In his white paper, Dr. Tony Kollarmalil, Medical Director, explores COVID-19’s impact from a risk adjustment perspective and evaluates how healthcare organizations can avoid hospitalizations and reduce morality.
Please click on the video to the right to learn more about the author, his paper’s key insights, and his motivation for writing on this subject.
To discuss this white paper in detail, please contact Tony using his information provided at end of the page.
The epidemic of COVID-19 began in December 2019, springing a surprise on the healthcare community. Scientists and the medical community have a good understanding of viruses that impact the global population on a massive scale. Whether it’s the annual Influenza outbreak that mutates year to year, the common chicken pox or even the less studied conditions like Ebola.
There are precautionary measures as well as treatment modalities to combat spread and alleviate symptoms. The challenge with COVID-19 has been understanding the spread and the basics such as risk factors and symptoms. There is consensus within the medical community that certain populations are at risk. The CDC regularly updates the list of conditions that pre-dispose individuals to increased risk for severe illness from COVID-19. An excerpt is provided below.
| Strongest and most consistent evidence | Mixed Evidence | Limited Evidence |
|---|---|---|
| Serious heart conditions, such as heart failure, coronary artery disease, or cardiomyopathies | Asthma | Bone marrow transplantation |
| Chronic kidney disease | Cerebrovascular disease | HIV |
| COPD | Hypertension | Immune deficiencies |
| Obesity (BMI> 30) | Pregnancy | Inherited metabolic disorders |
| Sickle cell disease | Smoking | Neurologic conditions |
| Solid organ transplantation | Use of corticosteroids or other immunosuppressive medications | Other chronic lung diseases |
| Type 2 diabetes mellitus | Liver disease | |
| Type 1 diabetes mellitus | ||
| Thalassemia |
This list clearly shows that the most at risk are the chronically ill patients who tend to be older. These conditions are debilitating even without COVID-19. Population health analytics can be used to identify these patients who are at risk to isolate them, or provide outreach and educate them about the ways they can protect themselves. Analytics can also identify these patients that require immediate testing with the onset of symptoms. Teams can be dispatched for in-home testing to avoid unnecessary ED visits that would put these patients at great risk.
Medicare and Medicaid have traditionally used risk adjustment to identify chronically ill patients that require regular care. ICD-10 codes submitted on claims is used to identify these patients. Some of the primary risk adjustable conditions are diabetes and complications, morbid obesity, chronic obstructive pulmonary disease, chronic kidney disease, congestive heart failure, atrial fibrillation, atherosclerotic heart disease, etc.
The list of risk adjustable diagnoses perfectly cross match the conditions that put individuals at risk for COVID-19. Although not designed to provide data during a pandemic, risk adjustment inadvertently can help identify at risk individuals. Some studies showed that older diabetic patients, especially those on insulin, are prone to death from COVID-19.
There is at least one organization, Medical Home Network, an organization serving 122,000 patients in the Cook County Chicago area, who used risk adjustment and predictive analytics to identify individuals who have an increased risk for severe complications from COVID-19. Cook County happens to be the most populous county in Illinois as well as the second most populated county in the country.
This initiative helped the organization conduct important patient outreach to drive coronavirus testing. Patients who were identified as high risk for severe complications from COVID-19 were contacted by care management teams that already had built trusted relationships with these patients. Community preparedness was vital.
Using AI and factoring in conditions like social determinants of health, they are able to identify patients at risk of admission, minimize ED visits with direct interaction with a care manager, and prepare resources such a bed capacity, staffing , testing , etc. They were also able to use social determinants of health to identify individuals who lived alone or did not have access to resources like housing since this section of the population would be at extreme risk. So instead of reaching out to all 122,000 patients, they were able to concentrate initial outreach to 4.4.% of the patients who were at particular risk. Telehealth rules have been relaxed and companies have gone so far as to provide at risk members with iPads for interaction with their physicians or care management teams.
Vee Healthtek’s services include clinical reviews to identify risk adjustable chronic conditions like diabetes and heart conditions that require regular care. We employ machine learning tools and clinical reviewers to analyze past medical records including labs, diagnostic reports, consult notes, and claims to inform physicians they need to address a certain chronic condition.
There is an unintended consequence of identifying this data; it can also be used to identify at risk individuals for targeted outreach and isolation to prevent adverse life-threatening complications from COVID-19. As pandemics rage on in parts of the country, risk adjustment can and should be employed by population health teams to avoid hospitalizations and reduce mortality.
1. Evidence used to update the list of underlying medical conditions that increase a person’s risk of severe illness from COVID-19
https://www.cdc.gov/coronavirus/2019-ncov/need-extra-precautions/evidence-table.html
2. Chen, Y., et al., Clinical Characteristics and Outcomes of Patients With Diabetes and COVID-19 in Association With Glucose-Lowering Medication. Diabetes Care, 2020.
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7320669/
3. Leveraging AI for COVID-19 Outreach, Population Health Management
https://healthitanalytics.com/news/leveraging-ai-for-covid-19-outreach-population-health-management
