{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T16:55:19Z","timestamp":1790873719587,"version":"4.1.0"},"reference-count":28,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"unspecified","delay-in-days":16,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"publisher","award":["TSGH-E-112246"],"award-info":[{"award-number":["TSGH-E-112246"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"publisher","award":["TSGH-C108-175"],"award-info":[{"award-number":["TSGH-C108-175"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"publisher","award":["TSGH-D-113200"],"award-info":[{"award-number":["TSGH-D-113200"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2025,9,1]]},"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Surgical pressure injuries (SPIs) are a significant patient safety risk due to prolonged immobility and tissue hypoperfusion under general anaesthesia. Existing risk assessment tools lack real-time predictive capabilities. This study developed and validated a machine-learning model for SPI prediction and clinical integration.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Method<\/jats:title>\n                  <jats:p>This retrospective cohort study analysed electronic health records from 931 surgical inpatients under general anaesthesia between January 2016 and December 2021. SPI cases were identified using ICD-10 codes with 1:1 matching by medical specialty. Data preprocessing included imputation, normalisation and outlier removal. Logistic regression (LR), multilayer perceptron (MLP) and decision tree (DT) models were developed and validated via cross-validation. Model performance was assessed using area under the curve (AUC), accuracy, precision, recall and F1 score.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Significant SPI predictors included the Charlson Comorbidity Index (p&lt;0.001), number of medication types (p=0.001) and body mass index (p&lt;0.001). The MLP outperformed LR (AUC=0.707) and DT (AUC=0.717), achieving the highest AUC (0.836), accuracy (0.773), precision (0.812), recall (0.688) and F1 score (0.745).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>The MLP model effectively identified key SPI risk factors, outperforming LR and DT by capturing non-linear relationships. Its integration into clinical workflows may enhance perioperative risk management through early detection and targeted interventions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Machine learning integration can improve early SPI detection and personalised prevention. The MLP model demonstrated the highest potential for real-time SPI risk stratification. Future research should validate this model across diverse surgical populations and develop scalable strategies for clinical implementation.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjhci-2025-101532","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T05:05:25Z","timestamp":1758171925000},"page":"e101532","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":3,"title":["Comparative performance of logistic regression, multilayer perceptron and decision tree models for predicting surgical pressure injuries: a retrospective cohort study"],"prefix":"10.1136","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1464-8871","authenticated-orcid":false,"given":"Chia-Yen","family":"Li","sequence":"first","affiliation":[{"name":"Quality Management Center, Tri-Service General Hospital, Taipei City, Taiwan"},{"name":"Graduate Institute of Medical Sciences, National Defense Medical University, Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Ming","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Public Health, National Defense Medical University, Taipei City, Taiwan"},{"name":"Department of Public Health, Kaohsiung Medical University, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao-Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"Division of Trauma & Critical Surgery, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yen","family":"Ke","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Surgery, Tri-Service General Hospital, Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng-Ching","family":"Hsiao","sequence":"additional","affiliation":[{"name":"Graduate Institute of Medical Sciences, National Defense Medical University, Taipei City, Taiwan"},{"name":"Department of Nursing, Tri-Service General Hospital, Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9020-3279","authenticated-orcid":false,"given":"Hsueh-Hsing","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Nursing, Tri-Service General Hospital, Taipei City, Taiwan"},{"name":"School of Nursing, National Defense Medical University, Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"2025091722051580000_32.1.e101532.1","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1097\/ASW.0000000000000130","article-title":"Risk Factors of Intraoperative Pressure Injury in Adult Patients Undergoing Neurologic Surgery","volume":"37","author":"Peng","year":"2024","journal-title":"Adv Skin Wound Care"},{"key":"2025091722051580000_32.1.e101532.2","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.jtv.2023.06.004","article-title":"The incidence and risk factors of pressure injuries in surgical patients","volume":"32","author":"\u0130lkhan","year":"2023","journal-title":"J Tissue Viability"},{"key":"2025091722051580000_32.1.e101532.3","doi-asserted-by":"crossref","unstructured":"Chen WY , Hsu TH , Chang CH , et al . Pressure injury risk factors in patients undergoing general anesthesia surgeries. Wound Manag Prev 2024;70. doi:10.25270\/wmp.23025","DOI":"10.25270\/wmp.23025"},{"key":"2025091722051580000_32.1.e101532.4","doi-asserted-by":"crossref","first-page":"104642","DOI":"10.1016\/j.ijnurstu.2023.104642","article-title":"Risk factors predicting hospital-acquired pressure injury in adult patients: An overview of reviews","volume":"150","author":"Wang","year":"2024","journal-title":"Int J Nurs Stud"},{"key":"2025091722051580000_32.1.e101532.5","doi-asserted-by":"crossref","first-page":"1924","DOI":"10.1111\/iwj.13482","article-title":"Risk of readmissions, mortality, and hospital-acquired conditions across hospital-acquired pressure injury (HAPI) stages in a US National Hospital Discharge database","volume":"17","author":"Wassel","year":"2020","journal-title":"Int Wound J"},{"key":"2025091722051580000_32.1.e101532.6","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.jtv.2020.04.003","article-title":"Pressure ulcer\/injury classification today: