Project Summary
One of PCORI’s goals is to improve the methods that researchers use for patient-centered outcomes research. PCORI funds methods projects like this one to better understand and advance the use of research methods that improve the strength and quality of comparative effectiveness research.
What is the project about?
Electronic health records, or EHRs, contain data that researchers can use to test treatments and improve patient care. Some of the most detailed information in EHRs is in clinicians’ notes. But clinicians don’t write notes in a standard way. For example, clinicians’ notes may include one topic or more than one topic in a sentence. As a result, researchers may have a hard time getting accurate information from these notes using current methods.
In this study, the research team is developing new methods that use natural language processing, or NLP, to extract data from clinicians’ notes for use in research. In NLP, computer programs interpret written language and make it easier to sort and study. The new methods help researchers to correctly identify complex concepts in clinicians’ notes. For example, the methods help identify the start and end of a topic. They can also tell if statements are positive or negative.
How can this project help improve research methods?
Researchers can use the results to obtain more accurate data from clinicians’ notes in EHRs.
What is the research team doing?
The research team is using two types of NLP software to create the new methods and looking to see how well each method works. The team is using three clinical examples from EHR data from a healthcare system in Massachusetts as the basis for developing the new methods:
- Medicine use in patients with high cholesterol
- Patient and provider discussion of surgery to help patients lose weight
- Patient history of smoking
To see if the new methods work with data from different healthcare organizations, the research team is testing the methods with EHR data from a healthcare system in Maryland. The team is also comparing the new methods with existing NLP methods.
Research methods at a glance
Design Element | Description |
---|---|
Goal | To improve the accuracy of NLP extraction of EHR data by developing and comparing methods for improving identification of (1) the start and end of topics and (2) negative vs. positive statements |
Approach | Supervised NLP technology |
COVID-19-Related Study
Comparing Health Outcomes among Patients with COVID-19 Who Are Taking Medicines to Improve Heart Function
Results Summary
In response to the COVID-19 public health crisis in 2020, PCORI launched an initiative to enhance existing research projects so that they could offer findings related to COVID-19. The initiative funded this study and others.
What was this COVID-19 study about?
COVID-19 is a viral disease that can be mild or severe. Patients with heart disease or risk factors like diabetes and obesity have a higher risk for severe illness from COVID-19. During the pandemic, questions arose about the effect of medicines that improve heart function on COVID-19 health outcomes.
In this study, the research team looked at four common types of medicines to improve heart function:
- Aspirin, which reduces inflammation and blood clotting
- Metformin, which helps control blood sugar
- Renin-angiotensin-aldosterone system inhibitors, or RAASi, which help control blood pressure
- Statins, which help to lower cholesterol levels
The research team wanted to learn how these medicines affected health outcomes for patients with or at risk for heart disease after testing positive for COVID-19. They compared patients taking and not taking these medicines.
What were the results?
Patients taking statins, RAASi, and metformin had a lower risk of death than patients not taking these medicines. Patients taking and not taking these medicines didn’t differ in the risk of being:
- Admitted to the hospital
- Admitted to the intensive care unit, or ICU
- Put on a machine to help them breathe
Patients taking aspirin had a higher risk of being admitted to the hospital than patients not taking aspirin. Patients taking and not taking aspirin didn’t differ in the risk of:
- Being admitted to the ICU
- Being put on a machine to help them breathe
- Dying
Who was in the study?
The study included data from 13,585 adults who tested positive for COVID-19 between March 2020 and March 2021. All patients received care from the Mass General Bingham health system in Massachusetts. Of these, 68 percent were White. The average age was 63, and 52 percent were women. Also, 78 percent of patients were currently taking at least one medicine to improve heart function.
What did the research team do?
The research team looked at health record data for two groups of patients. The first group had a current prescription for at least one of the medicines that improve heart function. The second group had a past prescription for these medicines but didn’t have a current one on the date of their positive COVID-19 test. The team compared health outcomes from COVID-19 across the two groups. In the analysis, the team used statistical methods to account for differences in patient traits, such as sex, age, and health status, between the two groups.
