Pub Date : 2026-01-05DOI: 10.1001/jamapediatrics.2025.5385
Jay G. Berry, Derek Mathieu, Steven J. Staffa, Ben Y. Reis, Peter Hong, Gabor Asztalos, Lynne Ferrari
Importance Hospitals are increasingly experiencing challenges with variable and unpredictable inpatient loads, including days with excessively high and excessively low capacity for surgical patients. Artificial intelligence has the potential to facilitate postoperative hospital bed management and stabilize capacity. Objectives To predict hospital length of stay (LOS) following elective surgical procedures using machine learning methods, and to implement the LOS prediction model in a perioperative clinical setting and evaluate its ability to optimize elective surgical scheduling and hospital bed capacity. Design, Setting, and Participants This preimplementation and postimplementation cohort study was conducted at a tertiary, freestanding, US children’s hospital among patients of any age undergoing an elective surgical procedure requiring inpatient recovery. For LOS prediction, a retrospective analysis was performed on elective surgical cases from January 1, 2018, to March 31, 2022, using Extreme Gradient Boosting (XGBoost) to predict postoperative LOS based on in-training and holdout datasets, with hyperparameter tuning using 5-fold cross-validation. For implementation and evaluation of the LOS prediction model, a preimplementation and postimplementation analysis was performed from July 1, 2022, to April 30, 2024. Data analysis was conducted from June 1 to October 31, 2024. Exposures Patients’ type of surgery, chronic conditions, and demographic characteristics. Main Outcomes and Measures Postoperative LOS, day-to-day variance in bedded days for elective surgical procedures, and days with excessively high capacity (&gt;75th percentile of historical elective surgical census) or excessively low capacity (&lt;25th percentile of historical elective surgical census). Results There were 21 352 elective surgical cases (mean [SD] age, 10.2 [7.4] years; 10 804 [50.6%] female) for patients included in the retrospective analysis of postoperative LOS prediction and 12 522 elective surgical cases in the pretest and posttest analysis of the prediction model (premodel implementation, n = 5867; postmodel implementation, n = 6655). The postoperative LOS model had 85.6% accuracy with a 1-night leniency. The model’s mean absolute error was 0.6 days. After implementation of the LOS model in elective surgery scheduling and hospital bed capacity management, the median number of elective surgical procedures increased by 5 (IQR, 4.5-5) for each weekday. Variation in postoperative bedded days across days of the week decreased significantly. The magnitude of the IQR of bedded days decreased the most during midweek: 43% and 44% reductions in the IQR occurred on Wednesdays and Thursdays, respectively. The percentage of weekdays with underused capacity (&lt;84 patients) decreased from 33% to 10% ( <jats:italic toggle="yes">P</jats:italic> &lt; .001), without a significant increase in days with excessive capacity. Conclusions and Relevance In th
{"title":"Artificial Intelligence Length-of-Stay Forecasting and Pediatric Surgical Capacity","authors":"Jay G. Berry, Derek Mathieu, Steven J. Staffa, Ben Y. Reis, Peter Hong, Gabor Asztalos, Lynne Ferrari","doi":"10.1001/jamapediatrics.2025.5385","DOIUrl":"https://doi.org/10.1001/jamapediatrics.2025.5385","url":null,"abstract":"Importance Hospitals are increasingly experiencing challenges with variable and unpredictable inpatient loads, including days with excessively high and excessively low capacity for surgical patients. Artificial intelligence has the potential to facilitate postoperative hospital bed management and stabilize capacity. Objectives To predict hospital length of stay (LOS) following elective surgical procedures using machine learning methods, and to implement the LOS prediction model in a perioperative clinical setting and evaluate its ability to optimize elective surgical scheduling and hospital bed capacity. Design, Setting, and Participants This preimplementation and postimplementation cohort study was conducted at a tertiary, freestanding, US children’s hospital among patients of any age undergoing an elective surgical procedure requiring inpatient recovery. For LOS prediction, a retrospective analysis was performed on elective surgical cases from January 1, 2018, to March 31, 2022, using Extreme Gradient Boosting (XGBoost) to predict