# INTERCHEST clinical prediction rule

INTERCHEST

Status: LIVE
Price: $0.005 USDC
`GET /api/calc/interchest`
HTML: https://magentlab.com/docs/interchest
Markdown: https://magentlab.com/docs/interchest.md

Not a medical device. Not a diagnosis, dose, or listing recommendation.

## What it computes

Sum the six Aerts 2017 INTERCHEST predictors and return whether CAD is considered absent (score <2) with the published binary-cutoff probabilities.

## When to use

When an agent needs the published INTERCHEST point total for primary-care chest pain and must not invent a chest exam, a HEART score, or per-point CAD percents.

## When not to use

- Not a medical device. Not a diagnosis, rule-out, or admission order.
- Primary-care chest-pain rule only (Aerts 2017). Not HEART, not EDACS, and not the Bösner 2010 five-item primary-care CAD rule.
- magent does not examine the chest. The five clinical flags are caller-assigned.
- CAD is considered absent iff score <2 (Aerts cutoff). When <2, published CAD probability is 2.1% (95% CI 1.1–3.9) in the 13.2% prevalence setting; when ≥2, 43.0% (35.8–50.4). magent does not invent per-point percents.
- Sex is required. Age ≥55 male or ≥65 female scores the age item (54 male and 64 female do not).

## Formula

```
INTERCHEST = (age ≥55 if male or ≥65 if female) + physician_suspected_serious + history_of_cad + pain_on_exertion + pressure_quality − pain_reproducible_on_palpation; each ±1; range −1 to 5; CAD considered absent iff score <2 (Aerts 2017); CAD probability 2.1% (95% CI 1.1–3.9) when <2 and 43.0% (35.8–50.4) when ≥2 in the 13.2% prevalence setting
```

## Citation

[Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care](https://doi.org/10.1016/j.jclinepi.2016.09.011)
Aerts M, Minalu G, Bösner S, Buntinx F, Burnand B, Haasenritter J, Herzig L, Knottnerus JA, Nilsson S, Renier W, Sox C, Sox H, Donner-Banzhoff N, International Working Group on Chest Pain in Primary Care (INTERCHEST)
J Clin Epidemiol. 2017;81:120-128
DOI: [10.1016/j.jclinepi.2016.09.011](https://doi.org/10.1016/j.jclinepi.2016.09.011)

## Worked example

### Age 40 female, all five clinical flags false

Given: `age=40, history_of_cad=false, pain_on_exertion=false, pain_reproducible_on_palpation=false, physician_suspected_serious=false, pressure_quality=false, sex=female`

1. Female 40 is not ≥65 → 0; five flags false → 0
2. Score = 0 (range −1 to 5); cad_absent true (score <2); CAD probability 2.1% (95% CI 1.1–3.9)


### Two +1 flags (published CAD-not-absent cutoff)

Given: `age=40, history_of_cad=true, pain_on_exertion=false, pain_reproducible_on_palpation=false, physician_suspected_serious=true, pressure_quality=false, sex=female`

1. Female 40 → 0; physician_suspected_serious → +1; history_of_cad → +1
2. Score = 2 (range −1 to 5); cad_absent false (score ≥2); CAD probability 43.0% (35.8–50.4)


## Also searched as

- INTERCHEST
- INTERCHEST rule
- Aerts chest pain rule
- primary care CAD prediction rule
- INTERCHEST clinical prediction rule
- Aerts 2017 CAD rule
- chest pain primary care INTERCHEST
- INTERCHEST coronary prediction

