Disease Prediction Use Case: Cardiovascular Disease


In the United States, heart disease is the leading cause of death for women and men, and one person dies every 36 seconds from cardiovascular disease in the US, according to the Centers for Disease Control and Prevention.[i] Heart disease is also expensive, costing the US about $219 billion each year due to the cost of healthcare services, medicines, and lost productivity due to death.[ii]

What if you could more easily identify patients who have risk factors for cardiovascular disease, and even predict disease onset? You’d be able to provide better care, achieve better outcomes, and reduce costs for everyone involved. Lumiata makes this possible.

Here’s a look at how you can use our artificial intelligence (AI) and machine learning (ML) solutions in the case of cardiovascular disease.

How Lumiata Works

We start by collecting your data, whether that’s claims, EHR, handwritten notes, or some other format. Once your data is in our ecosystem, we perform data quality checks and full quality assessments and provide you with a report of our findings. With all your data in one place, we then validate, clean, and normalize it to ensure consistency in the way the data is coded and to remove data that are incorrect, incomplete, duplicate, or improperly formatted.

Next, we enrich your data with our proprietary disease codes, which help identify risk factors and help predict the onset of cardiovascular diseases and other diseases. We also supplement your data with our data, which comes from 130 million patient records, 50 million published articles, and 35,000 physician curation hours. Lumiata then creates Person360 records, longitudinal records of each person in your data.

When your data has been ingested, validated, normalized, cleaned, cross-coded, and tagged for diseases and Person360 records have been generated, it’s ready for machine learning. This is where things get exciting! You can use our Lightning AI Model Builder to build and train data models, use pre-trained models from our Spectrum AI Model Catalog, or let Lumiata custom build a model based on your specific needs. These models can be used to gain a wide range of actionable insights for clinical and financial purposes, including disease onset prediction, risk factor identification, cost prediction, and more.

How providers can use predictive analytics to improve care

When caring for patients, it’s important to not only understand their current health status but also have insight into care utilization, prescription medications, and more. However, looking at a chart doesn’t always show the whole picture, especially if patients receive care from a variety of locations or doctors. That’s where artificial intelligence and machine learning come in. Lumiata’s AI and ML solutions show claims and behavior patterns that may not be visible when looking at a chart, helping care managers get a clearer picture.

You can also use our data models to identify key risk factors of cardiovascular disease, such as high blood pressure, diabetes, the use of statins or other medication, and more, as well as predict the onset of cardiovascular disease within the next 12 months. Our clinical model suite, which is up to 65% more accurate than the leading carrier, includes chronic condition management, disease onset, and hospitalization models, giving you insight into multiple aspects of patient health and care.  

When high-risk patients are identified for you and you’re given predictions regarding the onset of cardiovascular disease, you can make informed decisions to help keep patients healthy, such as adjusting their care management plan or making changes to their medication. Predictive analytics help you provide personalized care for patients at risk of developing cardiovascular disease and a better patient experience. By preventing disease onset, you can also help prevent costly hospitalizations and treatments, leading to reduced costs.

How payers can use predictive analytics to reduce costs

The ability to predict disease onset and identify high-risk patients is beneficial to payers as well as providers. Members who have serious health conditions will likely need more complex treatment and incur higher costs, resulting in greater expenses for your organization. Having insight into members at risk of developing cardiovascular disease and other diseases can help you identify potential high-cost members and groups. This insight helps you make informed decisions in underwriting and actuarial tasks, including setting plan costs that aren’t so high that people can’t afford them but aren’t so low that you don’t have enough money to cover costs. Lumiata’s financial model suite is up to 80% more accurate than the nearest competitors’ cost prediction models and include high-cost member or patient, group cost, and stop-loss models.

How patients benefit from predictive analytics

While predictive analytics help providers and payers, it also benefits patients. When doctors have greater insight into patients’ risk factors, they can provide more personalized care, resulting in patients getting the care and medications they need based on their specific circumstances. Providers can also address patients’ risk factors more quickly, helping prevent patients’ conditions from getting worse. In the case of patients at risk of developing cardiovascular disease, early intervention could mean avoiding expensive hospital stays, procedures, and medications. It could also mean the patient won’t have to deal with possible complications associated with cardiovascular diseases, such as heart failure, stroke, coronary artery disease, heart attack, and more.  

When payers use AI and ML to help set reasonable prices, patients may be more likely to pay for insurance and seek medical attention when they’re not feeling well. They’re also more likely to stay with the providers and payers who enable them to get great care. This helps ensure their risk factors are addressed in a timely manner, helping patients stay healthy.

About Lumiata

We’re ushering in a new era of groundbreaking predictive analytics using tools and applications custom-built for the healthcare industry. Our vision is to democratize AI in healthcare to reduce costs and improve the quality of care. Lumiata’s superior risk and cost predictions consistently outperform legacy methods, helping you better manage risk and provide care. Whether you want to predict the onset of cardiovascular disease and other diseases, predict high-cost patients and members, or something else, Lumiata has you covered. Want to learn more? Click here to request a demo.

[i] https://www.cdc.gov/heartdisease/facts.htm

[ii] https://www.cdc.gov/heartdisease/facts.htm