Following more than six months working alongside UTS Rapido, a research and development hub at the university, the AI models will allow Zurich to make an immediate underwriting decision on applications with mental health disclosures without the need for a doctor’s report, which previously would take as long as 22 days.
Jacqui Lennon, Head of Retail, Zurich Australia & New Zealand said: “By using AI models to assist the underwriting process, Zurich can reduce the need to access doctor’s reports, eliminating significant friction within the application process and reducing applicant concerns around privacy.”
The models, which draw on anonymised data from seven years of past applications, identified factors correlated to a mental health exclusion being placed on an applicant, including:
- Lack of participation in sports, pastimes or recreational activity;
- Occurrence of any ongoing health issues beyond mental health, such as chronic pain, cancer or heart disease;
- Time spent in hospital or having medical treatment during the past five years; and
- Having biological parents or siblings with a health condition, such as diabetes, cancer or heart disease.
Currently, around one quarter of the life insurance applications Zurich receives include a disclosure for a mental health condition. In 2023, Mental health was the third most common cause for claim at Zurich, accounting for 20 per cent of all claims and resulting in $255m in claims payments*. For some of Zurich’s retail life insurance products, mental health becomes the first or second most common reason for claim, accounting for up to 35 per cent of claims in some cases.
John Kim, Chief Data Officer, Zurich Australia & New Zealand said: “Using AI allows Zurich to analyse thousands of data points, which would not be possible for a human to do. This project is a key step in Zurich’s journey to being Australia’s leading digital insurer, and importantly, it allows us to provide protection to more Australians at a time when they need it most.”
“Beyond underwriting, the models’ findings will also be key in guiding the continued delivery and evolution of Zurich’s preventative health and wellness offerings. In future, and data-prevailing, models like these could potentially also be used to analyse and improve the underwriting of conditions beyond mental health, such as cancer, cardiovascular or musculoskeletal conditions,” Ms Lennon said.
The AI models will be used to verify decisions made by Zurich’s underwriting team and the existing rules engines they use, in keeping with Zurich’s AI philosophy to ‘always keep a human in the loop’.
———–