Integration of ML and IoT for Healthcare Systems

Introduction

Machine learning (ML) methods in healthcare use the increasing volume of health data carried by the Internet of Things (IOTs) for the improvement of patient outcomes. These methods provide auspicious applications as well as major challenges. More recently, IOTs and ML have joined to make several of things. IoT was firstly recommended to use radio frequency identification (RFID) systems to incorporate known objects and their electronic images into web architectures (Birje & Hanji, 2020; Lashkari et al., 2018; Liu et al., 2018). Ultimately, the IoT came in the form of sensors, GPS application, and mobile for health care domain (Dehkordi et al., 2020; Qi et al., 2017; Rodríguez-Mazahua et al., 2016). The endless integration in the global world and the supporting devices of these sensors has led to a number of discovery problems, from basic knowledge to processing and execution. In a transmission of wireless information, various appliances have been implemented. Regardless the ML-IoT in healthcare, there are challenge in about data security (Lee et al., 2018; Shahbazi & Byun, 2020). Accordingly, various studies have measured the integration of IoT -ML for checking patients with various medical disorders as a measure of data security. Today, IoT innovation has made rapid strides in multidisciplinary research (Kononenko, 2001; Yadav & Jadhav, 2019) in a myriad of scientific and mechanical controls, especially in medical services (Yadav & Jadhav, 2019). Multiobjective optimsation based research are an vital and effective methods for managing a health care problems. The article by (Fathollahi-Fard et al., 2021; Sharma & Yoon, 2018; Sharma & Yoon, 2019; Sharma & Yoon, 2021), in which used queuing theory based on multiobjective optimsation to examine waiting times and reservations in hospital outpatient departments.

Figure 1.

Application of ML in hospitals (Bote-Curiel et al., 2019)

Therefore, the combination of IoT technology and ML in healthcare development is now being shifted from the hospital to the home, as well as for routine medical testing for doctors and patients using medical devices. Thus by applying this technology we maintain the care for patients easier, especially in times of crisis. Furthermore, hospitals can ease the burden by moving some activities to the home environment (Otoom et al., 2015). Cost saving is one of the main benefits, patients can avoid hospital costs when they visit the doctor. Other limitations include the limitations of the existing network infrastructure incapable of handling sensitive applications in real time using IoT, so software-defined networks require a network infrastructure suitable for such applications (Aghdam et al., 2020; Evtodieva et al., 2020) Pharmacy containers can be used to increase the usability of the device through Android programs. IoT will improve people's lives. Aziz and Islam, 2020 Atiqur et al implemented an integrated device that will lead to many positive developments in administration services, arrangements and communications. There are areas that need to be addressed (Atiqur et al., 2020; Aziz & Islam, 2020; Ghose et al., 2014).

Different ways ML and IoT that change management in hospitals. Fig 1 show different application of ML in different field. Hospitals have vast amounts of data. Patient monitors record information such as heart beat rate, blood pressure, while doctors and specialists produce visual data in the form of MRI and CT scans report (Al-Fuqaha et al., 2015; Cook, 2006). All of this data can be hugely appreciated — but only if system of government access it at the exact time and have the tools to analyze it in a crisis.