The recent research used a machine learning model, namely the Pandemic Electricity Consumption Scenario (PECS) model, for the prediction of energy usage in India. This model was used to effectively analyze and measure the impact of the pandemic on electricity consumption based on weather, econometrics, and social distancing in seven major states in India. The machine learning model predicted a 15 to 33% drop in consumption from March to May in 2020 during the complete lockdown period, and a 6 to 13% drop from June to August 2020 during the unlocked period, returning to normal in September 2020. The analysis also showed a drop in CO2 emissions of between 7 and 5% compared to previous years. This prediction can be used in future energy policy decisions [159]. A similar study was conducted in China using a comparative regressive and neural network model to identify the impact of the pandemic on electricity and petroleum demand. The model showed a downtrend in the demand for fuel consumption [160].

The search engines for the extraction of COVID-19-oriented publications from servers are more important for researchers. A powerful language model, BERT, is used by Google for extracting data [161]. A CORD-19 search and COVID-19 research explorer information retrieval (IR) system were analyzed for the study. CORD-19 was subjected to a language processing service, in Amazon Comprehend Medical (ACM), which is a natural language processing (NLP) service for extracting clinical data from unstructured text [161].

The machine learning model of the pandemic oil demand analysis (PODA) predicted gasoline consumption in the USA. Since the oil price went negative due to the pandemic, the predictions were made based on public travel, their trip activities, and fuel usage. Later on, in October 2020, the prices gradually recovered, so this model predicts the demand for oil and its impact for a shorter duration [162].

Recent digital technologies were implemented in cardiology-based devices to collect and observe data. Machine learning (ML) was used to study large datasets from hospitals for clinical practice, and this was further used to identify complex heart problems and treatment strategies for COVID-19 patients [38]. There are various ML algorithms used to screen the structured data in hospitals, such as ensemble, support vector machine (SVM), hierarchical clustering, and topological data analysis, and for unstructured data, convolutional neural network (CNN), deep neural network (DNN), AdaBoost, and long short-time memory (LSTM). A DL model was proposed to identify which patient may receive more of a benefit from surgery in treating epilepsy [39]. AI assists in providing a strategic execution picture in operating theater surgeries by lowering risk and ensuring surgical success [163]. Cardiothoracic surgery, a fine example of AI-supported cognitive augmentation, requires a combination of a doctor team, highly advanced equipment, and special care [163].

The value of telemonitoring should be taken into account in the care and monitoring of patients in hospitals, and even in outlying areas nowadays. Various portable devices, such as a blood pressure cuff, glucometer, pulse oximeter, ECG + stethoscope, activity trackers, wearables, thermometer, etc., are now used by patients even at home. Aysha Shabbir et al. (2022) proposed an improved model for remotely monitoring a patient’s condition and to make decisions based on that condition using ML and DL models. In this process, the remote monitoring station’s patient monitoring device sends signals about higher and lower thresholds via the Internet using Cloud computing and IoT servers, which are relayed to a healthcare specialist. Later, primary/secondary care requirements are decided by specialists based on severity. This was framed by a pattern of sensing, transmission of data, interaction with the patient, and situational response [164]. In Italy, 23.2% of the population is 65 years of age or older, making it difficult to treat them during the COVID-19 pandemic. Therefore, they proposed a connected-care solution in the context of digital health, where the citizen or patient was kept in a high-priority center and supported with various integrated organizational measures. Further, in this recent organizational model, patient clinical information was shared with different healthcare workers involved in the treatment process. For this purpose, various healthcare models were combined to support patients with chronic illnesses. A remote/home healthcare Resilia app, a simple mobile phone application, was introduced by Italy healthcare, and guides users to identify nursing care, doctors, and other healthcare professionals for a quick response [165]. The northwest Tuscany region of Italy consists of local health units that have introduced territorial telemonitoring of chronic patients (Tel.Te.C.): telemedicine mobile applications since 2017. Both the patient and the healthcare professional receive a home monitoring kit and a professional monitoring kit, from which vital parameters such as temperature, heart rate, oxygen saturation, blood pressure, and weight can be measured; any parameter that is out of range raises an alarm for immediate action. Under compulsion, this platform has been used by 40 general physicians and 180 patients since March 2020. Patients with different stages of illnesses have been enrolled in this application, which has resulted in positive feedback from patients and doctors with reduced hospitalization and no mortality [166].

