Advertisement

A machine learning-based prediction model for in-hospital mortality among critically ill patients with hip fracture: An internal and external validated study

  • Author Footnotes
    Mingxing Lei
    Correspondence
    Mingxing Lei, Zhencan Han, and Shengjie Wang contributed equally to this work.
    Affiliations
    Department of Orthopedic Surgery, Hainan Hospital of Chinese PLA General Hospital, 80 Jianglin Road, Sanya 572022, China

    Chinese PLA Medical School, 28 Fuxing Road, Beijing 100853, China

    Department of Orthopedic Surgery, National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, Chinese PLA General Hospital, 28 Fuxing Road, Beijing 100853, China
    Search for articles by this author
  • Author Footnotes
    Zhencan Han
    Correspondence
    Mingxing Lei, Zhencan Han, and Shengjie Wang contributed equally to this work.
    Affiliations
    Xiangya School of Medicine, Central South University, 172 Tongzipo Road, Changsha 410013, China
    Search for articles by this author
  • Author Footnotes
    Shengjie Wang
    Correspondence
    Mingxing Lei, Zhencan Han, and Shengjie Wang contributed equally to this work.
    Affiliations
    Department of Orthopaedic Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University, 600 Yishan Road, Shanghai, 200233, China
    Search for articles by this author
  • Tao Han
    Affiliations
    Department of Orthopedic Surgery, Hainan Hospital of Chinese PLA General Hospital, 80 Jianglin Road, Sanya 572022, China
    Search for articles by this author
  • Shenyun Fang
    Correspondence
    Co-corresponding author at: Department of Orthopedic Surgery, the First Affiliated Hospital of Huzhou University, Huzhou 313000, China.
    Affiliations
    Department of Orthopedic Surgery, the First Affiliated Hospital of Huzhou University, 158 Guangchang Back Road, Huzhou 313000, China

    Department of Orthopedics Surgery, the First People Hospital of Huzhou, 158 Guangchang Back Road, Huzhou 313000, China
    Search for articles by this author
  • Feng Lin
    Correspondence
    Co-corresponding author at: Department of Orthopedic Surgery, Hainan Hospital of Chinese PLA General Hospital, 80 Jianglin Road, Sanya 572022, China.
    Affiliations
    Department of Orthopedic Surgery, Hainan Hospital of Chinese PLA General Hospital, 80 Jianglin Road, Sanya 572022, China

    Department of Orthopedic Surgery, National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, Chinese PLA General Hospital, 28 Fuxing Road, Beijing 100853, China
    Search for articles by this author
  • Tianlong Huang
    Correspondence
    Corresponding author at: Department of Orthopedic Surgery, the Second Xiangya Hospital of Central South University, 139 Renmin Middle Road, Changsha 410011, China.
    Affiliations
    Department of Orthopedic Surgery, the Second Xiangya Hospital of Central South University, 139 Renmin Middle Road, Changsha 410011, China
    Search for articles by this author
Published:November 11, 2022DOI:https://doi.org/10.1016/j.injury.2022.11.031

      Abstract

      Introduction

      Few studies have investigated the in-hospital mortality among critically ill patients with hip fracture. This study aimed to develop and validate a model to estimate the risk of in-hospital mortality among critically ill patients with hip fracture.

      Methods

      For this study, data from the Medical Information Mart for Intensive Care III (MIMIC-III) Database and electronic Intensive Care Unit (eICU) Collaborative Research Database were evaluated. Enrolled patients (n=391) in the MIMIC-III database were divided into a training (2/3, n=260) and a validation (1/3, n=131) group at random. Using machine learning algorithms such as random forest, gradient boosting machine, decision tree, and eXGBoosting machine approach, the training group was utilized to train and optimize models. The validation group was used to internally validate models and the optimal model could be obtained in terms of discrimination (area under the receiver operating characteristic curve, AUROC) and calibration (calibration curve). External validation was done in the eICU Collaborative Research Database (n=165). To encourage practical use of the model, a web-based calculator was developed according to the eXGBoosting machine approach.

