# NCCN-IPI for DLBCL (Zhou)

NCCN-IPI

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

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

## What it computes

Sum the Zhou 2014 NCCN International Prognostic Index (enhanced IPI for DLBCL treated in the rituximab era) and return low (0–1), low_intermediate (2–3), high_intermediate (4–5), or high (6–8).

## When to use

When an agent needs the published NCCN-IPI point total and risk group for DLBCL treated in the rituximab era and must not invent a DLBCL diagnosis or treatment choice, and must not substitute Shipp IPI, R-IPI, or CNS-IPI.

## When not to use

- Not a medical device and not a DLBCL diagnosis or treatment choice. magent does not examine the patient.
- This is Zhou 2014 NCCN-IPI (enhanced IPI for DLBCL in the rituximab era). It is not Shipp IPI (binary age >60, extranodal sites >1), not R-IPI, and not CNS-IPI.
- magent does not stage lymphoma, image extranodal sites, assign ECOG, or assay LDH. stage_iii_or_iv and extranodal_major are caller-assigned flags; extranodal_major is major-organ involvement (bone marrow, CNS, liver/GI tract, or lung), not IPI more than one extranodal site; ECOG is a caller-assigned integer 0–4; ldh_uln_ratio is the caller-assigned LDH/ULN ratio.

## Formula

```
NCCN-IPI = age (≤40 0, 41–60 1, 61–75 2, ≥76 3) + LDH/ULN (≤1 0, >1–3 1, >3 2) + stage_iii_or_iv 1 + extranodal_major 1 + ecog_ge_2 1; Zhou 2014; max 8; low 0-1, low_intermediate 2-3, high_intermediate 4-5, high 6-8
```

## Citation

[An enhanced International Prognostic Index (NCCN-IPI) for patients with diffuse large B-cell lymphoma treated in the rituximab era](https://doi.org/10.1182/blood-2013-09-524108)
Zhou Z, Sehn LH, Rademaker AW, Gordon LI, Lacasce AS, Crosby-Thompson A, Vanderplas A, Zelenetz AD, Abel GA, Rodriguez MA, Nademanee A, Kaminski MS, Czuczman MS, Millenson M, Niland J, Gascoyne RD, Connors JM, Friedberg JW, Winter JN
Blood. 2014;123(6):837-842
DOI: [10.1182/blood-2013-09-524108](https://doi.org/10.1182/blood-2013-09-524108)

## Worked example

### Age 40, no adverse factors

Given: `age=40, ecog=0, extranodal_major=false, ldh_uln_ratio=0.9, stage_iii_or_iv=false`

1. Age 40 is ≤40 → 0; LDH/ULN 0.9 is ≤1 → 0; ECOG 0 is not ≥2 → 0; both flags false
2. Score = 0 (max 8); nccn_ipi_risk = low


### Age ≥76, LDH/ULN >3, Ann Arbor III–IV, major-organ extranodal, ECOG ≥2

Given: `age=76, ecog=2, extranodal_major=true, ldh_uln_ratio=3.01, stage_iii_or_iv=true`

1. Age ≥76 → 3; LDH/ULN >3 → 2; stage_iii_or_iv → 1; extranodal_major → 1; ecog_ge_2 → 1
2. Score = 8 (max 8); nccn_ipi_risk = high (6–8)


## Also searched as

- NCCN-IPI
- NCCN IPI
- enhanced IPI
- Zhou NCCN-IPI
- DLBCL NCCN-IPI
- NCCN International Prognostic Index
- enhanced International Prognostic Index
- rituximab-era IPI

## Parameters

- `age` (integer, required): Age in years (18-120). ≤40 scores 0; 41–60 scores 1; 61–75 scores 2; ≥76 scores 3 (Zhou 2014 NCCN-IPI refined age). Age 40 scores 0; 41 and 60 score 1; 61 and 75 score 2; 76 scores 3. Not Shipp IPI binary >60.
- `ecog` (integer, required): ECOG performance status 0-4 as assigned by the caller (Zhou 2014 NCCN-IPI). ≥2 scores 1. magent does not assign ECOG.
- `ldh_uln_ratio` (number, required): Serum LDH divided by the laboratory ULN (0.1-20). ≤1 scores 0; >1 and ≤3 scores 1; >3 scores 2 (Zhou 2014 NCCN-IPI). 1.0 scores 0; 1.01 and 3.0 score 1; 3.01 scores 2. magent does not assay LDH.
- `stage_iii_or_iv` (boolean, required): Ann Arbor stage III or IV as assigned by the caller (Zhou 2014 NCCN-IPI). true scores 1. magent does not stage lymphoma.
- `extranodal_major` (boolean, required): Extranodal involvement of major organs (bone marrow, CNS, liver/GI tract, or lung) as assigned by the caller (Zhou 2014 NCCN-IPI). true scores 1. This is not IPI extranodal sites >1. magent does not image extranodal sites.

