{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T03:34:37Z","timestamp":1790652877904,"version":"4.1.0"},"reference-count":38,"publisher":"American Medical Association (AMA)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Pediatr"],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"\n Importance<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Objectives<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This preimplementation and postimplementation cohort study was conducted at a tertiary, freestanding, US children\u2019s 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.<\/jats:p>\n <\/jats:sec>\n \n Exposures<\/jats:title>\n Patients\u2019 type of surgery, chronic conditions, and demographic characteristics.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n 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).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n There were 21\u202f352 elective surgical cases (mean [SD] age, 10.2 [7.4] years; 10\u202f804 [50.6%] female) for patients included in the retrospective analysis of postoperative LOS prediction and 12\u202f522 elective surgical cases in the pretest and posttest analysis of the prediction model (premodel implementation, n\u2009=\u20095867; postmodel implementation, n\u2009=\u20096655). The postoperative LOS model had 85.6% accuracy with a 1-night leniency. The model\u2019s 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% (\n P<\/jats:italic>\n \u2009&amp;lt;\u2009.001), without a significant increase in days with excessive capacity.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this cohort study, use of a machine-learning, postoperative LOS model helped to reduce day-to-day variation in the number of elective surgical procedures performed, increase the total number of elective surgical procedures, and decrease underuse of hospital beds.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamapediatrics.2025.5385","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T16:00:41Z","timestamp":1767628841000},"page":"306","source":"Crossref","is-referenced-by-count":7,"title":["Artificial Intelligence Length-of-Stay Forecasting and Pediatric Surgical Capacity"],"prefix":"10.1001","volume":"180","author":[{"given":"Jay G.","family":"Berry","sequence":"first","affiliation":[{"name":"Complex Care, Division of General Pediatrics, Boston Children\u2019s Hospital, Boston, Massachusetts"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Mathieu","sequence":"additional","affiliation":[{"name":"Physician\u2019s Organization, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven J.","family":"Staffa","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben Y.","family":"Reis","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts"},{"name":"Predictive Medicine Group, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Hong","sequence":"additional","affiliation":[{"name":"Complex Care, Division of General Pediatrics, Boston Children\u2019s Hospital, Boston, Massachusetts"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts"},{"name":"Enterprise Data, Analytics, and Reporting, Information Technology, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabor","family":"Asztalos","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lynne","family":"Ferrari","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Harvard Medical School, Boston, Massachusetts"},{"name":"Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children\u2019s Hospital, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","reference":[{"issue":"4","key":"poi250075r1","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/j.jamcollsurg.2012.12.046","article-title":"Re-engineering the operating room using variability methodology to improve health care value.","volume":"216","author":"Smith","year":"2013","journal-title":"J Am Coll Surg"},{"issue":"4","key":"poi250075r2","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.jcjq.2023.01.007","article-title":"Hospital capacity command centers: a benchmarking survey on an emerging mechanism to manage patient flow.","volume":"49","author":"Franklin","year":"2023","journal-title":"Jt Comm J Qual Patient Saf"},{"issue":"1","key":"poi250075r3","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1186\/s12913-021-06947-7","article-title":"Changes in pediatric hospital care during the COVID-19 pandemic: a national qualitative study.","volume":"21","author":"Penwill","year":"2021","journal-title":"BMC Health Serv Res"},{"issue":"11","key":"poi250075r4","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1002\/jhm.2624","article-title":"Epidemiology of pediatric hospitalizations at general hospitals and freestanding children\u2019s hospitals in the United States.","volume":"11","author":"Leyenaar","year":"2016","journal-title":"J Hosp Med"},{"issue":"9","key":"poi250075r5","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.33943","article-title":"Pediatric bed capacity, bed strain, and load imbalance during the 2022 respiratory viral season.","volume":"8","author":"Ijaz","year":"2025","journal-title":"JAMA Netw