Short-term outcome prediction for myasthenia gravis: an explainable machine learning model

Huahua Zhong; Zhe Ruan; Chong Yan; Zhiguo Lv; Xueying Zheng; Li-Ying Goh; Jianying Xi; Jie Song; Lijun Luo; Lan Chu; Song Tan; Chao Zhang; Bitao Bu; Yuwei Da; Ruisheng Duan; Huan Yang; Sushan Luo; Ting Chang; Chongbo Zhao; Pan-Yangtze River Delta Alliance for Neuromuscular Disorders (PYDAN)

doi:10.1177/17562864231154976

Short-term outcome prediction for myasthenia gravis: an explainable machine learning model

Ther Adv Neurol Disord. 2023 Feb 24:16:17562864231154976. doi: 10.1177/17562864231154976. eCollection 2023.

Authors

Huahua Zhong^{1

2}, Zhe Ruan³, Chong Yan^{1

2}, Zhiguo Lv⁴, Xueying Zheng⁵, Li-Ying Goh⁶, Jianying Xi^{1

2}, Jie Song^{1

2}, Lijun Luo⁷, Lan Chu⁸, Song Tan⁹, Chao Zhang¹⁰, Bitao Bu¹¹, Yuwei Da¹², Ruisheng Duan¹³, Huan Yang¹⁴, Sushan Luo^{15

2}, Ting Chang¹⁶, Chongbo Zhao^{15

2}; Pan-Yangtze River Delta Alliance for Neuromuscular Disorders (PYDAN)

Affiliations

¹ Huashan Rare Disease Center, Department of Neurology, Huashan Hospital, Fudan University, Shanghai, China.
² National Center for Neurological Disorders, Shanghai, China.
³ Department of Neurology, Tangdu Hospital, The Air Force Medical University, Xi'an, China.
⁴ Department of Neurology, The Affiliated Hospital of Changchun University of Chinese Medicine, Changchun, China.
⁵ Department of Biostatistics, School of Public Health and Key Laboratory of Public Health Safety, Fudan University, Shanghai, China.
⁶ Shanghai Medical College, Fudan University, Shanghai, China.
⁷ Department of Neurology, Wuhan No.1 Hospital, Wuhan, China.
⁸ Department of Neurology, The Affiliated Hospital of Guizhou Medical University, Guiyang, China.
⁹ Department of Neurology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China.
¹⁰ Department of Neurology and Tianjin Neurological Institute, Tianjin Medical University General Hospital, Tianjin, China.
¹¹ Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
¹² Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China.
¹³ Department of Neurology, The First Affiliated Hospital of Shandong First Medical University, Jinan, China.
¹⁴ Department of Neurology, Xiangya Hospital, Central South University, Changsha, China.
¹⁵ Huashan Rare Disease Center, Department of Neurology, Huashan Hospital, Fudan University, Shanghai 200040, China.
¹⁶ Department of Neurology, Tangdu Hospital, The Air Force Medical University, Xi'an 710000, China.

Abstract

Background: Myasthenia gravis (MG) is an autoimmune disease characterized by muscle weakness and fatigability. The fluctuating nature of the disease course impedes the clinical management.

Objective: The purpose of the study was to establish and validate a machine learning (ML)-based model for predicting the short-term clinical outcome in MG patients with different antibody types.

Methods: We studied 890 MG patients who had regular follow-ups at 11 tertiary centers in China from 1 January 2015 to 31 July 2021 (653 patients for derivation and 237 for validation). The short-term outcome was the modified post-intervention status (PIS) at a 6-month visit. A two-step variable screening was used to determine the factors for model construction and 14 ML algorithms were used for model optimisation.

Results: The derivation cohort included 653 patients from Huashan hospital [age 44.24 (17.22) years, female 57.6%, generalized MG 73.5%], and the validation cohort included 237 patients from 10 independent centers [age 44.24 (17.22) years, female 55.0%, generalized MG 81.2%]. The ML model identified patients who were improved with an area under the receiver operating characteristic curve (AUC) of 0.91 [0.89-0.93], 'Unchanged' 0.89 [0.87-0.91], and 'Worse' 0.89 [0.85-0.92] in the derivation cohort, whereas identified patients who were improved with an AUC of 0.84 [0.79-0.89], 'Unchanged' 0.74 [0.67-0.82], and 'Worse' 0.79 [0.70-0.88] in the validation cohort. Both datasets presented a good calibration ability by fitting the expectation slopes. The model is finally explained by 25 simple predictors and transferred to a feasible web tool for an initial assessment.

Conclusion: The explainable, ML-based predictive model can aid in forecasting the short-term outcome for MG with good accuracy in clinical practice.

Keywords: machine learning; myasthenia gravis; prognosis; short-term.