Artificial intelligence for strengthening healthcare systems in low- and middle-income countries: a systematic scoping review

Advancement of Generative Pre-trained Transformer Chatbots in Answering Clinical Questions in the Practical Rhinoplasty Guideline

BACKGROUND

The Generative Pre-trained Transformer (GPT) series, which includes ChatGPT, is an artificial large language model that provides human-like text dialogue. This study aimed to evaluate the performance of artificial intelligence chatbots in answering clinical questions based on practical rhinoplasty guidelines.

METHODS

Clinical questions (CQs) developed from the guidelines were used as question sources. For each question, we asked GPT-4 and GPT-3.5 (ChatGPT), developed by OpenAI, to provide answers for the CQs, Policy Level, Aggregate Evidence Quality, Level of Confidence in Evidence, and References. We compared the performance of the two types of artificial intelligence (AI) chatbots.

RESULTS

A total of 10 questions were included in the final analysis, and the AI chatbots correctly answered 90.0% of these. GPT-4 demonstrated a lower accuracy rate than GPT-3.5 in answering CQs, although without statistically significant difference (86.0% vs. 94.0%; p = 0.05), whereas GPT-4 showed significantly higher accuracy for the level of confidence in Evidence than GPT-3.5 (52.0% vs. 28.0%; p < 0.01). No statistical differences were observed in Policy Level, Aggregate Evidence Quality, and Reference Match. In addition, GPT-4 rated significantly higher in presenting existing references than GPT-3.5 (36.9% vs. 24.1%; p = 0.01).

CONCLUSIONS

The overall performance of GPT-4 was similar to that of GPT-3.5. However, GPT-4 provided existing references at a higher rate than GPT-3.5. GPT-4 has the potential to provide a more accurate reference in professional fields, including rhinoplasty.

LEVEL OF EVIDENCE V

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Artificial Intelligence for Mohs and Dermatologic Surgery: A Systematic Review and Meta-Analysis

BACKGROUND

Over the past decade, several studies have shown that potential of artificial intelligence (AI) in dermatology. However, there has yet to be a systematic review evaluating the usage of AI specifically within the field of Mohs micrographic surgery (MMS).

OBJECTIVE

In this review, we aimed to comprehensively evaluate the current state, efficacy, and future implications of AI when applied to MMS for the treatment of nonmelanoma skin cancers (NMSC).

MATERIALS AND METHODS

A systematic review and meta-analysis was conducted following PRISMA guidelines across several databases, including PubMed/MEDLINE, Embase, and Cochrane libraries. A predefined protocol was registered in PROSPERO, with literature search involving specific keywords related to AI and Mohs surgery for NMSC.

RESULTS

From 23 studies evaluated, our results find that AI shows promise as a prediction tool for precisely identifying NMSC in tissue sections during MMS. Furthermore, high AUC and concordance values were also found across the various usages of AI in MMS, including margin control, surgical recommendations, similarity metrics, and in the prediction of stage and construction complexity.

CONCLUSION

The findings of this review suggest promising potential for AI to enhance the accuracy and efficiency of Mohs surgery, particularly for NMSC.

Use of artificial intelligence to address health disparities in low- and middle-income countries: a thematic analysis of ethical issues

OBJECTIVES

Artificial intelligence (AI) is reshaping health and medicine, especially through its potential to address health disparities in low- and middle-income countries (LMICs). However, there are several issues associated with the use of AI that may reduce its impact and potentially exacerbate global health disparities. This study presents the key issues in AI deployment faced by LMICs.

STUDY DESIGN

Thematic analysis.

METHODS

PubMed, Scopus, Embase and the Web of Science databases were searched, from the date of their inception until September 2023, using the terms "artificial intelligence", "LMICs", "ethic∗" and "global health". Additional searches were conducted by snowballing references before and after the primary search. The final studies were chosen based on their relevance to the topic of this article.

RESULTS

After reviewing 378 articles, 14 studies were included in the final analysis. A concept named the 'AI Deployment Paradox' was introduced to focus on the challenges of using AI to address health disparities in LMICs, and the following three categories were identified: (1) data poverty and contextual shifts; (2) cost-effectiveness and health equity; and (3) new technological colonisation and potential exploitation.

CONCLUSIONS

The relationship between global health, AI and ethical considerations is an area that requires systematic investigation. Relying on health data inherent with structural biases and deploying AI without systematic ethical considerations may exacerbate global health inequalities. Addressing these challenges requires nuanced socio-political comprehension, localised stakeholder engagement, and well-considered ethical and regulatory frameworks.

