Table 2. Related surveys on ML, DL, and smart healthcare. Within each group, the cutting-edge works are chronologically reported and grouped based on the relevant technology.

Authors	Year	Relevant Fields	Contribution and Techniques
Karim et al. [21]	2023		An brief overview of the application of ML models for fighting against flood using U-Netriver and FloodGAN techniques.
Mukerji et al. [22]	2023		An investigation on the neuropsychological characteristics of HIV-positive individuals with data-driven approach
Chen et al. [23]	2022		Study of the multiple convergence phenomenon management through machine learning having variable selection.
Halbouni et al. [24]	2022		Intrusion detection techniques are incorporated for leveraging ML models for mitigating the issues in the cybersecurity sector.
Luan et al. [25]	2021		An analysis of ML-based algorithms in the education field analyzing the algorithms, evaluation measures, and validation.
Reboredo et al. [26]	2021		The most recent developments of machine learning techniques such as NB, SVM, RF, and ANN in the pharmaceutical research.
Verbraeken et al. [27]	2020	ML/MLTechnique	Outlines the benefits and drawbacks of distributed machine learning in comparison to traditional (centralized) machine learning, as well as the techniques used to implement distributed machine learning.
Alanazi et al. [28]	2020		SIR-F and SIR models are proposed, implemented, additionally numerical along with mathematical analysis. Moreover, simulation results are presented for smart health care with the help of mathematical and numerical analyses.
Djenouri et al. [29]	2019		Survey and classification of ML applications in smart buildings to implement occupant-centric and energy centric solutions.
Narayan et al. [30]	2023		A brief explanation of techniques using deep learning to recognize human walking styles at a distance. Using the improvement of Human Gait Activity detection.
Abdusalomov et al. [31]	2023		A Deep Learning-based methodology that is used for the Improvement of forests fire detection technique.
Ibrahim et al. [32]	2022		A study on the deep learning-based techniques to classify the fruits using Convolution Neural Network (CNN)
Aqeel et al. [33]	2022	DL/DL Technique	A thorough investigation of DNA-based encryption using neural networks in the medical sector.
Ahmed et al. [34]	2021		A algorithm which is based on deep learning presents and constructs a noninvasive, automated IoT-based system for tracking and detecting patient discomfort.
Zhang et al. [35]	2021		Reviews recommended systems that use deep learning. Proposed a classification approach for grouping and organizing already-published materials.
Altaheri et al. [36]	2021		DL-based classification of MI-EEG studies from the last ten years. Here, CNN was used to classify MI.
Asraf et al. [37]	2020		Deep learning applications using several dimensions for innovative coronavirus control (COVID-19).
Rahman et al. [38]	2020		A distributed deep learning neural network-based COVID-19 management architecture was presented. Utilizes a distributed DL paradigm, in which one and all COVID-19 edge uses its own local DL framework.
Kumar et al. [39]	2023		A secure Blockchain and Deep learning based model for IoT based healthcare observing system including AutoEncoder (DSAE) with Bidirectional Long Short-Term Memory (BiLSTM).
Gnanasankaran et al. [40]	2023		Analysis NLP techniques of the growth of AI-based application of several areas of the medical field especially after the COVID-19 outbreak.
Azadi et al. [41]	2023		Using network data and deep learning involvement analysis, predicting the long-term viability of hospital distribution networks by developing a network DEA (NDEA) model.
Bhat et al. [42]	2023	Healthcare	The Impact and future opportunities of Deep Learning for Medical sector research areas.
Javaid et al. [43]	2022		Machine learning's relevance in healthcare system an analysis of the characteristics, tenets, and potential by applying sophisticated predictive analytics
Abdullah et al. [44]	2022		A Survey of Probabilistic Deep Learning's Solutions and Constraints in Healthcare
Futoma et al. [45]	2020		Machine Learning and the fallacy of adaptability in medical studies
Wiens et al. [46]	2019		A guide to ethical machine learning in the medical field.
