CriteriaMapper: establishing the automatic identification of clinical trial cohorts from electronic health records by matching normalized eligibility criteria and patient clinical characteristics

Abstract

The use of electronic health records (EHRs) holds the potential to enhance clinical trial activities. However, the identification of eligible patients within EHRs presents considerable challenges. We aimed to develop a CriteriaMapper system for phenotyping eligibility criteria, enabling the identification of patients from EHRs with clinical characteristics that match those criteria. We utilized clinical trial eligibility criteria and patient EHRs from the Mount Sinai Database. The CriteriaMapper system was developed to normalize the criteria using national standard terminologies and in-house databases, facilitating computability and queryability to bridge clinical trial criteria and EHRs. The system employed rule-based pattern recognition and manual annotation. Our system normalized 367 out of 640 unique eligibility criteria attributes, covering various medical conditions including non-small cell lung cancer, small cell lung cancer, prostate cancer, breast cancer, multiple myeloma, ulcerative colitis, Crohn's disease, non-alcoholic steatohepatitis, and sickle cell anemia. About 174 criteria were encoded with standard terminologies and 193 were normalized using the in-house reference tables. The agreement between automated and manual normalization was high (Cohen's Kappa = 0.82), and patient matching demonstrated a 0.94 F1 score. Our system has proven effective on EHRs from multiple institutions, showing broad applicability and promising improved clinical trial processes, leading to better patient selection, and enhanced clinical research outcomes.

Keywords: Clinical trials; Cohort identification; Electronic healthcare records; Eligibility criteria attribute normalization; Eligibility criteria phenotyping.

Fig. 1

The overall workflow of the normalization process involved standardizing attributes from seven clinical domains using standard codes and predefined mapping rules. ICD international classification of diseases, CPT current procedural terminology, LOINC logical observation identifiers names and codes, RxNorm prescription (Rx) normalized Names, UMLS unified medical language system, HSM horizon surgical manager.

Fig. 2

Clinical trial eligibility criteria phenotyping. (A) Eligibility criteria attributes from the condition domain are annotated, normalized, and mapped to clinical characteristics in EHR. (B) Eligibility criteria attributes from the procedure domain and clinical characteristics in EHR are annotated and normalized. Annotated and normalized attributes of eligibility criteria of clinical trials are mapped to normalized clinical characteristics in EHR. (C) Eligibility criteria attributes from the lab test domain are annotated and mapped to clinical characteristics in EHR from the lab test domain. Clinical characteristics in EHR from the lab test domain are annotated and normalized. Attributes of eligibility criteria of clinical trials are normalized through mapping to annotated and normalized clinical characteristics in EHR. (D) Eligibility criteria attributes from the therapy domain are annotated, normalized, and mapped to clinical characteristics in EHR. (E) Certain eligibility criteria attributes from the biomarker domain are annotated, normalized, and mapped to clinical characteristics in EHR. (F) Certain eligibility criteria attributes from the observation including demographic domain are annotated, normalized, and mapped to clinical characteristics in EHR. (G) Certain eligibility criteria attributes from the diagnosis modifier domain are annotated, normalized, and mapped to clinical characteristics in EHR.

Fig. 3

Clinical phenotypes in different clinical domains. (A) Distribution of annotated/normalized attributes across different clinical domains. (B) Distribution of annotated/normalized attributes of each disease across different clinical domains. NSCLC non-small cell lung cancer, PC prostate cancer, MM multiple myeloma, BC breast cancer, SCLC small cell lung cancer, NASH non-alcoholic steatohepatitis, IBD inflammatory bowel disease, SCA sickle cell disease.

Fig. 4

Clinical phenotypes in different attribute groups. (A) Distribution of annotated/normalized attributes across different attribute groups. (B) Distribution of annotated/normalized attributes across different modalities in clinical trials of cancer treatment.

Fig. 5

Common clinical phenotypes in clinical trials of cancer studies.

Fig. 6

Knowledge base for annotated and normalized eligibility criteria attributes and normalized clinical characteristics of EHR.