      Results

      The in-hospital death rate was 13.81% (54/391) in the MIMIC-III database and 10.91% (18/165) in the eICU Collaborative Research Database. Age, gender, anemia, mechanical ventilation, cardiac arrest, and chronic airway obstruction were the six model parameters which were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) method combined with 10-fold cross-validation. The model established using the eXGBoosting machine approach showed the highest area under curve (AUC) value (0.797, 95% CI: 0.696-0.898) and the best calibrating ability, with a calibration slope of 0.999 and intercept of -0.019. External validation also revealed favorable discrimination (AUC: 0.715, 95% CI: 0.566-0.864; accuracy: 0.788) and calibration (calibration slope: 0.805) in the eICU Collaborative Research Database. The web-based calculator could be available at https://doctorwangsj-webcalculator-main-yw69yd.streamlitapp.com/.

      Conclusion

      The model has the potential to be a pragmatic risk prediction tool that is able to identify hip fracture patients who are at a high risk of in-hospital mortality in ICU settings, guide patient risk counseling, and simplify prognosis bench-marking by controlling for baseline risk.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Injury
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Abrahamsen B.
        • van Staa T.
        • Ariely R.
        • Olson M.
        • Cooper C.
        Excess mortality following hip fracture: a systematic epidemiological review.
        Osteoporos Int. 2009; 20: 1633-1650
        • APA Chendrasekhar A.
        • Gollapalli R.
        • Ponukumati S.
        "Has Bled" Risk Index Is Predictive of Increased Mortality in Patients With Hip Fractures.
        Crit Care Med. 2013; 41: A48
        • Nijmeijer W.S.
        • Folbert E.C.
        • Vermeer M.
        • Slaets J.P.
        • Hegeman J.H.
        Prediction of early mortality following hip fracture surgery in frail elderly: The Almelo Hip Fracture Score (AHFS).
        Injury. 2016; 47: 2138-2143
        • Hu F.
        • Jiang C.
        • Shen J.
        • Tang P.
        • Wang Y.
        Preoperative predictors for mortality following hip fracture surgery: a systematic review and meta-analysis.
        Injury. 2012; 43: 676-685
        • Orford N.R.
        • Saunders K.
        • Merriman E.
        • Henry M.
        • Pasco J.
        • Stow P.
        • Kotowicz M.
        Skeletal morbidity among survivors of critical illness.
        Crit Care Med. 2011; 39: 1295-1300
        • Kim D.
        • Jo H.
        • Lee Y.
        • Kim K.O.
        Elixhauser comorbidity measures-based risk factors associated with 30-day mortality in elderly population after femur fracture surgery: a propensity scorematched retrospective case-control study.
        Acute Crit Care. 2020; 35: 10-15
        • Bombaci H.
        • Erdogan O.
        • Cetinkaya F.
        • Kuyumcu M.
        • Kaya E.
        • Bombaci E.
        Preoperative indicators affecting postoperative mortality in elderly patients with hip fractures.
        Acta Orthop Traumatol Turc. 2012; 46: 425-429
        • Liu Y.
        • Wang Z.
        • Xiao W.
        Risk factors for mortality in elderly patients with hip fractures: a meta-analysis of 18 studies.
        Aging Clin Exp Res. 2018; 30: 323-330
        • Chang W.
        • Lv H.
        • Feng C.
        • Yuwen P.
        • Wei N.
        • Chen W.
        • Zhang Y.
        Preventable risk factors of mortality after hip fracture surgery: Systematic review and meta-analysis.
        Int J Surg. 2018; 52: 320-328
        • Charlson M.E.
        • Pompei P.
        • Ales K.L.
        • MacKenzie C.R.
        A new method of classifying prognostic comorbidity in longitudinal studies: development and validation.
        J Chronic Dis. 1987; 40: 373-383
        • Maxwell M.J.
        • Moran C.G.
        • Moppett I.K.
        Development and validation of a preoperative scoring system to predict 30 day mortality in patients undergoing hip fracture surgery.
        Br J Anaesth. 2008; 101: 511-517
        • Hirose J.
        • Mizuta H.
        • Ide J.
        • Nomura K.