## Parameters

- `age` (integer, required): Age in years (18-120). Combined with sex: female ≥65 or male ≥55 scores 1 (Aerts 2017). Age 54 male does not score; 55 male does. Age 64 female does not; 65 female does. magent computes this; do not send a precomputed flag.
- `sex` (string, required): female or male (required). Combined with age: female ≥65 or male ≥55 scores 1 (Aerts 2017).
- `physician_suspected_serious` (boolean, required): Physician initially suspected a serious diagnosis (Aerts 2017). true or false as assigned by the caller. magent does not examine the chest. +1 if true.
- `history_of_cad` (boolean, required): History of coronary artery disease (Aerts 2017). true or false as assigned by the caller. magent does not take a cardiac history. +1 if true.
- `pain_on_exertion` (boolean, required): Pain related to exertion (Aerts 2017). true or false as assigned by the caller. +1 if true.
- `pressure_quality` (boolean, required): Pain has a pressure quality (Aerts 2017). true or false as assigned by the caller. +1 if true.
- `pain_reproducible_on_palpation` (boolean, required): Pain reproducible on chest-wall palpation (Aerts 2017). true or false as assigned by the caller. magent does not examine the chest. −1 if 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/interchest`
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": "40",
      "history_of_cad": "false",
      "pain_on_exertion": "false",
      "pain_reproducible_on_palpation": "false",
      "physician_suspected_serious": "false",
      "pressure_quality": "false",
      "sex": "female"
    },
    {
      "age": "40",
      "history_of_cad": "false",
      "pain_on_exertion": "false",
      "pain_reproducible_on_palpation": "false",
      "physician_suspected_serious": "false",
      "pressure_quality": "false",
      "sex": "female"
    }
  ]
}
```

Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/interchest

Example 200:

```json
{
  "count": 2,
  "path": "/api/calc/interchest",
  "items": [
    {
      "components": [
        {
          "value": 40,
          "factor": "age_sex",
          "points": 0,
          "present": false
        },
        {
          "factor": "physician_suspected_serious",
          "points": 0,
          "present": false
        },
        {
          "factor": "history_of_cad",
          "points": 0,
          "present": false
        },
        {
          "factor": "pain_on_exertion",
          "points": 0,
          "present": false
        },
        {
          "factor": "pressure_quality",
          "points": 0,
          "present": false
        },
        {
          "factor": "pain_reproducible_on_palpation",
          "points": 0,
          "present": false
        }
      ],
      "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": "Aerts M, Minalu G, Bösner S, Buntinx F, Burnand B, Haasenritter J, Herzig L, Knottnerus JA, Nilsson S, Renier W, Sox C, Sox H, Donner-Banzhoff N, International Working Group on Chest Pain in Primary Care (INTERCHEST)",
        "doi": "10.1016/j.jclinepi.2016.09.011",
        "id": "aerts-2017",
        "pmid": "27773828",
        "source": "J Clin Epidemiol. 2017;81:120-128",
        "title": "Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care"
      },
      "formula": "interchest",
      "formula_expression": "INTERCHEST = (age ≥55 if male or ≥65 if female) + physician_suspected_serious + history_of_cad + pain_on_exertion + pressure_quality − pain_reproducible_on_palpation; each ±1; range −1 to 5; CAD considered absent iff score <2 (Aerts 2017); CAD probability 2.1% (95% CI 1.1–3.9) when <2 and 43.0% (35.8–50.4) when ≥2 in the 13.2% prevalence setting",
      "age_years": 40,
      "max_score": 5,
      "score": 0,
      "sex": "female",
      "min_score": -1,
      "cad_absent": true,
      "cad_probability_ci_high_percent": 3.9,
      "cad_probability_ci_low_percent": 1.1,
      "cad_probability_percent": 2.1,
      "prevalence_setting_percent": 13.2
    },
    {
      "components": [
        {
          "value": 40,
          "factor": "age_sex",
          "points": 0,
          "present": false
        },
        {
          "factor": "physician_suspected_serious",
          "points": 0,
          "present": false
        },
        {
          "factor": "history_of_cad",
          "points": 0,
          "present": false
        },
        {
          "factor": "pain_on_exertion",
          "points": 0,
          "present": false
        },
        {
          "factor": "pressure_quality",
          "points": 0,
          "present": false
        },
        {
          "factor": "pain_reproducible_on_palpation",
          "points": 0,
          "present": false
        }
      ],
      "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": "Aerts M, Minalu G, Bösner S, Buntinx F, Burnand B, Haasenritter J, Herzig L, Knottnerus JA, Nilsson S, Renier W, Sox C, Sox H, Donner-Banzhoff N, International Working Group on Chest Pain in Primary Care (INTERCHEST)",
        "doi": "10.1016/j.jclinepi.2016.09.011",
        "id": "aerts-2017",
        "pmid": "27773828",
        "source": "J Clin Epidemiol. 2017;81:120-128",
        "title": "Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care"
      },
      "formula": "interchest",
      "formula_expression": "INTERCHEST = (age ≥55 if male or ≥65 if female) + physician_suspected_serious + history_of_cad + pain_on_exertion + pressure_quality − pain_reproducible_on_palpation; each ±1; range −1 to 5; CAD considered absent iff score <2 (Aerts 2017); CAD probability 2.1% (95% CI 1.1–3.9) when <2 and 43.0% (35.8–50.4) when ≥2 in the 13.2% prevalence setting",
      "age_years": 40,
      "max_score": 5,
      "score": 0,
      "sex": "female",
      "min_score": -1,
      "cad_absent": true,
      "cad_probability_ci_high_percent": 3.9,
      "cad_probability_ci_low_percent": 1.1,
      "cad_probability_percent": 2.1,
      "prevalence_setting_percent": 13.2
    }
  ]
}
```

## Response fields

- `formula` (string): interchest
- `formula_expression` (string): Exact expression used
- `score` (integer): INTERCHEST points -1 to 5
- `max_score` (integer): 5
- `min_score` (integer): -1
- `cad_absent` (boolean): true iff score <2 (Aerts 2017 CAD-absent cutoff). Not a diagnosis or rule-out.
- `cad_probability_percent` (number): Aerts 2017 published CAD probability at the binary cutoff only: 2.1 when score <2, 43.0 when score ≥2, in the 13.2% prevalence setting
- `cad_probability_ci_low_percent` (number): Lower 95% CI of that published probability: 1.1 when <2, 35.8 when ≥2
- `cad_probability_ci_high_percent` (number): Upper 95% CI of that published probability: 3.9 when <2, 50.4 when ≥2
- `prevalence_setting_percent` (number): Aerts 2017 pooled-data CAD prevalence setting (13.2) for those percents
- `sex` (string): female or male used with age for the age/sex predictor
- `age_years` (integer): Age used with sex for the age/sex predictor
- `components` (array): Per-predictor points
- `citation` (object): Aerts et al. J Clin Epidemiol 2017 citation
- `disclaimer` (string): Not-a-device notice

## Example JSON

Frozen fixture. Not a live lookup.