Artificial intelligence and the politics of avoidance in global health

For decades, global health actors have centered technology in their interventions. Today, artificial intelligence (AI) is emerging as the latest technology-based solution in global health. Yet, AI, like other technological interventions, is not a comprehensive solution to the fundamental determinants of global health inequities. This article gathers and critically appraises grey and peer-reviewed literature on AI in global health to explore the question: What is avoided when global health prioritizes technological solutions to problems with deep-seated political, economic, and commercial determinants? Our literature search and selection yielded 34 documents, which we analyzed to develop seven areas where AI both continues and disrupts past legacies of technological interventions in global health, with significant implications for health equity and human rights. By focusing on the power dynamics that underpin AI's expansion in global health, we situate it as the latest in a long line of technological interventions that avoids addressing the fundamental determinants of health inequities, albeit at times differently than its technology-based predecessors. We call this phenomenon the 'politics of avoidance.' We conclude with reflections on how the literature we reviewed engages with and recognizes the politics of avoidance and with suggestions for future research, practice, and advocacy.

Towards equitable AI in oncology

Artificial intelligence (AI) stands at the threshold of revolutionizing clinical oncology, with considerable potential to improve early cancer detection and risk assessment, and to enable more accurate personalized treatment recommendations. However, a notable imbalance exists in the distribution of the benefits of AI, which disproportionately favour those living in specific geographical locations and in specific populations. In this Perspective, we discuss the need to foster the development of equitable AI tools that are both accurate in and accessible to a diverse range of patient populations, including those in low-income to middle-income countries. We also discuss some of the challenges and potential solutions in attaining equitable AI, including addressing the historically limited representation of diverse populations in existing clinical datasets and the use of inadequate clinical validation methods. Additionally, we focus on extant sources of inequity including the type of model approach (such as deep learning, and feature engineering-based methods), the implications of dataset curation strategies, the need for rigorous validation across a variety of populations and settings, and the risk of introducing contextual bias that comes with developing tools predominantly in high-income countries.

Applied artificial intelligence for global child health: Addressing biases and barriers

Given the potential benefits of artificial intelligence and machine learning (AI/ML) within healthcare, it is critical to consider how these technologies can be deployed in pediatric research and practice. Currently, healthcare AI/ML has not yet adapted to the specific technical considerations related to pediatric data nor adequately addressed the specific vulnerabilities of children and young people (CYP) in relation to AI. While the greatest burden of disease in CYP is firmly concentrated in lower and middle-income countries (LMICs), existing applied pediatric AI/ML efforts are concentrated in a small number of high-income countries (HICs). In LMICs, use-cases remain primarily in the proof-of-concept stage. This narrative review identifies a number of intersecting challenges that pose barriers to effective AI/ML for CYP globally and explores the shifts needed to make progress across multiple domains. Child-specific technical considerations throughout the AI/ML lifecycle have been largely overlooked thus far, yet these can be critical to model effectiveness. Governance concerns are paramount, with suitable national and international frameworks and guidance required to enable the safe and responsible deployment of advanced technologies impacting the care of CYP and using their data. An ambitious vision for child health demands that the potential benefits of AI/Ml are realized universally through greater international collaboration, capacity building, strong oversight, and ultimately diffusing the AI/ML locus of power to empower researchers and clinicians globally. In order that AI/ML systems that do not exacerbate inequalities in pediatric care, teams researching and developing these technologies in LMICs must ensure that AI/ML research is inclusive of the needs and concerns of CYP and their caregivers. A broad, interdisciplinary, and human-centered approach to AI/ML is essential for developing tools for healthcare workers delivering care, such that the creation and deployment of ML is grounded in local systems, cultures, and clinical practice. Decisions to invest in developing and testing pediatric AI/ML in resource-constrained settings must always be part of a broader evaluation of the overall needs of a healthcare system, considering the critical building blocks underpinning effective, sustainable, and cost-efficient healthcare delivery for CYP.

A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task

BACKGROUND

Movement disorders in children and adolescents with dyskinetic cerebral palsy (CP) are commonly assessed from video recordings, however scoring is time-consuming and expert knowledge is required for an appropriate assessment.

OBJECTIVE

To explore a machine learning approach for automated classification of amplitude and duration of distal leg dystonia and choreoathetosis within short video sequences.

METHODS

Available videos of a heel-toe tapping task were preprocessed to optimize key point extraction using markerless motion analysis. Postprocessed key point data were passed to a time series classification ensemble algorithm to classify dystonia and choreoathetosis duration and amplitude classes (scores 0, 1, 2, 3, and 4), respectively. As ground truth clinical scoring of dystonia and choreoathetosis by the Dyskinesia Impairment Scale was used. Multiclass performance metrics as well as metrics for summarized scores: absence (score 0) and presence (score 1-4) were determined.