## 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/nccn_ipi`
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",
      "ecog": "0",
      "extranodal_major": "false",
      "ldh_uln_ratio": "0.9",
      "stage_iii_or_iv": "false"
    },
    {
      "age": "40",
      "ecog": "0",
      "extranodal_major": "false",
      "ldh_uln_ratio": "0.9",
      "stage_iii_or_iv": "false"
    }
  ]
}
```

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

Example 200:

```json
{
  "count": 2,
  "path": "/api/calc/nccn_ipi",
  "items": [
    {
      "components": [
        {
          "value": 40,
          "factor": "age",
          "points": 0,
          "present": false
        },
        {
          "value": 0.9,
          "factor": "ldh_uln_ratio",
          "points": 0,
          "present": false
        },
        {
          "factor": "stage_iii_or_iv",
          "points": 0,
          "present": false
        },
        {
          "factor": "extranodal_major",
          "points": 0,
          "present": false
        },
        {
          "value": 0,
          "factor": "ecog_ge_2",
          "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": "Zhou Z, Sehn LH, Rademaker AW, Gordon LI, Lacasce AS, Crosby-Thompson A, Vanderplas A, Zelenetz AD, Abel GA, Rodriguez MA, Nademanee A, Kaminski MS, Czuczman MS, Millenson M, Niland J, Gascoyne RD, Connors JM, Friedberg JW, Winter JN",
        "doi": "10.1182/blood-2013-09-524108",
        "id": "zhou-2014",
        "pmid": "24264230",
        "source": "Blood. 2014;123(6):837-842",
        "title": "An enhanced International Prognostic Index (NCCN-IPI) for patients with diffuse large B-cell lymphoma treated in the rituximab era"
      },
      "formula": "nccn_ipi",
      "formula_expression": "NCCN-IPI = age (≤40 0, 41–60 1, 61–75 2, ≥76 3) + LDH/ULN (≤1 0, >1–3 1, >3 2) + stage_iii_or_iv 1 + extranodal_major 1 + ecog_ge_2 1; Zhou 2014; max 8; low 0-1, low_intermediate 2-3, high_intermediate 4-5, high 6-8",
      "max_score": 8,
      "score": 0,
      "age_years": 40,
      "ecog": 0,
      "ldh_uln_ratio": 0.9,
      "extranodal_major": false,
      "nccn_ipi_risk": "low"
    },
    {
      "components": [
        {
          "value": 40,
          "factor": "age",
          "points": 0,
          "present": false
        },
        {
          "value": 0.9,
          "factor": "ldh_uln_ratio",
          "points": 0,
          "present": false
        },
        {
          "factor": "stage_iii_or_iv",
          "points": 0,
          "present": false
        },
        {
          "factor": "extranodal_major",
          "points": 0,
          "present": false
        },
        {
          "value": 0,
          "factor": "ecog_ge_2",
          "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": "Zhou Z, Sehn LH, Rademaker AW, Gordon LI, Lacasce AS, Crosby-Thompson A, Vanderplas A, Zelenetz AD, Abel GA, Rodriguez MA, Nademanee A, Kaminski MS, Czuczman MS, Millenson M, Niland J, Gascoyne RD, Connors JM, Friedberg JW, Winter JN",
        "doi": "10.1182/blood-2013-09-524108",
        "id": "zhou-2014",
        "pmid": "24264230",
        "source": "Blood. 2014;123(6):837-842",
        "title": "An enhanced International Prognostic Index (NCCN-IPI) for patients with diffuse large B-cell lymphoma treated in the rituximab era"
      },
      "formula": "nccn_ipi",
      "formula_expression": "NCCN-IPI = age (≤40 0, 41–60 1, 61–75 2, ≥76 3) + LDH/ULN (≤1 0, >1–3 1, >3 2) + stage_iii_or_iv 1 + extranodal_major 1 + ecog_ge_2 1; Zhou 2014; max 8; low 0-1, low_intermediate 2-3, high_intermediate 4-5, high 6-8",
      "max_score": 8,
      "score": 0,
      "age_years": 40,
      "ecog": 0,
      "ldh_uln_ratio": 0.9,
      "extranodal_major": false,
      "nccn_ipi_risk": "low"
    }
  ]
}
```

## Response fields

- `formula` (string): nccn_ipi
- `formula_expression` (string): Exact expression used
- `score` (integer): NCCN-IPI points 0-8
- `max_score` (integer): Always 8
- `nccn_ipi_risk` (string): low when score is 0-1, low_intermediate when 2-3, high_intermediate when 4-5, high when 6-8 (Zhou 2014 NCCN-IPI). Not a DLBCL diagnosis or treatment choice. NCCN-IPI (enhanced IPI), not Shipp IPI, not R-IPI, not CNS-IPI.
- `age_years` (integer): Age used for the Zhou 2014 refined age bands
- `ecog` (integer): Caller-assigned ECOG 0-4 used for ≥2
- `ldh_uln_ratio` (number): Caller-assigned LDH/ULN ratio used for scoring
- `extranodal_major` (boolean): Caller-assigned major-organ extranodal involvement flag used for +1 (not IPI extranodal sites >1)
- `components` (array): Per-factor points
- `citation` (object): Zhou 2014 Blood citation
- `disclaimer` (string): Not-a-device notice

## Example JSON

Frozen fixture. Not a live lookup.

