Table 2 Extracted data
Ser | Author(s) | Purpose/ Objective | Approach | Continent | Opportunities | Conclusions |
|---|---|---|---|---|---|---|
1 | Al’Aref et al. (2019) [31] | Using the New York Percutaneous Coronary Intervention Reporting System to elucidate the determinants of in-hospital mortality in patients undergoing percutaneous coronary intervention | Quantitative | North America | 1. Accurate diagnosis 2. Improved referrals | High accuracy predictive potential for in-hospital mortality in patients undergoing percutaneous coronary intervention |
2 | Al’Aref et al. (2020) [32] | Culprit Lesion (CL) precursors among Acute Coronary Syndrome (ACS) patients based on computed tomography-based plaque characteristics | Quantitative | North America | 1. Accurate diagnosis 2. Saves time | A boosted ensemble algorithm can be used to predict culprit lesion from non-culprit lesion precursors on coronary Computed Tomography Angiography (CTA) |
3 | Aljarboa and Miah (2021) [33] | Perceptions about Clinical Decision Support Systems (CDSS) uptake among healthcare sectors | Qualitative | Asia | 1. Improved quality of care 2. Improved patient health outcomes 3. Reduced patient waiting time | Patients’ confidence and diagnostic accuracy were new determinants of CDSS acceptability that emerged in this study |
4 | Aljarboa et al. (2019) [34] | Acceptance and intention of using Clinical Decision Support Systems (CDSS) | Qualitative | Asia | 1. Improved quality of diagnosis 2. Reduction in medical errors 3. Reduced cost of care 4. Improved patient waiting time | Participants were positive that AI tools would contribute positively to patients care |
5 | Al-Zaiti et al. (2020) [35] | Machine learning-based methods for the prediction of underlying Acute Myocardial Ischemia in patients with chest pain | Quantitative | North America | 1. Improved patient outcomes 2. Prompt referrals 3. Accurate diagnosis 4. Improved workflow | Machine learning model outperformed both commercial interpretation software and experienced clinician interpretation |
6 | Alumran et al. (2020) [36] | Electronic Canadian Triage and Acute Scale (E-CTAS) utilisation in emergency department | Quantitative | Asia | 1. Very useful during emergency care 2. Improved patient health outcome | Years of nursing experience moderated the utilisation of E-CTAS |
7 | Amarbayasgalan et al. (2019) [37] | Deep learning-based model, Reconstructive Error (RE) based Deep Neural Networks (DNNs) to predict risk of developing Coronary Heart Disease (CHD) | Quantitative | Asia | 1. Improved diagnostic capacity 2. High predictive capacity | The autoencoder (AE)-DNNs outperformed regular machine learning-based classifiers for coronary heart disease risk prediction |
8 | Ayatollahi et al. (2019) [38] | Positive Predictive Value (PPV) of Cardiovascular Disease using Artificial Intelligence Neural Network (ANN) and Support Vector Machine (SVM) algorithm and their distinction in terms of predicting Cardiovascular Disease | Quantitative | Asia | Improved diagnosis | The SVM algorithm presented higher accuracy and better performance than the ANN model and was characterised by higher power and sensitivity |
9 | Baskaran (2020) [39] | Using machine learning to gain insight into the relative importance of variables to predict obstructive Coronary Artery Disease (CAD) | Quantitative | North America | High potential for accurate diagnosis | Machine learning model showed BMI to be an important variable, although it is currently not included in most risk scores |
10 | Betriana (2021b) [40] | Interactions between healthcare robots and older persons | Qualitative | Asia | Improved quality of care | Interaction between healthcare robots and older people may improve quality of care |
11 | Beunza et al. (2019) [41] | Machine Learning (ML) algorithms for predicting clinical events in terms of their internal validity and accuracy | Quantitative | Europe | Improved diagnostic, prognostic, and therapeutic tools | Machine learning algorithms can reinforce the diagnostic and prognostic capacity of traditional regression techniques |
12 | Blanco et al. (2018) [42] | Barriers and facilitators related to uptake of Computerised Clinical Decision Support (CCDS) tools as part of a Clostridium Difficile Infection (CDI) reduction bundle | Qualitative | North America | Standardisation and error reduction | Findings shaped the development of Clostridium Difficile Infection reduction bundle |
