A Methodology for Applying Machine Learning Algorithms in the Medical Industry

Computer Engineering

In our day-to-day life, we use lots of machine learning (ML) techniques and applications for farming, Medical care, Products Recommendations, stock marketing, Social Media (Facebook, LinkedIn), Traffic flow Alerts (Maps), Transportation, and Commuting (Uber, OLA), etc. Machine learning is a type of learning in which the machine learns by itself without explicitly programmed it. This is the type of application of artificial intelligence that provides the facility with the facility to spontaneously learn and develop from their understanding. This research paper discusses the potential of applying machine learning skills in the medical sector. ML is organized in mainly four learning forms. Supervised learning contains labeled information when unsupervised learning contains unlabelled data. Semi-supervised learning is a combination of supervised and unsupervised learning. Reinforcement learning is a type of learning method that works together with its environment by generating actions and at the same stage determining errors and rewards. Trial & error search and delayed reward are all the most relevant features of reinforcement learning. ML is utilized in the healthcare sector like robotic surgery, Health Imaging Analysis, Sharing Patient Data, Drug Discovery, and Medical Imaging Diagnosis. Here we are studying in brief with several techniques and checking which algorithm is more accurate with less time consumption. This research paper summarizes some machine learning techniques such as K-nearest neighbor, support vector machine, random forest, a decision tree for disease prediction and disease detection. This work supports the dropping research gap between machine learning and the medical sector.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.