Advanced machine learning guiding cardiovascular therapy decisions in type 2 diabetes patients.

最近的研究表明，在2型糖尿病（T2DM）患者中，70%的死亡是由于心血管疾病（CVD），包括冠心病、中风、心力衰竭和外周动脉疾病。无T2DM受试者的CVD治疗由Qrisk3预后规则指导，然而，尽管有多种CVD预后规则可用，但尚不清楚哪种规则最适合T2DM患者。此外，尚不清楚是否有可能开发更高级的规则，联合预测单个CVD元素（例如，作为在T2DM护理中引入风险分层CVD管理的第一步，我将在英国200，000 + T2DM CPRD受试者样本中验证现有CVD预后算法。该项目的范围包括探索平均样本外表现，以及呈现地理位置，诊断环境，疾病持续时间，诊断年份和患者类型的分层结果。该项目的下一阶段重点是使用先进的竞争风险和多阶段方法开发新的糖尿病患者CVD预测规则。此外，我们希望利用基因组学数据来提高预后表现。该项目的范围还包括探索EHR数据和实时分析的实用性，以更新糖尿病人群中的CVD规则，设计预测重复依赖和预测疾病轨迹的方法。

Recent studies show that 70% percent of all deaths among type 2 diabetes (T2DM)patients are due to cardiovascular disease (CVD) involving coronary heart disease,stroke, heart failure and peripheral arterial disease. CVD treatment in subjects withoutT2DM is guided by the Qrisk3 prognostic rule, however while multiple CVD prognosticrules are available, it is unclear which rule is most appropriate for T2DM patients.Furthermore, it is unclear whether it is possible to develop more advanced rules, jointlypredicting individual CVD elements (e.g., CHD and stroke), while allowing for competingrisk and disease trajectories.As a first step in introducing risk-stratified CVD management in T2DM care I will validateexisting CVD prognostic algorithms on a British sample of 200,000+ T2DM CPRDsubjects. The scope of the project includes exploring average out-of-sampleperformance, as well as presenting stratified results for geographical location, diagnosissetting, disease duration, year of diagnosis and patient type.The next phase of the project focuses on developing novel CVD prediction rules indiabetes patients using advanced competing-risk and multi-stage methodologies.Moreover, we want to leverage genomics data to improve prognostic performance. Thescope of the project also includes exploring the utility of EHR data and real-time analyticsto update CVD rules in diabetes population, designing methods for predicting repeatedepisodes and predicting disease trajectory.