Recipe catalog / symptom-facets
Label the symptom facets a patient message states
Which of these does message state about a symptom: when it began, how bad it is, how long it has lasted, what makes it better or worse, what the patient has already tried?
You need to know which standard intake details a patient message already supplies so you can pre-fill a form or ask only for what is missing.
Explore this recipe interactively ยท Source and implementation guide
Use symptom-facets in TypeScript
Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.
import { symptomFacets } from 'jev-recipes/symptom-facets';
const result = await symptomFacets({
"message": "My lower back started hurting on Saturday after I moved some boxes, so it has been about five days now. Sitting sets it off and walking around settles it down. I have been taking ibuprofen twice a day and using a heating pad at night. Should I come in?",
"minConfidence": 0.8
});
console.log(result);Input contract
| Field | Type | Needed |
|---|---|---|
| message | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"message": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"message"
]
},
"result": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"model": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"input_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"input_tokens",
"output_tokens"
],
"additionalProperties": false
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"detected": {
"type": "array",
"items": {
"type": "string",
"enum": [
"statesOnset",
"statesSeverity",
"statesDuration",
"statesModifiers",
"statesPriorTreatment"
]
}
},
"labels": {
"type": "object",
"properties": {
"statesOnset": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"statesSeverity": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"statesDuration": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"statesModifiers": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"statesPriorTreatment": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
}
},
"required": [
"statesOnset",
"statesSeverity",
"statesDuration",
"statesModifiers",
"statesPriorTreatment"
],
"additionalProperties": false
}
},
"required": [
"model",
"usage",
"status",
"detected",
"labels"
],
"additionalProperties": false
}
}Saved example result
This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo symptom-facets.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"detected": [
"statesOnset",
"statesDuration",
"statesModifiers",
"statesPriorTreatment"
],
"labels": {
"statesOnset": {
"status": "ready",
"verdict": "present",
"probability": 0.95,
"confidence": 0.95
},
"statesSeverity": {
"status": "ready",
"verdict": "absent",
"probability": 0.12,
"confidence": 0.88
},
"statesDuration": {
"status": "ready",
"verdict": "present",
"probability": 0.93,
"confidence": 0.93
},
"statesModifiers": {
"status": "ready",
"verdict": "present",
"probability": 0.94,
"confidence": 0.94
},
"statesPriorTreatment": {
"status": "ready",
"verdict": "present",
"probability": 0.96,
"confidence": 0.96
}
}
}
Evaluation evidence
No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.
Use the evaluation guide to measure this decision on your own labeled cases.
Limitations
- Reports intake completeness only: whether the wording states each facet, not whether the details are accurate or clinically meaningful. It makes no diagnosis or triage judgment.
- Labels are independent, so a message can state several facets or none. Parse actual dates, durations, and doses in code.
Related recipes
- message-facets: Use message-facets for the general communicative facets of a message, such as questions, deadlines, and requests.
- clarify: Use clarify to decide whether to ask the patient a follow-up question about the facets this recipe finds missing.