Predicting the Future: Using Machine Learning to Forecast the Progression of Alzheimer's Disease
CSEF · 2018 Mathematical Sciences Third Award
Overview
Objectives/Goals Alzheimer's disease (AD) is the most common neurodegenerative disease in older people. Despite considerable efforts to find a cure for AD, there is a 99.6% failure rate of clinical trials for AD drugs, likely because AD patients cannot easily be identified at early stages. AD research would benefit from the ability to use current patient data to predict the clinical state of patients in future years. This project investigated machine learning approaches to enable such predictions. Methods/Materials Clinical data from 1737 patients was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and was preprocessed using a novel methodology involving the comparison of all possible pairs of temporal data points for each patient. This data was then used to train machine learning models implemented with the Python library scikit-learn. Models were first evaluated using k-fold cross-validation on the training dataset, and then confirmed using data from a separate testing dataset (110 patients). Results Several machine learning-based classifiers, including support vector machines and neural networks, were effective (86.6% MAUC score) at predicting the progression of AD, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment. Conclusions/Discussion This project developed a machine learning model that can correlate clinical data obtained from patients at one time point with the month-by-month progression of AD in the future. Such a model could be used to identify patients having high AD risk before they become symptomatic and who are therefore good candidates for clinical trials for AD therapeutics.
Summary statement
I developed a machine learning model and novel preprocessing technique that uses clinical data to identify patients at risk for Alzheimer's disease and predict the future progression of their clinical diagnoses on a month-by-month basis.
Help received
I received guidance from my computer science teacher Jen Selby and my science teacher Rachel Dragos. I also received feedback on my machine learning model from Alex Abbas, a bioinformatics researcher at Genentech, and Lisa Bell, a regulatory consultant experienced in neurological disease clinical trials.
Awards (1)
Competition history
- CSEF 2018
Resources
Related projects
ISEF · 2018
Alzheimer's Disease Prediction
CSEF · 2018
Early Classification of Alzheimer's Disease Using Machine Learning
ISEF · 2020
Developing a Pre-Risk Assessment Incorporating Machine-Learning and Biomarkers to Diagnose Alzheimer's Disease
CSEF · 2019
Implementation and Validation of a Machine Learning Model for the Early Detection of Alzheimer's Disease
ISEF · 2018
Early Diagnosis of Alzheimer's Disease Using Machine Learning
AJAS · 2019
Early Diagnosis of Alzheimer's Disease Using Deep Feedforward Neural Networks
CSEF · 2017
ALZCan: Machine Learning Based Multimodal Neuroimaging Genetics Framework to Predict Future Onset of Alzheimer's Disease
CSEF · 2015
ALZCan: Predicting Future Onset of Alzheimer's Using Gender, Genetics, Cognitive Tests, CSF Biomarkers, and Neuroimaging
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects