Bertsimas Dimitris, Ma Yu, Nohadani Omid
Sloan School of Management and Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA.
Artificial Intelligence and Data Science, Benefits Science Technologies, Boston, MA.
JCO Clin Cancer Inform. 2023 Sep;7:e2300026. doi: 10.1200/CCI.23.00026.
Abundant literature and clinical trials indicate that routine cancer screenings decrease patient mortality for several common cancers. However, current national cancer screening guidelines heavily rely on patient age as the predominant factor in deciding cancer screening timing, neglecting other important medical characteristics of individual patients. This approach either delays screening or prescribes excessive screenings. Another disadvantage of the current approach is its inability to combine information across hospital systems because of the lack of a coherent records system.
We propose to use claims data and medical insurance transactions that use consistent and pre-established sets of codes for diagnosis, procedures, and medications to develop a clinical support tool to supply supplemental insights and precautions for physicians to make more informed decisions. Furthermore, we propose a novel machine learning framework to recommend personalized, data-driven, and dynamic screening decisions.
We apply this new method to the study of breast cancer mammograms using claims data from 378,840 female patients to demonstrate that across different risk populations, personalized screening reduces the average delay in a cancer diagnosis by 2-3 months with statistical significance, with even stronger benefits for individual patients up to 10 months.
Incorporating personal medical characteristics using claims data and novel machine learning methodologies into breast cancer screening improves screening delay by more dynamically considering changing patient risks. Future incorporation of the proposed methodology in health care settings could be provided as a potential support tool for clinicians.
大量文献和临床试验表明，常规癌症筛查可降低几种常见癌症患者的死亡率。然而，当前的国家癌症筛查指南严重依赖患者年龄作为决定癌症筛查时机的主要因素，而忽视了个体患者的其他重要医学特征。这种方法要么延迟筛查，要么规定过度筛查。当前方法的另一个缺点是，由于缺乏连贯的记录系统，无法整合各医院系统的信息。
我们建议使用理赔数据和医疗保险交易数据，这些数据使用一致且预先确定的诊断、程序和药物代码集，以开发一种临床支持工具，为医生提供补充见解和预防措施，以便做出更明智的决策。此外，我们提出了一种新颖的机器学习框架，以推荐个性化、数据驱动和动态的筛查决策。
我们将这种新方法应用于乳腺癌乳房X光检查研究，使用来自378,840名女性患者的理赔数据，结果表明，在不同风险人群中，个性化筛查将癌症诊断的平均延迟缩短了2至3个月，具有统计学意义，对个别患者的益处甚至更强，可达10个月。
将理赔数据和新颖的机器学习方法纳入个人医学特征，可更动态地考虑不断变化的患者风险，从而改善乳腺癌筛查的延迟情况。未来，将所提出的方法纳入医疗保健环境中，可为临床医生提供潜在的支持工具。