        Evaluation of estimation of physiologic ability and surgical stress (E-PASS) to predict the postoperative risk for hip fracture in elder patients.
        Arch Orthop Trauma Surg. 2008; 128: 1447-1452
        • Copeland G.P.
        • Jones D.
        • Walters M.
        POSSUM: a scoring system for surgical audit.
        Br J Surg. 1991; 78: 355-360
        • Holt G.
        • Smith R.
        • Duncan K.
        • Finlayson D.F.
        • Gregori A.
        Early mortality after surgical fixation of hip fractures in the elderly: an analysis of data from the scottish hip fracture audit.
        J Bone Joint Surg Br. 2008; 90: 1357-1363
        • Marufu T.C.
        • Mannings A.
        • Moppett I.K.
        Risk scoring models for predicting peri-operative morbidity and mortality in people with fragility hip fractures: Qualitative systematic review.
        Injury. 2015; 46: 2325-2334
        • Karres J.
        • Heesakkers N.A.
        • Ultee J.M.
        Vrouenraets BC: Predicting 30-day mortality following hip fracture surgery: evaluation of six risk prediction models.
        Injury. 2015; 46: 371-377
        • Johnson A.E.
        • Pollard T.J.
        • Shen L.
        • Lehman L.W.
        • Feng M.
        • Ghassemi M.
        • Moody B.
        • Szolovits P.
        • Celi L.A.
        • Mark R.G.
        MIMIC-III, a freely accessible critical care database.
        Sci Data. 2016; 3160035
        • Khan O.
        • Badhiwala J.H.
        • Witiw C.D.
        • Wilson J.R.
        Fehlings MG: Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy.
        Spine J. 2021; 21: 1659-1669
        • Pollard T.J.
        • Johnson A.E.W.
        • Raffa J.D.
        • Celi L.A.
        • Mark R.G.
        • Badawi O.
        The eICU Collaborative Research Database, a freely available multi-center database for critical care research.
        Sci Data. 2018; 5180178
        • Goldberger A.L.
        • Amaral L.A.
        • Glass L.
        • Hausdorff J.M.
        • Ivanov P.C.
        • Mark R.G.
        • Mietus J.E.
        • Moody G.B.
        • Peng C.K.
        • Stanley H.E.
        PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.
        Circulation. 2000; 101: E215-E220
        • Wu W.T.
        • Li Y.J.
        • Feng A.Z.
        • Li L.
        • Huang T.
        • Xu A.D.
        • Lyu J.
        Data mining in clinical big data: the frequently used databases, steps, and methodological models.
        Mil Med Res. 2021; 8: 44
        • Garbharran U.
        • Chinthapalli S.
        • Hopper I.
        • George M.
        • Back D.L.
        • Dockery F.
        Red cell distribution width is an independent predictor of mortality in hip fracture.
        Age Ageing. 2013; 42: 258-261
        • Zehir S.
        • Sipahioglu S.
        • Ozdemir G.
        • Sahin E.
        • Yar U.
        • Akgul T.
        Red cell distribution width and mortality in patients with hip fracture treated with partial prosthesis.
        Acta Orthop Traumatol Turc. 2014; 48: 141-146
        • Hamdan M.
        • Haddad B.I.
        • Jabaiti M.
        • Alryalat S.A.
        • Abdulelah A.A.
        • Alabed S.H.
        • Alabdullah T.F.
        • Aouant A.N.
        • Shahein H.E.
        • Dweik H.I.
        • et al.
        Does Red Cell Distribution Width Predict Hip Fracture Mortality Among the Arab Population? A Single-Center Retrospective Cohort Study.
        Int J Gen Med. 2021; 14: 10195-10202
        • Jiang H.X.
        • Majumdar S.R.
        • Dick D.A.
        • Moreau M.
        • Raso J.
        • Otto D.D.
        • Johnston D.W.
        Development and initial validation of a risk score for predicting in-hospital and 1-year mortality in patients with hip fractures.
        J Bone Miner Res. 2005; 20: 494-500
        • Tibshirani R.
        Regression Shrinkage and Selection via the Lasso.
        J R Stat Soc Ser B (Methodological). 1996; 58: 267-288
        • Endo A.
        • Baer H.J.
        • Nagao M.
        • Weaver M.J.
        Prediction Model of In-Hospital Mortality After Hip Fracture Surgery.
        J Orthop Trauma. 2018; 32: 34-38
        • Enders C.K.
        Multiple imputation as a flexible tool for missing data handling in clinical research.
        Behav Res Ther. 2017; 98: 4-18