```json
{
  "components": [
    {
      "value": 40,
      "factor": "age",
      "points": 0,
      "present": false
    },
    {
      "value": 0.9,
      "factor": "ldh_uln_ratio",
      "points": 0,
      "present": false
    },
    {
      "factor": "stage_iii_or_iv",
      "points": 0,
      "present": false
    },
    {
      "factor": "extranodal_major",
      "points": 0,
      "present": false
    },
    {
      "value": 0,
      "factor": "ecog_ge_2",
      "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": "Zhou Z, Sehn LH, Rademaker AW, Gordon LI, Lacasce AS, Crosby-Thompson A, Vanderplas A, Zelenetz AD, Abel GA, Rodriguez MA, Nademanee A, Kaminski MS, Czuczman MS, Millenson M, Niland J, Gascoyne RD, Connors JM, Friedberg JW, Winter JN",
    "doi": "10.1182/blood-2013-09-524108",
    "id": "zhou-2014",
    "pmid": "24264230",
    "source": "Blood. 2014;123(6):837-842",
    "title": "An enhanced International Prognostic Index (NCCN-IPI) for patients with diffuse large B-cell lymphoma treated in the rituximab era"
  },
  "formula": "nccn_ipi",
  "formula_expression": "NCCN-IPI = age (≤40 0, 41–60 1, 61–75 2, ≥76 3) + LDH/ULN (≤1 0, >1–3 1, >3 2) + stage_iii_or_iv 1 + extranodal_major 1 + ecog_ge_2 1; Zhou 2014; max 8; low 0-1, low_intermediate 2-3, high_intermediate 4-5, high 6-8",
  "max_score": 8,
  "score": 0,
  "age_years": 40,
  "ecog": 0,
  "ldh_uln_ratio": 0.9,
  "extranodal_major": false,
  "nccn_ipi_risk": "low"
}
```

## Errors

- HTTP 400 `invalid_age`: age must be an integer from 18 to 120 Returned before settlement; you are not charged.
- HTTP 400 `invalid_ldh_ratio`: ldh_uln_ratio must be a number from 0.1 to 20 (Hoster 2008 simplified MIPI). Returned before settlement; you are not charged.
- HTTP 400 `invalid_ecog`: ecog must be an integer from 0 to 4 (Shipp 1993 IPI). 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

- [IPI](https://magentlab.com/docs/ipi) — Sum the Shipp 1993 five-factor International Prognostic Index (all ages) and return low (0–1), low_intermediate (2), high_intermediate (3), or high (4–5).
- [CNS-IPI](https://magentlab.com/docs/cns-ipi) — Sum the Schmitz 2016 CNS International Prognostic Index (Shipp IPI factors plus kidney/adrenal involvement) and return low (0–1), intermediate (2–3), or high (4–6).

## 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.
