MAGENT

Neurology · LIVE

AMT-10 abbreviated mental test (Hodkinson)

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.

LIVE $0.005 USDC GET /api/calc/amt_10

Markdown: /docs/amt-10.md · Canonical: https://magentlab.com/docs/amt-10

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

What it computes

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.

When to use

When an agent already has AMT-10 items assigned as correct or incorrect and needs the published 0–10 total, not a dementia diagnosis, not an invented cutoff, and not Swain 1997 AMT-4.

When not to use

  • Not a medical device and not a dementia diagnosis. magent does not interview the patient.
  • Each item is a caller-assigned boolean. This API does not collect an age, date of birth, place name, year, address, or monarch name.
  • Hodkinson 1972 abbreviated the 26-item test to 10 questions and did not publish a diagnostic cutoff. This tool returns the 0–10 sum only.
  • This is Hodkinson 1972 AMT-10 only. It is not Swain 1997 AMT-4.

Formula

AMT-10 = age_correct + time_correct + address_recall_correct + year_correct + place_correct + two_persons_correct + dob_correct + world_war_start_correct + monarch_correct + count_backwards_20_correct; each 1 if true; max 10 (Hodkinson 1972)

Citation

Title
Evaluation of a mental test score for assessment of mental impairment in the elderly
Authors
Hodkinson HM
Source
Age Ageing. 1972;1(4):233-238
DOI
10.1093/ageing/1.4.233

Worked example

All ten items correct

Given: address_recall_correct=trueage_correct=truecount_backwards_20_correct=truedob_correct=truemonarch_correct=trueplace_correct=truetime_correct=truetwo_persons_correct=trueworld_war_start_correct=trueyear_correct=true

  1. all ten caller-assigned flags are true
  2. Score = 10 (max 10); Hodkinson 1972 does not publish a cutoff

Date of birth incorrect, other items correct

Given: address_recall_correct=trueage_correct=truecount_backwards_20_correct=truedob_correct=falsemonarch_correct=trueplace_correct=truetime_correct=truetwo_persons_correct=trueworld_war_start_correct=trueyear_correct=true

  1. dob_correct false → 0; the other nine items true → 1 each
  2. Score = 9 (max 10)

Also searched as

  • AMT-10
  • Abbreviated Mental Test 10
  • Hodkinson AMT-10
  • AMT10
  • ten-item abbreviated mental test
  • Hodkinson 1972 AMT
  • abbreviated mental test score
  • AMT-10 cognitive screen
  • Hodkinson mental test

Try

Opens the live endpoint. Unpaid browser requests show the paywall; agents should send Accept: application/json.

/api/calc/amt_10?age_correct=true&time_correct=true&address_recall_correct=true&year_correct=true&place_correct=true&two_persons_correct=true&dob_correct=true&world_war_start_correct=true&monarch_correct=true&count_backwards_20_correct=true

Full URL: https://api.magentlab.com/api/calc/amt_10?age_correct=true&time_correct=true&address_recall_correct=true&year_correct=true&place_correct=true&two_persons_correct=true&dob_correct=true&world_war_start_correct=true&monarch_correct=true&count_backwards_20_correct=true

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/amt_10?age_correct=true&time_correct=true&address_recall_correct=true&year_correct=true&place_correct=true&two_persons_correct=true&dob_correct=true&world_war_start_correct=true&monarch_correct=true&count_backwards_20_correct=true"

Parameters

Name Type Required Description
age_correct boolean required Caller-assigned flag: age stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not interview the patient and does not collect an age.
time_correct boolean required Caller-assigned flag: time to the nearest hour stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a clock time.
address_recall_correct boolean required Caller-assigned flag: address recall at the end of the test (Hodkinson 1972 AMT-10; the classic 42 West Street prompt is assigned by the caller). true scores 1; false scores 0. magent does not collect an address.
year_correct boolean required Caller-assigned flag: current year stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a year.
place_correct boolean required Caller-assigned flag: name of place / hospital stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a place name.
two_persons_correct boolean required Caller-assigned flag: recognition of two persons (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not interview the patient.
dob_correct boolean required Caller-assigned flag: date of birth stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a date of birth.
world_war_start_correct boolean required Caller-assigned flag: year the First World War started stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a year.
monarch_correct boolean required Caller-assigned flag: name of the present monarch stated correctly (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not collect a monarch name.
count_backwards_20_correct boolean required Caller-assigned flag: count backwards from 20 to 1 (Hodkinson 1972 AMT-10). true scores 1; false scores 0. magent does not interview 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.