13 | Borracci et al. (2021) [43] | Application of Neural Network (NN) algorithm-based models to improve the Global Registry of Acute Coronary Events (GRACE) score performance to predict in-hospital mortality and acute Coronary Syndrome | Quantitative | South America | 1. Improved diagnosis 2. Improved turnaround time | Treatment of individual predictors of GRACE score with NN algorithms improved accuracy and discrimination power in all models |
14 | Bouzid et al. (2021) [44] | Consecutive patients evaluated for suspected Acute Coronary Syndrome | Quantitative | North America | 1. Improved turnaround time 2. Improved diagnosis | A subset of novel electrocardiograph features predictive of acute coronary syndrome with a fully interpretable model highly adaptable to clinical decision support application |
15 | Catho et al. (2020) [45] | Adherence to antimicrobial prescribing guidelines and Computerised Decision Support Systems (CDSSs) adoption | Qualitative | Europe | Improve clinicians’ adherence to guidelines and patient care | Features that could improve adoption include friendliness, ergonomics, transparency of the decision-making process and workflow |
16 | Cho (2020) [46] | Deep learning models to automatically classify Cervical Neoplasms on cloposcopic photographs | Quantitative | Asia | Early detection of disease | Provide a better potential of detecting high-risk lesions than previously reported |
17 | Chow et al. (2015) [47] | Physicians’ perceptions and attitudes toward antibiotic Computerised Decision Support Systems (CDSS) recommendations for empirical therapy | Mixed | Asia | Confidence in the credibility of CDSS recommendations | Physicians would prefer to rely on their own or clinical team’s decision over CDSS recommendations in complex patient situations when the antibiotic needs are not met |
18 | Davari Dolatabadi et al. (2017) [48] | Automatic diagnosis of normal and Coronary Artery Disease conditions using Heart Rate Variability (HRV) signal extracted from electrocardiogram | Quantitative | Asia | 1. Improved data quality 2. Reduced cost of care | Methods based on the feature extraction of the biomedical signals are an appropriate approach to predict the health situation of patients |
19 | Davis (2020) [49] | Machine Learning (ML) algorithm for marking Computer Tomography (CT) head examinations pending interpretation as higher probability of intracranial haemorrhage (ICH), on metrics across healthcare system | Quantitative | North America | 1. Reduced waiting time 2. Improved patient’s condition 3. Quality of diagnosis improved | There was significant reduction in length of stay for patients without ICH, but not for emergency department patients with intensive care unit |
20 | Dogan et al. (2018) [50] | Examined whether similar machine learning approaches could be used to develop a similar panel to predict Coronary Heart Disease (CHD) | Quantitative | North America | Accurate and improved diagnosis | The AI tool is more sensitive than conventional risk-factor based approaches, and performs well in both males and females |
21 | Du et al. (2020) [51] | Using high-precision Coronary Heart Disease (CHD) prediction model through big data and machine-learning | Quantitative | Asia | 1. Accurate and improved diagnosis 2. Real time diagnosis | Accurate risk-prediction of coronary heart disease from electronic health records is possible given a sufficiently large population of training data |
22 | Elahi et al. (2020) [52] | Traumatic Brain Injury (TBI) prognostic models | Mixed | Africa | Very effective in patient assessment at the triage especially in resource-limited settings | Addressed unmet needs to determine feasibility of TBI clinical decision support systems in low-resource settings |
23 | English et al. (2017) [53] | Application of a modified version of the unified theory of acceptance and use of technology (UTAUT) to evaluate disposition and satisfaction with computerised decision support systems (CDSS) | Quantitative | North America | Positively impacted the work of pharmacists | Organisational structures that facilitate CDSS use and user satisfaction affect the extent to which pharmacy and health care management maximise use in clinical pharmacy setting |
