JMIR Publications

ABSTRACT

Background:

Surveillance of hospital-acquired pressure injuries (HAPI) is often suboptimal when relying on administrative health data, as International Classification of Disease codes are known to have long delays and are under-coded. We leveraged Natural Language Processing applications on free text notes, particularly the inpatient nursing notes, from electronic medical records (EMR), to more accurately and timely identify HAPIs.

Objective:

This study aimed to develop EMR-based phenotyping algorithms to detect HAPIs, while the clinical logs are recorded, with higher accuracy via natural language processing (NLP) using nursing notes.

Methods:

Patients with HAPIs were identified from head-to-toe skin assessments in a local tertiary acute care hospital during a clinical trial that took place from 2015 to 2018 in Calgary, Alberta, Canada. Clinical notes documented during the trial were extracted from the EMR database after the linkage with the DAD. Different combinations of several types of clinical notes were processed by sequential forward selection during the model development. Text classification algorithms for HAPI detection were developed using random forest, XGBoost, and deep learning models. The classification threshold was tuned to enable the model to achieve similar specificity to an ICD-based phenotyping study. Each model’s performance was assessed, and comparisons were made between the metrics, including sensitivity, positive predictive value, negative predictive value, and F1 score.

Results:

Data of 280 eligible patients were used in this study, among which 97 patients had HAPIs during the trial. Random forest was the optimal performing model with a sensitivity of 46.4% (95% CI: 36.2%-56.8%), specificity of 98.4% (95% CI: 95.3%-99.7%), and F1 score of 59.1%. The machine learning model reached higher sensitivity without sacrificing much specificity compared to the previously reported performance of ICD-based algorithms.

Conclusions:

The EMR-based NLP phenotyping algorithms demonstrated improved performance in HAPI case detection over ICD-10-CA codes alone. Daily generated nursing notes in EMRs are a valuable data resource for machine learning models to accurately detect adverse events. The study contributes to enhancing automated healthcare quality and safety surveillance.