openmed

Add a CI gate that fails the build when an OpenMed de-identification model's recall on a held-out PHI set drops below threshold or any critical identifier leaks. Use when the user wants a pytest test or CLI step that exits nonzero on de-id regression, wants to wire OpenMed's leakage-first release gates into GitHub Actions / CI, needs a recall floor plus zero-leakage assertion against a synthetic held-out set, or wants to block merges that weaken de-identification. Trigger on "CI gate", "fail the build", "regression test", "de-id recall threshold", "block the merge", "exit nonzero", or "leakage check in CI" for OpenMed.

Generates synthetic but realistic patient records (FHIR R4 bundles, C-CDA documents, CSV) with MITRE Synthea for development, CI fixtures, demos, and leakage-gate test sets — zero real PHI. Use when you need safe, shareable test data for an OpenMed pipeline, reproducible fixtures for tests, or a held-out set for de-identification leakage gates, instead of touching real clinical data. Synthea output feeds the FHIR/C-CDA ingestion skills and openmed.eval. Trigger keywords: Synthea, synthetic data, fake patients, test fixtures, demo data, FHIR bundle generator, synthetic EHR, no PHI.

Replace detected PHI with realistic, type-matched fake values in OpenMed so clinical notes stay readable and parseable instead of full of [REDACTED] markers. Use when the user wants surrogate names, MRNs, addresses, or dates rather than opaque masks, needs consistent fake identities across a document, must keep notes natural for downstream NLP, or wants to register a custom surrogate generator or provider. Covers deidentify(method="replace", consistent=True, seed=..., locale=...), register_label_generator, register_clinical_provider, and Anonymizer/AnonymizerConfig. Pairs with OpenMed deidentifying-clinical-text and configuring-privacy-policies.

Turn scanned faxes, images, and CSV/CDA exports into clean text ready for OpenMed de-identification and NER, fully on-device. Use when the user has clinical documents (image scans, photographed/faxed notes, tabular CSV/TSV exports, C-CDA XML) and needs OCR or structured intake before openmed.deidentify and openmed.analyze_text, asks about openmed.multimodal, OCR engines (Tesseract / PaddleOCR), tabular redaction, or layout and reading order. Covers the verified ocr() and redact_document() entry points and the ExtractedDocument contract. Pairs before deidentifying-clinical-text and extracting-clinical-entities.

Links entities extracted by OpenMed to UMLS Metathesaurus CUIs using the USER'S OWN UTS API key, with nothing from the Metathesaurus bundled or cached. Use when the user wants to normalize concepts across vocabularies to a single CUI, resolve synonyms via the UMLS, filter by semantic type, or cross-walk between SNOMED CT, ICD-10, RxNorm and MeSH through their shared CUI. Trigger keywords: UMLS, CUI, Metathesaurus, UTS API key, semantic type, TUI, MetaMap, QuickUMLS, concept normalization, cross-vocabulary. Pairs after OpenMed NER: consume Disease/Pharmaceutical/Chemical/Anatomy entities from openmed.analyze_text and resolve each span to a CUI out-of-process. UMLS is license-restricted — the Metathesaurus is NEVER bundled; every call uses the user's UTS account.

Load OpenMed clinical/biomedical NER models from the Hugging Face Hub or a local path and reuse them efficiently across calls. Use when the user wants to load an OpenMed model, control the model cache, run fully offline after a one-time download, reuse a ModelLoader to avoid reloading, set a cache_dir or device, or pick between a registry key, a full Hugging Face id, and a local directory. Pairs with choosing-openmed-models (pick the model) and extracting-clinical-entities (run it).

