PDF(Pubmed)
Abstract：
BACKGROUND: Severe hypoglycemia (SH) in older adults (OAs) with type 1 diabetes is associated with profound morbidity and mortality, yet its etiology can be complex and multifactorial. Enhanced tools to identify OAs who are at high risk for SH are needed. This study used machine learning to identify characteristics that distinguish those with and without recent SH, selecting from a range of demographic and clinical, behavioral and lifestyle, and neurocognitive characteristics, along with continuous glucose monitoring (CGM) measures.
METHODS: Data from a case-control study involving OAs recruited from the T1D Exchange Clinical Network were analyzed. The random forest machine learning algorithm was used to elucidate the characteristics associated with case versus control status and their relative importance. Models with successively rich characteristic sets were examined to systematically incorporate each domain of possible risk characteristics.
RESULTS: Data from 191 OAs with type 1 diabetes (47.1% female, 92.1% non-Hispanic white) were analyzed. Across models, hypoglycemia unawareness was the top characteristic associated with SH history. For the model with the richest input data, the most important characteristics, in descending order, were hypoglycemia unawareness, hypoglycemia fear, coefficient of variation from CGM, % time blood glucose below 70 mg/dL, and trail making test B score.
CONCLUSIONS: Machine learning may augment risk stratification for OAs by identifying key characteristics associated with SH. Prospective studies are needed to identify the predictive performance of these risk characteristics.
METHODS: Data from a case-control study involving OAs recruited from the T1D Exchange Clinical Network were analyzed. The random forest machine learning algorithm was used to elucidate the characteristics associated with case versus control status and their relative importance. Models with successively rich characteristic sets were examined to systematically incorporate each domain of possible risk characteristics.
RESULTS: Data from 191 OAs with type 1 diabetes (47.1% female, 92.1% non-Hispanic white) were analyzed. Across models, hypoglycemia unawareness was the top characteristic associated with SH history. For the model with the richest input data, the most important characteristics, in descending order, were hypoglycemia unawareness, hypoglycemia fear, coefficient of variation from CGM, % time blood glucose below 70 mg/dL, and trail making test B score.
CONCLUSIONS: Machine learning may augment risk stratification for OAs by identifying key characteristics associated with SH. Prospective studies are needed to identify the predictive performance of these risk characteristics.
摘要：
背景：患有1型糖尿病的老年人（OAs）中的严重低血糖（SH）与高发病率和死亡率相关，然而，其病因可能是复杂和多因素的。需要增强的工具来识别处于SH高风险的OAs。这项研究使用机器学习来识别区分有和没有最近SH的特征，从一系列人口统计学和临床中进行选择，行为和生活方式，和神经认知特征，以及连续血糖监测（CGM）措施。
方法：分析了一项病例对照研究的数据，该研究涉及从T1D交换临床网络招募的OAs。使用随机森林机器学习算法来阐明与病例对对照状态相关的特征及其相对重要性。对具有连续丰富特征集的模型进行了检查，以系统地纳入可能的风险特征的每个领域。
结果：来自191名1型糖尿病患者的数据（47.1％为女性，92.1%非西班牙裔白人)进行了分析。跨模型，低血糖无意识是与SH病史相关的首要特征.对于输入数据最丰富的模型，最重要的特征，按降序排列，低血糖是无意识的，低血糖恐惧，来自CGM的变异系数，%时间血糖低于70mg/dL，并跟踪测试B得分。
结论：机器学习可以通过识别与SH相关的关键特征来增强OAs的风险分层。需要进行前瞻性研究以确定这些风险特征的预测性能。
方法：分析了一项病例对照研究的数据，该研究涉及从T1D交换临床网络招募的OAs。使用随机森林机器学习算法来阐明与病例对对照状态相关的特征及其相对重要性。对具有连续丰富特征集的模型进行了检查，以系统地纳入可能的风险特征的每个领域。
结果：来自191名1型糖尿病患者的数据（47.1％为女性，92.1%非西班牙裔白人)进行了分析。跨模型，低血糖无意识是与SH病史相关的首要特征.对于输入数据最丰富的模型，最重要的特征，按降序排列，低血糖是无意识的，低血糖恐惧，来自CGM的变异系数，%时间血糖低于70mg/dL，并跟踪测试B得分。
结论：机器学习可以通过识别与SH相关的关键特征来增强OAs的风险分层。需要进行前瞻性研究以确定这些风险特征的预测性能。
