# IWG-2 typical Alzheimer's criteria

IWG-2 typical AD

Status: LIVE
Price: $0.005 USDC
`GET /api/calc/iwg2_ad`
HTML: https://magentlab.com/docs/iwg2-ad
Markdown: https://magentlab.com/docs/iwg2-ad.md

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

## What it computes

Apply Dubois 2014 IWG-2 typical AD research criteria from caller-assigned hippocampal-type memory, in-vivo pathology, and exclusion flags. magent does not examine the patient or assay CSF/PET.

## When to use

When an agent already has IWG-2 typical AD phenotype and pathology flags as assigned by the caller and needs the published typical_ad result. Not NINCDS-ADRDA, not NIA-AA, not DSM, and not a diagnosis.

## When not to use

- Not a medical device.
- Not a diagnosis. IWG-2 typical AD is research diagnostic criteria only.
- Typical AD phenotype only. This tool does not implement IWG-2 atypical AD phenotypes (posterior cortical atrophy, logopenic variant, frontal variant, or Down syndrome).
- magent does not examine the patient, assay CSF, or read amyloid PET. All flags are caller-assigned.
- Not NIA-AA ATN. Not NINCDS-ADRDA. Not DSM.

## Formula

```
typical_ad iff no_better_explanation AND early_episodic_memory AND (csf_abeta_and_tau OR amyloid_pet OR autosomal_dominant_mutation) (Dubois 2014 IWG-2 typical AD). Not NINCDS-ADRDA. Not NIA-AA. Not DSM. magent does not examine the patient or assay CSF/PET.
```

## Citation

[Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria](https://doi.org/10.1016/S1474-4422(14)70090-0)
Dubois B, Feldman HH, Jacova C, Hampel H, Molinuevo JL, Blennow K, DeKosky ST, Gauthier S, Selkoe D, Bateman R, Cappa S, Crutch S, Engelborghs S, Frisoni GB, Fox NC, Galasko D, Habert MO, Jicha GA, Nordberg A, Pasquier F, Rabinovici G, Robert P, Rowe C, Salloway S, Sarazin M, Epelbaum S, de Souza LC, Vellas B, Visser PJ, Schneider L, Stern Y, Scheltens P, Cummings JL
Lancet Neurol. 2014;13(6):614-629
DOI: [10.1016/S1474-4422(14)70090-0](https://doi.org/10.1016/S1474-4422(14)70090-0)

## Worked example

### Typical AD by CSF Aβ and tau

Given: `amyloid_pet=false, autosomal_dominant_mutation=false, csf_abeta_and_tau=true, early_episodic_memory=true, no_better_explanation=true`

1. early_episodic_memory true (hippocampal-type phenotype as assigned by the caller)
2. csf_abeta_and_tau true; amyloid_pet false; autosomal_dominant_mutation false → in_vivo_pathology true
3. no_better_explanation true → typical_ad true


### Amyloid PET pathology with typical phenotype

Given: `amyloid_pet=true, autosomal_dominant_mutation=false, csf_abeta_and_tau=false, early_episodic_memory=true, no_better_explanation=true`

1. early_episodic_memory true and no_better_explanation true
2. amyloid_pet true; CSF and mutation false → in_vivo_pathology true
3. typical_ad true


### Memory phenotype without in-vivo pathology

Given: `amyloid_pet=false, autosomal_dominant_mutation=false, csf_abeta_and_tau=false, early_episodic_memory=true, no_better_explanation=true`

1. early_episodic_memory true and no_better_explanation true
2. csf_abeta_and_tau, amyloid_pet, and autosomal_dominant_mutation all false → in_vivo_pathology false
3. typical_ad false


## Also searched as

- IWG-2
- IWG-2 criteria
- International Working Group 2
- Dubois 2014
- IWG-2 Alzheimer's
- typical AD IWG-2
- IWG 2 Alzheimer
- Dubois IWG-2 criteria

