Enhanced prediction of spine surgery outcomes using advanced machine learning techniques and oversampling methods

Aug 4, 2026

Upload by Skyler

Accurate prediction of spine surgery outcomes enables more effective treatment planning and patient counseling. This study develops an enhanced machine learning framework to classify and predict surgical success by combining advanced oversampling strategies with grid search optimization. Models including GaussianNB, ComplementNB, KNN, Decision Tree, and oversampling-enhanced KNN variants are evaluated on a cohort of 244 patients using pre-surgical, psychometric, socioeconomic, and analytical variables. Results show KNN with RandomOverSampler and SMOTE achieving up to 76% accuracy and 67% F1-score, supporting decision support potential.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Purpose

Methods

Results

Conclusions

Introduction and related work

Benítez‑Andrades et al. Health Information Science and Systems (2025) 13:24 [https://doi.org/10.1007/s13755](https://doi.org/10.1007/s13755)‑025‑00343‑9 Health Information Science and Systems RESEARCH Enhanced prediction of spine surgery outcomes using advanced machine learning techniques and oversampling methods José Alberto Benítez‑Andrades1,2*† , Camino Prada‑García3,4†, Nicolás Ordás‑Reyes5†, Marta Esteban Blanco6†, Alicia Merayo5† and Antonio Serrano‑García2,7† Abstract Purpose: Accurate prediction of spine surgery outcomes is essential for optimizing treatment strategies. This study presents an enhanced machine learning approach to classify and predict the success of spine surgeries, incorporating advanced oversampling techniques and grid search optimization to improve model performance. Methods: Various machine learning models, including GaussianNB, ComplementNB, KNN, Decision Tree, KNN with RandomOverSampler, KNN with SMOTE, and grid‑searched optimized versions of KNN and Decision Tree, were applied to a dataset of 244 spine surgery patients. The dataset, comprising pre‑surgical, psychometric, socioeconomic, and analytical variables, was analyzed to determine the most efficient predictive model. The study explored the impact of different variable groupings and oversampling techniques. Results: Experimental results indicate that the KNN model, especially when enhanced with RandomOverSamplerand SMOTE, demonstrated superior performance, achieving accuracy values as high as 76% and an F1‑score of 67% . Grid‑searched optimized versions of KNN and Decision Tree also yielded significant improvements in predictive accu‑ racy and F1‑score. Conclusions: The study highlights the potential of advanced machine learning techniques and oversampling methods in predicting spine surgery outcomes. The results underscore the importance of careful variable selection and model optimization to achieve optimal performance. This system holds promise as a tool to assist healthcare professionals in decision‑making, thereby enhancing spine surgery outcomes. Future research should focus on further refining these models and exploring their application across larger datasets and diverse clinical settings. Keywords: Spine surgery, Machine learning, Predictive model, Oversampling techniques, Patient outcomes, Decision support systems, Surgical outcomes, Classification models, Healthcare analytics Introduction and related work Spine surgery is a critical intervention in the treatment of various spinal conditions, and accurate prediction of surgical outcomes is essential for optimizing treatment †José Alberto Benítez‑Andrades, Camino Prada‑García, Nicolás Ordás‑ Reyes, Marta Esteban Blanco, Alicia Merayo, Antonio Serrano‑García have contributed equally to this work. *Correspondence: [jbena@unileon.es](jbena@unileon.es) 2 Instituto de Investigación Biosanitaria de León (IBIOLEÓN), Calle Altos de Nava, s/n, 24008 León, Spain Full list of author information is available at the end of the article strategies. The variability in outcomes can be attributed not only to clinical and anatomical factors but also to a wide range of socio-economic and psychometric variables, which influence the recovery and satisfaction of patients. These factors include employment status, mental health conditions, and socio-economic background, which have been shown to significantly affect the success of spine surgeries by impacting post-operative recovery and long-term patient satisfaction [1–3]. Traditional methods for predicting spine surgery outcomes rely primarily on clinical evaluations, imaging studies, and patient-reported outcomes. However, © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the sou

FAQs

What is the main goal of this study on spine surgery outcomes?

To improve the accuracy of predicting the success of spine surgeries using enhanced machine learning methods and oversampling.

Which patient data types were used for prediction?

The dataset includes pre-surgical, psychometric, socioeconomic, and analytical variables for 244 spine surgery patients.

Which model performed best, and how effective was it?

KNN enhanced with RandomOverSampler and SMOTE showed the highest performance, with accuracy up to 76% and an F1-score of 67%.

Aug 4, 2026

Upload by Skyler