Periyasamy et al. [47]	2023		A research employing predictive modelling techniques to examine the effects of Singapore's elderly population on its medical system includes ANOVA and Correlation.
Patil et al. [48]	2023		This study provides a compressed overview of the application of ML models in the medical arena.
McCoy et al. [49]	2022		To investigate explainability's function in the application of machine learning for healthcare, as well as the requirement and importance of this function for the proper and moral deployment of MLHC.
Sabry et al. [50]	2022	ML-Healthcare	This article presents a survey of the many areas of contemporary automated learning development for wearable medical devices. The difficulties that various gadgets with autonomous learning algorithms face are highlighted using GAN.
Zhang et al. [51]	2022		Deep generative models and federated learning are used in this study as methods to enrich datasets for improved model performance. More advanced transformer algorithms are also used to enhance the simulation of clinical language.
Siddique et al. [52]	2021		This work emphasizes how the use of Machine Learning (ML) in medical communication may help people. The COVID-19 health awareness campaign, treatment for cancer, and imaging-related chatbots are included in this.
Chen et al. [53]	2021		The ethical part of the medical sector leveraging machine learning approach here a finite sequence of well-defined instructions and an algorithm is used.
Souri et al. [54]	2020		A novel machine learning-powered surveillance system for medical that uses the IoT to assess the illnesses of students with SVM.
Mageshkumar et al. [55]	2023		Automated Collection Reuse for Cloud-Based Medical System with Neural Machine Learning Enabled Categorization Model
Dhar et al. [56]	2023		Clinical vision assessment with deep learning issues, increasing explicitness and Reliability
Narayan et al. [57]	2023		A strategy based on real-time health data to improve the effectiveness of deep learning models
Jujjavarapu et al. [58]	2023	DL-Healthcare	Combining heterogeneous deep neural networks with patients' both organized and unorganized health data to predict the need for decompression therapy using classical and generalizability evaluation of DL
Buddenkotte et al. [59]	2023		An efficient model for ovarian cancer by leveraging deep learning methods with well-established “no-new-Net” (nnU-Net) framework.
Rajan et al. [60]	2022		An accurate signal prediction and estimate technique based on Deep Neural Networks was utilized in an advanced learning-based smart-monitor and patient monitoring system for Internet of Things-based medical infrastructure.
Jin et al. [61]	2022		Explainable DL model for a healthcare system with the help of data-driven technologies.
Vinod et al. [62]	2023		Analyzed the application of AI and ML based model for restricting the spread of COVID-19 with AI-driven techniques with performance metrics.
Zohuri et al. [63]	2023		Machine learning and deep learning components powered by artificial intelligence for robustness in the fields of medicine, advertising, homeland security, and other areas with the concept of Big Data solutions.
Hassan et al. [64]	2023		Recent trends, services, and consequences of AI and ML in the forecasting of postoperative risks with the help of AI algorithms.
Jenkins et al. [65]	2022		Medical facilities based on the Internet of Things, portable clinical sensory equipment, and machine and deep learning algorithms for COVID-19 patient examination, diagnosis, tracking, along with therapy.
Saravi et al. [66]	2022	ML-DL-Healthcare	Utilizing mixed ML models for decision-making and artificial intelligence-driven prediction modeling in the field of spine surgery using CNN.
Bahrami et al. [67]	2022		An in-depth examination of ML and DL algorithms for single-lead Electrocardiogram sleep disorder screening. The authors focused on deep CN such as VGG16, ZF-Net and AlexNet, Recurrent network, and also hybrid deep NN.
Stone et al. [68]	2022		COVID-19 Remote Patient Tracking Using ML and DL Techniques with sensor networks for the human body and IoT.
Afshar et al. [69]	2021		Datasets from computerized tomographic scans (COVID-CT-MD and COVID-19) useful for ML and DL. In this work, the images were reproduced by using the filtered backpropagation method.