Can feature structure improve model's precision? A novel prediction method using artificial image and image identification.

Abstract

This study aimed to develop an approach to enhance the model precision by artificial images. Given an epidemiological study designed to predict 1 response using f features with M samples, each feature was converted into a pixel with certain value. Permutated these pixels into F orders, resulting in F distinct artificial image sample sets. Based on the experience of image recognition techniques, appropriate training images results in higher precision model. In the preliminary experiment, a binary response was predicted by 76 features, the sample set included 223 patients and 1776 healthy controls. We randomly selected 10 000 artificial sample sets to train the model. Models' performance (area under the receiver operating characteristic curve values) depicted a bell-shaped distribution. The model construction strategy developed in the research has potential to capture feature order related information and enhance model predictability.