Computational Intelligence and Deep Learning in Health Informatics
J. Naskath, R. Geetha Rajakumari, Hamza Aldabbas, Zaid Mustafa · 2024
The past decade has seen a significant increase in the importance of data analytics in the field of health informatics, largely due to the influx of diverse multimodal data. This has led to a growing interest in developing analytical models based on machine learning (ML) specifically tailored for health informatics. In recent years, deep learning (DL), a technique rooted in artificial neural networks, has emerged as a powerful tool in the realm of machine learning, with the potential to bring about transformative changes in the field of artificial intelligence (AI). Its capacity to automatically enhance complex high-level features and perform semantic analysis on input data is complemented by rapid advancements in computational capabilities, efficient data storage, and seamless connectivity, all of which contribute to its rising prominence. This article not only offers a comprehensive assessment of the relative advantages, potential limitations, and future possibilities of this technology but also provides a contemporary and meticulous examination of the integration of deep learning in contexts related to health. The central focus of this investigation predominantly revolves around exploring key applications of deep learning, spanning translational bioinformatics, continuous sensing, medical imaging, and public health domains.