Dynamic hazards modelling for predictive longevity risk assessment

Predictive risk assessment and stratification models based on geodemographic postcode-based consumer classification are widely used in the pension life insurance industry. However, these static socio-economic not directly related to health information. Health information is increasingly for annuity underwriting UK, using status when purchased. In real life, people develop new conditions lifestyle habits can start stop a certain treatment regime at any time. This requires ability dynamically classify clients into time-varying profiles presence of evolving health-related conditions, treatments outcomes. We incorporate landmark analysis electronic records (EHR), combination with baseline hazards described by Gompertz survival distributions, dynamic prediction probabilities expectancy. discuss case-study experience cohort 110,243 healthy participants who reached age 60 between 1990–2000.