相关实验视频
Updated: Jun 1, 2025
06:09
An In Ovo Model for Testing Insulin-mimetic Compounds
Published on: April 23, 2018
10.3K
一个数据驱动的机器学习算法,用于预测胰岛素干预治疗II型糖尿病的有效性.
Shuheng Yang1, Ralf Weiskirchen2, Wenjing Zheng1
1School of Life Science and Technology, Wuhan Polytechnic University, Wuhan, China.
Frontiers in nutrition
|January 22, 2025
概括
一个机器学习模型有效地预测了哪些2型糖尿病 (T2DM) 患者可以从胰岛素营养治疗中受益. 像HbA1c和葡萄糖水平这样的关键因素有助于个性化治疗,以获得更好的结果.
科学领域:
- 内分泌学和新陈代谢学
- 营养科学 营养科学
- 计算生物学 计算生物学
背景情况:
- 2型糖尿病 (T2DM) 的发病率上升需要先进的管理策略.
- 营养治疗,特别是胰岛素补充剂,是T2DM护理的关键组成部分.
- 确定适合用于胰岛素干预的T2DM患者需要预测工具.
研究的目的:
- 开发和验证一种机器学习模型,用于预测T2DM患者胰岛素治疗的有效性.
- 确定影响对胰岛素治疗反应的关键患者特征.
主要方法:
- 利用了先前对接受胰岛素干预的T2DM患者研究的数据.
- 采用LASSO回归来进行特征选择和XGBoost用于预测模型开发.
- 使用准确性,特异性,正负预测值,ROC,校准和决策曲线评估模型性能.
主要成果:
- 在758名T2DM患者中,胰岛素干预成功降低了62.93%的糖化血红蛋白 (HbA1c).
- 通过LASSO回归识别的关键预测因素包括HbA1c,葡萄糖变化,禁食葡萄糖,HDL,年龄和BMI.
- XGBoost模型实现了高性能指标,训练集精度为0.819,测试集精度为0.709.
结论:
- XGBoost-SHAP框架有效预测T2DM中的胰岛素干预结果.
- 这种方法可以通过评估个体患者的特征和预测能力来实现个性化治疗.
- 建立了机器学习和T2DM管理的营养治疗之间的宝贵联系.
更多相关视频
07:15An In Vitro Batch-culture Model to Estimate the Effects of Interventional Regimens on Human Fecal Microbiota
Published on: July 31, 2019
9.5K
08:13Study of In Vivo Glucose Metabolism in High-fat Diet-fed Mice Using Oral Glucose Tolerance Test OGTT and Insulin Tolerance Test ITT
Published on: January 7, 2018
67.9K
相关概念视频
01:23Dipeptidyl Peptidase 4 Inhibitors
165
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...
165
01:26Oral Hypoglycemic Agents: Biguanides and Glitazones
165
Biguanides, particularly metformin (Glucophage), are insulin sensitizers that enhance glucose uptake, thereby reducing insulin resistance. Unlike sulfonylureas, metformin doesn't prompt insulin secretion, which helps to curb hypoglycemia risk. Metformin is beneficial in treating conditions like polycystic ovary syndrome due to its insulin-resistance reduction capability. The drug's primary action involves curtailing hepatic gluconeogenesis, a significant contributor to high blood...
165