Patient educators, researchers, and doctors gave input on the study.
What were the limits of the study?
The study didn’t assign people by chance to the medicines. As a result, the research team can’t say for sure if differences are due to the medicines or something else. The study took place before COVID-19 vaccines and treatments were widely available. Results may differ as COVID-19, vaccines, and treatments continue to change.
How can people use the results?
Patients with or at risk for heart disease and their doctors can use these results when considering risks related to COVID-19.
Professional Abstract
In response to the COVID-19 public health crisis in 2020, PCORI launched an initiative to enhance existing research projects so that they could offer findings related to COVID-19. The initiative funded this study and others.
Background
Patients with cardiovascular disease and cardiovascular risk factors, such as obesity and diabetes, have increased risk for adverse outcomes from COVID-19. Medications to improve cardiovascular function may reduce adverse outcomes from COVID-19. During the pandemic, questions arose about the potential risks and benefits of taking these medications for people who test positive for COVID-19.
Objective
To compare COVID-19 health outcomes among patients who are and are not taking medications to improve cardiovascular function
Study Design
Design Element | Description |
---|---|
Design | Retrospective cohort study |
Population | 13,585 patients ages 18 and older in the Mass General Brigham health system with current or past prescriptions for aspirin, metformin, RAASi, or statins who tested positive for COVID-19 |
Interventions/ Comparators |
|
Outcomes | Primary: hospitalization within 30 days of testing positive for COVID-19 Secondary: ICU admission due to COVID-19, intubation that started within 30 days of hospitalization for COVID-19 or of testing positive, death from any cause within 90 days of first testing positive for COVID-19 |
Data Collection Timeframe | March 2020–March 2021 |
This retrospective cohort study compared the effect of taking versus not taking medications for cardiovascular risk on rates of hospitalization, intensive care unit (ICU) admission, intubation, and death after testing positive for COVID-19.
Researchers analyzed electronic health record data for patients who received a COVID-19 diagnosis between March 2020 and March 2021. They compared two groups of patients. The first group had current prescriptions for at least one of four classes of medication for cardiovascular disease on the date of their positive COVID-19 test. These medication classes included aspirin, metformin, renin-angiotensin-aldosterone system inhibitors (RAASi), and statins. The second group had a previous prescription for at least one of the medication classes but did not have a current prescription on the date of their positive COVID-19 test. Researchers adjusted for patient characteristics such as sex, age, and health status in their analysis. Researchers used logistic regression models to estimate the risk for COVID-19 outcomes for each class of medication. The team also used multivariable analysis to adjust for patient demographics and comorbidities.
The study included health records for 13,585 adult patients receiving care from the Mass General Brigham healthcare system in Massachusetts. Of these patients, 68% were White. The average age was 63, and 52% were female. Patients with current prescriptions accounted for 78% of the study sample.
Patient educators, clinicians, clinical investigators, and data scientists provided input throughout the study.
Results
Patients taking statins (p<0.0001), RAASi (p<0.0001), and metformin (p=0.0032) had a lower risk of death compared with patients not taking these medications. Patients taking these medications did not differ significantly in risk of hospitalization, ICU admission, or intubation compared with patients not taking these medications.
Patients taking aspirin had an increased risk of hospitalization compared with patients not taking aspirin (p=0.0446). Patients taking aspirin did not differ significantly in risk of ICU admission, intubation, or death compared with patients not taking aspirin.
Limitations
Because the study used an observational design, associations between prescribed medications and outcomes cannot be assumed to be causal. The study occurred prior to the widespread availability of vaccinations and treatments for COVID-19. Results may differ as the virus and treatments evolve.
Conclusions and Relevance
In this study, statins, RAASi, and metformin were associated with a lower risk for death from COVID-19 among patients with a high risk for cardiovascular disease. Doctors can consider these findings when treating patients with cardiovascular disease and cardiovascular risk factors.
Peer Review Summary
The Peer-Review Summary for this COVID-19 study will be posted here soon.
Final Enhancement Report
This COVID-19 study's final enhancement report is expected to be available by August 2024.