The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach.

Pedro Berjano,Jorge Hugo Villafañe,Fabio Galbusera,Francesca Mangili,Paolo Barletta,Claudio Lamartina,Laura Azzimonti,Francesco Langella,Domenico Compagnone,Roberto Bassani,Marco Brayda-Bruno,Luca Ventriglia,David Huber,Laura Scaramuzzo,Andrea Cina,Lorenzo Monti,Tito Bassani,Ginevra Licandro

doi:10.3390/jpm11121377

Abstract

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index—ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a “good early outcome”. A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an “excellent early outcome”. The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months’ follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Highlights

Introduction distributed under the terms andDegenerative spine disorders represent a complex condition that mainly affects the elderly population, with an incidence in healthy people aged over 70 years of up to 68% [1].Pain and disability represent its main features, leading to a significant clinical and socio-economic impact with an increasing role in daily medical practice
Our study aimed to develop a preoperative machine learning (ML) model to predict a good to excellent early clinical outcome by using baseline demographic and health-related quality of life scores (HRQOL)
The inclusion criteria were age ≥ 18 years, both genders, lumbar arthrodesis procedure identified using the ICD-9 code (8106, 8107 or 8108), a follow up assessment (ODI, SF-36 and core outcome measures index—COMI back) and the capability to read and understand the Italian language

Summary

Introduction

Degenerative spine disorders represent a complex condition that mainly affects the elderly population, with an incidence in healthy people aged over 70 years of up to 68% [1]. Pain and disability represent its main features, leading to a significant clinical and socio-economic impact with an increasing role in daily medical practice. Goes hand in hand with the aging of the population of developed countries. The spinal disorders have a broad spectrum of clinical manifestations: from minimal or asymptomatic to an invalidating condition. The presentation pattern can variably affect segmental, regional, and global alignment. The pain and disability represent the main feature in a way that is comparable with other self-reported chronic conditions in the general population such as congestive heart failure, arthritis, chronic lung disease or diabetes [2]

Methods

Results

Discussion

Conclusion