RESULTS

Thirty-three participants were included: 29 with dyskinetic CP and 4 typically developing, age 14 years:6 months ± 5 years:15 months. The multiclass accuracy results for dystonia were 77% for duration and 68% for amplitude; for choreoathetosis 30% for duration and 38% for amplitude. The metrics for score 0 versus score 1 to 4 revealed an accuracy of 81% for dystonia duration, 77% for dystonia amplitude, 53% for choreoathetosis duration and amplitude.

CONCLUSIONS

This methodology study yielded encouraging results in distinguishing between presence and absence of dystonia, but not for choreoathetosis. A larger dataset is required for models to accurately represent distinct classes/scores. This study presents a novel methodology of automated assessment of movement disorders solely from video data.

Constructing and implementing a performance evaluation indicator set for artificial intelligence decision support systems in pediatric outpatient clinics: an observational study

Artificial intelligence (AI) decision support systems in pediatric healthcare have a complex application background. As an AI decision support system (AI-DSS) can be costly, once applied, it is crucial to focus on its performance, interpret its success, and then monitor and update it to ensure ongoing success consistently. Therefore, a set of evaluation indicators was explicitly developed for AI-DSS in pediatric healthcare, enabling continuous and systematic performance monitoring. The study unfolded in two stages. The first stage encompassed establishing the evaluation indicator set through a literature review, a focus group interview, and expert consultation using the Delphi method. In the second stage, weight analysis was conducted. Subjective weights were calculated based on expert opinions through analytic hierarchy process, while objective weights were determined using the entropy weight method. Subsequently, subject and object weights were synthesized to form the combined weight. In the two rounds of expert consultation, the authority coefficients were 0.834 and 0.846, Kendall's coordination coefficient was 0.135 in Round 1 and 0.312 in Round 2. The final evaluation indicator set has three first-class indicators, fifteen second-class indicators, and forty-seven third-class indicators. Indicator I-1(Organizational performance) carries the highest weight, followed by Indicator I-2(Societal performance) and Indicator I-3(User experience performance) in the objective and combined weights. Conversely, 'Societal performance' holds the most weight among the subjective weights, followed by 'Organizational performance' and 'User experience performance'. In this study, a comprehensive and specialized set of evaluation indicators for the AI-DSS in the pediatric outpatient clinic was established, and then implemented. Continuous evaluation still requires long-term data collection to optimize the weight proportions of the established indicators.

Effectiveness of chatbots in increasing uptake, intention, and attitudes related to any type of vaccination: A systematic review and meta-analysis

This systematic review and meta-analysis analyzed and summarized the growing literature on the effectiveness of chatbot-delivered interventions in increasing uptake, intention, and attitudes related to any type of vaccination. We identified randomized controlled studies (RCTs), quasi-experimental studies, and non-experimental studies from the following platforms: PubMed, Web of Science, MEDLINE, Global Health, APA PsycInfo, and EMBASE databases. A total of 12 eligible studies published from 2019 to 2023 were analyzed and summarized. In particular, one RCT showed that a chatbot-delivered tailored intervention was more effective than a chatbot-delivered non-tailored intervention in promoting seasonal influenza vaccine uptake among older adults (50.5% versus 35.3%, p = 0.002). Six RCTs were included in the meta-analysis to evaluate the effectiveness of chatbot interventions to improve vaccination attitudes and intentions. The pooled standard mean difference (SMD) of overall attitude change was 0.34 (95% confidence intervals [CI]: 0.13, 0.55, p = 0.001). We found a non-significant trivial effect of chatbot interventions on improving intentions of vaccination (SMD: 0.11, 95% CI: -0.13, 0.34, p = 0.38). However, further evidence is needed to draw a more precise conclusion. Additionally, study participants reported high satisfaction levels of using the chatbot and were likely to recommend it to others. The development of chatbots is still nascent and rooms for improvement exist.

Mitigating machine learning bias between high income and low-middle income countries for enhanced model fairness and generalizability

Collaborative efforts in artificial intelligence (AI) are increasingly common between high-income countries (HICs) and low- to middle-income countries (LMICs). Given the resource limitations often encountered by LMICs, collaboration becomes crucial for pooling resources, expertise, and knowledge. Despite the apparent advantages, ensuring the fairness and equity of these collaborative models is essential, especially considering the distinct differences between LMIC and HIC hospitals. In this study, we show that collaborative AI approaches can lead to divergent performance outcomes across HIC and LMIC settings, particularly in the presence of data imbalances. Through a real-world COVID-19 screening case study, we demonstrate that implementing algorithmic-level bias mitigation methods significantly improves outcome fairness between HIC and LMIC sites while maintaining high diagnostic sensitivity. We compare our results against previous benchmarks, utilizing datasets from four independent United Kingdom Hospitals and one Vietnamese hospital, representing HIC and LMIC settings, respectively.