Open"},{"issue":"3","key":"poi250075r6","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s10729-023-09638-3","article-title":"Evaluation and implementation of a Just-In-Time bed-assignment strategy to reduce wait times for surgical inpatients.","volume":"26","author":"Braaksma","year":"2023","journal-title":"Health Care Manag Sci"},{"issue":"9","key":"poi250075r7","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1111\/poms.12714","article-title":"Benefits of surgical smoothing and spare capacity: an econometric analysis of patient flow.","volume":"26","author":"Kc","year":"2017","journal-title":"Prod Oper Manag"},{"issue":"1","key":"poi250075r8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s12911-022-01787-9","article-title":"Machine learning based forecast for the prediction of inpatient bed demand.","volume":"22","author":"Tello","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"poi250075r9","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1186\/s12913-021-06912-4","article-title":"Forecasting the length-of-stay of pediatric patients in hospitals: a scoping review.","volume":"21","author":"Medeiros","year":"2021","journal-title":"BMC Health Serv Res"},{"issue":"11","key":"poi250075r10","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/S1553-7250(09)35073-4","article-title":"Redesigning intensive care unit flow using variability management to improve access and safety.","volume":"35","author":"Ryckman","year":"2009","journal-title":"Jt Comm J Qual Patient Saf"},{"issue":"8","key":"poi250075r11","doi-asserted-by":"publisher","DOI":"10.1056\/AIp2400223","article-title":"A call for artificial intelligence implementation science centers to evaluate clinical effectiveness.","volume":"1","author":"Longhurst","year":"2024","journal-title":"NEJM AI"},{"issue":"1","key":"poi250075r12","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1001\/jama.2015.6177","article-title":"The role of physicians in the era of predictive analytics.","volume":"314","author":"Sniderman","year":"2015","journal-title":"JAMA"},{"issue":"1","key":"poi250075r13","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review.","volume":"24","author":"Goldstein","year":"2017","journal-title":"J Am Med Inform Assoc"},{"issue":"2","key":"poi250075r14","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1038\/s41390-020-01237-0","article-title":"Prolonged hospital length of stay in pediatric trauma: a model for targeted interventions.","volume":"90","author":"Gibbs","year":"2021","journal-title":"Pediatr Res"},{"issue":"7","key":"poi250075r16","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1542\/hpeds.2016-0179","article-title":"Contributions of children with multiple chronic conditions to pediatric hospitalizations in the United States: a retrospective cohort analysis.","volume":"7","author":"Berry","year":"2017","journal-title":"Hosp Pediatr"},{"issue":"3","key":"poi250075r17","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2016-2574","article-title":"Comorbidities and complications of spinal fusion for scoliosis.","volume":"139","author":"Berry","year":"2017","journal-title":"Pediatrics"},{"issue":"10","key":"poi250075r18","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1542\/hpeds.2023-007622","article-title":"Factors affecting length of stay for children hospitalized after pediatric surgical procedures.","volume":"14","author":"Berry","year":"2024","journal-title":"Hosp Pediatr"},{"issue":"1","key":"poi250075r20","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1038\/s41746-022-00723-5","article-title":"Developing current procedural terminology codes that describe the work performed by machines.","volume":"5","author":"Frank","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"1","key":"poi250075r21","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1186\/s12911-021-01660-1","article-title":"Quantifying the impact of addressing data challenges in prediction of length of stay.","volume":"21","author":"Naemi","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"poi250075r22","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.23889\/ijpds.v6i1.1406","article-title":"Mapping three versions of the international classification of diseases to categories of chronic conditions.","volume":"6","author":"Hamad","year":"2021","journal-title":"Int J Popul Data Sci"},{"issue":"1","key":"poi250075r23","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1186\/s12913-024-11238-y","article-title":"Predicting hospital length of stay using machine learning on a large open health dataset.","volume":"24","author":"Jain","year":"2024","journal-title":"BMC Health Serv Res"},{"issue":"4","key":"poi250075r24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000017","article-title":"A systematic review of the prediction of hospital length of stay: towards a unified framework.","volume":"1","author":"Stone","year":"2022","journal-title":"PLOS Digit Health"},{"issue":"4","key":"poi250075r25","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2300176","article-title":"The impact of task set-up in algorithm design: regression versus classification.","volume":"1","author":"Vrudhula","year":"2024","journal-title":"NEJM