Application of Machine Learning in Developing Decision-Making Support Models for Decompressed Vertebroplasty.

Pei-Hung Liao,William Chu,Yu-Chuan Tsuei

doi:10.3390/healthcare10020214

Abstract

Background: The common treatment methods for vertebral compression fractures with osteoporosis are vertebroplasty and kyphoplasty, and the result of the operation may be related to the value of various measurement data during the operation. Material and Method: This study mainly uses machine learning algorithms, including Bayesian networks, neural networks, and discriminant analysis, to predict the effects of different decompression vertebroplasty methods on preoperative symptoms and changes in vital signs and oxygen saturation in intraoperative measurement data. Result: The neural network shows better analysis results, and the area under the curve is >0.7. In general, important determinants of surgery include numbness and immobility of the lower limbs before surgery. Conclusion: In the future, this association model can be used to assist in decision making regarding surgical methods. The results show that different surgical methods are related to abnormal vital signs and may affect the length of hospital stay.

Highlights

Academic Editors: Nicola Marotta, According to statistics obtained from the World Health Organization, human vertebrae are considered to experience the highest incidence rate of compression fractures caused by osteoporosis, which is more commonly seen in elderly patients, with approximately 27%
Vertebral compression fractures linked to osteoporosis can cause vertebral collapse, spinal deformation, and shrinkage of the abdominal and thoracic space, which could cause a concurrent reduction in pulmonary function and result in restricted mobility and psychological concerns for patients [2,3]
The commonly used treatment is the use of imaging guidance to inject a cement mixture into the fractured bone, while a more modified method includes the insertion of a balloon into the fractured bone to create a space, which is filled with cement [4,5], and both operations can improve the level of back pain

Summary

Introduction

Academic Editors: Nicola Marotta, According to statistics obtained from the World Health Organization, human vertebrae are considered to experience the highest incidence rate of compression fractures caused by osteoporosis, which is more commonly seen in elderly patients, with approximately 27%of patients over 65 years old [1]. Vertebral compression fractures linked to osteoporosis can cause vertebral collapse, spinal deformation, and shrinkage of the abdominal and thoracic space, which could cause a concurrent reduction in pulmonary function and result in restricted mobility and psychological concerns for patients [2,3]. Some doctors have used changed decompressed vertebroplasty, during which they observed that heart rate variability and decreased oxygen saturation occur less frequently [6]. The common treatment methods for vertebral compression fractures with osteoporosis are vertebroplasty and kyphoplasty, and the result of the operation may be related to the value of various measurement data during the operation. Material and Method: This study mainly uses machine learning algorithms, including Bayesian networks, neural networks, and discriminant analysis, to predict the effects of different decompression vertebroplasty methods on preoperative symptoms and changes in vital signs and oxygen saturation in intraoperative measurement data

Objectives

Methods

Results

Conclusion