## Parameters

- `early_episodic_memory` (boolean, required): Early and significant episodic memory impairment of the hippocampal type (IWG-2 specific phenotype for typical AD), as assigned by the caller. true or false. magent does not examine the patient.
- `csf_abeta_and_tau` (boolean, required): Decreased Aβ1-42 together with increased T-tau or P-tau in CSF, as assigned by the caller (Dubois 2014 IWG-2 in-vivo AD pathology). true or false. magent does not assay CSF.
- `amyloid_pet` (boolean, required): Increased tracer retention on amyloid PET, as assigned by the caller (Dubois 2014 IWG-2 in-vivo AD pathology). true or false. magent does not read PET.
- `autosomal_dominant_mutation` (boolean, required): Proven AD autosomal-dominant mutation in PSEN1, PSEN2, or APP, as assigned by the caller (Dubois 2014 IWG-2 in-vivo AD pathology). true or false. magent does not sequence genes.
- `no_better_explanation` (boolean, required): Exclusion of other disorders that could account for the phenotype, as assigned by the caller (Dubois 2014 IWG-2). true or false. magent does not examine the patient.

## 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/iwg2_ad`
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": [
    {
      "amyloid_pet": "false",
      "autosomal_dominant_mutation": "false",
      "csf_abeta_and_tau": "true",
      "early_episodic_memory": "true",
      "no_better_explanation": "true"
    },
    {
      "amyloid_pet": "false",
      "autosomal_dominant_mutation": "false",
      "csf_abeta_and_tau": "true",
      "early_episodic_memory": "true",
      "no_better_explanation": "true"
    }
  ]
}
```

Human paywall (two-item fixture): https://api.magentlab.com/paywall/bulk/iwg2-ad

Example 200:

```json
{
  "count": 2,
  "path": "/api/calc/iwg2_ad",
  "items": [
    {
      "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": "Dubois B, Feldman HH, Jacova C, Hampel H, Molinuevo JL, Blennow K, DeKosky ST, Gauthier S, Selkoe D, Bateman R, Cappa S, Crutch S, Engelborghs S, Frisoni GB, Fox NC, Galasko D, Habert MO, Jicha GA, Nordberg A, Pasquier F, Rabinovici G, Robert P, Rowe C, Salloway S, Sarazin M, Epelbaum S, de Souza LC, Vellas B, Visser PJ, Schneider L, Stern Y, Scheltens P, Cummings JL",
        "doi": "10.1016/S1474-4422(14)70090-0",
        "id": "dubois-2014",
        "pmid": "24849861",
        "source": "Lancet Neurol. 2014;13(6):614-629",
        "title": "Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria"
      },
      "formula": "iwg2_ad",
      "formula_expression": "typical_ad iff no_better_explanation AND early_episodic_memory AND (csf_abeta_and_tau OR amyloid_pet OR autosomal_dominant_mutation) (Dubois 2014 IWG-2 typical AD). Not NINCDS-ADRDA. Not NIA-AA. Not DSM. magent does not examine the patient or assay CSF/PET.",
      "criteria": [
        {
          "factor": "early_episodic_memory",
          "met": true
        },
        {
          "factor": "csf_abeta_and_tau",
          "met": true
        },
        {
          "factor": "amyloid_pet",
          "met": false
        },
        {
          "factor": "autosomal_dominant_mutation",
          "met": false
        },
        {
          "factor": "no_better_explanation",
          "met": true
        },
        {
          "factor": "in_vivo_pathology",
          "met": true
        }
      ],
      "in_vivo_pathology": true,
      "typical_ad": 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": "Dubois B, Feldman HH, Jacova C, Hampel H, Molinuevo JL, Blennow K, DeKosky ST, Gauthier S, Selkoe D, Bateman R, Cappa S, Crutch S, Engelborghs S, Frisoni GB, Fox NC, Galasko D, Habert MO, Jicha GA, Nordberg A, Pasquier F, Rabinovici G, Robert P, Rowe C, Salloway S, Sarazin M, Epelbaum S, de Souza LC, Vellas B, Visser PJ, Schneider L, Stern Y, Scheltens P, Cummings JL",
        "doi": "10.1016/S1474-4422(14)70090-0",
        "id": "dubois-2014",
        "pmid": "24849861",
        "source": "Lancet Neurol. 2014;13(6):614-629",
        "title": "Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria"
      },
      "formula": "iwg2_ad",
      "formula_expression": "typical_ad iff no_better_explanation AND early_episodic_memory AND (csf_abeta_and_tau OR amyloid_pet OR autosomal_dominant_mutation) (Dubois 2014 IWG-2 typical AD). Not NINCDS-ADRDA. Not NIA-AA. Not DSM. magent does not examine the patient or assay CSF/PET.",
      "criteria": [
        {
          "factor": "early_episodic_memory",
          "met": true
        },
        {
          "factor": "csf_abeta_and_tau",
          "met": true
        },
        {
          "factor": "amyloid_pet",
          "met": false
        },
        {
          "factor": "autosomal_dominant_mutation",
          "met": false
        },
        {
          "factor": "no_better_explanation",
          "met": true
        },
        {
          "factor": "in_vivo_pathology",
          "met": true
        }
      ],
      "in_vivo_pathology": true,
      "typical_ad": true
    }
  ]
}
```

## Response fields

- `formula` (string): iwg2_ad
- `formula_expression` (string): Published Dubois 2014 IWG-2 typical AD rule
- `typical_ad` (boolean): true iff no_better_explanation, early_episodic_memory, and in-vivo AD pathology (CSF, amyloid PET, or mutation). Not a diagnosis. Typical AD research criteria only.
- `in_vivo_pathology` (boolean): true iff csf_abeta_and_tau or amyloid_pet or autosomal_dominant_mutation. magent does not assay CSF or read PET.
- `criteria` (array): Per-factor Tree rows early_episodic_memory, csf_abeta_and_tau, amyloid_pet, autosomal_dominant_mutation, no_better_explanation, and derived in_vivo_pathology, each with factor and met
- `citation` (object): Dubois 2014 Lancet Neurol IWG-2 citation
- `disclaimer` (string): Not-a-device notice

## Example JSON

Frozen fixture. Not a live lookup.

