Artificial Intelligence and Advanced Analytics – The Key To Unlocking Actionable Insights For Health Plans

In Artificial Intelligence, Care Coordination by Marketing at Vital Data Technology

Healthcare changes are making managing member care more challenging. A rocky regulatory environment and rising costs require rigorous vigilance over acuity and activity among member populations to effectively deliver real-time insights and proactive interventions. For health plan executives, Medical Directors, Quality and Clinical leaders, it’s critical to find new ways to achieve higher quality scores and lower costs while improving member outcomes. But are health plans armed with the right approach to mine insights from voluminous data produced by every stakeholder throughout the healthcare continuum?

Industry Leaders To Unlock Trends

Mike Grover PMP, MCP, and Vital Data Technology’s CTO explained how the timely presence of Artificial Intelligence (AI), Machine Learning and Advanced “Big Data” Analysis techniques catalyzed a new era for payers; providing a new opportunity to unlock previously siloed healthcare data; thus enabling industry leaders to clearly understand member trends in new and exciting ways.

Powerful Analytics Point To Meaningful Insights

Vital Data Technology’s powerful analytics available through their Affinitē Web-based modules provide much-needed solutions to the problem of aggregating data elements and converting them into analyzable form. “The effectiveness of Artificial Intelligence and Machine Learning comes into play as it correlates unrelated data points into meaningful insights for our clients. As new healthcare data continuously comes into scope, algorithms are refreshed and readily mine data to see if something has changed,” stated Grover.

Without A Consolidated Platform, Showstoppers Prevail

Vital Data Technology understands the showstoppers health plan executives are faced with if they don’t have access to a platform that allows them to analyze real-time data. “The sheer volume of data related to healthcare is immense. The data health plans are provided is often raw and siloed – for instance, prescription data is not visible to the primary care doctor and may not be connected to emergency visits,” Grover explains. “You need a partner who is able to break through silos and consolidate data patterns that will tell the true story, analyzing demographic and geographic data in real time to improve member outcomes.” Plan executives may be poring over P&L statements, monitoring HEDIS® quality measures and trying to make raw data meaningful. “If leaders are not seeing improvements over time, their best bet is to go back to the financial statements, but it may be impossible to gain insights and see drivers in the raw data they already own.”

Vital Data Technology’s Unique Approach To Solving The Healthcare Problem

Affinitē delivers healthcare information from different data sources, updating each data source in a fast cadence. Lab data comes in daily, claims data from providers is refreshed as frequently as possible. Prescription data updates daily. Through an integrated billing and claims process Vital Data makes valuable data available to providers at a much faster rate, from 30 days down to a weekly or event daily cycle. Grover states, “First and foremost, Affinitē can consolidate rich data into the platform giving leaders a broader 360° view of each member.”

Identify, Stratify And Prioritize

The Affinitē platform’s advanced analytics and Artificial Intelligence identifies, stratifies and prioritizes cases in order to close care gaps faster, and to improve medical record review. Grover explains how Vital Data aggregates and streamlines healthcare data rapidly and forms the data into operational workflows immediately, effectively improving the speed of data usability – where health plans struggle the most. “Having a platform that can effectively plow through enormous amounts of healthcare data effectively and break down the silos of data is vital.”

Insights Needed To Slow Healthcare Spending

Reforms for slowing health care spending and increasing the value of care have largely focused on insurance-based solutions. However, the bulk of the increased costs are from treating chronic conditions linked to modifiable population risk factors such as heart disease, obesity and stress. Grover explains the powerful geo-spatial analytics in Affinitē can provide. “If you’re able to segment a population and understand they have an unusually high number of fast food restaurants providing only high fat, high sodium options, a health plan could get ahead of that problem. By choosing to monitor and identifying educational and healthy food solutions, such as advising them on ways to make healthier choices, they could be proactive and solve that issue,” stated Grover.

Healthcare Data Analytics Case Study – Hep C Treatment Targeted to Best Outcomes

Some health conditions cannot be avoided, but could be better managed if access to data revealed which members would be good candidates for drug treatment based on where they are in a disease progression. Hepatitis C is a serious, blood-borne disease that at one point was rampant, but has been under the radar for many years. There is a drug therapy proven to effectively treat all six main Hep C genotypes with a simple pill, once-a-day treatment regimen for the majority of patients and a 98% success rate. However, the problem is the drug is $150K-$300K for treatment. As a health plan, you want to be sure that the candidate member is the right one with no comorbidities and it’s the right time in the cycle of the disease for the drug to be effective. Member data such as race could determine low or high risk. For instance, statistically, individuals of Asian descent have less than a 1% chance of contracting Hepatitis C, yet the African American population is 20% more likely to develop this disease.

Healthcare data analytics can also be used to complete case studies in order to learn how to manage disease progression. For instance, studying data to learn when diabetes without complications progress into the disease with complications? Or discovering when can you begin dialysis treatment and potentially prevent liver failure and renal disease.

Moving Health Plans Into The New Era – From Reactive to Proactive Interventions

Rising healthcare costs and the transition from fee for service to value-based pricing models is prompting more health plans to analyze their member data in new ways. Health plans will now be able to track members who are genetically predisposed to different ailments. Medical conditions that typically run in a family are caused by changes in genes that are passed from generation to generation. Many different types of heart disease can be inherited. Some conditions, like high blood pressure or coronary artery disease, run in families but probably result from many different genetic changes that individually have a subtle effect, but may work collectively in a complex manner to cause disease.

For instance, a member with diabetes could have a sibling with slightly elevated sugar resistance. A health plan could gain insights and proactively enroll them in diabetes education.
The opportunity to identify causal relationships between hypertension and heart involvement. Tracking member data and supplying patient education is key to preventing the progression of hypertension to such conditions as coronary artery disease, diabetes and other chronic illnesses that have a higher propensity to occur.
Plan members identified by AI and ML as more likely to develop treatable chronic conditions can receive targeted and early attention from providers. Changes in lifestyle can often significantly reduce the risk of developing the condition or slowing the progression.

Translating Machine Learning Into Improved Outcomes

With Artificial Intelligence and Machine Learning innovations now available, the healthcare industry will be equipped for a new era of powerful, predictive analytics driving improvement in outcomes for members. Vital Data Technology data scientists have written and tested the algorithms behind the Machine Learning technology and data science models able to handle complex healthcare data.

Grover states that Vital Data Technology’s biggest strength is the human element, “in that we have continued to grow our deep understanding of healthcare data and bring several hundred collective years of clinical knowledge to the table. You need a partner who asks the right questions and can apply meaning to your member data, refining portions of healthcare information to help you understand stratifying populations.”