Liu Kui, Li Linyi, Ma Yifei, Jiang Jun, Liu Zhenhua, Ye Zichen, Liu Shuang, Pu Chen, Chen Changsheng, Wan Yi
Department of Health Service, Air Force Medical University, Xi'an, Shaanxi, China.
Department of Health Statistics, Air Force Medical University, Xi'an, Shaanxi, China.
JMIR Med Inform. 2023 Nov 20;11:e47833. doi: 10.2196/47833.
Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important.
In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity.
PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events.
In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia.
Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced.
PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.
机器学习（ML）模型为糖尿病（DM）患者提供了更多选择，以便更恰当地管理血糖（BG）水平。然而，由于ML算法种类繁多，选择合适的模型至关重要。
在一项系统评价和网络荟萃分析中，本研究旨在全面评估ML模型在预测BG水平方面的性能。此外，我们通过计算敏感性和特异性的合并估计值，评估了用于检测和预测不良BG（低血糖）事件的ML模型。
系统检索了PubMed、Embase、Web of Science和电气与电子工程师协会探索数据库，以查找从数据库创建至2022年11月期间使用ML模型预测BG水平以及预测或检测不良BG事件的研究。纳入评估不同ML模型在预测或检测DM患者BG水平或不良BG事件方面性能的研究。排除未提供ML模型推导或性能指标的研究。应用诊断准确性研究质量评估工具评估纳入研究的质量。主要结局是ML模型在不同预测期（PH）预测BG水平的相对排名，以及ML模型在检测或预测不良BG事件时敏感性和特异性的合并估计值。
总共纳入46项符合条件的研究进行荟萃分析。关于预测BG水平的ML模型，在15、30、45和60分钟的预测期内，绝对均方根误差（RMSE）的均值分别为18.88（标准差19.71）、21.40（标准差12.56）、21.27（标准差5.17）和30.01（标准差7.23）mg/dL。神经网络模型（NNM）在不同预测期内表现出最高的相对性能。此外，ML模型预测低血糖的阳性似然比和阴性似然比的合并估计值分别为8.3（95%CI 5.7 - 12.0）和0.3（95%CI 0.22 - 0.44），检测低血糖的阳性似然比和阴性似然比的合并估计值分别为2.4（95%CI 1.6 - 3.7）和0.37（95%CI 0.29 - 0.46）。
在所有亚组中均检测到具有不同异质性来源的统计学显著高异质性。为了预测精确的BG水平，RMSE随着预测期的增加而增加，并且NNM在所有ML模型中表现出最高的相对性能。同时，当前的ML模型有足够的能力预测不良BG事件，但其检测不良BG事件的能力需要提高。
PROSPERO CRD42022375250；https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250 。
需注意，原文中“0.3”疑为“0.31”的错误，译文已按正确内容翻译。
