糖尿病患者的治疗中止预测使用排名模型:机器学习模型开发
Hisashi Kurasawa1, Kayo Waki2, Akihiro Chiba1,3
1Nippon Telegraph and Telephone Corporation, Tokyo, Japan.
JMIR bioinformatics and biotechnology
|June 27, 2024
概括
一个新的机器学习模型通过计算停药时间得分来预测糖尿病治疗中断风险. 这有助于优先考虑患者的干预,改善糖尿病护理,防止错过预约.
科学领域:
- 医疗信息学 医疗信息学
- 糖尿病 护理 糖尿病 护理
- 机器学习 机器学习
背景情况:
- 治疗中止 (TD) 是糖尿病管理中的一个重要问题,影响患者的治疗结果.
- 现有的二元分类模型难以准确评估不规则预约时间表的患者的TD风险.
- 这种局限性阻碍了对患者进行关键干预支持的有效优先考虑.
研究的目的:
- 开发一种新的机器学习预测模型,用于停止糖尿病治疗.
- 该模型的目标是输出个性化患者优先级的时间到停药风险得分.
- 通过准确识别患有TD高风险的患者,增强干预策略.
主要方法:
- 利用了东京大学医院 (2004-2016) 7551名糖尿病患者的电子病历.
- 开发了一种机器学习的排名模型来计算TD风险得分,由错过的约会来定义.
- 使用C指数,AUC-ROC和AUC-PR评估模型性能,并进行内部验证.
主要成果:
- 在TD风险评分中,C指数为0.749,AUC-ROC为0.758,AUC-PR为0.713.
- 校准图表显示,观察到的和预测的概率之间存在很强的相关性.
- 该模型有效地根据患者个体的TD风险对患者进行排名.
结论:
- 通过机器学习和EHR数据,开发了一个强大的TD风险评分,用于糖尿病患者.
- 整合到医疗记录中可以识别高风险患者,帮助主动治疗糖尿病.
- 这种方法提供了一种有价值的工具,可以防止治疗中止并改善患者管理.
相关概念视频
Diabetes: Management and Pharmacotherapy
256
The therapy for diabetes aims to alleviate hyperglycemia-related symptoms, prevent acute metabolic decompensation, and reduce chronic end-organ complications. Glycemic control is evaluated through short-term (self-monitoring, continuous glucose monitoring) and long-term (A1c, fructosamine) metrics, enabling near real-time tracking of blood glucose levels and reflecting glycemic control over specific time frames.
Insulin remains the cornerstone of treatment for most patients with type 1 and many...
Insulin remains the cornerstone of treatment for most patients with type 1 and many...
256
Diabetes: Symptoms, Diagnosis, and Complications
521
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...
521
Diabetes Mellitus: Overview and Type I Subtype
2.5K
Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
2.5K
Dipeptidyl Peptidase 4 Inhibitors
180
Dipeptidyl peptidase 4 (DPP-4) is a serine protease widely distributed in the body. It's involved in the inactivation of GLP-1 and GIP hormones, which are crucial for insulin regulation. DPP-4 inhibitors, such as sitagliptin (Januvia), saxagliptin (Onglyza), linagliptin (Tradjenta), alogliptin (Nesina), and vildagliptin (Galvus), help increase the proportion of active GLP-1, enhancing insulin secretion. These inhibitors work by competitively binding to DPP-4. This binding causes a...
180


