaid valid requests return HTTP 402 with a base64
PAYMENT-REQUIRED
header. HTTP 503 is not a new quote: retry the same PAYMENT-SIGNATURE. Full handshake
and shared payment errors: Payments.
Stdio MCP: /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.