SAS for Healthcare Finance: Statistical Methods and Real-World Scenarios Across the Continuum of Care - Now in the Age of AI

Healthcare finance runs on numbers. The challenge is knowing whether those numbers answer the right question.

SAS for Healthcare Finance by Urmi K. Doshi connects statistical methods, SAS programming, and financial reasoning across the healthcare continuum. Through realistic scenarios, it shows how analysts turn claims, enrollment, pharmacy, provider, and clinical data into findings that support informed decisions.

Written for healthcare analysts, financial analysts, medical economists, health informatics professionals, and students with foundational SAS knowledge, it brings technical analysis into the conversations where it matters: explaining a cost increase, evaluating an intervention, forecasting revenue, investigating a payment discrepancy, or presenting a defensible recommendation.

The book uses the STAR framework— Situation, Task, Action, and Result—to connect each analytical question with its business context. Worked examples show what to measure, how a method addresses the question, and what the result does—and does not—justify.

Across six parts, readers explore:

• The healthcare analytics landscape, SAS and SAS Viya, generative AI, automation, and the importance of human judgment
• Core statistical methods: descriptive analysis, hypothesis testing, regression, survival analysis, and risk prediction
• Payer-side applications: utilization, medical loss ratio, premium development, pharmacy benefits, oncology costs, Medicare Star Ratings, and fraud, waste, and abuse screening
• Provider-side applications: denials, accounts receivable, hospital cost accounting, reimbursement, procedural productivity, and capital budgeting
• Enterprise questions: population health, frailty, value-based contracts, health equity, care management, model validation, and audit readiness
• Connections between SAS and R, with attention to the definitions, assumptions, and settings that make comparisons meaningful

MegaStar Health Plan, a fictional organization, provides a shared setting for synthetic teaching examples, so no real patient or member records are used.

The emphasis extends beyond getting a program to run. Readers examine how duplicate joins inflate spending, how an incorrect denominator distorts a rate, why an association does not establish savings, and how missing values can undermine a reassuring result. An impressive p-value never substitutes for a clear business case.

Examples address questions such as:

• What is driving pharmacy spending, and how do rebates change the answer?
• How should enrollment changes affect a revenue forecast?
• Does a care-management program create value after accounting for selection and program costs?
• What explains a reconciliation gap between a claims source and a reporting table?
• What evidence should accompany a model before its findings reach leadership?

Chapter quizzes,