Dementia risk predictions from German claims data using methods of machine learning

Abstract

Introduction We examined whether German claims data are suitable for dementia risk prediction, how machine learning (ML) compares to classical regression, and what the important predictors for dementia risk are. Methods We analyzed data from the largest German health insurance company, including 117,895 dementia‐free people age 65+. Follow‐up was 10 years. Predictors were: 23 age‐related diseases, 212 medical prescriptions, 87 surgery codes, as well as age and sex. Statistical methods included logistic regression (LR), gradient boosting (GBM), and random forests (RFs). Results Discriminatory power was moderate for LR (C‐statistic = 0.714; 95% confidence interval [CI] = 0.708–0.720) and GBM (C‐statistic = 0.707; 95% CI = 0.700–0.713) and lower for RF (C‐statistic = 0.636; 95% CI = 0.628–0.643). GBM had the best model calibration. We identified antipsychotic medications and cerebrovascular disease but also a less‐established specific antibacterial medical prescription as important predictors. Discussion Our models from German claims data have acceptable accuracy and may provide cost‐effective decision support for early dementia screening.

Machine learning for predicting neurodegenerative diseases in the general older population: a cohort study

“…Reinke et al studied dementia risk in a population with German claims data in 117,895 individuals during a 10-year follow-up. They performed three different ML algorithms obtaining moderated discriminate accuracy from 0.64 (random forests) to 0.7 (logistic regression and gradient boosting) [11]. However, prediction models of NDs in cohort studies (designed to answer specific questions and have subjective and objective for-purposed information) with participants from the general population are not frequently performed due to the difficulty of obtaining funding, having an adequate sample size and an extended follow-up.…”

Identifying dementia from cognitive footprints in hospital records among Chinese older adults: a machine-learning study

“… 27 , 28 Our models showed comparable predictive power compared to other models including age. 23 , 29 The findings suggested that incorporating age-related predictors may provide a more nuanced understanding of dementia risk across the lifespan. Additionally, our subgroup analysis showed that the discriminatory ability decreased as the increase of age, which concurs with previous studies.…”

“…Based solely on easily accessible predictors that are available in health records, our models exhibited comparable or superior performance to existing studies that utilized primary care data. For example, a German study that used claims data showed a C-statistic of 0.71 23 ; and a US study which used diagnosis records of comorbidities and symptoms obtained a C-statistic of 0.63 for predicting dementia among those aged ≥ 65. 24 …”

Artificial intelligence approaches for early detection of neurocognitive disorders among older adults

“…A limited number of studies used other modern data science algorithms ( viz. classification trees ensemble, nearest-neighbor classification, Bayesian network, artificial neural network, and support vector machine) to predict the risk of dementia ( Barnes and Yaffe, 2009 ; Tang et al, 2015 ; Walters et al, 2016 ; Jeune et al, 2018 ; Nori et al, 2019 ; Gill et al, 2020 ; Kumar et al, 2021 ; Reinke et al, 2022 ). Logistic regression (LR), gradient boosting (GBM), and random forests (RFs) were used to develop predictive models to investigate whether the German claims data are suitable for dementia risk prediction ( Gill et al, 2020 ).…”