AI-Powered Chat and Healthcare: In-the-Moment Analysis

9 Oct, 2023 •

filling document

AI-Powered Chat and Healthcare is going to make waves in productivity. In-the-moment analysis can better understand and manage risk among patient populations by ‘chatting with their data’ to improve patient risk stratification as well as consultation and engagement efforts.  

Centers for Medicare and Medicaid Services (CMS) STAR ratings are focused on driving improvements in care quality. Payors are looking for new ways to improve member outcomes and ratings. Therefore, payors need to understand the members more holistically. That is done through segmenting members based upon demographics, claim history, and social determinants of health.  

Predicting future health risks helps payors achieve the best qualitative and cost-effective outcomes in member care. And that helps to determine which members are at higher risk for disease and what preventive care is appropriate. Ultimately, that means pharmacies can offer more personalized patient journeys to increase care quality and associated ratings. 

The challenge: “in-the-moment, iterative analysis.”  

To say the challenge is simply “ad hoc analysis” understates the data challenge. The ad hoc nature of analysis is also both iterative and “in-the-moment.” The requirements cannot wait days for an ad hoc analysis by a BI or data team.  

BI reports often give a reasonable starting point for the investigation of an “in-the-moment” hypothesis. BI assets are developed by data analysis experts who understand the data well, and their efforts often solidly address the more obvious 80% of the reporting analysis requirements. But in many scenarios, the care manager needs to go much deeper and pivot to many other related questions – all very quickly and iteratively, and in-the-moment.  

Care managers need to be able to analyze and segment the Patient Populations with “in-the-moment iterative analysis,” based upon factors such as Claim History, Demographics, and Social Determination of Health factors. 

DvSum Superior Value Proposition 

With DvSum CADDI, the staff such as the care manager can quickly and easily know which patients need additional consultation and design appropriate care support. 

Complementing existing Population Health Reporting and Analytics with DvSum CADDI allows pharmacies to better allocate the right resources based on patient populations and personalize patient engagement. This can lead to improvements in medication adherence, health outcomes, patient retention, and ratings. 

Example Population Health Use Cases 

There are a variety of use cases where “in-the-moment, iterative analysis” is required, and AI-powered chat can help greatly: 

a. Story1: Chronic Care Management 

  • Utilization Management queries of hospital admissions and utilization trend across all-plan chronic care members (by health condition classification) with more than one co-morbidity.  
  • Chronic care members are segmented by risk profile by plan type for care manager and care plan follow up. 
  • What percentage of Medicare patients within this classification meet “actively managed” criteria for purposes of CMS reimbursement?  Remediation? 
  • Does utilization trend have any correlation to physician, hospital, or other place of service? 
  • Which members and member types in this cohort have driven 30-day hospital readmissions? 
  • Identify existing care gaps for documentation, resolution, and closure. 

b. Story 2: Medicare Advantage (MA)  

  • Pre-qualifying member eligibility for transitions to Medicare Advantage from other plans (non-Medicare) plans, ex: commercial, small group, etc. 
  • Querying PCP metrics that drive STAR ratings to identify opportunities for physician engagement and improvement. (More than 75% of STAR driven by PCP metrics *EMR extraction to validate) 
  • Monitor changes in average risk adjustment factor (RAF) scores across population health cohorts for provider collaboration and coding improvements 
  • Assess priority chronic care cohorts to measure levels of member engagement and effectiveness (digital/consumer experience, etc.) 

c. Story 3: Population Health Pharmacy Utilization Management 

  • Monitoring for medication utilization across high-risk condition categories, including the medical necessity of specialty drugs, total spend, etc. 
  • Evaluation of polypharmacy trends and contraindications (ex:  members taking more than 4 maintenance meds and potential interactions) 
  • Brand vs Generic distribution and formulary substitutions or replacements  
  • Identification of medication management potential adverse events in high-risk populations  
  • Compliance with vaccination schedules for high-risk members or other preventive health and wellness screening measures  

4) Digital app customers  

It is important to reach out to members as quickly and easily as possible. Digital app customers can be reached more easily for the use cases mentioned above as well as other situations. 

5) Operational Metrics  

DvSum CADDI can also be used to analyze data quickly and easily for the purpose of driving operational efficiency that can help improve patient experience and reduce cost, for example, to cut time to fill prescriptions and to cut overall wait time for patients in the store. 

Conclusion  

DvSum securely combines OpenAI’s GPT-4 with a powerful underlying data infrastructure so that pharmacy companies can query their data quickly, easily, and iteratively. This empowers staff to become more autonomous and productive “in-the-moment” and thus to drive patient satisfaction scores and the overall business. Contact us today to see how DvSum CADDI can help you.  Review our webinar on Population Health to learn more. 

Share this post:

You may also like