```json
{
  "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": "Dubois B, Feldman HH, Jacova C, Hampel H, Molinuevo JL, Blennow K, DeKosky ST, Gauthier S, Selkoe D, Bateman R, Cappa S, Crutch S, Engelborghs S, Frisoni GB, Fox NC, Galasko D, Habert MO, Jicha GA, Nordberg A, Pasquier F, Rabinovici G, Robert P, Rowe C, Salloway S, Sarazin M, Epelbaum S, de Souza LC, Vellas B, Visser PJ, Schneider L, Stern Y, Scheltens P, Cummings JL",
    "doi": "10.1016/S1474-4422(14)70090-0",
    "id": "dubois-2014",
    "pmid": "24849861",
    "source": "Lancet Neurol. 2014;13(6):614-629",
    "title": "Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria"
  },
  "formula": "iwg2_ad",
  "formula_expression": "typical_ad iff no_better_explanation AND early_episodic_memory AND (csf_abeta_and_tau OR amyloid_pet OR autosomal_dominant_mutation) (Dubois 2014 IWG-2 typical AD). Not NINCDS-ADRDA. Not NIA-AA. Not DSM. magent does not examine the patient or assay CSF/PET.",
  "criteria": [
    {
      "factor": "early_episodic_memory",
      "met": true
    },
    {
      "factor": "csf_abeta_and_tau",
      "met": true
    },
    {
      "factor": "amyloid_pet",
      "met": false
    },
    {
      "factor": "autosomal_dominant_mutation",
      "met": false
    },
    {
      "factor": "no_better_explanation",
      "met": true
    },
    {
      "factor": "in_vivo_pathology",
      "met": true
    }
  ],
  "in_vivo_pathology": true,
  "typical_ad": true
}
```

## Errors

- 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

- [NINCDS-ADRDA](https://magentlab.com/docs/nincds-adrda) — Echo the caller-assigned McKhann 1984 NINCDS-ADRDA diagnostic category (definite, probable, possible, or unlikely) with the published defining-features description. magent does not examine the patient. Not NIA-AA 2011/2018. Not DSM.
- [AMT-10](https://magentlab.com/docs/amt-10) — Sum the ten Hodkinson 1972 AMT-10 items from caller-assigned correct/incorrect flags and return the 0–10 total. Hodkinson 1972 did not publish a diagnostic cutoff.

## 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.