Emergency · LIVE

Step-by-Step febrile infant

Apply the Gomez 2016 sequential Step-by-Step approach and return high, intermediate, or low IBI-risk tier for a febrile infant 90 days or younger.

LIVE $0.005 USDC GET /api/calc/step_by_step

Markdown: /docs/step-by-step.md · Canonical: https://magentlab.com/docs/step-by-step

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

What it computes

Apply the Gomez 2016 sequential Step-by-Step approach and return high, intermediate, or low IBI-risk tier for a febrile infant 90 days or younger.

When to use

When an agent already has age in days, a caller-assigned well-appearing flag, leukocyturia, serum procalcitonin, CRP, and ANC and needs the published three-tier Step-by-Step result. magent does not examine the infant or assay UA, PCT, CRP, or ANC. Not Rochester, Boston, Philadelphia, or PECARN febrile.

When not to use

• Not a medical device.
• Not a diagnosis of invasive bacterial infection (IBI) and not a discharge, admission, lumbar-puncture, or antibiotic order.
• magent does not examine the infant. The caller assigns well_appearing. magent does not assay urine dipstick/UA, procalcitonin, CRP, or ANC.
• This tool is the Gomez 2016 sequential Step-by-Step only (derivation Mintegi 2014). Not Rochester, Boston, Philadelphia, or PECARN febrile (Kuppermann 2019 ANC 4090 / PCT 1.71).
• Age 0-90 days pins the published population (febrile infants 90 days and younger). Age 21 days is high-risk; age 22 can be low when remaining low-risk criteria hold.
• Returns the published high/intermediate/low tier only. Does not report an IBI probability.

Formula

risk = high if not well_appearing or age_days <= 21 or leukocyturia or pct_ng_ml >= 0.5; else intermediate if crp_mg_l > 20 or anc_per_ul > 10000; else low; low_risk iff well_appearing and age_gt_21 and no_leukocyturia and pct_lt_0_5 and crp_le_20 and anc_le_10000 (Gomez 2016 Step-by-Step; derivation Mintegi 2014)

Citation

Title

Validation of the "Step-by-Step" Approach in the Management of Young Febrile Infants

Authors

Gomez B, Mintegi S, Bressan S, Da Dalt L, Gervaix A, Lacroix L

Source

Pediatrics. 2016;138(2):e20154381

DOI

10.1542/peds.2015-4381

Worked example

Also searched as

• Step-by-Step febrile infant
• Gomez 2016
• Mintegi 2014
• febrile infant 90 days
• infant procalcitonin CRP
• febrile infant leukocyturia
• Gomez Mintegi Bressan
• young febrile infant IBI

Try

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

/api/calc/step_by_step?age_days=47&well_appearing=true&leukocyturia=false&pct_ng_ml=0.2&crp_mg_l=5&anc_per_ul=4000

Full URL: https://api.magentlab.com/api/calc/step_by_step?age_days=47&well_appearing=true&leukocyturia=false&pct_ng_ml=0.2&crp_mg_l=5&anc_per_ul=4000

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/step_by_step?age_days=47&well_appearing=true&leukocyturia=false&pct_ng_ml=0.2&crp_mg_l=5&anc_per_ul=4000"

