Predictive models and life insurance

Munich Re assessed version 2.2 of Irix^® - Risk Score, a predictive modeling tool developed and owned by Milliman that assesses mortality risk using an individual’s prescription drug history. Insurers either considering or already using prescription drug-based scores should perform a retrospective validation study on their own experience data. Munich Re can assist carriers with the retrospective study, advise on changes to mortality assumptions, and recommend ways to incorporate the scores to streamline the underwriting process.

Key Findings

Primary high-level findings include the following:

• Relative mortality risks increase as Irix^® - Risk Score 2.2 increases.
• Risk Score 2.2 has more lives with higher scores and more lives with lower scores compared to prior versions, allowing carriers to identify more lives with better mortality.
• A larger proportion of lives in lower scores and higher scores compared to previous versions is observed across all age groups, but more noticeably for ages below 70.
• The score effectively stratifies mortality risk across age groups, and is particularly effective at segmenting mortality for ages 30 to 49.
• The score continues to be especially effective at identifying high mortality risk at earlier durations.
• Applicants with a prescription history hit have better mortality relative to those without one. For individuals with a hit, the score provides segmentation regardless of the severity of an applicant’s drug history.

Executive Summary

Irix^® - Risk Score is a proprietary scoring algorithm that uses prescription drug history to predict the mortality risk of individuals relative to other individuals of the same age and gender.

In 2018, Munich Re assessed Risk Score 2.0, an earlier version of the prescription drug-based mortality score, and concluded the scores are predictive of mortality for the U.S. insurance applicant population. Since then, Milliman enhanced its methodology to incorporate clinical mortality rules into the score and further refined the score across risk attributes, resulting in Risk Score 2.2.

Milliman provided Munich Re with 25 million lives sampled from the U.S. general insurance applicant population which includes life, health, Medicare supplement, LTC, final expense, and DI lines of business, the same population used to validate Risk Score 2.0. The Risk Score ranges within 0.0 and 10.0.

Munich Re performed an analysis of Risk Score 2.2 and confirmed it is predictive of mortality for the U.S. insurance applicant population. Compared to previous versions, Risk Score 2.2 more effectively stratifies mortality risk and identifies more lives with better mortality. A company-specific insured population is not expected to have identical underlying characteristics as this insurance applicant population; Munich Re recommends replicating the study on a company-specific insured dataset to help assess the value of Irix^® - Risk Score.

Life insurers interested in Irix^® - Risk Score should conduct a retrospective study in order to calibrate the tool to the carrier’s own underwriting paradigm. This process will help carriers balance the score with expected mortality with respect to their unique target markets, distribution channels, and underwriting processes. For carriers who are already using Irix^® - Risk Score, version 2.2 provides more effective mortality segmentation than its prior versions.

Methodology

Munich Re assessed the effectiveness of the latest version of Irix^® - Risk Score in stratifying the mortality risk profile of a pool of 25 million applicants with entry ages 0 - 100. Each life entered the study between the first quarter of 2005 and the last quarter of 2016. Deaths were sourced from the Social Security Death Master File and third-party proprietary databases. The study population is comprised of 468,491 deaths out of 104 million exposed life-years.

The expected mortality basis was taken from the 2015 VBT primary select and ultimate ANB tables split by age and gender with a 1 percent mortality improvement. We did not have the smoking status of each applicant, so we used an 85 percent non-smoker/15 percent smoker blend of the smoker distinct tables.

Munich Re completed additional analyses of relative actual to expected ratios (A/E) by various factors (e.g., age, gender, duration, line of business, and most severe drug priority) to assess whether the mortality risk stratification by Irix^® - Risk Score 2.2 is influenced by those factors.

Download the report to view the full results.