POST /api/calc/amt_10 Max 25 unit_amount + extra_item_amount * (n - 1) extra $0.002 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 (fixture)

{
  "items": [
    {
      "address_recall_correct": "true",
      "age_correct": "true",
      "count_backwards_20_correct": "true",
      "dob_correct": "true",
      "monarch_correct": "true",
      "place_correct": "true",
      "time_correct": "true",
      "two_persons_correct": "true",
      "world_war_start_correct": "true",
      "year_correct": "true"
    },
    {
      "address_recall_correct": "true",
      "age_correct": "true",
      "count_backwards_20_correct": "true",
      "dob_correct": "true",
      "monarch_correct": "true",
      "place_correct": "true",
      "time_correct": "true",
      "two_persons_correct": "true",
      "world_war_start_correct": "true",
      "year_correct": "true"
    }
  ]
}

Open bulk paywall →

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/amt_10",
  "items": [
    {
      "components": [
        {
          "factor": "age_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "time_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "address_recall_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "year_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "place_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "two_persons_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "dob_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "world_war_start_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "monarch_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "count_backwards_20_correct",
          "points": 1,
          "present": 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": "Hodkinson HM",
        "doi": "10.1093/ageing/1.4.233",
        "id": "hodkinson-1972",
        "pmid": "4669880",
        "source": "Age Ageing. 1972;1(4):233-238",
        "title": "Evaluation of a mental test score for assessment of mental impairment in the elderly"
      },
      "formula": "amt_10",
      "formula_expression": "AMT-10 = age_correct + time_correct + address_recall_correct + year_correct + place_correct + two_persons_correct + dob_correct + world_war_start_correct + monarch_correct + count_backwards_20_correct; each 1 if true; max 10 (Hodkinson 1972)",
      "max_score": 10,
      "score": 10
    },
    {
      "components": [
        {
          "factor": "age_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "time_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "address_recall_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "year_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "place_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "two_persons_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "dob_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "world_war_start_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "monarch_correct",
          "points": 1,
          "present": true
        },
        {
          "factor": "count_backwards_20_correct",
          "points": 1,
          "present": 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": "Hodkinson HM",
        "doi": "10.1093/ageing/1.4.233",
        "id": "hodkinson-1972",
        "pmid": "4669880",
        "source": "Age Ageing. 1972;1(4):233-238",
        "title": "Evaluation of a mental test score for assessment of mental impairment in the elderly"
      },
      "formula": "amt_10",
      "formula_expression": "AMT-10 = age_correct + time_correct + address_recall_correct + year_correct + place_correct + two_persons_correct + dob_correct + world_war_start_correct + monarch_correct + count_backwards_20_correct; each 1 if true; max 10 (Hodkinson 1972)",
      "max_score": 10,
      "score": 10
    }
  ]
}

Response

Field Type Description
formula string amt_10
formula_expression string Exact expression used
score integer AMT-10 points 0-10 (Hodkinson 1972)
max_score integer Always 10
components array Per-item points
citation object Hodkinson 1972 Age Ageing citation
disclaimer string Not-a-device notice

Example JSON

Machine form of the same example. Frozen fixture. Not a live lookup.

{
  "components": [
    {
      "factor": "age_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "time_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "address_recall_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "year_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "place_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "two_persons_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "dob_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "world_war_start_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "monarch_correct",
      "points": 1,
      "present": true
    },
    {
      "factor": "count_backwards_20_correct",
      "points": 1,
      "present": 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": "Hodkinson HM",
    "doi": "10.1093/ageing/1.4.233",
    "id": "hodkinson-1972",
    "pmid": "4669880",
    "source": "Age Ageing. 1972;1(4):233-238",
    "title": "Evaluation of a mental test score for assessment of mental impairment in the elderly"
  },
  "formula": "amt_10",
  "formula_expression": "AMT-10 = age_correct + time_correct + address_recall_correct + year_correct + place_correct + two_persons_correct + dob_correct + world_war_start_correct + monarch_correct + count_backwards_20_correct; each 1 if true; max 10 (Hodkinson 1972)",
  "max_score": 10,
  "score": 10
}

Client errors (HTTP 400)

Invalid params return 400 without charge. Shared HTTP 402 and 503 meanings: Payments.

HTTP Code When
400 invalid_flag boolean clinical flags must be true or false 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

  • AMT-4 — Sum the four Swain 1997 AMT-4 items from caller-assigned correct/incorrect flags and return whether the score is less than 4 (impaired).
  • 4AT — Sum the Bellelli 2014 4AT items and return unlikely (0), possible cognitive impairment (1–3), or possible delirium (≥4).
  • CAM-ICU — Apply the Ely 2001 CAM-ICU algorithm and return whether delirium is present from four caller-assigned features.

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.