skills.rest
maziyarpanahi
maziyarpanahiCOMMUNITY
Explore all skills by this author →
Website𝕏@maziyarpanahiGitHub

resolving-clinical-context

Assign negation, temporality, and uncertainty status to clinical entities from biomedical text.

5.0k|615|Updated Oct 4, 2025
Search Tags:#uncertainty#fhir#clinical nlp#negation detection#temporality#conText#negex
One-click install
npx skills add https://github.com/maziyarpanahi/openmed --skill resolving-clinical-context
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: resolving-clinical-context
Source: https://github.com/maziyarpanahi/openmed/tree/main/skills/resolving-clinical-context
Command: npx skills add https://github.com/maziyarpanahi/openmed --skill resolving-clinical-context

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents clinical NLP systems from treating every mentioned condition as an active patient finding by identifying negation, historical context, hypothetical language, and uncertainty.

Core Features & Use Cases

  • Negation Detection: Classify findings as affirmed or negated using deterministic ConText and NegEx-style cues.
  • Temporal and Uncertainty Resolution: Distinguish recent, historical, and hypothetical mentions while flagging uncertain or provisional findings.
  • Downstream Clinical Safety: Prepare context-aware entities for problem lists, FHIR Condition mapping, clinical analytics, and human review.
  • Use Case: Apply the Skill after entity extraction to ensure that “denies chest pain,” “history of MI,” and “rule out PE” are routed appropriately instead of being recorded as active conditions.

Quick Start

Use the resolving-clinical-context skill after extracting clinical entities to assign negation, temporality, and uncertainty to each entity using its surrounding sentence as context.

Frequently Asked Questions about resolving-clinical-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect negation in clinical NLP text to avoid false positive findings?▼

Negation detection in clinical text is resolved by applying deterministic ConText and NegEx-style cues to classify extracted entities as affirmed or negated. This prevents conditions like "denies chest pain" from being recorded as active patient findings.

What is the best way to distinguish historical and hypothetical conditions from active problems in medical text?▼

Temporal and uncertainty resolution distinguishes historical and hypothetical mentions from active problems by assigning temporality and uncertainty status to extracted clinical entities using their surrounding sentence context, ensuring accurate problem-list construction.

How does assertion detection work for FHIR Condition grounding and clinical analytics?▼

Assertion detection assigns negation, temporality, and uncertainty context axes to biomedical text entities to produce deterministic, auditable outputs. This prepares context-aware entities for safe FHIR Condition mapping and reliable clinical analytics.

Can I use this clinical context resolution after named entity recognition?▼

Yes, you apply this skill after named entity recognition to assign negation, temporality, and uncertainty to each extracted clinical entity. It requires OpenMed ConText resolution helpers and clinical assertion constants to function properly.

Why does my clinical NLP system treat "rule out PE" as an active condition?▼

Clinical NLP systems treat hypothetical language like "rule out PE" as active conditions when assertion detection is missing. Applying ConText resolution identifies hypothetical and uncertain findings, routing them appropriately for human review instead of active problem lists.

Related Skills

Explore More Data & Analytics Skills→
maziyarpanahimaziyarpanahi
5.0k

extracting-clinical-entities

Extract biomedical entities from clinical text using OpenMed token-classification models.

Community
Intermediate
maziyarpanahimaziyarpanahi
5.0k

reconciling-problem-lists

Reconcile fragmented clinical condition mentions into deduplicated problem lists with statuses.

Community
Advanced
maziyarpanahimaziyarpanahi
5.0k

extracting-sdoh

Extract social determinants of health and map findings to ICD-10-CM Z-codes.

Community
Advanced
maziyarpanahimaziyarpanahi
5.0k

computing-ecqms

Extract eCQM evidence from clinical notes and map it to QDM data elements.

Community
Advanced