PMID- 33278631 OWN - NLM STAT- MEDLINE DCOM- 20210701 LR - 20210701 IS - 1879-0534 (Electronic) IS - 0010-4825 (Linking) VI - 129 DP - 2021 Feb TI - Natural language processing with deep learning for medical adverse event detection from free-text medical narratives: A case study of detecting total hip replacement dislocation. PG - 104140 LID - S0010-4825(20)30471-6 [pii] LID - 10.1016/j.compbiomed.2020.104140 [doi] AB - BACKGROUND: Accurate and timely detection of medical adverse events (AEs) from free-text medical narratives can be challenging. Natural language processing (NLP) with deep learning has already shown great potential for analyzing free-text data, but its application for medical AE detection has been limited. METHOD: In this study, we developed deep learning based NLP (DL-NLP) models for efficient and accurate hip dislocation AE detection following primary total hip replacement from standard (radiology notes) and non-standard (follow-up telephone notes) free-text medical narratives. We benchmarked these proposed models with traditional machine learning based NLP (ML-NLP) models, and also assessed the accuracy of International Classification of Diseases (ICD) and Current Procedural Terminology (CPT) codes in capturing these hip dislocation AEs in a multi-center orthopaedic registry. RESULTS: All DL-NLP models outperformed all of the ML-NLP models, with a convolutional neural network (CNN) model achieving the best overall performance (Kappa = 0.97 for radiology notes, and Kappa = 1.00 for follow-up telephone notes). On the other hand, the ICD/CPT codes of the patients who sustained a hip dislocation AE were only 75.24% accurate. CONCLUSIONS: We demonstrated that a DL-NLP model can be used in largescale orthopaedic registries for accurate and efficient detection of hip dislocation AEs. The NLP model in this study was developed with data from the most frequently used electronic medical record (EMR) system in the U.S., Epic. This NLP model could potentially be implemented in other Epic-based EMR systems to improve AE detection, and consequently, quality of care and patient outcomes. CI - Copyright (c) 2020 Elsevier Ltd. All rights reserved. FAU - Borjali, Alireza AU - Borjali A AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA; Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA. FAU - Magneli, Martin AU - Magneli M AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA; Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA; Karolinska Institutet, Department of Clinical Sciences, Danderyd Hospital, Stockholm, Sweden. FAU - Shin, David AU - Shin D AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA. FAU - Malchau, Henrik AU - Malchau H AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA; Department of Orthopaedic Surgery, Sahlgrenska University Hospital, Sweden. FAU - Muratoglu, Orhun K AU - Muratoglu OK AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA; Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA. FAU - Varadarajan, Kartik M AU - Varadarajan KM AD - Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA; Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA. Electronic address: kmangudivaradarajan@mgh.harvard.edu. LA - eng PT - Journal Article PT - Research Support, Non-U.S. Gov't DEP - 20201124 PL - United States TA - Comput Biol Med JT - Computers in biology and medicine JID - 1250250 SB - IM MH - *Arthroplasty, Replacement, Hip/adverse effects MH - *Deep Learning MH - Electronic Health Records MH - Humans MH - Machine Learning MH - Natural Language Processing MH - Neural Networks, Computer OTO - NOTNLM OT - Deep learning OT - Electronic medical records OT - Hip dislocation OT - Medical adverse event OT - Natural language processing EDAT- 2020/12/06 06:00 MHDA- 2021/07/02 06:00 CRDT- 2020/12/05 20:10 PHST- 2020/10/01 00:00 [received] PHST- 2020/11/18 00:00 [revised] PHST- 2020/11/19 00:00 [accepted] PHST- 2020/12/06 06:00 [pubmed] PHST- 2021/07/02 06:00 [medline] PHST- 2020/12/05 20:10 [entrez] AID - S0010-4825(20)30471-6 [pii] AID - 10.1016/j.compbiomed.2020.104140 [doi] PST - ppublish SO - Comput Biol Med. 2021 Feb;129:104140. doi: 10.1016/j.compbiomed.2020.104140. Epub 2020 Nov 24.