Machine learning models on a web application to predict short-term postoperative outcomes following anterior cervical discectomy and fusion

被引:2
|
作者
Karabacak, Mert [1 ]
Bhimani, Abhiraj D. [1 ]
Schupper, Alexander J. [1 ]
Carr, Matthew T. [1 ]
Steinberger, Jeremy [1 ]
Margetis, Konstantinos [1 ]
机构
[1] Mt Sinai Hlth Syst, Dept Neurosurg, 1468 Madison Ave, New York, NY 10029 USA
关键词
Artificial intelligence; Machine learning; Outcome prediction; Web application; ACDF; Personalized medicine; Precision medicine; Spine surgery; ALGORITHMS; AREA;
D O I
10.1186/s12891-024-07528-5
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
Background The frequency of anterior cervical discectomy and fusion (ACDF) has increased up to 400% since 2011, underscoring the need to preoperatively anticipate adverse postoperative outcomes given the procedure's expanding use. Our study aims to accomplish two goals: firstly, to develop a suite of explainable machine learning (ML) models capable of predicting adverse postoperative outcomes following ACDF surgery, and secondly, to embed these models in a user-friendly web application, demonstrating their potential utility.Methods We utilized data from the National Surgical Quality Improvement Program database to identify patients who underwent ACDF surgery. The outcomes of interest were four short-term postoperative adverse outcomes: prolonged length of stay (LOS), non-home discharges, 30-day readmissions, and major complications. We utilized five ML algorithms - TabPFN, TabNET, XGBoost, LightGBM, and Random Forest - coupled with the Optuna optimization library for hyperparameter tuning. To bolster the interpretability of our models, we employed SHapley Additive exPlanations (SHAP) for evaluating predictor variables' relative importance and used partial dependence plots to illustrate the impact of individual variables on the predictions generated by our top-performing models. We visualized model performance using receiver operating characteristic (ROC) curves and precision-recall curves (PRC). Quantitative metrics calculated were the area under the ROC curve (AUROC), balanced accuracy, weighted area under the PRC (AUPRC), weighted precision, and weighted recall. Models with the highest AUROC values were selected for inclusion in a web application.Results The analysis included 57,760 patients for prolonged LOS [11.1% with prolonged LOS], 57,780 for non-home discharges [3.3% non-home discharges], 57,790 for 30-day readmissions [2.9% readmitted], and 57,800 for major complications [1.4% with major complications]. The top-performing models, which were the ones built with the Random Forest algorithm, yielded mean AUROCs of 0.776, 0.846, 0.775, and 0.747 for predicting prolonged LOS, non-home discharges, readmissions, and complications, respectively.Conclusions Our study employs advanced ML methodologies to enhance the prediction of adverse postoperative outcomes following ACDF. We designed an accessible web application to integrate these models into clinical practice. Our findings affirm that ML tools serve as vital supplements in risk stratification, facilitating the prediction of diverse outcomes and enhancing patient counseling for ACDF.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Short-term clinical outcomes and technical advantages of mini-open endoscope assisted anterior cervical discectomy and fusion in the treatment of cervical spondylotic myelopathy
    Hua-zhang Zhong
    Li Cheng
    Qi-fei Wang
    Bin Zhu
    Lei Chen
    Jue-hua Jing
    Da-sheng Tian
    Yun Zhou
    BMC Musculoskeletal Disorders, 26 (1)
  • [22] Impact of Insulin Dependence on Perioperative Outcomes Following Anterior Cervical Discectomy and Fusion
    Phan, Kevin
    Kim, Jun S.
    Lee, Nathan
    Kothari, Parth
    Cho, Samuel K.
    SPINE, 2017, 42 (07) : 456 - 464
  • [23] The Short-Term to Midterm Follow-Up of Patients with Hirayama Disease After Anterior Cervical Discectomy and Fusion
    Liu, Siyang
    Zou, Fei
    Lu, Feizhou
    Xia, Xinlei
    Wang, Hongli
    Zheng, Chaojun
    Gong, Zhaoyang
    Ma, Xiaosheng
    Jiang, Jianyuan
    WORLD NEUROSURGERY, 2021, 150 : E705 - E713
  • [24] Machine Learning-Based Prediction of Short-Term Adverse Postoperative Outcomes in Cervical Disc Arthroplasty Patients
    Karabacak, Mert
    Margetis, Konstantinos
    WORLD NEUROSURGERY, 2023, 177 : E226 - E238
  • [25] Coagulation Profile as a Significant Risk Factor for Short-Term Complications and Mortality after Anterior Cervical Discectomy and Fusion
    Almeida, Neil D.
    Lee, Ryan
    Wei, Chapman
    Lee, Danny
    Asif, Usman
    Almeida, Nyle C.
    Klein, Andrea L.
    Hogan, Elizabeth
    Sack, Kenneth
    Sherman, Jonathan H.
    WORLD NEUROSURGERY, 2021, 148 : E74 - E86
  • [26] A machine learning-based approach for individualized prediction of short-term outcomes after anterior cervical corpectomy
    Karabacak, Mert
    Schupper, Alexander
    Carr, Matthew
    Margetis, Konstantinos
    ASIAN SPINE JOURNAL, 2024, 18 (04) : 541 - 549
  • [27] Using Machine Learning Algorithms to Predict Postoperative Anterior Bone Loss Following Anterior Cervical Disc Replacement
    Zong, Rui
    Guo, Can
    He, Jun-bo
    Wu, Ting-kui
    Liu, Hao
    GLOBAL SPINE JOURNAL, 2024,
  • [28] Robust prediction of nonhome discharge following elective anterior cervical discectomy and fusion using explainable machine learning
    Geng, Eric A. A.
    Gal, Jonathan S. S.
    Kim, Jun S. S.
    Martini, Michael L. L.
    Markowitz, Jonathan
    Neifert, Sean N. N.
    Tang, Justin E. E.
    Shah, Kush C. C.
    White, Christopher A. A.
    Dominy, Calista L. L.
    Valliani, Aly A. A.
    Duey, Akiro H. H.
    Li, Gavin
    Zaidat, Bashar
    Bueno, Brian
    Caridi, John M. M.
    Cho, Samuel K. K.
    EUROPEAN SPINE JOURNAL, 2023, 32 (06) : 2149 - 2156
  • [29] Robust prediction of nonhome discharge following elective anterior cervical discectomy and fusion using explainable machine learning
    Eric A. Geng
    Jonathan S. Gal
    Jun S. Kim
    Michael L. Martini
    Jonathan Markowitz
    Sean N. Neifert
    Justin E. Tang
    Kush C. Shah
    Christopher A. White
    Calista L. Dominy
    Aly A. Valliani
    Akiro H. Duey
    Gavin Li
    Bashar Zaidat
    Brian Bueno
    John M. Caridi
    Samuel K. Cho
    European Spine Journal, 2023, 32 : 2149 - 2156
  • [30] Elderly Age as a Risk Factor for 30-Day Postoperative Outcomes Following Elective Anterior Cervical Discectomy and Fusion
    Di Capua, John
    Somani, Sulaiman
    Kim, Jun S.
    Phan, Kevin
    Lee, Nathan J.
    Kothari, Parth
    Cho, Samuel K.
    GLOBAL SPINE JOURNAL, 2017, 7 (05) : 425 - 431