JMIR Publications

ABSTRACT

Background:

Type 2 Diabetes (T2D) has an immense disease burden, affecting millions of people worldwide and costing billions of dollars in treatment. As T2D is a multifactorial disease with both genetic and non-genetic influences, accurate risk assessments for patients are difficult to do. Machine learning has served as a useful tool in T2D risk prediction as it can analyze and detect patterns in large and complex datasets like that of RNA sequencing. However, before machine learning can be implemented, feature selection is a necessary step to reduce the dimensionality in high dimensional data and optimize modeling results. Different combinations of feature selection methods and machine learning models have been utilized in studies reporting disease predictions and classifications with high accuracy.

Objective:

The purpose of this study was to assess the use of feature selection and classification approaches that integrate different data types to predict weight loss for prevention of T2D.

Methods:

Participant (n=56) data (i.e., demographic and clinical factors, dietary scores, step counts, transcriptomics) was obtained from a previously completed randomized clinical trial adaptation of the Diabetes Prevention Program study. Feature selection methods were used to select for subsets of transcripts to be in classification approaches. Data types were included in different classification approaches in an additive manner to assess model performance for the prediction of weight loss.

Results:

Incorporating dietary and step count data did not improve modeling performance compared to classifiers that included only demographic and clinical data. Optimal subsets of transcripts identified through feature selection yielded higher prediction accuracy compared to when all available transcripts were included. After comparison of different feature selection methods and classifiers, DESeq2 as a feature selection method and an extra-tree classifier with and without ensemble learning provided the most optimal results as defined by difference in training and testing accuracy, cross validated area under the curve, and others. We identified 5 genes identified in two or more of the feature selection selected subsets (i.e., CDIPT, MRC2, PATL2, RFXANK, SUMO3).

Conclusions:

Our results suggest that inclusion of transcriptomic data in classification approaches for prediction has the potential to improve weight loss prediction models. Identification of which individuals are likely to respond to interventions for weight loss may help to prevent incident type 2 diabetes. Out of the 5 genes identified as optimal predictors, three (i.e., CDIPT, MRC2, and SUMO3) have been previously associated with type 2 diabetes or obesity. Clinical Trial: ClinicalTrials.gov NCT02278939