Using Machine Learning to Predict Dementia from Neuropsychiatric Symptom and Neuroimaging Data

Abstract

Background: Machine learning (ML) is a promising technique for patient-specific prediction of mild cognitive impairment (MCI) and dementia development. Neuropsychiatric symptoms (NPS) might improve the accuracy of ML models but have barely been used for this purpose. Objectives: To investigate if baseline mild behavioral impairment (MBI) status used for NPS quantification along with brain morphology features are predictive of follow-up diagnosis, median 40 months later in patients with normal cognition (NC) or MCI. Method: Baseline neuroimaging, neuropsychiatric, and clinical data from 102 individuals with NC and 239 with MCI were extracted from the Alzheimer's Disease Neuroimaging Initiative database. Neuropsychiatric inventory questionnaire items were transformed to MBI domains using a published algorithm. Diagnosis at latest follow-up was used as the outcome variable and ground truth classification. A logistic model tree classifier combined with information gain feature selection was trained to predict follow-up diagnosis. Results: In the binary classification (NC versus MCI/AD), the optimal ML model required only two features from over 200, MBI total score and left hippocampal volume. These features correctly classified participants as remaining normal or developing cognitive impairment with 84.4% accuracy (area under the receiver operating characteristics curve [ROC-AUC] = 0.86). Seven features were selected for the three-class model (NC versus MCI versus dementia) achieving an accuracy of 58.8% (ROC-AUC=0.73).

Mild behavioral impairment is related to frailty in non-dementia older adults: a cross-sectional study

“…MBI has also been used in machine learning models to predict neurocognitive diagnostic category 40 months later (36). These ndings suggested that the early recognition of the NPS that constitute MBI may contribute to earlier detection of neurodegeneration, and may represent a clinical entity and premorbid treatment target to explore for intervention strategies to prevent or delay the onset of dementia (37).…”

Neural Correlates of the Impulse Dyscontrol Domain of Mild Behavioral Impairment

“…Future studies that use MBI-C should further investigate the neural correlates associated with MBI impulse dyscontrol and other domains to verify our results. Additionally, ADNI excludes patients with psychiatric illness (some of which may actually be prodromal dementia symptoms) (20) or those with severe NPS. Thus, the sample included in this study might underappreciate the extent of NPS in the preclinical and prodromal population.…”

“…Mild behavioral impairment (MBI) is a validated neurobehavioral syndrome that describes the later life emergence of persistent NPS as an atrisk state for incident cognitive decline and dementia (11). These NPS have been suggested to be an index manifestation of dementia for some (12)(13)(14)(15)(16)(17)(18)(19)(20). MBI captures preclinical and prodromal disease symptoms and is associated with known dementia biomarkers including amyloid- (21), tau (22,23), neuro lament light (24), brain atrophy (25,26), and AD risk genes (27,28).…”

Risk Score Stratification of Alzheimer’s Disease and Mild Cognitive Impairment using Deep Learning

“…A large array of neurocognitive tests are currently used to detect cognitive impairment and classify amongst normal controls (CN), EMCI, LMCI and AD [7][8]. Many studies have identified a few top classifiers using logistic regression and machine learning methods [9][10][11][12][13][14][15][16][17][18]. Some studies have also used MRI and genetic data in conjunction with neurocognitive measures for classification [19][20].…”