Opportunities and Considerations for the Incorporation of Artificial Intelligence into Global Neurosurgery: A Generative Pretrained Transformer Chatbot-Based Approach

OBJECTIVE

Global neurosurgery is a public health focus in neurosurgery that seeks to ensure safe, timely, and affordable neurosurgical care to all individuals worldwide. Although investigators have begun to explore the promise of artificial intelligence (AI) for neurosurgery, its applicability to global neurosurgery has been largely hypothetical. We characterize opportunities and considerations for the incorporation of AI into global neurosurgery by synthesizing key themes yielded from a series of generative pretrained transformers (GPTs), discuss important limitations of GPTs and cautions when using AI in neurosurgery, and develop a framework for the equitable incorporation of AI into global neurosurgery.

METHODS

ChatGPT, Bing Chat/Copilot, You, Perplexity.ai, and Google Bard were queried with the prompt "How can AI be incorporated into global neurosurgery?" A layered ChatGPT-based thematic analysis was performed. The authors synthesized the results into opportunities and considerations for the incorporation of AI in global neurosurgery. A Pareto analysis was conducted to determine common themes.

RESULTS

Eight opportunities and 14 important considerations were synthesized. Six opportunities related to patient care, 1 to education, and another to public health planning. Four of the important considerations were deemed specific to global neurosurgery. The Pareto analysis included all 8 opportunities and 5 considerations.

CONCLUSIONS

AI may be incorporated into global neurosurgery in a variety of capacities requiring numerous considerations. The framework presented in this manuscript may facilitate the incorporation of AI into global neurosurgery initiatives while balancing contextual factors and the reality of limited resources.

Automated machine learning model for fundus image classification by health-care professionals with no coding experience

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

Frameworks for procurement, integration, monitoring, and evaluation of artificial intelligence tools in clinical settings: A systematic review

Research on the applications of artificial intelligence (AI) tools in medicine has increased exponentially over the last few years but its implementation in clinical practice has not seen a commensurate increase with a lack of consensus on implementing and maintaining such tools. This systematic review aims to summarize frameworks focusing on procuring, implementing, monitoring, and evaluating AI tools in clinical practice. A comprehensive literature search, following PRSIMA guidelines was performed on MEDLINE, Wiley Cochrane, Scopus, and EBSCO databases, to identify and include articles recommending practices, frameworks or guidelines for AI procurement, integration, monitoring, and evaluation. From the included articles, data regarding study aim, use of a framework, rationale of the framework, details regarding AI implementation involving procurement, integration, monitoring, and evaluation were extracted. The extracted details were then mapped on to the Donabedian Plan, Do, Study, Act cycle domains. The search yielded 17,537 unique articles, out of which 47 were evaluated for inclusion based on their full texts and 25 articles were included in the review. Common themes extracted included transparency, feasibility of operation within existing workflows, integrating into existing workflows, validation of the tool using predefined performance indicators and improving the algorithm and/or adjusting the tool to improve performance. Among the four domains (Plan, Do, Study, Act) the most common domain was Plan (84%, n = 21), followed by Study (60%, n = 15), Do (52%, n = 13), & Act (24%, n = 6). Among 172 authors, only 1 (0.6%) was from a low-income country (LIC) and 2 (1.2%) were from lower-middle-income countries (LMICs). Healthcare professionals cite the implementation of AI tools within clinical settings as challenging owing to low levels of evidence focusing on integration in the Do and Act domains. The current healthcare AI landscape calls for increased data sharing and knowledge translation to facilitate common goals and reap maximum clinical benefit.

Evaluating the World Health Organization's SkinNTDs App as a Training Tool for Skin Neglected Tropical Diseases in Ghana and Kenya: Cross-Sectional Study

BACKGROUND

Neglected tropical diseases (NTDs) affect over 1.5 billion people worldwide, primarily impoverished populations in low- and middle-income countries. Skin NTDs, a significant subgroup, manifest primarily as skin lesions and require extensive diagnosis and treatment resources, including trained personnel and financial backing. The World Health Organization has introduced the SkinNTDs app, a mobile health tool designed to train and be used as a decision support tool for frontline health care workers. As most digital health guidelines prioritize the thorough evaluation of mobile health interventions, it is essential to conduct a rigorous and validated assessment of this app.