24 | Fan et al. (2021) [54] | Real-world utilisation of AI health chatbot for primary care self-diagnosis | Mixed | Asia | 1. Trusted to support patients care 2. Easily applicable in patient care | Although the AI tool is perceived convenient in improving patient-care, issues and barriers exist |
25 | Fritsch et al. (2022) [55] | Perception about artificial intelligence in healthcare | Quantitative | Europe | 1. Accurate diagnosis 2. Improved patient outcomes 3. Promotes personal care | Patients and their companions are open to AI usage in healthcare and see it as a positive development |
26 | Garzon-Chavez et al. (2021) [56] | Utilisation of AI-assisted computed tomography screening tool for COVID-19 patient at triage | Quantitative | South America | 1. Facilitates diagnostic decisions by clinicians 2. Facilitates workflow 3. Compatible with existing technology | There were differences in laboratory parameters between cases at the intensive care and non-intensive care units |
27 | Goldman et al. (2021) [57] | Model based on Artificial Intelligence Neural Network (ANN) for predicting Coronary Heart Diseases risk | Quantitative | Asia | 1. Accurate diagnosis 2. Facilitates referral decisions | The artificial intelligence neural network model is a promising approach for predicting coronary heart disease-risk and a good screening procedure to identify high-risk subjects |
28 | Golpour et al. (2020) [58] | Compare support vector machine, naïve Bayes and logistic regressions to determine the diagnostic factors that can predict the need for Coronary Angiography | Quantitative | Asia | 1. Cost effective 2. Accurate and improved diagnosis 3. Supports workflow | Gender, age and fasting blood sugar found to be the most important factors that predict the result of coronary angiography |
29 | Gonçalves (2020) [59] | Nurses’ experiences with technological tools to support the early detection of sepsis | Qualitative | South America | 1. Early diagnosis 2. Reduced waiting time. | Nurses in the technology incorporation process enable a rapid decision-making in the identification of sepsis |
30 | Gonzalez-Briceno (2020) [60] | Diabetes retinopathy screening programme based on artificial intelligence | Quantitative | North America | 1. Prompt and early detection of disease 2. Improved patient waiting time 3. Improved referral systems | Implementation of diabetes retinopathy screening programme in primary care promotes the early detection and prompt treatment of patients |
31 | Grau et al. (2019) [61] | Using Electronic Support Tools and Orders for Prevention of Smoking (E-STOPS) | Qualitative | North America | Provide essential information for physician use | Improvements in provider training and feedback as well as the timing and content of the electronic tools may increase their use by physicians |
32 | Hand et al. (2018) [62] | Fertility preservation discussions with pediatric and adolescent cancer patients | Quantitative | Australia | Improved adherence to clinical pathways, policy, and standards of care | The Clinical Decision Support System (CDSS) provided significant perceived benefits to oncofertility care |
33 | Horsfall et al. (2021) [63] | Attitudes of surgeons and the wider surgical team toward the role of artificial intelligence in neurosurgery | Mixed | North America | Very useful in facilitating and predicting potential complications during surgery | Artificial intelligence widely accepted as a useful tool in neurosurgery |
34 | Hsiao et al. (2013) [64] | Factors affecting acceptance of Pain Management Decision Support System (PM-DSS) by nurse anaesthetists | Quantitative | Asia | Promotes the work of nurse anaesthetists | Findings would help hospital managers understand the important considerations for nurse anaesthetists in accepting PM-DSS |
35 | Hu et al. (2019) [65] | Using Rough Set Theory (RST) and Dempster-Shafer Theory (DST) of evidence to remedy Major Adverse Cardiac Event (MACE) prediction | Quantitative | Asia | High diagnostic potential | The model achieved better performance for the problem of MACE prediction when compared with the single models |
