Related Experiment Video
Updated: Jun 11, 2026
09:47
DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
Published on: December 15, 2023
Machine learning for Alzheimer's disease progression under extreme class imbalance
Patrick O Akinwumi1, Meihua Qian1, Taiwo A Olorunsogbon2
1College of Education, Clemson University, Clemson, SC, United States.
Frontiers in Neuroscience
|June 10, 2026
Summary
Predicting Alzheimer's disease (AD) progression using accessible data shows limited but measurable signal. Machine learning models offer a proof-of-concept for short-term risk assessment, but require external validation for clinical use.
Area of Science:
- Neuroscience
- Biomedical Informatics
- Machine Learning
Background:
- Alzheimer's disease (AD) progression prediction is clinically challenging.
- Traditional methods lack prognostic insight; ML models often require costly biomarkers or are uninterpretable.
- This study explores using accessible demographic, clinical, and cognitive data for AD progression prediction with interpretable ML.
Purpose of the Study:
- To evaluate the efficacy of baseline demographic, clinical, and cognitive measures in predicting short-term Alzheimer's disease progression.
- To apply interpretable machine learning methods to address extreme class imbalance in AD progression prediction.
- To assess the clinical scalability and utility of predictive models based on widely available data.
Main Methods:
- Analysis of 3,240 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) with 24-month follow-up.
- Training XGBoost and logistic regression models on baseline data under natural class imbalance.
- Performance evaluation using AUROC, AUPRC, calibration, and SHAP for feature importance. Sensitivity analyses included cost-sensitive learning and imputation strategies.
Main Results:
- XGBoost achieved an AUROC of 0.912 and AUPRC of 0.051; logistic regression achieved AUROC of 0.787 and AUPRC of 0.038.
- Despite exceeding baseline prevalence, precision was low, and threshold optimization led to high false-positive rates.
- SHAP analysis identified cognitive severity, functional measures, and diagnostic status as key predictors. Significant cognitive decline was confirmed over time.
Conclusions:
- Accessible baseline data provide a limited but measurable signal for short-term AD progression prediction.
- Current models serve as an early-stage proof-of-concept, not a deployable clinical tool, due to low precision and high false-positive rates.
- External validation is crucial before clinical translation of these predictive models.
Related Concept Videos
01:29Alzheimer Disease l: Introduction
Alzheimer disease is a chronic, progressive, and irreversible neurodegenerative disorder and the most common cause of dementia in older adults. It leads to gradual neuronal loss, causing cognitive decline, behavioral changes, and loss of functional independence.Risk Factors and EtiologyThe disease is multifactorial. Age is the strongest risk factor, with prevalence doubling every 5 years after age 65. Genetic factors include mutations in genes such as APP, PSEN1, and PSEN2, which are associated...
01:22Alzheimer's Disease: Treatment
Alzheimer's Disease (AD), a neurodegenerative disorder, is pathologically identified by amyloid plaques and neurofibrillary tangles composed of tau protein. AD pharmacotherapy aims to manage cognitive symptoms, delay disease progression, and treat behavioral symptoms. The treatment is primarily symptomatic and palliative, with no definitive disease-modifying therapy available. Cholinesterase inhibitors, including donepezil (Aricept), rivastigmine (Exelon), and galantamine (Razadyne), are...
01:26Alzheimer's Disease: Overview
Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...
01:23Alzheimer Disease ll: Pathophysiology
Alzheimer disease involves structural changes in the brain that begin long before symptoms appear. The most distinctive features are extracellular neuritic plaques and intracellular neurofibrillary tangles.Neuritic plaques form in the cerebral cortex and around blood vessels. These plaques contain a dense core of beta-amyloid (Aβ)—a toxic protein fragment that clumps outside neurons. The core is surrounded by damaged neuronal extensions, as well as reactive astrocytes and microglia. Abnormal...
01:22Dementia l: Introduction
Dementia is an acquired, progressive syndrome characterized by a decline in multiple cognitive domains severe enough to impair daily functioning and reduce independence. Although memory loss is a central feature, the diagnosis requires additional deficits involving language, executive function, visuospatial skills, judgment, calculation, or abstract reasoning. These cognitive impairments reflect underlying neurodegenerative or vascular processes that gradually disrupt neuronal networks...