Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare

Abstract

Artificial intelligence (AI) is a modern approach based on computer science that develops programs and algorithms to make devices intelligent and efficient for performing tasks that usually require skilled human intelligence. AI involves various subsets, including machine learning (ML), deep learning (DL), conventional neural networks, fuzzy logic, and speech recognition, with unique capabilities and functionalities that can improve the performances of modern medical sciences. Such intelligent systems simplify human intervention in clinical diagnosis, medical imaging, and decision-making ability. In the same era, the Internet of Medical Things (IoMT) emerges as a next-generation bio-analytical tool that combines network-linked biomedical devices with a software application for advancing human health. In this review, we discuss the importance of AI in improving the capabilities of IoMT and point-of-care (POC) devices used in advanced healthcare sectors such as cardiac measurement, cancer diagnosis, and diabetes management. The role of AI in supporting advanced robotic surgeries developed for advanced biomedical applications is also discussed in this article. The position and importance of AI in improving the functionality, detection accuracy, decision-making ability of IoMT devices, and evaluation of associated risks assessment is discussed carefully and critically in this review. This review also encompasses the technological and engineering challenges and prospects for AI-based cloud-integrated personalized IoMT devices for designing efficient POC biomedical systems suitable for next-generation intelligent healthcare.

Keywords: Internet of Medical Things; artificial intelligence; healthcare; point-of-care sensors; smart sensors; wearable devices.

Figure 1

Schematic representation of IoMT devices and cloud data transfer. Body sensors are those that are directly attached to the body, embedded in fabric, or implanted into the human body. Smart sensing technology is used to analyze the collected data and transfer it to the cloud. The cloud serves as a bridge between body sensors and the recipient of the output.

Figure 2

Schematic representation of relation between AI, ML, and DL (A); classification of ML algorithm (B).

Figure 3

Use of various AI methods in medical applications.

Figure 4

Schematic representation of the role of AI-based approaches in various themes of healthcare research, including cardiac monitoring, surgery, cancer theragnostic, and diabetes mellitus management.

Figure 5

Mxene as a breathable and biodegradable material for developing E-skin-based pressure sensors (A) [63]. Utilizing the HET and high surface area of Mxene for developing second-generation glucose-monitoring devices (B) [64]. (Reproduced with permission from the American Chemical Society).

Figure 6

Interfacing interconnection of 1D graphene nanoribbons with 2D Mxene for developing pressure sensors trained using a machine learning algorithm. (Reproduced with permission from the American Chemical Society [66]).

Figure 7

ML-assisted quantitative analysis of optical spectra of gold nanoparticles (Reproduced with permission from the American Chemical Society) [87].

Figure 8

Role of AI/ML in cardiology. The biomedical data collected through cardiac electrophysiology measurement are interpreted through either traditional or modern ML algorithms for advancing the health outcome.

Figure 9

Role of AI in surgery. Framework integrating AI in spinal surgeries, which involves raw data acquisition to convert the inputs into digitalized form and pre-processing methods for machine learning such as metric extraction to train the ML and metric selection to differentiate between two groups. The optimum algorithm is selected based on the input, and then the output is generated.

Figure 10

(A) Schematic representation of the methodology used for skin diagnosing. (B) Representation of matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectroscopy.

Figure 11

Representation of artificial neural network using patient data to identify the correct treatment plan.

Figure 12

Concept of personalized nutrition measurement system. (A) Monitoring food intake (a) and ingestion behavior (b). Wearable sensing of metabolites in human biofluid (c). (B) Schematic representation of comprehensive nutrient-monitoring system for simultaneous monitoring of nutrients present in the food and metabolites in humans. (Reproduced with permissions from the American Chemical Society) [118].

Figure 13

Role of AI/ML in advancing the performance of biosensor systems. (Reproduced with permission from the American Chemical Society) [125].