Carly E Milliren, Al Ozonoff, Kerri A Fournier, Jennifer Welcher, Assaf Landschaft, Amir A Kimia
{"title":"利用自然语言处理技术加强压力伤害监测。","authors":"Carly E Milliren, Al Ozonoff, Kerri A Fournier, Jennifer Welcher, Assaf Landschaft, Amir A Kimia","doi":"10.1097/PTS.0000000000001193","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>This study assessed the feasibility of nursing handoff notes to identify underreported hospital-acquired pressure injury (HAPI) events.</p><p><strong>Methods: </strong>We have established a natural language processing-assisted manual review process and workflow for data extraction from a corpus of nursing notes across all medical inpatient and intensive care units in a tertiary care pediatric center. This system is trained by 2 domain experts. Our workflow started with keywords around HAPI and treatments, then regular expressions, distributive semantics, and finally a document classifier. We generated 3 models: a tri-gram classifier, binary logistic regression model using the regular expressions as predictors, and a random forest model using both models together. Our final output presented to the event screener was generated using a random forest model validated using derivation and validation sets.</p><p><strong>Results: </strong>Our initial corpus involved 70,981 notes during a 1-year period from 5484 unique admissions for 4220 patients. Our interrater human reviewer agreement on identifying HAPI was high ( κ = 0.67; 95% confidence interval [CI], 0.58-0.75). Our random forest model had 95% sensitivity (95% CI, 90.6%-99.3%), 71.2% specificity (95% CI, 65.1%-77.2%), and 78.7% accuracy (95% CI, 74.1%-83.2%). A total of 264 notes from 148 unique admissions (2.7% of all admissions) were identified describing likely HAPI. Sixty-one described new injuries, and 64 describe known yet possibly evolving injuries. Relative to the total patient population during our study period, HAPI incidence was 11.9 per 1000 discharges, and incidence rate was 1.2 per 1000 bed-days.</p><p><strong>Conclusions: </strong>Natural language processing-based surveillance is proven to be feasible and high yield using nursing handoff notes.</p>","PeriodicalId":48901,"journal":{"name":"Journal of Patient Safety","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10922576/pdf/","citationCount":"0","resultStr":"{\"title\":\"Enhancing Pressure Injury Surveillance Using Natural Language Processing.\",\"authors\":\"Carly E Milliren, Al Ozonoff, Kerri A Fournier, Jennifer Welcher, Assaf Landschaft, Amir A Kimia\",\"doi\":\"10.1097/PTS.0000000000001193\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>This study assessed the feasibility of nursing handoff notes to identify underreported hospital-acquired pressure injury (HAPI) events.</p><p><strong>Methods: </strong>We have established a natural language processing-assisted manual review process and workflow for data extraction from a corpus of nursing notes across all medical inpatient and intensive care units in a tertiary care pediatric center. This system is trained by 2 domain experts. Our workflow started with keywords around HAPI and treatments, then regular expressions, distributive semantics, and finally a document classifier. We generated 3 models: a tri-gram classifier, binary logistic regression model using the regular expressions as predictors, and a random forest model using both models together. Our final output presented to the event screener was generated using a random forest model validated using derivation and validation sets.</p><p><strong>Results: </strong>Our initial corpus involved 70,981 notes during a 1-year period from 5484 unique admissions for 4220 patients. Our interrater human reviewer agreement on identifying HAPI was high ( κ = 0.67; 95% confidence interval [CI], 0.58-0.75). Our random forest model had 95% sensitivity (95% CI, 90.6%-99.3%), 71.2% specificity (95% CI, 65.1%-77.2%), and 78.7% accuracy (95% CI, 74.1%-83.2%). A total of 264 notes from 148 unique admissions (2.7% of all admissions) were identified describing likely HAPI. Sixty-one described new injuries, and 64 describe known yet possibly evolving injuries. Relative to the total patient population during our study period, HAPI incidence was 11.9 per 1000 discharges, and incidence rate was 1.2 per 1000 bed-days.</p><p><strong>Conclusions: </strong>Natural language processing-based surveillance is proven to be feasible and high yield using nursing handoff notes.</p>\",\"PeriodicalId\":48901,\"journal\":{\"name\":\"Journal of Patient Safety\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10922576/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Patient Safety\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/PTS.0000000000001193\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/12/26 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Patient Safety","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/PTS.0000000000001193","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/12/26 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
Enhancing Pressure Injury Surveillance Using Natural Language Processing.
Objective: This study assessed the feasibility of nursing handoff notes to identify underreported hospital-acquired pressure injury (HAPI) events.
Methods: We have established a natural language processing-assisted manual review process and workflow for data extraction from a corpus of nursing notes across all medical inpatient and intensive care units in a tertiary care pediatric center. This system is trained by 2 domain experts. Our workflow started with keywords around HAPI and treatments, then regular expressions, distributive semantics, and finally a document classifier. We generated 3 models: a tri-gram classifier, binary logistic regression model using the regular expressions as predictors, and a random forest model using both models together. Our final output presented to the event screener was generated using a random forest model validated using derivation and validation sets.
Results: Our initial corpus involved 70,981 notes during a 1-year period from 5484 unique admissions for 4220 patients. Our interrater human reviewer agreement on identifying HAPI was high ( κ = 0.67; 95% confidence interval [CI], 0.58-0.75). Our random forest model had 95% sensitivity (95% CI, 90.6%-99.3%), 71.2% specificity (95% CI, 65.1%-77.2%), and 78.7% accuracy (95% CI, 74.1%-83.2%). A total of 264 notes from 148 unique admissions (2.7% of all admissions) were identified describing likely HAPI. Sixty-one described new injuries, and 64 describe known yet possibly evolving injuries. Relative to the total patient population during our study period, HAPI incidence was 11.9 per 1000 discharges, and incidence rate was 1.2 per 1000 bed-days.
Conclusions: Natural language processing-based surveillance is proven to be feasible and high yield using nursing handoff notes.
期刊介绍:
Journal of Patient Safety (ISSN 1549-8417; online ISSN 1549-8425) is dedicated to presenting research advances and field applications in every area of patient safety. While Journal of Patient Safety has a research emphasis, it also publishes articles describing near-miss opportunities, system modifications that are barriers to error, and the impact of regulatory changes on healthcare delivery. This mix of research and real-world findings makes Journal of Patient Safety a valuable resource across the breadth of health professions and from bench to bedside.