Computer assisted clinical decision support tool for management of statins

描述（由申请方提供）：高胆固醇血症（特别是低密度脂蛋白胆固醇（LDL-c））是动脉粥样硬化性心血管疾病（ASCVD）的主要可改变风险因素，ASCVD是美国的主要死亡原因。今天，美国估计有4100万人患有高胆固醇血症伴ASCVD，这4100万人中有75%服用七种他汀类药物之一，这些药物在降低LDL-c升高和心血管发病率方面非常有效。然而，近55%的他汀类药物治疗患者在治疗的第一年没有达到目标LDL-c水平，导致可预防的死亡和不必要的医疗保健费用。达到目标LDL-c水平的最重要障碍是缺乏从大型循证数据集综合的实时他汀类药物治疗建议。由于临床医生在他汀类药物的选择方面几乎没有指导，他们通常根据不精确的过去经验选择他汀类药物，从最低剂量开始，并在很长一段时间内滴定，从而产生本可预防的成本。 在VA医院环境中进行的初步研究表明，“他汀类药物管理器”（SM）是一种正在申请专利的基于计算机化、电子病历（EMR）的算法，可以高准确度地预测达到目标LDL-c水平的可能性。这些初步结果已得到证实，使用国家退伍军人管理局医院样本的106万名患者。使用基于个体患者特征（包括伴随临床疾病和药物）的多变量逻辑回归模型，SM预测特定剂量的特定他汀类药物达到目标LDL-c水平的概率。SM确保在适当的剂量下为每位患者开具正确的他汀类药物， 治疗方案的开始。他汀类药物管理算法的进一步开发、扩展和商业化将降低实现目标LDL-c水平的实验的高成本、延长的时间和频繁的挫折，潜在地降低副作用，改善治疗依从性，并最终降低与升高的LDL-c相关的ASCVD的所得风险。据估计，仅在美国，与ASCVD结局的医疗保健改善相关的经济节省每年就达数十亿美元。 第二阶段的总体目标是完成开始推广和商业化SM所需的研究和开发。II期有五个目标：1）使用代表性、异质性、非VA、国家患者数据库在回顾性队列研究中进行SM外部验证和改进; 2）基于I期研究结果和II期目标1的SM算法增强，开发稳健的SM原型; 3）在临床实用示范项目中评估SM; 4）卫生经济学研究，以确认直接的健康成本节省和较低的LDL-c值与SM的推荐他汀类药物和剂量治疗;并且，在本发明中，5）数据-使用现有软件和生物医学文献进行挖掘，以确定与他汀类药物疗效相关的临床变量和基因组标记，以改善SM模型性能和预测有效性。

DESCRIPTION (provided by applicant): Hypercholesterolemia (particularly low-density lipoprotein-cholesterol (LDL-c)) is a major, modifiable risk factor for atherosclerotic cardiovascular disease (ASCVD), the primary cause of death in the US. Today, an estimated 41 million people in the US are hypercholesterolemic with ASCVD and 75% of these 41 million people take one of seven statin drugs that are remarkably effective in reducing elevated LDL-c and cardiovascular morbidity. However, nearly 55% of statin-treated patients do not achieve target LDL-c levels during the first year of treatment, resulting in preventable mortality and unnecessary health care costs. The most important barrier to achieving target LDL-c levels is the lack of real-time statin treatment recommendations synthesized from large, evidence-based datasets. Since clinicians have little guidance in statin selection, they instead typically select statins based on imprecise past experience, start at the lowest dosage and titrate over a prolonged period, generating otherwise preventable costs. Preliminary research in a VA hospital setting indicates that Statin Manager" (SM), a patent-pending computerized, electronic medical record (EMR)-based algorithm can predict with high accuracy the probability of achieving target LDL-c levels. These preliminary results have been confirmed using a national VA Hospital sample of 1.06 million patients. Using multivariate logistic regression models based on individual patient characteristics, including concomitant clinical conditions and medications, SM predicts the probability that target LDL-c levels will be achieved by specific statins at specifc doses. SM ensures that the right statin, in the right dosage, is prescribed for each patient at the beginning of the treatment regimen. Further development, extension, and commercialization of the statin management algorithm will reduce the high cost, extended time and frequent frustration of experimentation to achieve target LDL-c levels, potentially reduce side effects, improve treatment adherence and ultimately reduce the resultant risk of ASCVD associated with elevated LDL- c. The economic savings associated with improved healthcare for ASCVD outcomes is estimated in the billions of dollars annually in the US alone. The overarching goal of Phase II is to complete the research and development necessary to begin roll- out and commercialization of SM. There are five Aims in Phase II: 1) SM external validation and refinement in a retrospective cohort study using a representative, heterogeneous, non-VA, national patient database; 2) develop a robust SM prototype based on phase I study results and SM algorithm enhancements from Phase II Aim 1; 3) evaluate SM in a Clinical Utility Demonstration Project; 4) health economics research to confirm direct health cost savings and lower LDL-c values for those treated with SM's recommended statin and dose; and, 5) Data-Mining using existing software and biomedical literature to identify clinical variables and genomic markers linked to statin efficacy to improve SM's model performance and predictive validity.