Disease detection is an emerging research area in the field of health informatics. Disease detection aims to detect potential health disorders for providing effective treatment. The goal of disease detection is early detection and surveillance to reduce disease risk. A common challenge in medical data for disease detection is the presence of missing values. Some methods eliminate such missing values, which may contain useful factors to detect the disorder. Missing value imputation is the method to handle missing values by replacing missing data with substituted values. A deep neural network for missing value imputation possesses the ability to capture complex data patterns, which consist of both linear and nonlinear data.
   Deep learning techniques for missing data imputation in medical datasets reconstruct appropriate missing values, even when in the presence of a high degree of missing data, and estimate missing values for large datasets. Missing value imputation in disease detection utilizes an artificial neural network to impute the missing data with high accuracy from large datasets while maintaining the characteristics and representativeness of the data’s original distribution.