Risk Magnitude

Status: stable Category: composite Added: 2026-06-03 Last reviewed: 2026-06-03

Summary

The standalone "how much" readout. /magnitude/compute accepts the same permissive input as /cdri/compute (any subset of the 14 instruments plus optional demographics) and returns just the magnitude block — the seven phenotype-named severities, an overall_magnitude, and a ranked ordering — plus confidence and any red_flags. It does not return a cdri_score, a phenotype distribution, or per-finding detail.

Use it when you want the per-pattern severity vector without the full composite envelope — for example to drive a dashboard that charts the seven magnitudes, or to rank which pattern is strongest for a subject.

⚠ Not a clinical diagnosis

Magnitudes are risk severities, not diagnoses. See the CDRI disclaimer.

Endpoint

Field	Value
Method	POST
Path	/api/magnitude/compute
Full URL	https://engine.tripod-health.com/api/magnitude/compute
Authentication	API key (required)
Request body	application/json
Rate-limited	Yes

Request

Headers, query parameters (recommend, audience), body shape (instruments + optional demographics), partial-instrument handling, ORT sex-conditioning, and the de-identification filter are identical to /cdri/compute. This endpoint does not take situation/onset (that is the acuity endpoint).

{
  "instruments": {
    "depression_screen": { "responses": { "item_1": 3, "item_2": 3, "item_3": 2, "item_4": 3, "item_5": 2, "item_6": 3, "item_7": 2, "item_8": 1, "item_9": 1 } },
    "orebro": { "responses": { "item_1": 4, "item_2": 5, "item_3": 4, "item_4": 6, "item_5": 6, "item_6": 4, "item_7": 5, "item_8": 6, "item_9": 6, "item_10": 4, "item_11": 6, "item_12": 6, "item_13": 4, "item_14": 5, "item_15": 4, "item_16": 6, "item_17": 6, "item_18": 4, "item_19": 4, "item_20": 5, "item_21": 4 } }
  },
  "demographics": { "age_bracket": "35-44", "sex": "female", "occupation_class": "office", "region": "CA" }
}

Response

Success — 200 OK

Live capture against production with ?recommend=rules (a psychosocially-loaded subject). Real engine output.

{
  "composite_id": "magnitude",
  "magnitudes": {
    "pain_dominant": 0.5,
    "psychosocial_dominant": 0.731,
    "fear_avoidance_dominant": 0.5,
    "rtw_barrier": 0.5,
    "multi_domain_catastrophic": 0.65,
    "iatrogenic_escalation": 0.5,
    "established_chronicity": 0.62
  },
  "overall_magnitude": 0.731,
  "ranked": [
    "psychosocial_dominant",
    "multi_domain_catastrophic",
    "established_chronicity",
    "fear_avoidance_dominant",
    "iatrogenic_escalation",
    "pain_dominant",
    "rtw_barrier"
  ],
  "matrix_version": "2026-06-02-first-pass",
  "red_flags": [
    {
      "code": "complex_case_review",
      "severity": "urgent",
      "rule_id": "rec.escalation.multi_domain_catastrophic_top2",
      "rule_version": "1.0.0",
      "detail": "Phenotype 'multi_domain_catastrophic' appears in the top-two of the classifier's distribution.",
      "triggers": {
        "phenotype.top_name": "psychosocial_dominant",
        "phenotype.second_name": "multi_domain_catastrophic"
      }
    },
    {
      "code": "suicide_risk_assessment",
      "severity": "urgent",
      "rule_id": "rec.escalation.phq9_item9_suicidality",
      "rule_version": "1.0.0",
      "detail": "PHQ-9 item 9 response is at or above the positive threshold. Widely-used screening frameworks treat any non-zero item-9 response as a trigger for follow-up risk assessment regardless of total PHQ-9 score.",
      "triggers": { "depression_screen.item_9": 1 }
    }
  ],
  "confidence": {
    "overall": 0.5547,
    "tier": "medium",
    "breakdown": {
      "input_completeness": 0.5,
      "imputation_variance": 1,
      "model_certainty": 0.1825
    }
  },
  "recommendations": {
    "engine_version": "1.0.0",
    "ruleset_version": "1.0.0",
    "disclaimer": "The Trinity Engine is a decision-support tool. Output is not medical advice, not a diagnosis, not a prescription, and not a benefits determination. The calling organization is responsible for clinical governance and for the interpretation and use of these suggestions.",
    "ai_summary": null,
    "items": [ "... see /cdri/compute for the recommendation item shape ..." ],
    "suppressed": [],
    "cardinality_cap": null
  },
  "depth": "full",
  "catalog_version": "0.13.0",
  "request_id": "docs-magnitude",
  "timestamp": "2026-06-03T04:21:42.866684+00:00"
}

The recommendations.items payload is shown in full on the CDRI doc; the item shape is identical here. This capture had two urgent escalations, also surfaced in red_flags.

Response fields

Field	Type	Description
composite_id	string	Always "magnitude".
magnitudes	object	Seven phenotype-named severities (0.0–1.0). Same semantics as CDRI magnitudes.
overall_magnitude	number | null	The peak of the seven magnitudes.
ranked	array<string>	The seven phenotype names ordered highest-magnitude first. A convenience ordering so callers do not have to sort magnitudes themselves.
matrix_version	string | null	Opaque version tag for the active scoring configuration. Do not pin.
red_flags	array	Safety escalations. Same shape as CDRI red flags. Independent of ?recommend=.
confidence	object	Same shape as CDRI confidence.
recommendations	object | null	Same shape and modes as CDRI recommendations; null under ?recommend=off.
depth	string	Always "full".
catalog_version	string	Catalog version served.
request_id	string	Correlation ID.
timestamp	string (ISO 8601 UTC)	Server time.

There is no findings, phenotype, or cdri_score in this response. Reach for /cdri/compute when you need those.

Examples

curl

curl -sS -X POST "https://engine.tripod-health.com/api/magnitude/compute?recommend=rules" \
  -H "apikey: $ENGINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "instruments": {
      "depression_screen": { "responses": { "item_1": 3, "item_2": 3, "item_3": 2, "item_4": 3, "item_5": 2, "item_6": 3, "item_7": 2, "item_8": 1, "item_9": 1 } },
      "orebro": { "responses": { "item_1": 4, "item_2": 5, "item_3": 4, "item_4": 6, "item_5": 6, "item_6": 4, "item_7": 5, "item_8": 6, "item_9": 6, "item_10": 4, "item_11": 6, "item_12": 6, "item_13": 4, "item_14": 5, "item_15": 4, "item_16": 6, "item_17": 6, "item_18": 4, "item_19": 4, "item_20": 5, "item_21": 4 } }
    },
    "demographics": { "age_bracket": "35-44", "sex": "female", "occupation_class": "office", "region": "CA" }
  }'

Python (requests)

# Uses the call() helper from quickstart.md.
result = call("POST", "/api/magnitude/compute?recommend=rules", body)
print(f"strongest pattern: {result['ranked'][0]} ({result['overall_magnitude']})")
for name in result["ranked"]:
    print(f"  {name:26} {result['magnitudes'][name]:.3f}")

Status codes

Same as /cdri/compute.

Related

• composite-cdri-compute.md — the full composite (score + phenotype + findings + magnitudes + acuity).
• composite-acuity-compute.md — the "how urgent" readout.
• composite-phenotype-classify.md — the "which pattern" readout.

Change history

Date	Change
2026-06-03	Initial publication (Risk Magnitude split out as a standalone surface).