postoperative LOS based on in-training and holdout datasets, with hyperparameter tuning using 5-fold cross-validation. For implementation and evaluation of the LOS prediction model, a preimplementation and postimplementation analysis was performed from July 1, 2022, to April 30, 2024. Data analysis was conducted from June 1 to October 31, 2024. Exposures Patients’ type of surgery, chronic conditions, and demographic characteristics. Main Outcomes and Measures Postoperative LOS, day-to-day variance in bedded days for elective surgical procedures, and days with excessively high capacity (&amp;gt;75th percentile of historical elective surgical census) or excessively low capacity (&amp;lt;25th percentile of historical elective surgical census). Results There were 21 352 elective surgical cases (mean [SD] age, 10.2 [7.4] years; 10 804 [50.6%] female) for patients included in the retrospective analysis of postoperative LOS prediction and 12 522 elective surgical cases in the pretest and posttest analysis of the prediction model (premodel implementation, n = 5867; postmodel implementation, n = 6655). The postoperative LOS model had 85.6% accuracy with a 1-night leniency. The model’s mean absolute error was 0.6 days. After implementation of the LOS model in elective surgery scheduling and hospital bed capacity management, the median number of elective surgical procedures increased by 5 (IQR, 4.5-5) for each weekday. Variation in postoperative bedded days across days of the week decreased significantly. The magnitude of the IQR of bedded days decreased the most during midweek: 43% and 44% reductions in the IQR occurred on Wednesdays and Thursdays, respectively. The percentage of weekdays with underused capacity (&amp;lt;84 patients) decreased from 33% to 10% ( <jats:italic toggle=\"yes\">P</jats:italic> &amp;lt; .001), without a significant increase in days with excessive capacity. Conclusions and Relevance In th","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":"19 1","pages":""},"PeriodicalIF":26.1,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145897754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1001/jamapediatrics.2025.5835
{"title":"Change to Open Access.","authors":"","doi":"10.1001/jamapediatrics.2025.5835","DOIUrl":"10.1001/jamapediatrics.2025.5835","url":null,"abstract":"","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":"180 1","pages":"118"},"PeriodicalIF":18.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12771226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145906131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1001/jamapediatrics.2025.4534
Aditi Vasan, Jeffrey P Brosco
{"title":"Medicaid and Child Health-Threats and Opportunities.","authors":"Aditi Vasan, Jeffrey P Brosco","doi":"10.1001/jamapediatrics.2025.4534","DOIUrl":"10.1001/jamapediatrics.2025.4534","url":null,"abstract":"","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":" ","pages":"15-17"},"PeriodicalIF":18.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145540807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1001/jamapediatrics.2025.5223
{"title":"Errors in Letter and Supplement.","authors":"","doi":"10.1001/jamapediatrics.2025.5223","DOIUrl":"10.1001/jamapediatrics.2025.5223","url":null,"abstract":"","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":" ","pages":"118"},"PeriodicalIF":18.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12645393/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145587452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1001/jamapediatrics.2025.4361
Carlo V Bellieni
{"title":"Considering Pain in Newborn Circumcision.","authors":"Carlo V Bellieni","doi":"10.1001/jamapediatrics.2025.4361","DOIUrl":"10.1001/jamapediatrics.2025.4361","url":null,"abstract":"","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":" ","pages":"114"},"PeriodicalIF":18.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145540719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1001/jamapediatrics.2025.4492
João Paulo Lima Santos, Adriane M Soehner
{"title":"Revisiting the Screen-Sleep-Mood Pathway-Reply.","authors":"João Paulo Lima Santos, Adriane M Soehner","doi":"10.1001/jamapediatrics.2025.4492","DOIUrl":"10.1001/jamapediatrics.2025.4492","url":null,"abstract":"","PeriodicalId":14683,"journal":{"name":"JAMA Pediatrics","volume":" ","pages":"116"},"PeriodicalIF":18.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145481209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：