在1型糖尿病中个性化血糖预测使用meta-learning与双向长短期记忆转换器混合模型
Kihoon Moon1, Jaehong Kim1, Seohyun Yoo1
1Department of Software Engineering, Jeonbuk National University, Jeonju-si, Jeollabuk-do, Republic of Korea.
Scientific reports
|August 20, 2025
概括
一个新的混合模型,BiT-MAML,通过减少预测错误,改善了针对1型糖尿病 (T1D) 的个性化血糖预测. 这种先进的模型为患者提供了更一致的性能,有助于临床安全.
科学领域:
- 生物医学工程 生物医学工程
- 人工智能在医学中的应用
- 糖尿病 技术 技术
背景情况:
- 在1型糖尿病 (T1D) 中个性化血糖 (BG) 预测面临挑战,原因是患者间的显著变化.
- 准确的BG预测对于有效的糖尿病管理和预防并发症至关重要.
研究的目的:
- 开发和评估一种新的混合模型,BiT-MAML,用于在T1D中改进个性化BG预测.
- 通过双向LSTM转换器和模型不可知的超级学习的组合来解决患者间异质性.
主要方法:
- 提出了一个混合模型:BiT-MAML (双向LSTM转换器与模型不可知的超级学习).
- 在俄俄州T1DM数据集上使用了假期-一个患者-退出交叉验证 (LOPO-CV).
- 使用根平均平方误差 (RMSE) 和克拉克误差网格分析 (CEGA) 对LSTM和Edge-LSTM基线进行性能比较.
主要成果:
- 双T-MAML实现了平均30分钟预测RMSE24.89 mg/dL,超过了LSTM (19.3%更高的RMSE) 和Edge-LSTM (14.2%更高的RMSE).
- 在所有预测中,与最低标准偏差 (±4.60 mg/dL) 显示出卓越的一致性.
- 个体患者的RMSE变化 (19.6430.57毫克/分升),突出了个性化的预测挑战.
- 超过92%的预测属于每个CEGA的临床可接受区域 (A和B),证实了强度.
结论:
- 双T-MAML显示了在T1D中增强个性化BG预测的显著潜力.
- 强大的评估方法对于透明地报告性能变化和临床效用至关重要.
- 这些发现为更可靠,更安全的糖尿病管理临床工具铺平了道路.
相关概念视频
Diabetes Mellitus: Overview and Type I Subtype
3.2K
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...
3.2K
Diabetes Mellitus: Type 2 and Gestational
2.9K
Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...
2.9K
Diabetes: Management and Pharmacotherapy
362
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...
362
Diabetes: Symptoms, Diagnosis, and Complications
687
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...
687


