Description: A summary recap of the recent SOA Health Conference held in Dallas, TX in June of 2025. With the intentional use of AI to assist with the summary, this article gives a good overview of the recent conference with personal commentary from one of the attendees.

Description: This article provides an overview of critical illness insurance: history, product description, and the three primary ways to offer critical illness coverage in the United States. This article also contains an illustration of an issue age premium rate calculation, as well as product features and rating applications specific to the various types of critical illness coverage.

Description: Discover the key components of value-based care (VBC) contracts and their impact on provider credibility. Learn about benchmarks, measurement period results, and the unique challenges providers face in managing insurance risk. Gain insights into reducing costs and aligning financial incentives in the US healthcare market.

Description: This article provides a brief overview of the current state of machine learning (ML) and artificial intelligence (AI) as they apply to actuarial science, including discussion around the integration of actuarial judgment with ML and AI. It concludes with an example of explainable ML through a python tool known as SHAP (SHapley Additive exPlanations), which is able to explain the key drivers behind individual ML or AI predictions.

Description: This article is a brief overview of what digital health is, how it is regulated, and who some of the big unicorns are.

Description: Review of events and highlights from the Spring 2019 SOA Health Meeting in Phoenix, AZ.

Description: Review of events and highlights from the Spring 2019 SOA Health Meeting in Phoenix, AZ.

Description: Healthcare risk adjustment methodologies have become increasingly complex, largely due to the belief that complexity enhances accuracy. However, a disconnect exists between how healthcare risk is assessed and how payments are adjusted. This article explores the stark difference between measuring the accuracy of a risk assessment model at a member level, and that of a risk adjustment mechanism at the health plan level. I show that a highly simplified approach that does not use diagnosis codes can have similar accuracy on risk adjusted payments to models that do. These findings suggest that accuracy is not a barrier to developing simpler risk adjustment methodologies, which can improve payment accuracy and reduce the financial incentive for coding diagnoses.

Description: This article is an update on the No Surprises Act, which is a U.S. Act aimed to reduce the risk that a person unexpectedly receives out of network charges for their health care visits. This is Part 2; Part 1 was featured in Health Watch's Sept 2024 issue.

Description: Article reviews the data a year into the unwinding of continuous coverage provisions in Medicaid, the impact on enrollment counts, how capitation rates have been adjusted, and compares those results to what has been modeled with the SOA Mediciad Unwinding model.