AI"},{"issue":"1","key":"poi250075r26","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1002\/sim.8766","article-title":"Minimum sample size for external validation of a clinical prediction model with a continuous outcome.","volume":"40","author":"Archer","year":"2021","journal-title":"Stat Med"},{"key":"poi250075r27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105527","article-title":"Towards reliable forecasting of healthcare capacity needs: a scoping review and evidence mapping.","volume":"189","author":"Gr\u00f8ntved","year":"2024","journal-title":"Int J Med Inform"},{"issue":"6","key":"poi250075r28","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1007\/s11606-021-07106-8","article-title":"The impact of hospital capacity strain: a qualitative analysis of experience and solutions at 13 academic medical centers.","volume":"37","author":"Arogyaswamy","year":"2022","journal-title":"J Gen Intern Med"},{"issue":"1","key":"poi250075r29","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1038\/s41746-023-00938-0","article-title":"Predictive analytics for cardio-thoracic surgery duration as a stepstone towards data-driven capacity management.","volume":"6","author":"Nikolova-Simons","year":"2023","journal-title":"NPJ Digit Med"},{"issue":"1","key":"poi250075r30","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s10916-024-02137-0","article-title":"Forecasting mortality associated emergency department crowding with LightGBM and time series data.","volume":"49","author":"Nevanlinna","year":"2025","journal-title":"J Med Syst"},{"issue":"1","key":"poi250075r31","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10916-025-02201-3","article-title":"Forecasting surgical bed utilization: architectural design of a machine learning pipeline incorporating predicted length of stay and surgical volume.","volume":"49","author":"Singh","year":"2025","journal-title":"J Med Syst"},{"key":"poi250075r32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbusres.2023.113806","article-title":"Artificial intelligence and discrete-event simulation for capacity management of intensive care units during the Covid-19 pandemic: a case study.","volume":"160","author":"Ortiz-Barrios","year":"2023","journal-title":"J Bus Res"},{"issue":"1","key":"poi250075r33","doi-asserted-by":"publisher","first-page":"17028","DOI":"10.1038\/s41598-025-01265-y","article-title":"Predicting hospital outpatient volume using XGBoost: a machine learning approach.","volume":"15","author":"Zhou","year":"2025","journal-title":"Sci Rep"},{"issue":"1","key":"poi250075r34","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10729-015-9334-2","article-title":"Scheduling elective surgeries: the tradeoff among bed capacity, waiting patients and operating room utilization using goal programming.","volume":"20","author":"Li","year":"2017","journal-title":"Health Care Manag Sci"},{"issue":"e1","key":"poi250075r35","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.1093\/jamia\/ocv106","article-title":"Real-time prediction of inpatient length of stay for discharge prioritization.","volume":"23","author":"Barnes","year":"2016","journal-title":"J Am Med Inform Assoc"},{"issue":"6","key":"poi250075r36","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1007\/s11606-016-3936-3","article-title":"The association between hospital capacity strain and inpatient outcomes in highly developed countries: a systematic review.","volume":"32","author":"Eriksson","year":"2017","journal-title":"J Gen Intern Med"},{"issue":"4","key":"poi250075r37","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1080\/08998280.2025.2489222","article-title":"Operation capacity: how one hospital system improved access and outcomes for patients.","volume":"38","author":"Winter","year":"2025","journal-title":"Proc (Bayl Univ Med Cent)"},{"issue":"3","key":"poi250075r38","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2400296","article-title":"Impact of artificial intelligence\u2013based triage decision support on emergency department care.","volume":"2","author":"Taylor","year":"2025","journal-title":"NEJM AI"},{"key":"poi250075r15","unstructured":"Healthcare Cost and Utilization Project, Agency for Healthcare Research and Quality. Chronic Condition Indicator. Accessed December 13, 2024. https:\/\/hcup-us.ahrq.gov\/toolssoftware\/chronic\/chronic.jsp"},{"key":"poi250075r19","unstructured":"American Medical Association. CPT overview and code approval. Accessed December 13, 2024. https:\/\/www.ama-assn.org\/practice-management\/cpt\/cpt-overview-and-code-approval"}],"container-title":["JAMA Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamapediatrics\/articlepdf\/2843099\/jamapediatrics_berry_2026_oi_250075_1772122150.08936.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T16:01:17Z","timestamp":1772467277000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamapediatrics\/fullarticle\/2843099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamapediatrics.2025.5385","relation":{},"ISSN":["2168-6203"],"issn-type":[{"value":"2168-6203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,1]]}}}