Natural Language Processing and Machine Learning to Identify People Who Inject Drugs in Electronic Health Records.

BACKGROUND

Improving the identification of people who inject drugs (PWID) in electronic medical records can improve clinical decision making, risk assessment and mitigation, and health service research. Identification of PWID currently consists of heterogeneous, nonspecific () codes as proxies. Natural language processing (NLP) and machine learning (ML) methods may have better diagnostic metrics than nonspecific codes for identifying PWID.

METHODS

We manually reviewed 1000 records of patients diagnosed with bacteremia admitted to Veterans Health Administration hospitals from 2003 through 2014. The manual review was the reference standard. We developed and trained NLP/ML algorithms with and without regular expression filters for negation (NegEx) and compared these with 11 proxy combinations of codes to identify PWID. Data were split 70% for training and 30% for testing. We calculated diagnostic metrics and estimated 95% confidence intervals (CIs) by bootstrapping the hold-out test set. Best models were determined by best F-score, a summary of sensitivity and positive predictive value.

RESULTS

Random forest with and without NegEx were the best-performing NLP/ML algorithms in the training set. Random forest with NegEx outperformed all -based algorithms. F-score for the best NLP/ML algorithm was 0.905 (95% CI, .786-.967) and 0.592 (95% CI, .550-.632) for the best -based algorithm. The NLP/ML algorithm had a sensitivity of 92.6% and specificity of 95.4%.

CONCLUSIONS

NLP/ML outperformed -based coding algorithms at identifying PWID in electronic health records. NLP/ML models should be considered in identifying cohorts of PWID to improve clinical decision making, health services research, and administrative surveillance.