Abstract:
Machine learning offers a principled approach for developing sophisticated and automatic algorithms to analyze high-dimensional and multimodal biomedical data. This study focuses on using machine learning algorithms to improve detection and diagnosis of human disease. Human disease evaluation was never been easy and still a complicated process and requires a high level of expertise. Several decision support system demonstrated promising diagnostic performances in formal evaluations but only a few have been formally evaluated in clinical environments. Stand-alone decision support systems depend heavily on a vast amount of data. This study describes a research work aiming to find out how much efficient k-means can be to build an expert system to detect human disease by evaluating symptoms data to improve the quality of health evaluation. Healthcare professionals and practitioners can also use this to corroborate diagnosis. This proposed system also evaluates its performance and effectiveness and exhibits satisfactory result.