Maps laboratory and clinical observation names extracted by OpenMed to LOINC codes using the public Regenstrief LOINC and FHIR terminology APIs. Use when the user wants to code lab tests, vital signs, or observations to LOINC, resolve a test name plus specimen and method to the correct LOINC part-model code, attach UCUM units, or build a US Core Laboratory Result Observation. Trigger keywords: LOINC, lab coding, observation code, UCUM units, specimen, method, US Core lab, FHIR Observation, lab result mapping, panel vs analyte. Pairs after OpenMed NER: consume Disease/Chemical/lab-name entities from openmed.analyze_text and map each measurement to a LOINC code. LOINC is free to use under the Regenstrief license (registration/terms-of-use, no fee); UMLS/SNOMED stay user-supplied and out-of-process.

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL query, translate via a ConceptMap, or resolve a span to a concept id with FHIR $lookup/$translate/$validate-code. Trigger keywords: SNOMED CT, SNOMED concept id, ECL, ConceptMap, $translate, $lookup, Ontoserver, Snowstorm, SCTID, post-coordination, terminology server. Pairs after OpenMed NER: consume Disease/Anatomy/Pharmaceutical entities from openmed.analyze_text and map each span out-of-process. SNOMED CT is license-restricted — it is NEVER bundled; the user calls their own affiliate-licensed server.

Searches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build text corpora. Use when the user wants citations for a condition or drug, abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over. Trigger keywords: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence. Pairs adjacent to OpenMed: fetched abstracts feed openmed.analyze_text for biomedical NER, and OpenMed-extracted diagnoses/drugs/genes become the search terms. E-utilities are public; an optional free API key raises rate limits from 3 to 10 requests/second.

Normalizes drug mentions extracted by OpenMed to RxNorm RxCUIs using the free public RxNav/RxNorm REST API. Use when the user wants to code, standardize, or de-duplicate medication names, resolve a brand/generic/ingredient to a stable RxCUI, link strength+dose-form to an SCD/SBD, attach NDCs, or build a US Core Medication resource. Trigger keywords: RxNorm, RxCUI, RxNav, drug normalization, medication coding, NDC, ingredient, SCD, SBD, brand vs generic, getApproximateMatch. Pairs after OpenMed NER: consume Pharmaceutical/Chemical entities from openmed.analyze_text and map each drug span to an RxCUI. RxNorm and RxNav are fully public and free — no API key, no license barrier, the lowest-friction terminology in this set.

Parses C-CDA / CCD XML clinical documents to extract human-readable section narrative plus coded entries, keyed by section LOINC codes and templateIds. Use before OpenMed processing when ingesting C-CDA R2.1 documents (CCD, Discharge Summary, H&P, Consultation Note) exported from an EHR and you need the narrative section text de-identified and analyzed. Hand section narrative to openmed.deidentify and openmed.analyze_text; XML-aware de-identification that preserves CDA markup is available via openmed.interop.cda. Trigger keywords: C-CDA, CCD, CDA, clinical document, templateId, LOINC section, narrative block, discharge summary XML, ClinicalDocument.

Decodes pipe-delimited HL7 v2.x messages (ADT, ORU, MDM, ORM) into structured segments/fields/components and surfaces OBX-5 and NTE-3 free-text narrative for OpenMed. Use before OpenMed processing when ingesting HL7 v2 feeds from an interface engine, lab/results system, or ADT stream and you need the embedded clinical note text de-identified and analyzed. Flatten OBX/NTE text then call openmed.deidentify and openmed.analyze_text; segment-aware redaction is available via openmed.interop.hl7v2. Trigger keywords: HL7, HL7 v2, ADT, ORU, OBX, MSH, PID, pipe-delimited, interface engine, Mirth, lab results.

Parse laboratory values and reference ranges from clinical text and flag results as low, normal, high, or critical with OpenMed. Use when the user needs to interpret lab results, compute abnormal flags, parse reference ranges like "135-145" or "<5", honor an originating-lab flag (H/L/critical), or turn extracted lab entities into structured high/low/critical signals. Covers openmed.clinical.parse_reference_range, derive_abnormal_flag, ReferenceRange, and AbnormalFlag, with UCUM/LOINC framing. Unit-agnostic — it does not convert units. Pairs after extracting-clinical-entities (lab entities from analyze_text).