36 | Huang et al. (2017) [66] | Data-mining based approach for Major Adverse Cardiac Events (MACE) prediction | Quantitative | Asia | High potential for accurate diagnosis | The proposed iterative boosting approach has demonstrated great potential to meet the challenge of MACE prediction for acute coronary syndrome (ACS) patients |
37 | Huang et al. (2021) [67] | Using magneticocardiography parameters to detect Coronary Artery Diseases in patients with chest pain | Quantitative | Asia | 1. Potential for accurate diagnosis 2. Could save patients time | The method of multilayer perceptron neural network, magnetcocardigraphy is applicable in identifying coronary artery disease in patients with chest pain, which is beneficial for detection of coronary artery disease |
38 | Isbanner et al. (2022) [68] | Public judgments about AI use in healthcare | Quantitative | Australia | 1. Enhanced speed of service 2. Improved patient outcomes 3. Accurate diagnosis | AI systems should augment rather than replace humans in the provision of healthcare |
39 | Jauk et al. (2021) [69] | Machine learning-based application for predicting the risk of delirium for in-patients | Mixed | Europe | 1. Accurate in predicting patient conditions 2. Improved workflow | In order to improve quality and safety in healthcare, computerised decision support should predict actionable events and be highly accepted by users |
40 | Joloudari et al. (2020) [70] | Integrated method using random trees (RTs), decision tree of C5.0, support vector machine (SVM), and decision tree of Chi-squared automatic interaction detection (CHAID) | Quantitative | Asia | High potential for accurate diagnosis | The random tree model yielded the highest accuracy rate than others |
41 | Jones et al. (2022) [71] | Comprehensive Clinical Decision Support (CDS) to predict end-user acceptance of Thoracic Trauma CDS systems care | Qualitative | North America | 1. Reduced medical errors 2. Comprehensive care 3. Reduced patient waiting time | End-user feedback reinforces intention towards factors that improve the acceptance and use of a CDS map for patients with thoracic trauma |
42 | Kanagasundaram et al. (2016) [72] | Using in-patient Acute Kidney Injury (AKI) Computerised Clinical Decision Support (CCDS) | Qualitative | Australia | Potentially useful prompt to early clinical re-assessment | Systems intruding on workflow, particularly involving complex interactions, may be unsustainable even if there has been a positive impact on care |
43 | Kayvanpour et al. (2021) [73] | Genome-wide miRNA levels in a prospective cohort of patients with clinically suspected Acute Coronary Syndromes by applying an in Silico Neural Network | Quantitative | Europe | 1. High potential for accurate diagnosis 2. Saves patient time 3. Improved workflow | The approach opens the possibility to include multi-modal data points to further increase precision and performance classification of other differential diagnoses |
44 | Kim et al. (2017) [74] | Neural Network (NN) based prediction of Coronary Heart Disease risk using feature correlation analysis (NN-FCA) | Quantitative | Asia | High potential for accurate and timely diagnosis | The model was better than Framingham risk score (FRS) in terms of coronary heart diseases risk prediction |
45 | Kisling et al. (2019) [75] | Automatic treatment planning system for conventional radiotherapy of Cervical Cancer | Quantitative | Africa | 1. Facilitates diagnostics decisions by clinicians 2. Promotes workflow | Fully automatic treatment planning is effective for cervical cancer radiotherapy and may provide a reliable option for low-resource clinics |
46 | Krittanawong et al. (2021) [76] | Deep neural network to predict in-hospital mortality in patients with Spontaneous Coronary Artery Dissection (SCAD) | Quantitative | North America | High potential for diagnostic accuracy | The deep neural network model was associated with higher predictive accuracy and discriminative power than logistic regression or ML models for identification of patients with ACS due to SCAD prone to early mortality |
47 | Lee (2015) [77] | Emergency department decision support system that couples machine learning, simulation, and optimisation to address improvement goals | Mixed | North America | 1. Reduced EM re-admissions 2. Reduced cost of care 3. Reduced patient length of stay 4. Improved patient data | General improvement in patient care at the emergency care department |
