| Chen et al. [104] (2023) |
Information fusion and artificial intelligence |
The process of combining many information sources to produce more accurate, consistent, and dependable information to aid in making the best decisions possible is known as information fusion. |
Artificial intelligence and information fusion for smart healthcare |
Process Under observations. |
| Chatzinikolaou et al. [105] (2022) |
Data Mining and ML |
Predictive and descriptive techniques for data mining along with clinical decision support system |
Clinical decision support system based on Body area network (BAN) using wearable sensors |
Universal interoperation are still not established. |
| Balakrishnan et al. [106] (2022) |
RFID, Wireless sensor and IoT |
Radio Frequency Identification (RFID), Wireless Sensor Network, Brainsense headband and smart mobile, all with the Internet of Things (IoT) as its linking platform |
To follow the condition of the patient, Smart Healthcare Sensor (SHS) and RFID are used |
System based automated prescription can be harmful if the gadgets have a power issue. |
| Awotunde et al. [107] (2022) |
Internet of Medical Things (IoMT) and Artificial intelligence (AI) |
Proposed a framework for real-time patient diagnosis and monitoring based on ML and AI-IoMT. |
The model was put to the test using a dataset of cytology images, and its performance was assessed based on F-score, accuracy, specificity, sensitivity, and precision |
Will seriously reduce human intervention in medical practice. |
| Bahalul et al. [108] (2022) |
IoT, ML and wireless body area network |
IoT and ML based security mechanisms as countermeasures to various cyber-attacks |
Security mechanism and countermeasures |
Smart healthcare in the context of the smart city only. |
| Singh et al. [109] (2022) |
IoT, Federated Learning and blockchain technology |
Privacy preservation of IoT healthcare data using Federated Learning and blockchain technology |
Privacy preservation of data using the latest technology |
Only focuses on Data privacy. |
| Ahmed et al. [110] (2022) |
Explainable Artificial Intelligence |
Artificial Intelligence for sustainable smart healthcare |
Explainable artificial intelligence in smart healthcare |
Sustainable development only. |
| Verma et al. [111] (2022) |
Internet of Things, ML and Artificial Intelligence |
Continuous information exchange and physiological data replacement using Internet of Things, ML, and artificial intelligence technologies |
Smart Healthcare Cyber-Physical Systems (SHCPS) are the systems of the future that can help the medical community deal with pandemic situations successfully |
Universal acceptability and reliability are the main drawbacks. |
| Rahman et al. [112] (2022) |
Federated Learning (FL), Artificial Intelligence (AI), and Explainable Artificial Intelligence (XAI) |
The combination of FL, AI, and XAI approaches may be able to reduce a number of systemic constraints and difficulties |
The current issues, such as security, privacy, stability, and dependability, may be handled by combining and classifying FL-AI with healthcare technologies |
Healthcare is not limited to only AI and FL techniques. |
| Dwivedi et al. [113] (2022) |
IoMT, ML, Previous data |
Robots, sensors, telemedicine, remote monitoring, and other related technologies have all assisted in solving a variety of issues with IoMT. |
IoMT-based smart gadgets are becoming more and more prevalent, especially in the wake of the worldwide pandemic, and healthcare is no longer solely reliant on these methods |
These procedures are not the only ones used in healthcare. |
| Ghosh et al. [114] (2022) |
Statistical and deep learning-based feature analysis with ML |
Used facial pain expression databases along with cutting edge techniques during experimentation |
Smart sentiment analysis system for pain detection |
Medical science is not limited to pain expression only, it needs to address many more fields. |
| Javaid et al. [43] (2022) |
ML and Artificial Intelligence |
ML-based techniques assist in detecting early indicators of an epidemic or pandemic |
In order to determine if the illness may spiral out of control, the system employs ML to examine satellite data, news and social media reports, and even video sources. |
Treatment using previous data is not always enough. |
| Kondaka et al. [115] (2022) |
ML, iCloud Assisted Intensive Deep Learning (iCAIDL) |
By bridging between IoT and cloud computing it generates iCAIDL |
An intensive healthcare monitoring paradigm by using IoT based ML concepts |
Universal operation of this method is not accepted. |
| Unal et al. [116] (2022) |
IoMT, ML and security |
Wireless communications, wearable devices, and big data enables continuous supervision of a patient's medical indicators |
Continuous monitoring of a patient's medical indicators is made possible by an e-healthcare system, making routine patient follow-ups easier and boosting human productivity |
Need to address more medical issues. |
| Verma et al. [117] (2022) |
ML |
CNN, Random Forest, Artificial Neural Network (ANN),logistic regression, and Support Vector Machine (SVM) |
Review several ML algorithms, applications, techniques, opportunities, and challenges for the healthcare sector |
Critical healthcare problem solutions haven't proposed yet. |
| Kumari et al. [118] (2022) |
ML and IoT |
Deployment of ML Based Internet of Things Networks for Tele-Medical and Remote Healthcare |
This study offers a thorough collection of IoT- and ML-based treatments for patients and telemedicine. |
Usable for remote treatment only. |
| Rehman et al. [119] (2022) |
ML, Federated ML and blockchain |
Blockchain technology entangled with federated learning technique |
RTS-DELM-based secure healthcare 5.0 system |
Estimation of intrusion detection. |
| Kute et al. [120] (2022) |
IoT and ML |
Application availability, information management, storage, and storage integrity, authentication, trust, and confidentiality |
E-healthcare based on the internet of things and ML faces, privacy, security, and trust challenges. |
Need to address more scope and solutions. |
| Talaat et al. [121] (2022) |
IoT and ML with EPRAM and Fog computing |
Prediction algorithm with fog computing for smart healthcare |
EPRAM uses a real-time resource allocation and prediction system to try to manage resources effectively in a foggy environment |
Automated prescription systems need to be incorporated. |
| Swain et al. [122] (2022) |
Deep learning, ML and H-ToT |
Information collected through healthcare-IoT devices and then DL and ML are applied on them |
The majority of the statistical ML (ML) frameworks that are optimized and drive better clinical service delivery are covered in this study. |
No measurement of accuracy. |
| Shakila et al. [123] (2022) |
Nature-inspired algorithm, ML |
Used Nature-inspired algorithm for feature subset selection and ML for PD classification |
Presented a comprehensive analysis of feature selection algorithms and ML models for Parkinson disease diagnosis |
Only experimented with ML, DL could be used |
| Mohanty et al. [124] (2021) |
Decision tree, ML, and Random forest |
Supervised ML, SVM, Artificial Neural Network, Decision Tree, K-Nearest Neighbor, Random Forest, and Logistic Regression and “Pima Indians (PIDD) dataset” |
Utilize historical data analysis to forecast the development of chronic diabetes by handling patients with care. |
Universal interoperation is still not established. |
