Short-term outcome prediction for myasthenia gravis: an explainable machine learning model.
Short-term outcome prediction for myasthenia gravis: an explainable machine learning model.
复制标题
重症肌无力的短期预后预测：一个可解释的机器学习模型。
DOI：
10.1177/17562864231154976
复制
发表时间：
2023
影响因子：
5.9
通讯作者：
Zhao, Chongbo
中科院分区：
文献类型：
--
作者：
Zhong, Huahua;Ruan, Zhe;Yan, Chong;Lv, Zhiguo;Zheng, Xueying;Goh, Li-Ying;Xi, Jianying;Song, Jie;Luo, Lijun;Chu, Lan;Tan, Song;Zhang, Chao;Bu, Bitao;Da, Yuwei;Duan, Ruisheng;Yang, Huan;Luo, Sushan;Chang, Ting;Zhao, Chongbo
重症肌无力（MG）是一种以肌无力和易疲劳为特征的自身免疫性疾病。疾病过程的波动性阻碍了临床管理。本研究的目的是建立和验证一种基于机器学习（ML）的模型，用于预测具有不同抗体类型的MG患者的短期临床结局。我们研究了2015年1月1日至2021年7月31日期间在中国11家三级中心定期随访的890例MG患者（653例患者用于推导，237例患者用于验证）。短期结局是6个月访视时的改良干预后状态（PIS）。两步变量筛选用于确定模型构建的因素，14 ML算法用于模型优化。推导队列包括华山医院的653例患者[年龄44.24（17.22）岁，女性57.6%，全身MG 73.5%]，验证队列包括10个独立中心的237例患者[年龄44.24（17.22）岁，女性55.0%，全身MG 81.2%]。ML模型识别出获得改善的患者，在推导队列中，受试者工作特征曲线下面积（AUC）为0.91 [0.89-0.93]、“不变”0.89 [0.87-0.91]和“更差”0.89 [0.85-0.92]，而在验证队列中，确定了AUC为0.84 [0.79-0.89]、“不变”为0.74 [0.67-0.82]和“更差”为0.79 [0.70-0.88]的改善患者。通过拟合期望斜率，两个数据集都呈现出良好的校准能力。该模型最后解释了25个简单的预测，并转移到一个可行的网络工具进行初步评估。可解释的，基于ML的预测模型可以帮助预测MG的短期结果，在临床实践中具有良好的准确性。
Myasthenia gravis (MG) is an autoimmune disease characterized by muscle weakness and fatigability. The fluctuating nature of the disease course impedes the clinical management. 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. 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. 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. The explainable, ML-based predictive model can aid in forecasting the short-term outcome for MG with good accuracy in clinical practice.
登录
查看更多内容
影响因子：
2.4
作者：
Barnett C;Herbelin L;Dimachkie MM;Barohn RJ
通讯作者：
Barohn RJ
影响因子：
5.1
作者：
Alcantara, M.;Sarpong, E.;Bril, V.
通讯作者：
Bril, V.
影响因子：
28.1
作者：
Lundberg, Scott M.;Nair, Bala;Lee, Su-In
通讯作者：
Lee, Su-In
影响因子：
3.9
作者：
Chang CC;Yeh JH;Chen YM;Jhou MJ;Lu CJ
通讯作者：
Lu CJ
影响因子：
7.2
作者：
Collins, Gary S.;Reitsma, Johannes B.;Moons, Karel G. M.
通讯作者：
Moons, Karel G. M.