What's New in Dementia Risk Prediction Modelling? An Updated Systematic Review

Abstract

Introduction: Identifying individuals at high risk of dementia is critical to optimized clinical care, formulating effective preventative strategies, and determining eligibility for clinical trials. Since our previous systematic reviews in 2010 and 2015, there has been a surge in dementia risk prediction modelling. The aim of this study was to update our previous reviews to explore, and critically review, new developments in dementia risk modelling.

Methods: MEDLINE, Embase, Scopus, and Web of Science were searched from March 2014 to June 2022. Studies were included if they were population- or community-based cohorts (including electronic health record data), had developed a model for predicting late-life incident dementia, and included model performance indices such as discrimination, calibration, or external validation.

Results: In total, 9,209 articles were identified from the electronic search, of which 74 met the inclusion criteria. We found a substantial increase in the number of new models published from 2014 (>50 new models), including an increase in the number of models developed using machine learning. Over 450 unique predictor (component) variables have been tested. Nineteen studies (26%) undertook external validation of newly developed or existing models, with mixed results. For the first time, models have also been developed in low- and middle-income countries (LMICs) and others validated in racial and ethnic minority groups.

Conclusion: The literature on dementia risk prediction modelling is rapidly evolving with new analytical developments and testing in LMICs. However, it is still challenging to make recommendations about which one model is the most suitable for routine use in a clinical setting. There is an urgent need to develop a suitable, robust, validated risk prediction model in the general population that can be widely implemented in clinical practice to improve dementia prevention.

Keywords: Alzheimer disease; Dementia; Incidence; Risk prediction; Statistical model.

Fig. 1.

PRISMA flow diagram showing the selection of studies for inclusion in the review study design and characteristics.

Fig. 2.

Treemap of the most commonly used variables, with size and colour representing frequency and variable category. Key: types of variables represented: green = demographic; red = health; orange = lifestyle; pink = functioning; blue = cognitive; yellow = genetic. BMI, body mass index; HDL, high-density lipoprotein; IADL, instrumental activities of daily living; MMSE, Mini-Mental State Examination; TBI, traumatic brain injury.

Fig. 3.

AUC/c-statistic indices comparing development and external validation of dementia risk models. Key: The dashed line represents the lowest cut-off value (AUC/c-statistic = 0.70) for acceptable discriminative accuracy and clinical significance. See Table 1 for a comprehensive list of abbreviations. Grey = calibration not reported; green = good calibration; red = poor calibration (underestimated/overestimated risk). *Model development cohort. ¹Risk model not initially developed for dementia risk prediction. ²Taken from the total population at 7-year follow-up due to having calibration results. ³LIBRA basic model. ⁴Heart failure population. ⁵Atrial fibrillation population. ⁶Taken from 10-year follow-up due to having calibration results.