Clinical Predictors of Prolonged Hospital Stay in Patients with Myasthenia Gravis: A Study Using Machine Learning Algorithms.

Che-Cheng Chang,Yen-Ming Chen,Mao-Jhen Jhou,Chi-Jie Lu,Jiann-Horng Yeh

doi:10.3390/jcm10194393

Che-Cheng Chang, Yen-Ming Chen + Show 3 more

Open Access

https://doi.org/10.3390/jcm10194393

Copy DOI

Abstract

Myasthenia gravis (MG) is an autoimmune disorder that causes muscle weakness. Although the management is well established, some patients are refractory and require prolonged hospitalization. Our study is aimed to identify the important factors that predict the duration of hospitalization in patients with MG by using machine learning methods. A total of 21 factors were chosen for machine learning analyses. We retrospectively reviewed the data of patients with MG who were admitted to hospital. Five machine learning methods, including stochastic gradient boosting (SGB), least absolute shrinkage and selection operator (Lasso), ridge regression (Ridge), eXtreme gradient boosting (XGboost), and gradient boosting with categorical features support (Catboost), were used to construct models for identify the important factors affecting the duration of hospital stay. A total of 232 data points of 204 hospitalized MG patients admitted were enrolled into the study. The MGFA classification, treatment of high-dose intravenous corticosteroid, age at admission, treatment with intravenous immunoglobulins, and thymoma were the top five significant variables affecting prolonged hospitalization. Our findings from machine learning will provide physicians with information to evaluate the potential risk of MG patients having prolonged hospital stay. The use of high-dose corticosteroids is associated with prolonged hospital stay and to be used cautiously in MG patients.

Highlights

This study applied five machine learning methods, namely, stochastic gradient boosting (SGB), least absolute shrinkage and selection operator (Lasso), ridge regression (Ridge), eXtreme gradient boosting (XGboost), and gradient boosting with categorical features support (Catboost), to construct predictive models for predicting hospital staying in patient with Myasthenia gravis (MG) and to evaluate the importance of different treatments and factors for MG
Classification in a fixed time frame before admission or after treatment. This is the first study that uses a machine learning approach to develop a model to predict the hospital staying in patients with MG
We demonstrate, based on the integrated information of five machine learning (ML) methods, that the Myasthenia Gravis Foundation of America (MGFA) clinical classification before admission, treatment with high-dose intravenous corticosteroid, age at admission, treatment with

Summary

Introduction

Myasthenia gravis (MG) is an autoimmune disorder that affects the postsynaptic muscle membrane of the neuromuscular junction (NMJ) and can cause skeletal muscle weakness [1]. Its prevalence in Taiwan is approximately 84 to 140 per million persons [2]. It presents in varying degrees and with a combination of weakness in the ocular, bulbar, limb, and respiratory muscles in fluctuation. The pathogenesis includes antibody-mediated immunologic attack of the receptors in the postsynaptic membrane, directed against acetylcholine receptors (AchR), muscle-specific kinase (MuSK), and lipoprotein-related protein 4

Objectives

Methods

Findings

Discussion

Conclusion