Various countries understand the importance of AI-based technology and their applications in the health sector and are moving forward to bring AI under national law. A proper legal channel is suggested by different counties to justify its safety and reliability in the healthcare and clinical sectors. Similarly, the FDA approved 350 AI- and ML-based equipment for use in the healthcare in the United States of America until 2021 [167]. Similarly, various countries implemented AI/ML laws in the area of data protection, AI robotics, decision support software, diagnosis and predicting patient conditions, COVID-19 tracking apps, etc. (see Table 1).

Country	Law/Regulation	Purpose of This Law	Date Effective
USA	No Vaccine Passports Act [168]	Relaxing the restrictions of forcing vaccine certificate	4 August 2021
The Netherlands (Red Cross)	510 Data Responsibility Policy [169]	Data protection	12 November 2018
United Kingdom	Contact-tracing app (General Data Protection Regulation (UK GDPR) and Data Protection Act (DPA) 2018) [170]	Data protection and digital COVID tracking app	May 2020
European Union	General Data Protection Regulation [171]	Data protection of public and health records	27 April 2016
European Union	Medical Devices Regulations 2017/745 (MDR) [172]	Protection of patients from medical device, protection of produced data using this device	5 April 2017
European Union	The 2017/746 In Vitro Diagnostic Medical Devices Regulation (IVDR) [173]	Protection of patient health and users, quality and safety of in vitro medical devices	25 January 2022
European Union	Regulation of the European Parliament and of the council laying down harmonized rules on AI (Artificial Intelligence ACT) and amending certain union legislative acts [174]	Facilitate and creating innovation in AI, creating trusted AI applications	21 April 2021
European Union	Civil Law Rules on Robotics [175]	Implementation of AI robotics	16 February 2017
Singapore	Personal Data Protection Act 2012 [176]	Data protection	31 December 2021
Australia	Therapeutic Goods (Medical Devices) Regulations 2002 [177]	Clinical decision support software	25 February 2021
China	Notice of the State Council Issuing the New Generation of Artificial Intelligence Development Plan. State Council Document. No. 35. 2017 [178]	Healthcare and management	8 July 2017
Kingdom of Saudi Arabia	Guidance on Software as a Medical Device/SFDA MDS-G23 [179]	AI- and BigData-based medical software to diagnose and predict patient conditions	27 April 2021
Russia	Development of AI in healthcare up to 2030, approved on 10 October 2019, No. 490 [180]	Software as medical device in healthcare	10 October 2019
South Korea	Medical Devices Act No. 15945, 11 December 2018 [181]	Software as medical device in healthcare	11 December 2008
Singapore	Standalone Medical Mobile Applications (SaMD) and Qualification of Clinical Decision Support Software (CDSS) [182]	Clinical decision support software	19 July 2021
China	Cybersecurity Law of the People’s Republic of China [183]	To preserve cyberspace sovereignty and national security	7 November 2016
Malaysia	Medical Device Act 737-2012 [184]	Medical device, software regulation in healthcare	30 January 2012
Emirate of Abu Dhabi	Artificial Intelligence (AI) in the Healthcare Sector of the Emirate of Abu Dhabi, Policy/AI/0.9, Version 0.9 [185]	Health system monitors, analysis, and public health observation	30 April 2018
Canada	Digital Charter Implementation Act, 2022 (Bill C-27) [186]	Protection of personal information, data, and health records, along with any serious direct cause to patients by AI	16 June 2022
Brazil	LGPD–General Personal Data Protection Law (Federal Law no. 13,709/2018) [187]	AI regulation in health sector of Brazil	14 August 2018
Brazil	Brazilian Artificial Intelligence Bill (Bill No. 21/2020) [188]	Development and applying of AI in various sectors of Brazil	29 September 2021