Recently, disease prediction using diagnostic reports and images are one of the most popular applications of artificial intelligence (AI) and machine learning (ML). Several authors reported significant results in this area by combining cutting-edge hardware with AI and ML-based technologies. In this chapter, the authors present a review of different works carried for the prediction of several chronic diseases by researchers in last five years. Reported AI and ML based methodologies have been used to forecast chronic disease such as heart problems, brain tumors, asthma, diabetes, cholera, arthritis, liver diseases, kidney diseases, malaria, and leukemia. In the literature, the authors also discuss the different user interfaces which have been used to interact with real time AI and ML based disease prediction models. The authors have presented the detailed discussion of each paper including advantages, disadvantages, datasets, performance metrics such as precision, recall, accuracy and F1 score. In the final section, the survey concludes with a description of research gaps that can be addressed by future research attempts.
TopIntroduction
Many organisations have been founded around the world in this digital era to supply equipment for continuous monitoring of people's health. Patients visit the clinic, and health professionals use a traditional method to advice patients based on their knowledge of the condition (Simarjeet Kaur et al, 2020; Md Manjurul Ahsan et al, 2022; Samir Malakar et al, 2022). Traditional approaches can occasionally result in subpar patient care, which can be harmful. They are also costly. As a result, technology offers an alternative to the old system, such as the introduction of a large number of computer-assisted support systems and instruments into healthcare systems (Kaustubh Arun Bhavsar et al, 2021 ; Samir Malakar et al, 2022). This bonding thus reduced treatment costs while also enhancing patient care. In this context, it's important to note that over the past six years, data mining and machine learning (ML) techniques have gained significant popularity in healthcare and patient care systems due to the increasing accessibility of digital documents and data. According to the World Health Organization's (WHO) third worldwide research on electronic health (eHealth) published in 2016, there has been a consistent increase in the usage of electronic health records (EHR) during the last 15 years, with a global increase of 46.009% in the last five years (Samir Malakar et al 2022).
A disease is an abnormal condition that primarily impacts a portion of an organ and is unrelated to damage from the outside world. There are numerous different diseases in the field of medicine, including acute, infectious, inherited, and chronic (Igor Barone de Medeiros et al, 2017). There are around 2 million people who have been diagnosed with diseases such as heart disease, brain tumours, asthma, diabetes, cholera, arthritis, chronic liver disease, renal illness, malaria, and leukaemia. This figure is very large on a global scale, demonstrating the importance of early detection of many diseases (Md Manjurul Ahsan et al 2022; Samir Malakar et al 2022). In terms of mortality, heart disease, brain tumours, asthma, diabetes, cholera, arthritis, chronic liver disease, renal illness, malaria, and leukaemia are the major diseases. Most studies in developed countries show that the number of people affected by these diseases and dying as a result of them has increased by up to 300% in the last three decades (Samir Malakar et al 2022).
The primary goal of artificial intelligence (AI) is to create algorithms and techniques for determining system's behaviour in disease diagnosis is correct or not. Machine learning (ML) is used in practically every area, from high technology. More and more industries are using machine learning, including healthcare to diagnose diseases (Md Manjurul Ahsan et al 2022; Kaustubh Arun Bhavsar et al, 2021). The potential of automatic diagnostic system which is both time and cost-effective, has been shown by several researchers and practitioner. We give a review in this paper that highlights emerging applications of ML and DL to provide some clarity on the present trend, approaches, and difficulties associated with ML in illness diagnosis, this paper describes the evolution in this subject and provides an overview of those developments (Md Manjurul Ahsan et al 2022).
The use of chatbots to speed up doctor-patient communication for disease diagnosis has emerged as a potential avenue (Sambit Satpathy et al, 2019). Such chats are more popular as synchronous text-based discussion systems are employed for remote health interventions. The use of chatbots may be most beneficial to people with long-term illnesses since they can continually keeping an eye on their health, provide accurate, information that is current and a reminder to take medication. Chatbot technology needs sophisticated reasoning abilities based on the formalisation of medical information and patient health status, as well as language vocabularies and dialogue engines, in order to be effective in the healthcare domain (Nicholas A. I. Omoregbe et al, 2020).