Beyond the model:
Building assessments and risk tools for EHRs in alitheia
business meeting discussing survey results
© mauritius images / Hero Images

Life insurance underwriters face increasing pressure: more data, more complexity, and the constant demand for faster, more accurate decisions. While automation and AI promise solutions, underwriting is about more than just building models. It requires nuanced judgment, domain expertise, and the ability to see the story behind the data.​

​The team behind Munich Re’s alitheia platform goes beyond the model, combining advanced technology with underwriter expertise to address these real-world challenges. In this article, we show how our underwriters and data scientists collaborate to leverage electronic health records (EHRs), large language models (LLMs), and other AI tools, delivering flexible automation without sacrificing quality.

Why LLMs alone aren't enough

We started with a common question: Could we put all our underwriting manuals and EHRs (Electronic Health Records) into a large language model (LLM) and let it generate risk classes and decisions? It’s possible, but not practical. ​

LLMs are powerful knowledge bases, but they lack the deep, contextual expertise of seasoned underwriters. They can summarize, reason, and even mimic decision-making, but they often miss the subtle connections and judgment calls that define great underwriting.

Supporting sound decision-making

Even advanced models can miss key details, so alitheia builds guardrails into its rules. If the system can’t find the necessary data, the case is referred to an underwriter for manual review. This approach ensures that automation supports, not replaces, expert judgment. ​

​The work doesn’t stop with sleep apnea. The team is actively developing rules for other impairments and continues to refine assessments for cardiac and respiratory conditions as EHRs become more robust.​

​alitheia shows what’s possible when technology and human expertise work together. By building small, agile teams and focusing on continuous improvement, alitheia delivers faster, more accurate decisions, without sacrificing the nuance that defines great underwriting. For carriers, the message is clear: the future of risk assessment is about empowering underwriters with the best tools and insights available.

Contact

Magd Bayoumi
Magd Bayoumi
Staff Machine Learning Engineer
Rachel Eberle
Rachel Eberle
Director, Underwriting Risk, Integrated Analytics
Munich Re North America Life

Newsletter

Subscribe to our newsletter for the latest industry research, insights on life and health-related topics, and relevant Munich Re Life US updates. Join today and stay connected with our business.
    alt txt

    properties.trackTitle

    properties.trackSubtitle

    0:00
    0:00