Spinopelvic Anatomic Parameters Prediction Model of NSLBP based on data mining

TL;DR

This study develops a predictive model for non-specific chronic low back pain using spinopelvic parameters and machine learning, achieving high accuracy and demonstrating the effectiveness of neural networks in clinical prediction tasks.

Contribution

It introduces a novel predictive model for NSLBP based on spinopelvic parameters using logistic regression and MLP, highlighting the superior performance of neural networks.

Findings

MLP model achieves 95.2% accuracy in predicting NSLBP.

Four key predictors identified: DS, PR, SS, PT.

MLP outperforms traditional regression in predictive accuracy.

Abstract

Objective: The purpose of this study is to perform analysis through the low back pain open data set to predict the incidence of non-specific chronic low back pain (NSLBP) to obtain a more accurate and convenient sagittal spinopelvic parameter model. Methods: The logistic regression analysis and multilayer perceptron(MLP) algorithm is used to construct a NSLBP prediction model based on the parameters of the spinopelvic parameters from open data source. Results: Degree of spondylolisthesis(DS), Pelvic radius (PR), Sacral slope (SS), Pelvic tilt (PT) are four predictors screened out by regression analysis that have significant predictive power for the risk of NSLBP. The overall accuracy of the equation prediction model is 85.8%.The MLP network algorithm determines that DS is the most powerful predictor of NSLBP through more precise modeling. The model has good predictive ability of 95.2% of accuracy. Conclusions: MLP models play a more accurate role in the construction of predictive models. Computer science is playing a greater role in helping precision medicine clinical research.