{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T15:08:01Z","timestamp":1791644881393,"version":"4.3.4"},"reference-count":49,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n \n Standardized registries, such as the\n International Classification of Diseases<\/jats:italic>\n (\n ICD<\/jats:italic>\n ) codes, are commonly built using administrative codes assigned to patient encounters. However, patients with fall injury are often coded using subsequent injury codes, such as hip fractures. This necessitates manual screening to ensure the accuracy of data registries.\n <\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n \n This study aimed to automate the extraction of fall incidents and mechanisms using natural language processing (NLP) and compare this approach with the\n ICD<\/jats:italic>\n method.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Clinical notes for patients with fall-induced hip fractures were retrospectively reviewed by medical experts. Fall incidences were detected, annotated, and classified among patients who had a fall-induced hip fracture (case group). The control group included patients with hip fractures without any evidence of falls. NLP models were developed using the annotated notes of the study groups to fulfill two separate tasks: fall occurrence detection and fall mechanism classification. The performances of the models were compared using accuracy, sensitivity, specificity, positive predictive value, negative predictive value,\n F<\/jats:italic>\n 1<\/jats:sub>\n -score, and area under the receiver operating characteristic curve.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 1769 clinical notes were included in the final analysis for the fall occurrence task, and 783 clinical notes were analyzed for the fall mechanism classification task. The highest\n F<\/jats:italic>\n 1<\/jats:sub>\n -score using NLP for fall occurrence was 0.97 (specificity=0.96; sensitivity=0.97), and for fall mechanism classification was 0.61 (specificity=0.56; sensitivity=0.62). Natural language processing could detect up to 98% of the fall occurrences and 65% of the fall mechanisms accurately, compared to 26% and 12%, respectively, by\n ICD<\/jats:italic>\n codes.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Our findings showed promising performance with higher accuracy of NLP algorithms compared to the conventional method for detecting fall occurrence and mechanism in developing disease registries using clinical notes. Our approach can be introduced to other registries that are based on large data and are in need of accurate annotation and classification.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/66973","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:00:12Z","timestamp":1740103212000},"page":"e66973-e66973","source":"Crossref","is-referenced-by-count":3,"title":["Performance of Natural Language Processing versus International Classification of Diseases Codes in Building Registries for Patients With Fall Injury: Retrospective Analysis"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7485-1500","authenticated-orcid":false,"given":"Atta","family":"Taseh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5929-3786","authenticated-orcid":false,"given":"Souri","family":"Sasanfar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6741-3673","authenticated-orcid":false,"given":"Michelle","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5037-0061","authenticated-orcid":false,"given":"Evan","family":"Sirls","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3992-3489","authenticated-orcid":false,"given":"Ara","family":"Nazarian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9893-9136","authenticated-orcid":false,"given":"Kayhan","family":"Batmanghelich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8385-8210","authenticated-orcid":false,"given":"Jonathan F","family":"Bean","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2299-6278","authenticated-orcid":false,"given":"Soheil","family":"Ashkani-Esfahani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,7,14]]},"reference":[{"issue":"37","key":"R1","doi-asserted-by":"publisher","first-page":"993","DOI":"10.15585\/mmwr.mm6537a2","article-title":"Falls and fall injuries among adults aged \u226565 years - United States, 2014","volume":"65","author":"Bergen","journal-title":"MMWR Morb Mortal Wkly Rep"},{"issue":"27","key":"R2","doi-asserted-by":"publisher","first-page":"875","DOI":"10.15585\/mmwr.mm6927a5","article-title":"Trends in nonfatal falls and fall-related injuries among adults aged \u226565 years - United States, 2012-2018","volume":"69","author":"Moreland","journal-title":"MMWR Morb Mortal Wkly Rep"},{"key":"R3","unstructured":"Cost of older adult falls. US Centers for Disease Control and Prevention. URL: https:\/\/stacks.cdc.gov\/view\/cdc\/122747 [Accessed 17-07-2024]"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1111\/jgs.15304","article-title":"The medical costs of fatal falls and fall injuries among older adults","volume":"66","author":"Florence","journal-title":"J Am Geriatr Soc"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1097\/JTN.0000000000000295","article-title":"Development of a falls registry: a pilot study","volume":"24","author":"Berg","journal-title":"J Trauma Nurs"},{"issue":"4","key":"R6","first-page":"211","volume":"4","author":"Trotter","journal-title":"Ochsner J"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S91125","article-title":"The Danish National Patient Registry: a review of content, data quality, and research potential","volume":"7","author":"Schmidt","journal-title":"Clin Epidemiol"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.amjsurg.2018.01.008","article-title":"Ten-year trends in traumatic