```json
{
  "components": [
    {
      "value": 40,
      "factor": "age_sex",
      "points": 0,
      "present": false
    },
    {
      "factor": "physician_suspected_serious",
      "points": 0,
      "present": false
    },
    {
      "factor": "history_of_cad",
      "points": 0,
      "present": false
    },
    {
      "factor": "pain_on_exertion",
      "points": 0,
      "present": false
    },
    {
      "factor": "pressure_quality",
      "points": 0,
      "present": false
    },
    {
      "factor": "pain_reproducible_on_palpation",
      "points": 0,
      "present": false
    }
  ],
  "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": "Aerts M, Minalu G, Bösner S, Buntinx F, Burnand B, Haasenritter J, Herzig L, Knottnerus JA, Nilsson S, Renier W, Sox C, Sox H, Donner-Banzhoff N, International Working Group on Chest Pain in Primary Care (INTERCHEST)",
    "doi": "10.1016/j.jclinepi.2016.09.011",
    "id": "aerts-2017",
    "pmid": "27773828",
    "source": "J Clin Epidemiol. 2017;81:120-128",
    "title": "Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care"
  },
  "formula": "interchest",
  "formula_expression": "INTERCHEST = (age ≥55 if male or ≥65 if female) + physician_suspected_serious + history_of_cad + pain_on_exertion + pressure_quality − pain_reproducible_on_palpation; each ±1; range −1 to 5; CAD considered absent iff score <2 (Aerts 2017); CAD probability 2.1% (95% CI 1.1–3.9) when <2 and 43.0% (35.8–50.4) when ≥2 in the 13.2% prevalence setting",
  "age_years": 40,
  "max_score": 5,
  "score": 0,
  "sex": "female",
  "min_score": -1,
  "cad_absent": true,
  "cad_probability_ci_high_percent": 3.9,
  "cad_probability_ci_low_percent": 1.1,
  "cad_probability_percent": 2.1,
  "prevalence_setting_percent": 13.2
}
```

## Errors

- HTTP 400 `invalid_age`: age must be an integer from 18 to 120 Returned before settlement; you are not charged.
- HTTP 400 `invalid_sex`: sex must be female or male 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_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

- [HEART score](https://magentlab.com/docs/heart) — Compute the HEART score as age points plus caller-assigned history, ECG, risk factors, and troponin (each 0-2).
- [AUB-HAS2](https://magentlab.com/docs/aub-has2) — Sum the six Dakik 2019 AUB-HAS2 1-point elements and return the integer score with low / intermediate / high bands.

## 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.