Parses free-text clinical-trial eligibility criteria into structured inclusion and exclusion logic, then matches them against patient facts that OpenMed extracted. Use when the user wants to turn a ClinicalTrials.gov eligibility block into machine-readable rules, screen a synthetic patient for trial fit, or explain why a patient does or does not meet criteria. Trigger keywords: eligibility criteria, inclusion, exclusion, trial matching, patient screening, criteria parsing, eligibilityModule, age/sex gates. Pairs after OpenMed and after searching-clinicaltrials: consume the eligibilityModule text from a study, structure it, and match against conditions, medications, labs, and demographics from openmed.analyze_text. Decision-support only — never autonomous enrollment.

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

Apply GDPR-grade pseudonymization to clinical or personal text with OpenMed, keeping a separately-held re-linkage key so the data can be controlled-re-linked later. Use when the user must process EU personal/health data under GDPR, asks for pseudonymization vs anonymization, needs Art. 4(5) / Art. 9 / Recital 26 alignment, wants a reversible mapping/key vault held apart from the data, or needs controlled re-linkage. Covers openmed.deidentify(policy="gdpr_pseudonymization", keep_mapping=True), storing the mapping in a separate key vault, reidentify() for authorized re-linkage, and retention. Pairs after extracting-pii-entities and configuring-privacy-policies.

Looks up FDA drug labels, NDC directory entries, indications, boxed warnings, and recalls/enforcement actions via the free public OpenFDA API to enrich drugs that OpenMed extracts. Use when the user wants the prescribing information for a drug, its boxed warning, approved indications, dosage forms and routes, package NDC codes, RxCUI, or whether a product has an open recall. Trigger keywords: OpenFDA, drug label, SPL, prescribing information, boxed warning, black box warning, indications, NDC, package code, recall, enforcement, Class I recall, drug enrichment. Pairs adjacent to OpenMed NER: take a drug name (or RxNorm RxCUI) from openmed.analyze_text and resolve its label, NDC, and recall status. OpenFDA is public and free — no license barrier; send only de-identified drug names, never raw clinical notes.

Call a user-supplied FHIR terminology server ($validate-code, $expand, $lookup, $translate) to validate and expand clinical codes without bundling restricted vocabulary (SNOMED CT, RxNorm, LOINC, ICD-10) into OpenMed. Covers a thin local client, ValueSet $expand with filters/ECL, CodeSystem $lookup, ConceptMap $translate, and pointing at Ontoserver / HAPI / tx.fhir.org. Use as the grounding step for OpenMed coding skills — turn an OpenMed entity span into a validated coded CodeableConcept — when the user mentions terminology server, $validate-code, $expand, ValueSet, ECL, SNOMED/RxNorm/LOINC lookups, or code validation. Pairs adjacent.

Deduplicate and reconcile OpenMed-extracted conditions into one clean active problem list with clinical status (active / resolved / historical). Use after NER and context resolution when the user wants a problem list, condition reconciliation, dedup of synonymous diagnosis mentions, or active-vs-resolved status from a note. Covers clustering synonymous mentions into one concept, excluding negated mentions, applying clinical context (historical / hypothetical / recent) to set status, and emitting a USCDI-Problem-shaped list. SNOMED CT concept grounding is user-supplied and out-of-process. Hand-off: consume openmed.analyze_text Disease entities plus resolving-clinical-context axes. Pairs after extracting-clinical-entities.

Reversibly de-identify clinical text with OpenMed and later restore the original PHI from a saved mapping. Use when the user needs pseudonymization rather than permanent anonymization, wants to mask PHI now and re-link it later under authorization (e.g. recontact, adjudication, GDPR pseudonymization), asks about deidentify keep_mapping, reidentify, or how to store and protect the re-identification mapping. Covers when reversibility is and is not appropriate (pseudonymization vs HIPAA Safe Harbor anonymization). Pairs after extracting-pii-entities and deidentifying-clinical-text.