APPLICATION OF DEEP LEARNING IN HEALTH INFORMATICS: A REVIEW

Abstract

- Today a variety of health care practices have been evolved to maintain and restore health by the latest prevention and best treatment. This implements biomedical sciences, biomedical research, genetics and medical technology to diagnose, treat, and prevent injury and disease, typically through pharmaceuticals or surgery, therapies as divers as psychotherapy, external splints and traction, medical devices, biologics, and ionizing radiation. With advances in technology, the health sciences are constantly pushing toward more effective treatments and cures. With a massive influx of multimodality data, the role of data analytics in health informatics has grown rapidly in the last decade. This has also provoked increasing interests in the generation of analytical, data driven models based on machine learning in health informatics. Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reform the future of artificial intelligence. Rapid improvements in computational power, fast data storage, and parallelization have also contributed to the rapid uptake of the technology in addition to its predictive power and ability to generate automatically optimized high-level features and semantic interpretation from the input data. This paper presents a comprehensive review of research employing deep learning in health informatics, providing a critical analysis of the relative merit, and potential pitfalls of the technique as well as its future outlook. The paper mainly focuses on key applications of deep learning in the fields of translational bioinformatics, medical imaging, pervasive sensing, medical informatics, and public health. Finally the limitations and challenges of deep learning in the field of health informatics have been discussed.