ABSTRACT
In the realm of computational intelligence, various nature-inspired computational methodologies are being used. To solve real-world problems, artificial neural networks (ANNs), swarm intelligence, and fuzzy systems are used, to name a few. In current time, we are surrounded by sensors, various machines, and electronic devices. All of these generate large quantities of data. This large volume of data has changed our lives in a variety of ways, and the field of healthcare is no exception. Clinical trials, personalized gadgets like smart watches, fit-bits, medical insurance records, hospital billing software, medical reports, genetic information, medical IOT devices, medical imaging, scholarly journals, pathology lab networks, and other sources of data generate massive amounts of information in healthcare. The amount of data being generated is increasing all the time. Recent improvements in computational intelligence techniques have enriched the importance of big data analytics, genetics & genomics, medical image processing, computer vision, Internet of Things, drug discovery, disease diagnosis, and disease prevention in the field of healthcare. The main computational intelligence techniques to address these issues will be discussed in this chapter. Healthcare is a critical industry because, in addition to money, people's lives are at risk. As a result, the approaches and models employed must be extremely accurate and efficient. The effectiveness of a machine learning model is determined by the quality of data provided to it during the learning phase. Data errors, such as missing data and unbalanced data, are particularly widespread in the healthcare industry. In this chapter, we'll examine feature engineering as a solution to these kinds of problems. Healthcare is projected to be significantly impacted by genetics and genomics, which will disclose new dimensions, including personalised medicine, disease prediction, and genetic engineering. This case study will be presented in this chapter.
