Methods to detect anomalies can be used to find fraudulent claims in insurance, especially in products with a large frequency of payments, such as in healthcare.

As more evidence emerges about long-term clinical impacts of Covid-19 and long Covid, insurers will need to consider the implications for medical underwriting.

With diabetes, adherence to noninsulin antidiabetic medications correlates with more outpatient and fewer inpatient visits, and lower total expenditures.

Techniques in explainable artificial intelligence can indicate the reasons why a model expects a claim to be truly fraudulent, saving time for investigators.

The onset of the COVID-19 pandemic has had numerous impacts on health systems worldwide, with extra support needed globally to address the healthcare needs associated with the pandemic.

In this article we discuss the techniques available to mitigate machine learning becoming black boxes and what should be considered in their implementation.

This article describes the application of two methods for the detection of potential fraudulent claims in healthcare provider invoices.

This analysis compares information provided in the Quantitative Reporting Templates and Solvency and Financial Condition Reports and makes observations about the balance sheets and risk exposures of European health insurers.

The effects of COVID-19 for specific insurers are dependent on benefit packages and policy terms and conditions, as well as government responses and macro-economic factors.

Machine learning makes the role of the actuary in the Dutch healthcare landscape more crucial than ever.