糖尿病患者的系统性风险因素评估,以随机森林分类模型检测糖尿病视网膜病变
Ramesh Venkatesh1, Priyanka Gandhi1, Ayushi Choudhary1
1Department of Retina and Vitreous, Narayana Nethralaya, Bengaluru 560010, India.
Diagnostics (Basel, Switzerland)
|August 29, 2024
概括
随机森林模型使用系统性风险因素准确预测糖尿病患者的糖尿病视网膜病变 (DR). 这种方法可能有助于减少不必要的DR查转诊.
科学领域:
- 眼科医生 眼科 眼科
- 医疗信息学 医疗信息学
- 机器学习 机器学习
背景情况:
- 糖尿病视网膜病变 (DR) 是糖尿病 (DM) 的一个重要并发症.
- 识别系统性风险因素对于预测DR发展至关重要.
- 早期发现和预测DR可以预防视力丧失.
研究的目的:
- 在糖尿病患者中评估与糖尿病视网膜病变 (DR) 相关的全身风险因素.
- 开发和评估一个随机森林 (RF) 分类模型,用于预测DR和视觉威胁DR (STDR).
主要方法:
- 收集了1416名DM患者的数据集,包括人口统计,临床和并发症数据.
- 在80%的数据上训练了一种随机森林 (RF) 模型,以预测DR和STDR.
- 模型性能在20%的测试组上使用准确度,灵敏度和特异性来评估.
主要成果:
- 射频模型在测试组中实现了对DR检测的100%准确性,灵敏性和特异性.
- 对于视力威胁的DR (STDR),该模型显示了76%的准确性,53%的灵敏度和80%的特异性.
- 该模型显示在识别患有DR风险的患者方面具有很高的潜力.
结论:
- 随机森林模型有效地根据系统性风险因素预测糖尿病患者的糖尿病视网膜病变 (DR).
- 这种预测能力可以优化DR查协议,减少不必要的转诊.
- 为临床实施,建议使用多种数据集进行进一步的验证.
相关概念视频
01:15Diabetes: Symptoms, Diagnosis, and Complications
520
For most patients, experiencing several weeks of polyuria, polydipsia, fatigue, and significant weight loss may indicate the presence of diabetes. Furthermore, adults displaying the phenotypic appearance of type 2 diabetes (particularly those who are obese and not initially insulin-requiring), may have islet cell autoantibodies, suggesting autoimmune-mediated β cell destruction and a diagnosis of latent autoimmune diabetes of adults (LADA). The categorization of glucose homeostasis is...
520
01:15Receiver Operating Characteristic Plot
104
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
104