An international perspective","volume":"29","author":"Kottner","year":"2020","journal-title":"J Tissue Viability"},{"key":"2025091722051580000_32.1.e101532.7","doi-asserted-by":"crossref","first-page":"108","DOI":"10.17085\/apm.20081","article-title":"An exploratory study of risk factors for pressure injury in patients undergoing spine surgery","volume":"16","author":"Suh","year":"2021","journal-title":"Anesth Pain Med"},{"key":"2025091722051580000_32.1.e101532.8","doi-asserted-by":"crossref","first-page":"104768","DOI":"10.1016\/j.ijnurstu.2024.104768","article-title":"The effect of pressure injury prevention care bundles on pressure injuries in hospital patients: A complex intervention systematic review and meta-analysis","volume":"155","author":"Chaboyer","year":"2024","journal-title":"Int J Nurs Stud"},{"key":"2025091722051580000_32.1.e101532.9","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1002\/aorn.13918","article-title":"Prevention of Perioperative Pressure Injury","volume":"117","author":"Spruce","year":"2023","journal-title":"AORN J"},{"key":"2025091722051580000_32.1.e101532.10","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000005247"},{"key":"2025091722051580000_32.1.e101532.11","doi-asserted-by":"crossref","unstructured":"Zelen\u00fd O , Fryza T . Multi-branch multi layer perceptron: a solution for precise regression using machine learning. 2023 33rd International Conference Radioelektronika (RADIOELEKTRONIKA); 1\u20135. Pardubice, Czech Republic. doi:10.1109\/RADIOELEKTRONIKA57919.2023.10109076","DOI":"10.1109\/RADIOELEKTRONIKA57919.2023.10109076"},{"key":"2025091722051580000_32.1.e101532.12","doi-asserted-by":"crossref","unstructured":"Charbuty B , Abdulazeez AM . Classification Based on Decision Tree Algorithm for Machine Learning. Journal of Applied Science and Technology Trends 2021. doi:10.38094\/jastt20165","DOI":"10.38094\/jastt20165"},{"key":"2025091722051580000_32.1.e101532.13","doi-asserted-by":"publisher","DOI":"10.1080\/00273171.2011.568786"},{"key":"2025091722051580000_32.1.e101532.14","doi-asserted-by":"crossref","DOI":"10.1186\/s12883-020-01888-w","article-title":"Establishment of age group classification for risk stratification in glioma patients","volume":"20","author":"Lin","year":"2020","journal-title":"BMC Neurol"},{"key":"2025091722051580000_32.1.e101532.15","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1016\/S0140-6736(16)30175-1","article-title":"Body-mass index and all-cause mortality: individual-participant-data meta-analysis of 239 prospective studies in four continents","volume":"388","author":"Di Angelantonio","year":"2016","journal-title":"The Lancet"},{"key":"2025091722051580000_32.1.e101532.16","doi-asserted-by":"publisher","DOI":"10.1159\/000521288"},{"key":"2025091722051580000_32.1.e101532.17","doi-asserted-by":"crossref","unstructured":"Sharma Y , Avina P , Ross E , et al . Validity of the Malnutrition Universal Screening Tool for Evaluation of Frailty Status in Older Hospitalised Patients. Gerontol Geriatr Med 2022. doi:10.1177\/23337214221107817","DOI":"10.1177\/23337214221107817"},{"key":"2025091722051580000_32.1.e101532.18","doi-asserted-by":"crossref","first-page":"7110","DOI":"10.1038\/s41598-022-10736-5","article-title":"Discordant American Society of Anesthesiologists Physical Status Classification between anesthesiologists and surgeons and its correlation with adverse patient outcomes","volume":"12","author":"Kwa","year":"2022","journal-title":"Sci Rep"},{"key":"2025091722051580000_32.1.e101532.19","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1002\/aorn.13563","article-title":"Management and Mitigation of Temperature and Humidity Events in the Perioperative Setting","volume":"114","author":"Curless","year":"2021","journal-title":"Aorn j"},{"key":"2025091722051580000_32.1.e101532.20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0587.2012.07348.x"},{"key":"2025091722051580000_32.1.e101532.21","doi-asserted-by":"crossref","DOI":"10.1590\/1677-5449.200186","article-title":"Use of ROC curves in clinical and experimental studies","volume":"19","author":"Polo","year":"2020","journal-title":"J Vasc Bras"},{"key":"2025091722051580000_32.1.e101532.22","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7992"},{"key":"2025091722051580000_32.1.e101532.23","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.jtv.2020.05.001","article-title":"Sex-specific differences in prevention and treatment of institutional-acquired pressure ulcers in hospitals and nursing homes","volume":"29","author":"Lichterfeld-Kottner","year":"2020","journal-title":"J Tissue Viability"},{"key":"2025091722051580000_32.1.e101532.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtv.2023.04.006"},{"key":"2025091722051580000_32.1.e101532.25","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.jtv.2016.10.003","article-title":"Effects of two different fabrics on skin barrier function under real pressure conditions","volume":"26","author":"Schario","year":"2017","journal-title":"J Tissue Viability"},{"key":"2025091722051580000_32.1.e101532.26","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.jtv.2015.04.002","article-title":"Skin response to sustained loading: A clinical explorative study","volume":"24","author":"Kottner","year":"2015","journal-title":"J Tissue Viability"},{"key":"2025091722051580000_32.1.e101532.27","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1111\/iwj.12883","article-title":"Comparing the effects of 3 different pressure ulcer prevention support surfaces on the structure and function of heel and sacral skin: An exploratory cross-over trial","volume":"Scholar","author":"Tomova-Simitchieva","year":"2018","journal-title":"Int Wound J"},{"key":"2025091722051580000_32.1.e101532.28","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1097\/01.ASW.0000833612.84272.da","article-title":"The Effects of Skin Temperature Changes on the Integrity of Skin Tissue: A Systematic Review","volume":"35","author":"Mifsud","year":"2022","journal-title":"Adv Skin Wound Care"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2025-101532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T05:05:30Z","timestamp":1758171930000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2025-101532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,9,17]]},"published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1136\/bmjhci-2025-101532"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2025-101532","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}