RevOps health

Trinity Health <> Clientell

Trinity Health is one of the largest not-for-profit, Catholic health care systems in the US. It is a family of 115,000 colleagues and nearly 26,000 physicians and clinicians caring for diverse communities across 25 states. Nationally recognized for care and experience, the Trinity Health system includes 88 hospitals, 131 continuing care locations, the second largest PACE program in the country, 125 urgent care locations and many other health and well-being services.

Problem Statement:

• Current State: The rate of visibility of Trinity’s revenue income is low leading to lack of growth opportunities.
• Gap: This is due to fragmented data, inaccurate pipeline and limited data exploration.
• Future State: With the help of Clientell trinity can increase 55% decrease in A/R, 85% average insight accuracy, 78% fewer denials, 120% uplift in scoring accuracy and 10x increase in claim pipeline velocity

Dataset and datapoints

The data used to increase visibility is as follows:

• Demographic: Name, Age, Gender, Address.

• Administrative: Health insurance eligibility and membership, Type of practitioner, Physician specialty, "Insurance claim" information, e.g., charges for diagnostic tests and procedures and amounts paid

• Health Risk: Health-related behavior, e.g., use of tobacco products and seat belts, exercise, Genetic predisposition

• Health status (or health-related quality of life): Physical functioning, Mental and emotional well-being, Cognitive functioning

• Medical History: Past medical problems, injuries, hospital admissions, pregnancies, births; Family history or events (e.g., alcoholism or parental divorce)

• Present Health Management: Current problems and diagnoses, Medications prescribed, Allergies, Health screening

• Outcomes: GeneMedical ral and/or condition-specific states, e.g., functional status, readmission to hospital, and unexpected medical or surgical complications of care; Satisfaction

• Other: Discharge Date, Accommodation Days, Accommodation Charges, Service Charges

Insights

Claims data analysed across unified profiles to identify and assign factor weightages based on claims settlement.

• Administrative: The rate of clearing their claim from past claim data is inferred to be 45%.
• Health Risk: The rate of clearing their claim due to smoking habits is 7%
• Medical History: The rate of clearing their claim due to pregnancy is 1.5% and 1% through vital signs
• Present Health Management: The tendency to get their claim cleared from DAS is 5% .

Clientell’s Decision Landscape

• Analyse opportunity/risk in claims: Understand drivers of revenue growth by locating the highest and lowest performing claims
• Unified individual account details: Auto clean data and unify data from all data sources including third party sources
• Insurer’s propensity to clear claims: Identify underperforming claims in the pipeline and predict revenue losses
• AI-powered Micro segmentation: Risk and opportunity classification by breaking down revenue into streams based on region, Claims, BU & Managers
• Analyse revenue based on Health Units & Patients: Provide and 360 view of patients, claims, TPAs and resultant revenue
• Time series forecasts of revenue: Predict successfully on when and which claims will give highest revenue and analysing the factors driving it