48 | Liberati et al. (2017) [78] | Barriers and facilitators to the uptake of an evidence-based Computerised Decision Support Systems (CDSS) | Qualitative | Europe | Fosters organisational learning and improves practitioner skills | Attitudes of healthcare workers towards scientific evidence and guidelines, quality of inter-disciplinary relationships, and organisational ethos of transparency and accountability need to be considered when exploring facility readiness to implement AI tools |
49 | Li et al. (2021) [79] | Machine learning-aided risk stratification system to simplify the procedure of the diagnosis of Coronary Artery Disease | Quantitative | Asia | 1. Helps improve diagnostic accuracy 2. Reduces patient waiting time | The model could be useful in risk stratification of prediction for the coronary artery disease |
50 | Liu et al. (2021) [80] | Machine learning models for predicting mortality in Coronary Artery Disease (CAD) patients with Atrial Fibrillation (AF) | Quantitative | Asia | 1. Potential for improved and accurate diagnosis 2. Improve patient turnaround time | Combining the performance of all aspects of the models, the regularisation logistic regression model was recommended to be used in clinical practice |
51 | Love et al. (2018) [81] | Using AI-based Computer-Assisted Diagnosis (CADx) in training healthcare workers | Quantitative | North America | 1. Facilitates diagnostics decisions by clinicians 2. Promotes workflow | A portable ultrasound system with CADx software can be successfully used by first-level healthcare workers to triage palpable breast lumps |
52 | MacPherson et al. (2021) [82] | Costs and yield from systematic HIV-TB screening, including computer-aided digital chest X-Ray | Quantitative | Africa | 1. Facilitates diagnostics decisions by clinicians 2. Reduced patient waiting time 3. Improved patient health outcomes | Digital chest X-Ray computer-aided digital with universal HIV screening significantly increased the timelines and completeness of HIV and TB diagnosis |
53 | McCoy (2017) [83] | Machine learning-based sepsis prediction algorithm to identify patients with sepsis earlier | Quantitative | North America | 1. Improved patient outcomes 2. Reduction in mortality rate | The machine learning-based sepsis prediction algorithm improved patient outcomes |
54 | Mehta et al. (2021) [84] | Knowledge, perceptions, and preferences about AI use in medical education | Quantitative | North America | 1. Improved clinical and administrative functions 2. Provide useful preventive health suggestions to patients 3. Accurate diagnosis 4. Improve referral procedures | Optimistic about AI's capabilities to carry out a variety of healthcare functions, including clinical and administrative Sceptical about AI utility in personal counselling and empathetic care |
55 | Moon (2018) [85] | Automated delirium-risk assessment system (Auto-DelRAS) that automatically alerts healthcare providers of an intensive care unit patient’s delirium-risk | Quantitative | Asia | 1. Improved data 2. Improved patient outcome 3. Quality diagnostic ability | A relatively high level of predictive validity was maintained with the Auto-DelRAS system, even one year following clinical application |
56 | Morgenstern et al. (2021) [86] | Impacts of artificial intelligence (AI) on public health practice | Qualitative | North America & Asia | Improved diagnosis and disease surveillance | Experts are cautiously optimistic AI’s potential to improve diagnosis and disease surveillance. However, perceived substantial barriers like inadequate regulation exist |
57 | Motwani et al. (2017) [87] | Traditional prognostic risk assessment in patients undergoing non-invasive imaging | Quantitative | North America | 1. Potential for accurate diagnostic capacity 2. Improved turnaround time | Machine learning combining clinical and coronary computed tomographic angiography data was found to predict 5-year all-cause mortality significantly better than existing models |
58 | Betriana et al. (2021a) [88] | Access to palliative care (PC) by integrating predictive model into a comprehensive clinical framework | Quantitative | North America | 1. Improved workflow 2. Improved patient outcomes | A machine learning model can effectively predict the need for in-patient palliative care consult and has been successfully integrated into practice to refer new patients to palliative care |
59 | Naushad et al. (2018) [89] | Coronary artery disease risk and percentage stenosis prediction models using ensemble machine learning algorithms, multifactor dimensionality reduction and recursive partitioning | Quantitative | Asia | 1. High potential for diagnostic accuracy 2. Timely diagnosis | The model exhibited higher predictability both in terms of disease prediction and stenosis prediction |
60 | Nydert et al. (2017) [90] | Clinical Decision Support System (CDSS) among paediatricians | Qualitative | Europe | Very useful during emergency care | Generally, the system is considered very useful to patient drug management |
61 | O’Leary et al. (2014) [91] | Support systems in healthcare and the concept of decision support for clinical pathways | Mixed | Europe | 1. Reduced medical error 2. Allows for multi-disciplinary intervention | The success of these systems depend on other factors outside of itself |
62 | Orlenko et al. (2020) [92] | Tree-based Pipeline Optimisation Tool (TPOT) to predict angiographic diagnoses of Coronary Artery Disease (CAD) | Quantitative | Europe | High potential for accurate diagnosis | Phenotypic profile that distinguishes non-obstructive coronary artery disease patients from non-coronary artery disease patients is associated with higher precision |
63 | Pattarabanjird et al. (2020) [93] | Novel machine learning that combine traditional Cardiac Risk Factors (CRF) with a Single Nucleotide Polymorphism (SNP) in a gene associated with human Coronary Artery Disease severity | Quantitative | North America | 1. Could improve diagnostic accuracy 2. Improved workflow | The model improved prediction of coronary artery disease severity |
64 | Pieszko (2019) [94] | Risk assessment tool based on easily obtained features, including haematological indices and inflammation markers | Quantitative | Europe | 1. High diagnostic capacity 2. Improved patient outcomes | The machine-learning model can provide long-term predictions of accuracy comparable or superior to well-validated risk scores |
65 | Ploug et al. (2021) [95] | Preferences for the performance and explainability of AI decision making in health care | Quantitative | Europe | 1. Improved diagnosis and treatment 2. Improved patient outcomes | Physicians must take ultimately responsibility for diagnostics and treatment planning, AI decision support should be explainable, and AI system must be tested for discrimination |
66 | Polero (2020) [96] | Random forest and elastic net algorithms to improve acute coronary syndrome risk prediction tools | Quantitative | South America | 1. High potential for accurate diagnosis 2. Improved turnaround time | Random forest significantly outperformed exiting models and can perform at par with previously developed scoring metrics |
67 | Prakash and Das (2020) [97] | Factors influencing the uptake and use of intelligent conversational agents in mental healthcare | Qualitative | Asia | 1. Improved quality of care 2. Reduced patient waiting time | AI tools have proven efficacious in improving the health outcomes of patients. However, there are inadequate legal regimes to guide usage |
68 | Pumplun et al. (2021) [98] | Factors that influence the adoption of machine learning systems for medical diagnosis in clinics | Qualitative | Europe | Accurate diagnosis | Many clinics still face major problems in the application of machine learning systems for medical diagnostics |
69 | Richardson et al. (2021) [99] | Patient views of diverse applications of AI in healthcare | Qualitative | North America | 1. Improved patient outcomes 2. Wider range of conditions 3. Accurate diagnosis | Addressing patient concerns relating to AI applications in healthcare is essential for effective clinical implementation |
70 | Romero-Brufau (2020) [100] | Reduce unplanned hospital readmissions through the use of artificial intelligence-based clinical decision support | Quantitative | North America | 1. Reduced readmission rates 2. Improved patient outcome | Six months following a successful application of intervention, readmissions rates decreased by 25% |
71 | Sarwar et al. (2019) [101] | Perspectives on AI implementation in clinical practice | Quantitative | North America & Europe | 1. Facilitates and improves service delivery 2. Accurate diagnosis 3. Improve traditional practice 4. Improve diagnostic capacity | Most respondents envision eventual rollout of AI-tools to complement and not replace physicians in healthcare |
72 | Scheetz et al. (2021) [102] | Diagnostic performance, feasibility, and end-user experiences of AI assisted diabetic retinopathy | Mixed | Australia | 1. Real-time reports 2. Accurate diagnoses | AI in healthcare well-accepted by patients and clinicians |
73 | Schuh (2018) [103] | Creation and modification of Arden-Syntax-based Clinical Decision Support Systems (CDSSs) | Quantitative | Australia | 1. Improved data quality 2. Reduced cost of care | Despite its high utility in patient care, inconsistent electronic data, lack of social acceptance among healthcare personnel, and weak legislative issues remain |
74 | Sendak (2020) [104] | Integration of a deep learning sepsis detection and management platform, sepsis watch, into routine clinical care | Quantitative | North America | 1. Early detection of sepsis 2. Improved workflow | Although there is no playbook for integrating deep learning into clinical care, learning from the sepsis watch integration can inform efforts to develop machines learning technologies at other healthcare delivery systems |
75 | Sherazi et al. (2020) [105] | Propose a machine learning-based on 1-year mortality prediction model after discharge in clinical patients with acute coronary syndrome | Quantitative | Asia | 1. Produced accurate diagnosis 2. Reduced delays in diagnosis | The model would be beneficial for prediction and early detection of major adverse cardiovascular events in acute coronary syndrome patients |
76 | Sujan et al. (2022) [106] | Views about AI in healthcare | Qualitative | Europe | 1. Diagnostic precision 2. Faster services | Safety and assurance of healthcare AI need to be based on a systems approach that expands the current technology-centric focus |
77 | Tayefi et al. (2017) [107] | Establish a predictive model for coronary heart disease using a decision tree algorithm | Quantitative | Asia | May support accurate and timely diagnosis | Proven to be accurate, specific and sensitive model for identifying the presence of coronary heart disease |
78 | Terry et al. (2022) [108] | Views about the use of AI tools in healthcare | Qualitative | North America | Improved healthcare | Use of AI in primary healthcare may have a positive impact, but many factors need to be considered regarding its implementation |
79 | Tscholl et al. (2018) [109] | Perceptions about patient monitoring technology (visual patient) for transforming numerical and waveform data into a virtual model | Mixed | Europe | 1. Improved turnaround time 2. Easy to use 3. Effective in non-monitoring care | The new avatar-based technology improves the turnaround time in patient care |
80 | Uzir et al. (2021) [110] | AI-enabled smartwatch use in healthcare | Quantitative | Asia | 1. Significantly reduce large patient attendance 2. Reduced cost and inconvenience of access to essential healthcare 3. Promotes efficient healthcare 4. Very useful during national emergencies 5. Automation of critical health services 6. Promotes personnel care | AI promoting health democracy and personal healthcare |
81 | van der Heijden (2018) [111] | Incorporation of IDx-diabetes retinopathy (IDx-DR 2.0) in clinical workflow, to detect retinopathy in persons with type 2 diabetes | Quantitative | Europe | 1. Improved data 2. Improved patient outcome 3. Quality diagnostic ability | High predictive validity recorded for IDx-DR 2.0 device |
82 | van der Zander et al. (2022) [112] | Perspectives about AI use in healthcare | Quantitative | Europe | 1. Improved quality of care 2. Speed of service 3. Accurate diagnostics | Both patients and physicians hold positive perspectives towards AI in healthcare |
83 | Velusamy et al. (2021) [113] | Machine learning algorithm to accurately diagnose coronary artery disease | Qualitative | Asia | 1. High potential for accurate diagnosis 2. Can improve patient turnaround time | Weighted-average voting algorithm good in reliably discriminating the coronary artery disease patients from healthy ones with high precision, and therefore it can be used for developing a decision support system for diagnosing coronary artery disease at an early stage |
84 | Visram et al. (2023) [114] | Attitudes towards AI and its future applications in medicine and healthcare | Qualitative | Europe | 1. Improved health outcomes 2. Accurate diagnosis | Children and young people to be included in developing AI. This requires an enabling environment for human-centred AI involving children and young people |
85 | Walter et al. (2020) [115] | Automatic pain recognition (APR) system for the recognition of pain quality | Quantitative | Europe | 1. Accurate in detecting pain 2. Helps detect and avoid over or under-supply of analgesics in patients | Automated pain recognition system is useful in managing pain during patient care |
86 | Wang et al. (2021a) [116] | AI-powered clinical decision support systems in clinical decision-making scenarios | Qualitative | Asia | 1. Facilitates diagnostics decisions by clinicians 2. Promotes workflow 3. Improved diagnosis and treatment 4. Improved turnaround time | Despite difficulties, there is a strong and positive expectation about the role of AI- clinical decision support systems in the future |
87 | Wang et al. (2021b) [117] | Utilisation of social support chatbot for online health community | Mixed | Asia | 1. Improved diagnostic and treatment time 2. Improved patient health outcomes | Chatbot architecture social support has proven useful in supporting individual members who seek emotional support |
88 | Wittal et al. (2022) [118] | Public perception and knowledge of AI use in healthcare, therapy, and diagnosis | Quantitative | Europe | 1. Rapid and accurate diagnoses 2. Longer and better quality of life | Need to improve education and perception of medical AI applications by increasing awareness, highlighting the potentials, and ensuring compliance with guidelines and regulations to handle data protection |
89 | Xu (2020) [119] | Medical-grade wireless monitoring system based on wearable and artificial intelligence technology | Quantitative | Asia | 1. Improved workflow 2. Fast and better diagnosis | The AI tool can provide reliable psychological monitoring for patients in general wards and has the potential to generate more personalised pathophysiological information related to disease diagnosis and treatment |
90 | Yurdaisik and Aksoy (2021) [120] | Knowledge and attitudes of workers at radiology department towards AI applications | Quantitative | Europe & Asia | 1. Saves time 2. Improves workflow | AI applications are very helpful in improving the health outcome of patients |
91 | Zhai et al. (2021) [121] | Develop and test a model for investigating the factors that drive radiation oncologists’ acceptance of AI contouring technology | Quantitative | Asia | Improved workflow and patient outcome | Clinicians had very high perceptions about AI-assisted technology for radiation contouring |
92 | Zhang et al. (2020) [122] | Provide Optimal Detection Models for suspected Coronary Artery Disease detection | Quantitative | Asia | 1. Promote accurate diagnosis 2. Improve turnaround time | Multi-modal features fusion and hybrid features selection can obtain more effective information for coronary artery disease detection and provide a reference for physicians to diagnosis coronary artery disease patients |
93 | Zheng et al. (2021) [123] | Clinicians’ and other professional technicians’ familiarity with, attitudes towards, and concerns about AI in ophthalmology | Quantitative | Asia | Improved health outcomes for patients | AI tools are relevant in ophthalmology and would help improve patient health outcomes |
94 | Zhou et al. (2019) [124] | Examine concordance between the treatment recommendation proposed by Watson for Oncology and actual clinical decisions by oncologists in a cancer centre | Quantitative | Asia | 1. Facilitates diagnostics decisions by clinicians 2. Improved diagnostic tests | There is concordance between AI tools and human clinician decisions |
95 | Zhou et al. (2020) [125] | Develop and internally validate a Laboratory-Based Model with data from a Chinese cohort of inpatients with suspected Stable Chest Pain | Quantitative | Asia | 1. Improved diagnostic potential 2. Improved turnaround time | The present model provided a large net benefit compared with coronary artery diseases consortium ½ score (CAD1/2), Duke clinical score, and Forrester score |