Can machine learning predict the accuracy of preoperative planning for total hip arthroplasty, basing on patient-related factors? An explorative investigation on Supervised machine learning classification models

B Zampogna; G Torre; A Zampoli; F Parisi; A Ferrini; S Shanmugasundaram; E Franceschetti; R Papalia

doi:10.1016/j.jcot.2024.102470

Can machine learning predict the accuracy of preoperative planning for total hip arthroplasty, basing on patient-related factors? An explorative investigation on Supervised machine learning classification models

J Clin Orthop Trauma. 2024 Jun 24:53:102470. doi: 10.1016/j.jcot.2024.102470. eCollection 2024 Jun.

Authors

B Zampogna^{1

2

3

4}, G Torre^{5

6}, A Zampoli^{1

2}, F Parisi^{1

2}, A Ferrini⁷, S Shanmugasundaram⁸, E Franceschetti^{1

2}, R Papalia^{1

2}

Affiliations

¹ Department of Orthopaedics and Trauma Surgery, Università Campus Bio-Medico di Roma, Roma, Italy.
² Research Unit of Orthopaedic and Trauma Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, Rome, Italy.
³ BIOMORF Department, Biomedical, Dental and Morphological and Functional Images, Italy.
⁴ University of Messina. A.O.U. Policlinico "G.Martino" Messina, Italy.
⁵ Villa Stuart Sport Clinic, FIFA Medical Centre of Excellence, Rome, Italy.
⁶ Department of Movement, Human and Health Sciences, University of Rome "Foro Italico", Rome, Italy.
⁷ Department of Clinical Science and Translational Medicine, Section of Orthopaedics and Traumatology, The University of Rome "Tor Vergata", Rome, Italy.
⁸ Sri Lakshmi Narayana Institute of Medical Sciences, Puducherry, India.

PMID: 39045495
PMCID: PMC11261062 (available on 2025-06-24)
DOI: 10.1016/j.jcot.2024.102470

Abstract

Background: The success of Total Hip Arthroplasty (THA) is influenced by preoperative planning, with traditional 2D approaches displaying varied reliability as well. The present study investigates the use of Supervised Machine Learning (SML) models with patient-related features to improve accuracy.

Methods: Preoperative and perioperative data, as well as planning and final implant information, were obtained from 800 consecutive cementless primary THA, which was performed uniformly by a specialized surgical team. Six Supervised Machine Learning models were trained and validated using patient characteristics and implant data: Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (CART), Gaussian Naive Bayes (GN), and Support Vector Classifier (SVC). The models' ability to predict planning reliability and leg length disparity was evaluated.

Results: KNN performed better on the cup model (97.9 %), femur model (96.7 %), and femur size (99.2 %). SVM emerged as the model with the highest accuracy for cup size (60.4 %) and head size (62.1 %). CART had the best accuracy (99 %) when determining leg length discrepancy.

Conclusion: The study demonstrates the utility of Supervised Machine Learning models, specifically KNN, in predicting the accuracy of preoperative planning in THA. The accuracy of these models, which are driven by patient-related characteristics, provides useful information for optimizing patients' selection and improving surgical outcome.

Keywords: Artificial intelligence; K-Nearest Neighbors; Preoperative planning; Supervised machine learning; Total hip arthroplasty.