Predicting extended hospital stay following revision total hip arthroplasty: a machine learning model analysis based on the ACS-NSQIP database

被引:0
|
作者
Chen, Tony Lin-Wei [1 ,2 ]
RezazadehSaatlou, MohammadAmin [1 ]
Buddhiraju, Anirudh [1 ]
Seo, Henry Hojoon [1 ]
Shimizu, Michelle Riyo [1 ]
Kwon, Young-Min [1 ]
机构
[1] Harvard Med Sch, Massachusetts Gen Hosp, Dept Orthopaed Surg, Bioengn Lab, 55 Fruit St, Boston, MA 02114 USA
[2] Hong Kong Polytech Univ, Dept Biomed Engn, Yuk Choi Rd 11, Hong Kong 999077, Peoples R China
关键词
Revision total hip arthroplasty; Machine learning; Artificial intelligence; Hospital stay; Risk factors; Clinical decision support; LENGTH-OF-STAY; RISK;
D O I
10.1007/s00402-024-05542-9
中图分类号
R826.8 [整形外科学]; R782.2 [口腔颌面部整形外科学]; R726.2 [小儿整形外科学]; R62 [整形外科学(修复外科学)];
学科分类号
摘要
IntroductionProlonged length of stay (LOS) following revision total hip arthroplasty (THA) can lead to increased healthcare costs, higher rates of readmission, and lower patient satisfaction. In this study, we investigated the predictive power of machine learning (ML) models for prolonged LOS after revision THA using patient data from a national-scale patient repository.Materials and methodsWe identified 11,737 revision THA cases from the American College of Surgeons National Surgical Quality Improvement Program database from 2013 to 2020. Prolonged LOS was defined as exceeding the 75th value of all LOSs in the study cohort. We developed four ML models: artificial neural network (ANN), random forest, histogram-based gradient boosting, and k-nearest neighbor, to predict prolonged LOS after revision THA. Each model's performance was assessed during training and testing sessions in terms of discrimination, calibration, and clinical utility.ResultsThe ANN model was the most accurate with an AUC of 0.82, calibration slope of 0.90, calibration intercept of 0.02, and Brier score of 0.140 during testing, indicating the model's competency in distinguishing patients subject to prolonged LOS with minimal prediction error. All models showed clinical utility by producing net benefits in the decision curve analyses. The most significant predictors of prolonged LOS were preoperative blood tests (hematocrit, platelet count, and leukocyte count), preoperative transfusion, operation time, indications for revision THA (infection), and age.ConclusionsOur study demonstrated that the ML model accurately predicted prolonged LOS after revision THA. The results highlighted the importance of the indications for revision surgery in determining the risk of prolonged LOS. With the model's aid, clinicians can stratify individual patients based on key factors, improve care coordination and discharge planning for those at risk of prolonged LOS, and increase cost efficiency.
引用
收藏
页码:4411 / 4420
页数:10
相关论文
共 47 条
  • [1] Discharge to a Non-Home Destination Following Total Ankle Arthroplasty (TAA): An Analysis of the ACS-NSQIP Database
    Malik, Azeem Tariq
    Groth, Adam T.
    Khan, Safdar N.
    JOURNAL OF FOOT & ANKLE SURGERY, 2020, 59 (04): : 694 - 697
  • [2] Predicting prolonged length of stay following revision total knee arthroplasty: A national database analysis using machine learning models
    Mittal, Ashish
    Buddhiraju, Anirudh
    Subih, Murad Abdullah
    Chen, Tony Lin-Wei
    Shimizu, Michelle
    Seo, Henry Hojoon
    Rezazadehsaatlou, Mohammadamin
    Xiao, Pengwei
    Kwon, Young-Min
    INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2024, 192
  • [3] The "July Effect" in Primary Total Hip and Knee Arthroplasty: Analysis of 21,434 Cases From the ACS-NSQIP Database
    Bohl, Daniel D.
    Fu, Michael C.
    Golinvaux, Nicholas S.
    Basques, Bryce A.
    Gruskay, Jordan A.
    Grauer, Jonathan N.
    JOURNAL OF ARTHROPLASTY, 2014, 29 (07): : 1332 - 1338
  • [4] Extended length of stay in diabetic octogenarians following revision total hip arthroplasty
    Gupta, Puneet
    Quan, Theodore
    Patel, Chirag J.
    Manzi, Joseph E.
    Gu, Alex
    Tabaie, Sean
    Campbell, Joshua C.
    EUROPEAN JOURNAL OF ORTHOPAEDIC SURGERY AND TRAUMATOLOGY, 2023, 33 (04): : 1217 - 1222
  • [5] Extended length of stay in diabetic octogenarians following revision total hip arthroplasty
    Puneet Gupta
    Theodore Quan
    Chirag J. Patel
    Joseph E. Manzi
    Alex Gu
    Sean Tabaie
    Joshua C. Campbell
    European Journal of Orthopaedic Surgery & Traumatology, 2023, 33 : 1217 - 1222
  • [6] The effect of operative time on early postoperative complications in total shoulder arthroplasty: An analysis of the ACS-NSQIP database
    Wilson, Jacob M.
    Holzgrefe, Russell E.
    Staley, Christopher A.
    Karas, Spero
    Gottschalk, Michael B.
    Wagner, Eric R.
    SHOULDER & ELBOW, 2021, 13 (01) : 79 - 88
  • [7] Perioperative Complications and Length of Stay After Revision Total Hip and Knee Arthroplasties: An Analysis of the NSQIP Database
    Liodakis, Emmanouil
    Bergeron, Stephane G.
    Zukor, David J.
    Huk, Olga L.
    Epure, Laura M.
    Antoniou, John
    JOURNAL OF ARTHROPLASTY, 2015, 30 (11): : 1868 - 1871
  • [8] Factors Associated With Inability to Bear Weight Following Hip Fracture Surgery: An Analysis of the ACS-NSQIP Hip Fracture Procedure Targeted Database
    Malik, Azeem Tariq
    Quatman-Yates, Catherine
    Phieffer, Laura S.
    Ly, Thuan, V
    Khan, Safdar N.
    Quatman, Carmen E.
    GERIATRIC ORTHOPAEDIC SURGERY & REHABILITATION, 2019, 10
  • [9] Effect of operative time on complications following primary total hip arthroplasty: analysis of the NSQIP database
    Sikov, Mark
    Sloan, Matthew
    Sheth, Neil P.
    HIP INTERNATIONAL, 2021, 31 (02) : 231 - 236
  • [10] Validation of Machine Learning Model Performance in Predicting Blood Transfusion After Primary and Revision Total Hip Arthroplasty
    Buddhiraju, Anirudh
    Shimizu, Michelle Riyo
    Subih, Murad A.
    Chen, Tony Lin-Wei
    Seo, Henry Hojoon
    Kwon, Young-Min
    JOURNAL OF ARTHROPLASTY, 2023, 38 (10): : 1959 - 1966