Development of a Late-Life Dementia Prediction Index with Supervised Machine Learning in the Population-Based CAIDE Study

Abstract

Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study.Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors (national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC).Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype.Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions.

Predicting Global Cognitive Decline in the General Population Using the Disease State Index

“…DSI was chosen as a classification method because this method is able to handle datasets with missing data, which is often the case in population study datasets. Also, this method has been successfully applied in previous studies and performed comparable to other state-of-the-art classifiers (Mattila et al, 2012;Pekkala et al, 2017).…”

“…If the number of features is high, their cumulative effect may, however, be remarkable. Previous results have shown that when including many features with a low relevance, the performance of DSI may decrease (Pekkala et al, 2017). We therefore included an experiment evaluating the effect of feature selection on MRI features using their relevance.…”

“…The DSI method has previously been tested in specific patient populations and has shown to perform reasonably well in the early prediction of progression from mild cognitive impairment (MCI) to Alzheimer's disease and has been successful in the classification of different dementia subtypes (Mattila et al, 2011(Mattila et al, , 2012Munoz-Ruiz et al, 2014;Hall et al, 2015). In a recent study DSI has been validated in a populationbased setting to predict late-life dementia (Pekkala et al, 2017). Identification of persons at risk for global cognitive decline may aid in early detection of persons at risk of dementia and may help to develop therapeutic or preventive measures to postpone or even prevent further cognitive decline and dementia (Blumenthal et al, 2017).…”

Risk score prediction model for dementia in patients with type 2 diabetes

“…In our prediction model, BMI and the variation in FPG and HbA1c were included. A recent study reported a latelife dementia prediction model using a validated supervised machine learning method in a Finnish population with baseline measurement in 1998 [4]. Factors considered included cognitive performance, vascular factors and apolipoprotein E genotype.…”

Applications of Machine Learning Predictive Models in the Chronic Disease Diagnosis

“…At the same time, dementia is one of the chronic diseases that happen in older people, and, in particular, Alzheimer's is associated with 60-70% of dementia cases. AD prediction through ML models concluded that prediction accuracy depends on the data type and model input [28,31]. These studies with the Disease State Index (DSI) technique produced an accuracy of 79%.…”