A hybrid model to identify fall occurrence from electronic health records. (June 2022)

• Record Type: Journal Article
• Authors: Fu, Sunyang; Thorsteinsdottir, Bjoerg; Zhang, Xin; Lopes, Guilherme S.; Pagali, Sandeep R.; LeBrasseur, Nathan K.; Wen, Andrew; Liu, Hongfang; Rocca, Walter A.; Olson, Janet E.; Sauver, Jennifer St.; Sohn, Sunghwan
• Is Part Of: International journal of medical informatics. Volume 162(2022)
• Publication Date: 2022-06
• Subjects: NLP -- BERT -- Fall -- EHR; NLP Natural Language Processing -- BERT Bidirectional Encoder Representations from Transformers -- CNN Convolutional Neural Network -- Bi-LSTM Bidirectional Long Short-term Memory -- EHR Electronic Health Record -- ANA American Nurses Association -- RNN Recurrent Neural Networks -- UIMA Unstructured Information Management Architecture -- ICD International Classification of Diseases -- PPV Positive Predictive Value -- NPV Negative Predictive Value -- FP False Positive -- FN False Negative -- TF-IDF Term Frequency Inverse Document Frequency; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2022.104736
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: Falls are a leading cause of unintentional injury among older adults. EHR documents contain many fall events, not captured by ICD-9/10 codes. A BERT model can capture fall events that require context understanding. A hybrid model further improves the performance of BERT through post-hoc rules. Abstract: Introduction: Falls are a leading cause of unintentional injury in the elderly. Electronic health records (EHRs) offer the unique opportunity to develop models that can identify fall events. However, identifying fall events in clinical notes requires advanced natural language processing (NLP) to simultaneously address multiple issues because the word "fall" is a typical homonym. Methods: We implemented a context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) to identify falls from the EHR text and further fused the BERT model into a hybrid architecture coupled with post-hoc heuristic rules to enhance the performance. The models were evaluated on real world EHR data and were compared to conventional rule-based and deep learning models (CNN and Bi-LSTM). To better understand the ability of each approach to identify falls, we further categorize fall-related concepts (i.e., risk of fall, prevention of fall, homonym) and performed a detailed error analysis. Results: The hybrid model achieved the highest f1-score on sentence (0.971), document (0.985), and patient (0.954) level. At the sentence level (basic data unit in the model), the hybrid model had 0.954, 1.000, 0.988, and 0.999 in sensitivity, specificity, positive predictive value, and negative predictive value, respectively. The error analysis showed that that machine learning-based approaches demonstrated higher performance than a rule-based approach in challenging cases that required contextual understanding. The context-aware language model (BERT) slightly outperformed the word embedding approach trained on Bi-LSTM. No single model yielded the best performance for all fall-related semantic categories. Conclusion: A context-aware language model (BERT) was able to identify challenging fall events that requires context understanding in EHR free text. The hybrid model combined with post-hoc rules allowed a custom fix on the BERT outcomes and further improved the performance of fall detection.