injury mechanisms and outcomes: a trauma registry analysis","volume":"215","author":"Khorgami","journal-title":"Am J Surg"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1186\/s40621-020-0234-7","article-title":"Mechanisms of accidental fall injuries and involved injury factors: a registry-based study","volume":"7","author":"Unguryanu","journal-title":"Inj Epidemiol"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1007\/s00198-016-3808-z","article-title":"Proximal humeral fractures in Sweden-a registry-based study","volume":"28","author":"Sumrein","journal-title":"Osteoporos Int"},{"issue":"4","key":"R11","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s10799-009-0061-6","article-title":"Identifying fall-related injuries: text mining the electronic medical record","volume":"10","author":"Tremblay","journal-title":"Inf Technol Manag"},{"issue":"6","key":"R12","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1038\/nrg3208","article-title":"Mining electronic health records: towards better research applications and clinical care","volume":"13","author":"Jensen","journal-title":"Nat Rev Genet"},{"issue":"11","key":"R13","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1016\/j.injury.2005.05.024","article-title":"The acute medical care costs of fall-related injuries among the U.S. older adults","volume":"36","author":"Roudsari","journal-title":"Injury"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Gliklich RE Leavy MB Dreyer NA . Registries for Evaluating Patient Outcomes: A User\u2019s Guide. Agency for Healthcare Research and Quality (AHRQ); 2020. [doi: 10.23970\/AHRQEPCREGISTRIES4]","DOI":"10.23970\/AHRQEPCREGISTRIES4"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0843-7","article-title":"Development and validation of a pragmatic natural language processing approach to identifying falls in older adults in the emergency department","volume":"19","author":"Patterson","journal-title":"BMC Med Inform Decis Mak"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"e174","DOI":"10.1097\/PTS.0000000000000275","article-title":"Identification of inpatient falls using automated review of text-based medical records","volume":"16","author":"Shiner","journal-title":"J Patient Saf"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104736","article-title":"A hybrid model to identify fall occurrence from electronic health records","volume":"162","author":"Fu","journal-title":"Int J Med Inform"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.injury.2008.06.040","article-title":"Epidemiology of traumatic spine fractures","volume":"40","author":"Leucht","journal-title":"Injury"},{"key":"R19","unstructured":"Institute of Medicine (US) Division of Health Promotion and Disease PreventionBerg RL Cassells JS . Falls in older persons: risk factors and prevention. In: The Second Fifty Years: Promoting Health and Preventing Disability, National Academies Press (US). 1992. URL: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK235613 [Accessed 17-07-2024]"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1097\/00005373-200101000-00021","article-title":"Geriatric falls: injury severity is high and disproportionate to mechanism","volume":"50","author":"Sterling","journal-title":"The Journal of Trauma: Injury, Infection, and Critical Care"},{"issue":"2","key":"R21","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1093\/jamia\/ocac219","article-title":"Automated deidentification of radiology reports combining transformer and \u201chide in plain sight\u201d rule-based methods","volume":"30","author":"Chambon","journal-title":"J Am Med Inform Assoc"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","first-page":"1756","DOI":"10.1093\/jamia\/ocab048","article-title":"Evaluating resampling methods and structured features to improve fall incident report identification by the severity level","volume":"28","author":"Liu","journal-title":"J Am Med Inform Assoc"},{"key":"#cr-split#-R23.1","unstructured":"Devlin J Chang MW Lee K Toutanova K . BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein J Doran C Solorio T , editors. Presented at: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics. 4171-4186"},{"key":"#cr-split#-R23.2","doi-asserted-by":"crossref","unstructured":"Jun 2019.[doi: 10.18653\/v1\/N19-1423]","DOI":"10.18653\/v1\/N19-1423"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/BF00116251","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","journal-title":"Mach Learn"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","journal-title":"J Comput Syst Sci"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.04.001","article-title":"Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction","volume":"58","author":"Zi\u0119ba","journal-title":"Expert Syst Appl"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C . XGBoost: a scalable tree boosting system. Presented at: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD \u201916. Association for Computing Machinery. 785-794; Aug 2016.[doi: 10.1145\/2939672.2939785]","DOI":"10.1145\/2939672.2939785"},{"issue":"10","key":"R28","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/aadf0f","article-title":"Classification of short single-lead electrocardiograms (ECGs) for atrial fibrillation detection using piecewise linear spline and XGBoost","volume":"39","author":"Chen","journal-title":"Physiol Meas"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s40708-017-0065-7","article-title":"Machine learning\u2013XGBoost analysis of language networks to classify patients with epilepsy","volume":"4","author":"Torlay","journal-title":"Brain Inf"},{"issue":"3","key":"R30","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.jcct.2018.04.011","article-title":"Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry","volume":"12","author":"van Rosendael","journal-title":"J Cardiovasc Comput Tomogr"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Alizadehsani R Hosseini MJ Sani ZA Ghandeharioun A Boghrati R . Diagnosis of coronary artery disease using cost-sensitive algorithms. In: Proceedings of 2012 IEEE 12th International Conference on Data Mining Workshops. 