Parameters

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/step_by_step 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": [
    {
      "age_days": "47",
      "anc_per_ul": "4000",
      "crp_mg_l": "5",
      "leukocyturia": "false",
      "pct_ng_ml": "0.2",
      "well_appearing": "true"
    },
    {
      "age_days": "47",
      "anc_per_ul": "4000",
      "crp_mg_l": "5",
      "leukocyturia": "false",
      "pct_ng_ml": "0.2",
      "well_appearing": "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/step_by_step",
  "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": "Gomez B, Mintegi S, Bressan S, Da Dalt L, Gervaix A, Lacroix L",
        "doi": "10.1542/peds.2015-4381",
        "id": "gomez-2016",
        "pmid": "27382134",
        "source": "Pediatrics. 2016;138(2):e20154381",
        "title": "Validation of the \"Step-by-Step\" Approach in the Management of Young Febrile Infants"
      },
      "formula": "step_by_step",
      "formula_expression": "risk = high if not well_appearing or age_days <= 21 or leukocyturia or pct_ng_ml >= 0.5; else intermediate if crp_mg_l > 20 or anc_per_ul > 10000; else low; low_risk iff well_appearing and age_gt_21 and no_leukocyturia and pct_lt_0_5 and crp_le_20 and anc_le_10000 (Gomez 2016 Step-by-Step; derivation Mintegi 2014)",
      "anc_per_ul": 4.0e3,
      "low_risk": true,
      "crp_mg_l": 5.0,
      "criteria": [
        {
          "factor": "well_appearing",
          "met": true
        },
        {
          "value": 47,
          "factor": "age_gt_21",
          "met": true
        },
        {
          "factor": "no_leukocyturia",
          "met": true
        },
        {
          "value": 0.2,
          "factor": "pct_lt_0_5",
          "met": true
        },
        {
          "value": 5.0,
          "factor": "crp_le_20",
          "met": true
        },
        {
          "value": 4.0e3,
          "factor": "anc_le_10000",
          "met": true
        }
      ],
      "high_risk": false,
      "risk": "low",
      "age_days": 47,
      "pct_ng_ml": 0.2,
      "intermediate_risk": 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": "Gomez B, Mintegi S, Bressan S, Da Dalt L, Gervaix A, Lacroix L",
        "doi": "10.1542/peds.2015-4381",
        "id": "gomez-2016",
        "pmid": "27382134",
        "source": "Pediatrics. 2016;138(2):e20154381",
        "title": "Validation of the \"Step-by-Step\" Approach in the Management of Young Febrile Infants"
      },
      "formula": "step_by_step",
      "formula_expression": "risk = high if not well_appearing or age_days <= 21 or leukocyturia or pct_ng_ml >= 0.5; else intermediate if crp_mg_l > 20 or anc_per_ul > 10000; else low; low_risk iff well_appearing and age_gt_21 and no_leukocyturia and pct_lt_0_5 and crp_le_20 and anc_le_10000 (Gomez 2016 Step-by-Step; derivation Mintegi 2014)",
      "anc_per_ul": 4.0e3,
      "low_risk": true,
      "crp_mg_l": 5.0,
      "criteria": [
        {
          "factor": "well_appearing",
          "met": true
        },
        {
          "value": 47,
          "factor": "age_gt_21",
          "met": true
        },
        {
          "factor": "no_leukocyturia",
          "met": true
        },
        {
          "value": 0.2,
          "factor": "pct_lt_0_5",
          "met": true
        },
        {
          "value": 5.0,
          "factor": "crp_le_20",
          "met": true
        },
        {
          "value": 4.0e3,
          "factor": "anc_le_10000",
          "met": true
        }
      ],
      "high_risk": false,
      "risk": "low",
      "age_days": 47,
      "pct_ng_ml": 0.2,
      "intermediate_risk": false
    }
  ]
}

Response

Example JSON

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

{
  "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": "Gomez B, Mintegi S, Bressan S, Da Dalt L, Gervaix A, Lacroix L",
    "doi": "10.1542/peds.2015-4381",
    "id": "gomez-2016",
    "pmid": "27382134",
    "source": "Pediatrics. 2016;138(2):e20154381",
    "title": "Validation of the \"Step-by-Step\" Approach in the Management of Young Febrile Infants"
  },
  "formula": "step_by_step",
  "formula_expression": "risk = high if not well_appearing or age_days <= 21 or leukocyturia or pct_ng_ml >= 0.5; else intermediate if crp_mg_l > 20 or anc_per_ul > 10000; else low; low_risk iff well_appearing and age_gt_21 and no_leukocyturia and pct_lt_0_5 and crp_le_20 and anc_le_10000 (Gomez 2016 Step-by-Step; derivation Mintegi 2014)",
  "anc_per_ul": 4.0e3,
  "low_risk": true,
  "crp_mg_l": 5.0,
  "criteria": [
    {
      "factor": "well_appearing",
      "met": true
    },
    {
      "value": 47,
      "factor": "age_gt_21",
      "met": true
    },
    {
      "factor": "no_leukocyturia",
      "met": true
    },
    {
      "value": 0.2,
      "factor": "pct_lt_0_5",
      "met": true
    },
    {
      "value": 5.0,
      "factor": "crp_le_20",
      "met": true
    },
    {
      "value": 4.0e3,
      "factor": "anc_le_10000",
      "met": true
    }
  ],
  "high_risk": false,
  "risk": "low",
  "age_days": 47,
  "pct_ng_ml": 0.2,
  "intermediate_risk": false
}

Client errors (HTTP 400)

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

Related tools

• PECARN febrile infant — Apply the Kuppermann 2019 PECARN clinical prediction rule and return low_risk only when a febrile infant 60 days or younger has a caller-assigned negative urinalysis, ANC ≤4090/µL, and serum procalcitonin ≤1.71 ng/mL.
• Rochester criteria — Apply the Dagan 1985 Rochester criteria and return low_risk only when every published criterion holds for an infant younger than 3 months.

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.