Key result
A logistic regression model combining ICD codes, medications, and clinical notes achieved an AUROC of 0.968 for identifying congestive heart failure from electronic health records.
Why the study?
Manual chart review to identify CHF is time-consuming and ICD codes are less accurate, while automated EHR analysis through NLP has not been validated across multiple sites.
Does an NLP model using structured and unstructured EHR data accurately identify congestive heart failure compared to models using only ICD codes or medications?
Observational (n=1,821)
Yes
Does an NLP model using structured and unstructured EHR data accurately identify congestive heart failure compared to models using only ICD codes or medications?
Answers are grounded in this paper and cite their sources.
An EHR-based NLP model combining clinical notes, ICD codes, and medications accurately identifies congestive heart failure, outperforming models that rely solely on ICD codes or medications.
BACKGROUND: Congestive heart failure (CHF) is a common cause of hospital admissions. Medical records contain valuable information about CHF, but manual chart review is time-consuming. Claims databases (using International Classification of Diseases [ICD] codes) provide a scalable alternative but are less accurate. Automated analysis of medical records through natural language processing (NLP) enables more efficient adjudication but has not yet been validated across multiple sites. OBJECTIVE: We seek to accurately classify the diagnosis of CHF based on structured and unstructured data from each patient, including medications, ICD codes, and information extracted through NLP of notes left by providers, by comparing the effectiveness of several machine learning models. METHODS: We developed an NLP model to identify CHF from medical records using electronic health records (EHRs) from two hospitals (Mass General Hospital and Beth Israel Deaconess Medical Center; from 2010 to 2023), with 2800 clinical visit notes from 1821 patients. We trained and compared the performance of logistic regression, random forests, and RoBERTa models. We measured model performance using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). These models were also externally validated by training the data on one hospital sample and testing on the other, and an overall estimated error was calculated using a completely random sample from both hospitals. RESULTS: The average age of the patients was 66.7 (SD 17.2) years; 978 (54.3%) out of 1821 patients were female. The logistic regression model achieved the best performance using a combination of ICD codes, medications, and notes, with an AUROC of 0.968 (95% CI 0.940-0.982) and an AUPRC of 0.921 (95% CI 0.835-0.969). The models that only used ICD codes or medications had lower performance. The estimated overall error rate in a random EHR sample was 1.6%. The model also showed high external validity from training on Mass General Hospital data and testing on Beth Israel Deaconess Medical Center data (AUROC 0.927, 95% CI 0.908-0.944) and vice versa (AUROC 0.968, 95% CI 0.957-0.976). CONCLUSIONS: The proposed EHR-based phenotyping model for CHF achieved excellent performance, external validity, and generalization across two institutions. The model enables multiple downstream uses, paving the way for large-scale studies of CHF treatment effectiveness, comorbidities, outcomes, and mechanisms.
No takes yet. Share an insight, caveat, or question.
Sumsion et al. (2024) conducted an observational in Congestive heart failure (n=1,821). Logistic regression model using ICD codes, medications, and clinical notes vs. Models using only ICD codes or medications was evaluated on Area under the receiver operating characteristic curve (AUROC) for identifying CHF (AUROC 0.968, 95% CI 0.940-0.982). A logistic regression model combining ICD codes, medications, and clinical notes achieved an AUROC of 0.968 for identifying congestive heart failure from electronic health records.
Synapse has enriched 10 related papers. Consider them for comparative context: