Diabetes Unit, Endocrine Division, Massachusetts General Hospital, Boston, Massachusetts, United States of America.
Department of Medicine, Harvard Medical School, Boston, Massachusetts, United States of America.
PLoS One. 2022 Dec 12;17(12):e0278759. doi: 10.1371/journal.pone.0278759. eCollection 2022.
Understanding atypical forms of diabetes (AD) may advance precision medicine, but methods to identify such patients are needed. We propose an electronic health record (EHR)-based algorithmic approach to identify patients who may have AD, specifically those with insulin-sufficient, non-metabolic diabetes, in order to improve feasibility of identifying these patients through detailed chart review.
Patients with likely T2D were selected using a validated machine-learning (ML) algorithm applied to EHR data. "Typical" T2D cases were removed by excluding individuals with obesity, evidence of dyslipidemia, antibody-positive diabetes, or cystic fibrosis. To filter out likely type 1 diabetes (T1D) cases, we applied six additional "branch algorithms," relying on various clinical characteristics, which resulted in six overlapping cohorts. Diabetes type was classified by manual chart review as atypical, not atypical, or indeterminate due to missing information.
Of 114,975 biobank participants, the algorithms collectively identified 119 (0.1%) potential AD cases, of which 16 (0.014%) were confirmed after expert review. The branch algorithm that excluded T1D based on outpatient insulin use had the highest percentage yield of AD (13 of 27; 48.2% yield). Together, the 16 AD cases had significantly lower BMI and higher HDL than either unselected T1D or T2D cases identified by ML algorithms (P<0.05). Compared to the ML T1D group, the AD group had a significantly higher T2D polygenic score (P<0.01) and lower hemoglobin A1c (P<0.01).
Our EHR-based algorithms followed by manual chart review identified collectively 16 individuals with AD, representing 0.22% of biobank enrollees with T2D. With a maximum yield of 48% cases after manual chart review, our algorithms have the potential to drastically improve efficiency of AD identification. Recognizing patients with AD may inform on the heterogeneity of T2D and facilitate enrollment in studies like the Rare and Atypical Diabetes Network (RADIANT).
了解非典型糖尿病（AD）的形式可能会推进精准医学，但需要找到识别此类患者的方法。我们提出了一种基于电子健康记录（EHR）的算法方法，以识别可能患有 AD 的患者，特别是那些胰岛素充足、非代谢性糖尿病患者，以便通过详细的图表审查来提高识别这些患者的可行性。
使用经过验证的机器学习（ML）算法从 EHR 数据中选择可能患有 T2D 的患者。通过排除肥胖、血脂异常证据、抗体阳性糖尿病或囊性纤维化的个体，去除“典型”T2D 病例。为了筛选出可能的 1 型糖尿病（T1D）病例，我们应用了六个额外的“分支算法”，依赖于各种临床特征，这导致了六个重叠的队列。通过手动图表审查将糖尿病类型分类为非典型、非非典型或由于信息缺失而不确定。
在 114975 名生物库参与者中，该算法总共确定了 119 例（0.1%）潜在的 AD 病例，其中 16 例（0.014%）经专家审查后得到确认。基于门诊胰岛素使用排除 T1D 的分支算法的 AD 检出率最高（27 例中有 13 例；48.2%的检出率）。总的来说，与 ML 算法确定的未选择的 T1D 或 T2D 病例相比，16 例 AD 病例的 BMI 明显更低，HDL 更高（P<0.05）。与 ML T1D 组相比，AD 组的 T2D 多基因评分明显更高（P<0.01），糖化血红蛋白（HbA1c）明显更低（P<0.01）。
我们的基于 EHR 的算法通过手动图表审查共识别出 16 名 AD 患者，占生物库中 T2D 患者的 0.22%。通过手动图表审查的最大检出率为 48%，我们的算法有可能大大提高 AD 识别的效率。识别 AD 患者可能有助于了解 T2D 的异质性，并促进在罕见和非典型糖尿病网络（RADIANT）等研究中招募患者。
