A pragmatic dementia risk score for patients with mild cognitive impairment in a memory clinic population: Development and validation of a dementia risk score using routinely collected data

Abstract

Introduction This study aimed to develop and validate a 3‐year dementia risk score in individuals with mild cognitive impairment (MCI) based on variables collected in routine clinical care. Methods The prediction score was trained and developed using data from the National Alzheimer's Coordinating Center (NACC). Selection criteria included aged 55 years and older with MCI. Cox models were validated externally using two independent cohorts from the Prospective Registry of Persons with Memory Symptoms (PROMPT) registry and the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results Our Mild Cognitive Impairment to Dementia Risk (CIDER) score predicted dementia risk with c‐indices of 0.69 (95% confidence interval [CI] 0.66–0.72), 0.61 (95% CI 0.59–0.63), and 0.72 (95% CI 0.69–0.75), for the internally validated and the external validation PROMPT, and ADNI cohorts, respectively. Discussion The CIDER score could be used to inform clinicians and patients about the relative probabilities of developing dementia in patients with MCI.

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

“…However, the generated SVM models performed the best, with an accuracy of 93.3% for all patients, 94.4% for men exclusively, and 95.5% for women-only models. The top 10 significant predictors based on the developed SVM model for all patients are ranked as ( Winblad et al, 2016 ) education, ( Cummings-Vaughn et al, 2014 ) bedtime, ( Ferencz and Gerritsen, 2015 ) taking pills for chronic pain, ( Wang et al, 2022 ) diabetes, ( Wang et al, 2021 ) stroke, ( Doblhammer et al, 2022 ) gender, ( Goerdten et al, 2019 ) chronic pains, ( Kilander et al, 1998 ) coronary artery diseases, and ( Walker et al, 2017 ) wake-up time. The key novelty of this study is the early detection of cognitive function without relying on the radiological findings.…”

“…Typically, each table row demonstrates an observed class, and each column is a predicted class. Several statistical methods of performance evaluation were used for assessing the established models, including prediction accuracy, recall (true positive rate), precision (positive predictive value), and F1 score, as described in Equation (1 – 4) ( Wang et al, 2022 ).…”

“…This multi-etiological syndrome is caused by different neurodegenerative diseases, including AD, which accounts for 70 to 80% of all cases of dementia ( Ferencz and Gerritsen, 2015 ). Other types of dementia include vascular dementia, frontotemporal lobar degeneration (FTLD), and Lewy body dementia ( Wang et al, 2022 ). The neuropathological hallmarks of AD are the abnormal accumulation of cortical extracellular senile amyloid-beta (Aβ) plaques and intracellular neurofibrillary tangles (NFTs), which selectively affect specific types of neurons and brain circuits.…”

Expert elicitation of risk factors for progression to dementia in individuals with mild cognitive impairment

“…An important finding from this elicitation study is that some but not all predictors identified as important for dementia risk prediction in the research literature are being routinely collected or analyzed in clinical practice, existing registries, and observational studies. Age, which was identified as the most important predictor by the expert panel, is an example of a variable routinely collected and included as a predictor in many dementia risk‐scoring algorithms 5,20,21 but not all 22 . In contrast, APOE4 status, which is commonly included in published risk scores, 5 is not routinely collected in clinical practice and was only ranked 20th by the experts.…”

The Alzheimer's Disease Neuroimaging Initiative in the era of Alzheimer's disease treatment: A review of ADNI studies from 2021 to 2022

“…Another framework based on a multifactorial cascade model of disease progression was used to simulate a personalized response to anti-amyloid therapies using either aducanumab or donanemab 119. The model simulated both short-(78 weeks) and long-term (10 years) individualized responses that took into account potential side effects such as amyloid-related imaging abnormalities (ARIA).A dementia risk score, the Mild Cognitive Impairment to Dementia Risk (CIDER) score, designed to be used in primary care to predict time to all-cause dementia within 3 years of an MCI diagnosis, was developed in the NACC cohort and validated in two cohorts including ADNI 120. CIDER was implemented as a nomogram with variables easily determined in clinic: age, sex, education, marital status, hypertension, mood disorder, and either MoCA or MMSE (FigureS16in supporting information).…”