2012:9-16. [doi: 10.1109\/ICDMW.2012.29] ISBN: 978-1-4673-5164-5","DOI":"10.1109\/ICDMW.2012.29"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/8826088","article-title":"Human falling detection algorithm based on multisensor data fusion with SVM","volume":"2020","author":"Pan","journal-title":"Mobile Information Systems"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Parmar A Katariya R Patel V . A review on random forest: an ensemble classifier. In: Hemanth J Fernando X Lafata P Baig Z , editors. International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI). Springer, Cham; 2019:758-763. Lecture Notes on Data Engineering and Communications Technologies. [doi: 10.1007\/978-3-030-03146-6_86]","DOI":"10.1007\/978-3-030-03146-6_86"},{"key":"R34","unstructured":"Opitz J . From bias and prevalence to macro F1, kappa, and MCC: a structured overview of metrics for multi-class evaluation. Semantic Scholar. URL: https:\/\/www.semanticscholar.org\/paper\/From-Bias-and-Prevalence-to-Macro-F1%2C-Kappa%2C-and-A-Opitz\/ff334e8cee3550eb5c80a61213ad0aecb549f48f [Accessed 28-06-2025]"},{"issue":"4","key":"R35","doi-asserted-by":"publisher","DOI":"10.2196\/16970","article-title":"Predicting inpatient falls using natural language processing of nursing records obtained from Japanese electronic medical records: case-control study","volume":"8","author":"Nakatani","journal-title":"JMIR Med Inform"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/1089815.1089824","article-title":"Using text mining and natural language processing for health care claims processing","volume":"7","author":"Popowich","journal-title":"SIGKDD Explor Newsl"},{"issue":"7","key":"R37","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1097\/MLR.0000000000000531","article-title":"Claims-based identification methods and the cost of fall-related injuries among US older adults","volume":"54","author":"Hoffman","journal-title":"Med Care"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.2196\/48995","article-title":"BERT-Based neural network for inpatient fall detection from electronic medical records: retrospective cohort study","volume":"12","author":"Cheligeer","journal-title":"JMIR Med Inform"},{"issue":"6","key":"R39","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.2105\/AJPH.2014.302440","article-title":"Improving identification of fall-related injuries in ambulatory care using statistical text mining","volume":"105","author":"Luther","journal-title":"Am J Public Health"},{"key":"R40","doi-asserted-by":"crossref","unstructured":"dos Santos HDP Silva AP Maciel MCO Burin HMV Urbanetto JS Vieira R . Fall detection in EHR using word embeddings and deep learning. Presented at: 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). Oct 28-30, 2019:IEEE. 265-268; Athens, Greece. [doi: 10.1109\/BIBE.2019.00054]","DOI":"10.1109\/BIBE.2019.00054"},{"key":"R41","unstructured":"Gani R Chalaguine L . Feature engineering vs BERT on twitter data. ArXiv. Preprint posted online on Oct 28, 2022. [doi: 10.48550\/ARXIV.2210.16168]"},{"key":"R42","unstructured":"Albano A Sciandra M Plaia A . Ensemble method for text classification in medicine with multiple rare classes. In: CLADAG 2023. Pearson, Italy; 2023:17. URL: https:\/\/www.statlab-unisa.it\/cladag2023\/book-of-abstracts\/ [Accessed 06-07-2025]"},{"key":"R43","unstructured":"Gliklich RE Dreyer NA Leavy MB . Registries for Evaluating Patient Outcomes: A User\u2019s Guide. Rockville (MD): Agency for Healthcare Research and Quality (US); 2014. ISBN: 24945055"},{"issue":"9","key":"R44","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1001\/jamadermatol.2021.2856","article-title":"Validity of using billing codes from electronic health records to estimate skin cancer counts","volume":"157","author":"Anand","journal-title":"JAMA Dermatol"},{"issue":"8","key":"R45","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1016\/j.jclinepi.2006.01.004","article-title":"International classification of diseases and current procedural terminology codes underestimated thrombolytic use for ischemic stroke","volume":"59","author":"Qureshi","journal-title":"J Clin Epidemiol"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S63758","article-title":"Acromegaly according to the Danish National Registry of Patients: how valid are ICD diagnoses and how do patterns of registration affect the accuracy of registry data?","author":"Dal","journal-title":"CLEP"},{"issue":"Suppl 3","key":"R47","doi-asserted-by":"publisher","first-page":"39","DOI":"10.2106\/JBJS.22.00565","article-title":"Administrative data use in national registry efforts: blessing or curse?","volume":"104","author":"Bedard","journal-title":"Journal of Bone and Joint Surgery"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-35482-0","article-title":"Constructing a disease database and using natural language processing to capture and standardize free text clinical information","volume":"13","author":"Raza","journal-title":"Sci Rep"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e66973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:28:17Z","timestamp":1785536897000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e66973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,14]]},"references-count":49,"URL":"https:\/\/doi.org\/10.2196\/66973","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,14]]},"article-number":"v13i37e66973"}}