Unlocking the Power of Practical Taxonomy from EHR Data for Precision Medicine < Cardiovascular Medicine

Hypertension or hypertension has proven difficult to manage in the United States. Despite the availability of antihypertensive drugs and the benefits of regular exercise, a significant number of patients continue to suffer from persistent hypertension. To address this issue, new taxonomies have been developed that target the root causes of this condition.

Led by Yuan Lu, ScD, an assistant professor at Yale School of Medicine and a member of Yale’s Center for Outcomes, Research and Evaluation (CORE), the study was published in the journal February 2. Circulation: Cardiovascular Quality and Outcomes.

Doctors may prescribe one or more antihypertensive treatments to help patients achieve target blood pressures below 130 mmHg and 80 mmHg. However, patients with treatment-resistant hypertension have underlying conditions that make drugs less effective. The term persistent hypertension is a more comprehensive concept than resistant hypertension, which refers to multiple increases in blood pressure over time. Patients with persistent hypertension include those with resistant hypertension, lack of diagnosis, inadequate treatment or lifestyle changes, poor adherence, missed appointments, and other barriers to health care. there is. In this study, Lu and his colleagues investigated the Yale New Haven Health System patients who had five or more consecutive increases in blood pressure between January 1, 2013 and her October 31, 2018 analyzed the patient. EHR).

“Data from the Yale New Haven Health System show that refractory hypertension accounts for 5-10% of all hypertension patients. I have persistent high blood pressure because of it,” Lu said.

A Phase 2 clinical trial of a treatment-resistant hypertension drug is expected to begin later this year. But new drugs don’t address the cause of the problem. “Given the many reasons a patient may develop persistent hypertension, interventions to address these reasons will vary,” he said. “First, we need to categorize people, identify barriers to achieving blood pressure control, and then match them to targeted interventions that address these barriers.” Some patients may benefit from having a social worker if they have financial difficulties. We are currently leveraging the taxonomy through the Yale New Haven Health System, but we believe this pipeline can be applied to other health systems and other chronic diseases such as diabetes.” she said. The goal is to automate this classification method using a computational Her algorithm to enhance individualized interventions for patients with persistent hypertension.

We need to classify people, identify barriers to achieving blood pressure control, and match them to targeted interventions that address these barriers.

Yuan Lu, ScD

The Power of Data Science to Advance Hypertension Treatment

Data science and implementation science research can be used to enhance personalized care for hypertension. The next step in this research is to use machine learning and natural language processing methods to develop a system that can automate classification, and his EHR base that can connect patients to targeted, high-quality care at scale. is to design a clinical decision support tool for Such tools can send automated notifications to primary care teams, recommend appropriate treatments, and connect patients to services to improve their overall health.

“One of the ideas we have is what we call a command center for monitoring patients, matching them to clinical decision support tools, and conducting face-to-face sessions as needed. How do we design adapted interventions and are physicians willing to use them? It is a combination of data science and implementation science that guides precision interventions for these patients,” said a senior author of the paper. said Harlan Krumholtz, M.D., Ph.D., director of the Center for Outcomes Research and Evaluation.

The team hopes to pilot this idea with the Yale New Haven Health System in the future. Their current focus is on improving hypertension management for the 40,000 hospital staff and their dependents. “We have a very diverse population here in terms of age, gender and race. We are working with leaders at the Yale New Haven Health Cardiovascular Center to better stratify patients by treatment barriers. We are developing his algorithm for the computer,” he said.

Patients are more likely to see another provider out of hours, potentially missing treatment opportunities and increasing clinician burden. “Patients may not see the same provider during their trajectory. During a 15- to 20-minute clinical visit, the algorithm goes through all these notes and after talking to the patient, finds the root cause,” she added.

“We also provide possible actions to address each of these issues,” added Lu. Regarding non-intensification of treatment, data suggest that the most common issue is provider authority. This meant that the patient was seen by multiple specialists for a variety of primary concerns, including concerns unrelated to hypertension. Clinic visits where elevated blood pressure was measured were often by specialists who did not treat hypertension. For example, these visits were frequent for orthopedic, podiatric, or radiation oncology providers who did not routinely manage hypertension. A possible solution is to send an EHR notification to the primary care provider’s office to automatically schedule an appointment.

Data science and implementation science research can be used to optimize hypertension care. The goal of this research is to develop a system that can automate classification and connect patients to targeted, high-quality care at scale.

This study was funded in part by the National Heart, Lung, and Blood Institute (K12HL138037) and the Centers for Disease Control and Prevention (20042801-Sub01), and the National Institute on Minority Health and Health Disparities (U54MD010711-01). rice field. Lu received additional support from the Yale Center for Implementation Science and the Yale Scholars in Implementation Science (YSIS) Career Development Program.

Other authors are Cindy Xinxin Du, Hazar Khidir, César Caraballo, Shiwani Mahajan, Erica S. Spatz, and Leslie A. Curry, all from Yale.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *