Combined Artificial Intelligence Approaches Analyzing 1000 Conservative Patients with Back Pain-A Methodological Pathway to Predicting Treatment Efficacy and Diagnostic Groups.

André Wirries,Samir Jabari,Ingmar Bluemcke,Andreas Redder,Steffen Ruchholtz,Ahmed Hammad,Florian Geiger,Ludwig Oberkircher

doi:10.3390/diagnostics11111934

André Wirries, Samir Jabari + Show 6 more

Open Access

https://doi.org/10.3390/diagnostics11111934

Copy DOI

Abstract

Patients with back pain are common and present a challenge in everyday medical practice due to the multitude of possible causes and the individual effects of treatments. Predicting causes and therapy efficien cy with the help of artificial intelligence could improve and simplify the treatment. In an exemplary collective of 1000 conservatively treated back pain patients, it was investigated whether the prediction of therapy efficiency and the underlying diagnosis is possible by combining different artificial intelligence approaches. For this purpose, supervised and unsupervised artificial intelligence methods were analyzed and a methodology for combining the predictions was developed. Supervised AI is suitable for predicting therapy efficiency at the borderline of minimal clinical difference. Non-supervised AI can show patterns in the dataset. We can show that the identification of the underlying diagnostic groups only becomes possible through a combination of different AI approaches and the baseline data. The presented methodology for the combined application of artificial intelligence algorithms shows a transferable path to establish correlations in heterogeneous data sets when individual AI approaches only provide weak results.

Highlights

Artificial Intelligence (AI) is gaining more and more influence in medical care
In an exemplary collective of 1000 conservatively treated back pain patients, it was investigated whether the prediction of therapy efficiency and the underlying diagnosis is possible by combining different artificial intelligence approaches
Complaints were assessed at baseline and at the end of therapy using the Oswestry Disability Index (ODI) and a visual analogue scale (VAS), separately for leg and back pain

Summary

Introduction

Artificial Intelligence (AI) is gaining more and more influence in medical care. Clinical disease presentations are complex and prediction of the progress of a disease for the individual patient is often difficult. Finding the right cause of back pain and better estimation of success rates of a conservative therapy would help to propose a suitable treatment. This could facilitate the initiation of individually appropriate therapy and the determination of a suitable diagnosis without the excessive use of costly and time-consuming, often invasive diagnostics. An insufficient or too excessive care of patients could be avoided

Methods

Findings

Discussion

Conclusion