Please note: this event has passed
Dr Olesya Ajnakina is a researcher from University College London. She holds a PhD in Psychosis Studies from King’s College London where she was supervised by Sir Robin Murray. Prior to that Olesya graduated in the top 5% of the BSc in Psychology class of 2011 and later pursued an MSc in Clinical Neuroscience (2012). Olesya research career has focussed on predicting who is at risk for developing psychosis and other severe health conditions as well as improving long-terms outcomes for the patients. To achieve these goals, Olesya combines the start-of-the-art methods in statistical analyses, such as machine learning and interrogation of human genomes.
Using modern statistical learning methods to estimate all-cause mortality risk: a large population-based cohort study and external validation
Background: In increasingly ageing populations, there is an emergent need to develop a robust prediction model for estimating an individual risk for all-cause mortality so that relevant assessments and interventions can be targeted appropriately. Existing models to predict risk of all-cause mortality in older people are based on standard regression techniques that are known to lead to overfitting, multicollinearity and poor prediction of new cases, fail to handle missing data appropriately, are not externally validated, and are poorly reported making it difficult to make a positive recommendation on any of the tools.
Methods and Results: For the model development, data came from English Longitudinal Study of Ageing study, which comprised 9154 population-representative individuals aged 50-75 years, 1240 (13.4%) of whom died during the 10-year follow-up. Internal validation was carried out using Harrell’s optimism-correction procedure; external validation was carried out using Health and Retirement Study (HRS), which is a nationally representative, biannual longitudinal survey of adults aged ≥50 years residing in the United States. Cox proportional hazards model with regularisation by the least absolute shrinkage and selection operator, where the optimisation parameters were chosen based on repeated cross-validation, was employed for variable selection and model fitting. Measures of calibration, discrimination, sensitivity and specificity were determined in the development and validation cohorts. The model selected 13 prognostic factors of all-cause mortality encompassing information on demographic characteristics, health comorbidity, lifestyle and cognitive functioning. The internally validated model had good discriminatory ability (c-index=0.74), specificity (72.5%) and sensitivity (73.0%). Following external validation, the model’s prediction accuracy remained within a clinically acceptable range (c-index=0.69, calibration slope β=0.80, specificity=71.5% and sensitivity=70.6%). The main limitation of our model is twofold: 1) it may not be applicable to nursing home and other institutional populations, and 2) it was developed and validated in the cohorts with predominately white ethnicity.
Conclusions: Having employed modern statistical learning algorithms and addressed the weaknesses of previous models, a new mortality model achieved good discrimination and calibration to quantify absolute 10-year risk of all-cause mortality in older adults in the general population of older adults, as shown by its performance in a separate validation cohort. The model can be useful for clinical, policy, and epidemiological applications.