Clinically relevant subgroups of T2DM patients using unsupervised clustering analysis
<p dir="ltr">Type 2 Diabetes Mellitus (T2DM) is a complex condition characterized by a variety of risk factors, clinical presentations, progression patterns, and outcomes. In practice, T2DM is unclassified but defined in the absence of Type-1 Diabetes Mellitus with or without the cla...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| الملخص: | <p dir="ltr">Type 2 Diabetes Mellitus (T2DM) is a complex condition characterized by a variety of risk factors, clinical presentations, progression patterns, and outcomes. In practice, T2DM is unclassified but defined in the absence of Type-1 Diabetes Mellitus with or without the classical lesions of obesity. This lack of classification can be misleading, as various integrated risk factors significantly influence how T2DM manifests and progresses, making it challenging to predict patient prognosis and responses to treatment. </p><p dir="ltr">To address this issue, it is beneficial to explore the clinical features of T2DM for better patient classification. This approach is not only cost-effective but also critical for developing personalized interventions that can save lives and reduce healthcare costs. </p><p dir="ltr">In our analysis, we utilized unsupervised, patient-data-driven cluster analysis to identify subgroups among long-term T2DM patients. Our goal is to provide baseline evidence of T2DM subgroups that exhibit different cardiovascular risk profiles, which can guide future large-scale research efforts. We have emphasized our clustering analysis on the major and inexpensive of metabolic syndrome:</p><ul><li>body mass index (general obesity)</li><li>Fat mass index (central obesity)</li><li>glycated haemoglobin (Beta cell function/insulin resistance)</li><li>triglyceride_glucose index (Beta cell function/insulin resistance)</li></ul><p dir="ltr">Using standard prediction equations, the novel clusters were compared to patient data re-organised into cardiovascular disease risk outcomes.</p> |
|---|