Robust Discovery of Mild Cognitive impairment subtypes and their Risk of Alzheimer's Disease conversion using unsupervised machine learning and Gaussian Mixture Modeling

Background: Alzheimers disease (AD) is an irreversible, progressive brain disorder that slowly destroys memory and thinking skills. The ability to correctly predict the diagnosis of Alzheimers disease in its earliest stages can help physicians make more informed clinical decisions on therapy plans. Objective: To determine whether the unsupervised discovering of latent classes of subjects with mild cognitive impairment (MCI) may be useful in finding different prodromal AD stages and/or subjects that have a low MCI to AD conversion risk. Methods: 18 features relevant with the MCI to AD conversion process described 681 subjects with early MCI. Subjects were split into training (70%) and validation (30%) sets. Subjects from the training set were analyzed using consensus clustering and Gaussian mixture models (GMM) were used to describe the shape of the discovered latent classes. The discovered GMM predicted the latent class of the validation set. Finally, descriptive statistics, rates of conversion, and odds ratios (OR) were computed for each discovered class. Results: Through consensus clustering we discovered three different clusters among MCI subjects. The three clusters were associated with low-risk (OR = 0.12, 95%CI = 0.04 to 0.3|), medium-risk (OR = 1.33, 95%CI = 0.75 to 2.37), and high-risk (OR = 3.02, 95%CI = 1.64 to 5.57) of converting from MCI to AD, with the high-risk and low-risk groups highly contrasting. Hence, prodromal AD subjects were present on only two clusters. Conclusion: We successfully discovered three different latent classes among MCI subjects with varied risk of MCI-to-AD conversion through consensus clustering. Two of the discovered classes may represent two different prodromal presentations of the Alzheimers disease.