Blueprinting the Workflow of Medical Diagnosis through the Lens of Machine Learning Perspective

Abstract

The association of machine learning into medical data and healthcare communities embraces substantial improvement in both health care and machine learning itself. Many companies are racing to integrate machine learning into medical diagnosis process that boosts the automatic medical decision, reducing the inferior effects of data overload and increasing the accurate prediction and time effectiveness. It is one of today's most rapidly growing technical fields, lying at the intersection between health care and computer science in general. Thus, there is an urgent need to optimize medical processes, guidelines and workflows to increase the workload capacity while reducing costs and improving efficiencies. Moreover, no medical doctor or experts can manually keep pace today due to increasingly large and complex datasets. In this paper, the authors aim at addressing the mentioned issue by proposing a workflow of medical diagnosis through the lens of the machine learning perspective. An intensive comparison has been conducted applying 5 well-known machine learning algorithms on 8 real-world categorized datasets. A mobile application has been also deployed to enhance the incorporation from hospital experts.

Ähnliche Arbeiten