OBJECTIVE

This study aims to assess the usability and user experience of World Health Organization SkinNTDs app (version 3) as a capacity-building tool and decision-support tool for frontline health care workers.

METHODS

A cross-sectional study was conducted in Ghana and Kenya. Frontline health care workers dealing with skin NTDs were recruited through snowball sampling. They used the SkinNTDs app for at least 5 days before completing a web-based survey containing demographic variables and the user version of the Mobile Application Rating Scale (uMARS), a validated scale for assessing health apps. A smaller group of participants took part in semistructured interviews and one focus group. Quantitative data were analyzed using SPSS with a 95% CI and P≤.05 for statistical significance and qualitative data using ATLAS.ti to identify attributes, cluster themes, and code various dimensions that were explored.

RESULTS

Overall, 60 participants participated in the quantitative phase and 17 in the qualitative phase. The SkinNTDs app scored highly on the uMARS questionnaire, with an app quality mean score of 4.02 (SD 0.47) of 5, a subjective quality score of 3.82 (SD 0.61) of 5, and a perceived impact of 4.47 (SD 0.56) of 5. There was no significant association between the app quality mean score and any of the categorical variables examined, according to Pearson correlation analysis; app quality mean score vs age (P=.37), sex (P=.70), type of health worker (P=.35), country (P=.94), work context (P=.17), frequency of dealing with skin NTDs (P=.09), and dermatology experience (P=.63). Qualitative results echoed the quantitative outcomes, highlighting the ease of use, the offline functionality, and the potential utility for frontline health care workers in remote and resource-constrained settings. Areas for improvement were identified, such as enhancing the signs and symptoms section.

CONCLUSIONS

The SkinNTDs app demonstrates notable usability and user-friendliness. The results indicate that the app could play a crucial role in improving capacity building of frontline health care workers dealing with skin NTDs. It could be improved in the future by including new features such as epidemiological context and direct contact with experts. The possibility of using the app as a diagnostic tool should be considered.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/39393.

Building a house without foundations? A 24-country qualitative interview study on artificial intelligence in intensive care medicine

OBJECTIVES

To explore the views of intensive care professionals in high-income countries (HICs) and lower-to-middle-income countries (LMICs) regarding the use and implementation of artificial intelligence (AI) technologies in intensive care units (ICUs).

METHODS

Individual semi-structured qualitative interviews were conducted between December 2021 and August 2022 with 59 intensive care professionals from 24 countries. Transcripts were analysed using conventional content analysis.

RESULTS

Participants had generally positive views about the potential use of AI in ICUs but also reported some well-known concerns about the use of AI in clinical practice and important technical and non-technical barriers to the implementation of AI. Important differences existed between ICUs regarding their current readiness to implement AI. However, these differences were not primarily between HICs and LMICs, but between a small number of ICUs in large tertiary hospitals in HICs, which were reported to have the necessary digital infrastructure for AI, and nearly all other ICUs in both HICs and LMICs, which were reported to neither have the technical capability to capture the necessary data or use AI, nor the staff with the right knowledge and skills to use the technology.

CONCLUSION

Pouring massive amounts of resources into developing AI without first building the necessary digital infrastructure foundation needed for AI is unethical. Real-world implementation and routine use of AI in the vast majority of ICUs in both HICs and LMICs included in our study is unlikely to occur any time soon. ICUs should not be using AI until certain preconditions are met.

The path from task-specific to general purpose artificial intelligence for medical diagnostics: A bibliometric analysis

Artificial intelligence (AI) has revolutionized many fields, and its potential in healthcare has been increasingly recognized. Based on diverse data sources such as imaging, laboratory tests, medical records, and electrophysiological data, diagnostic AI has witnessed rapid development in recent years. A comprehensive understanding of the development status, contributing factors, and their relationships in the application of AI to medical diagnostics is essential to further promote its use in clinical practice. In this study, we conducted a bibliometric analysis to explore the evolution of task-specific to general-purpose AI for medical diagnostics. We used the Web of Science database to search for relevant articles published between 2010 and 2023, and applied VOSviewer, the R package Bibliometrix, and CiteSpace to analyze collaborative networks and keywords. Our analysis revealed that the field of AI in medical diagnostics has experienced rapid growth in recent years, with a focus on tasks such as image analysis, disease prediction, and decision support. Collaborative networks were observed among researchers and institutions, indicating a trend of global cooperation in this field. Additionally, we identified several key factors contributing to the development of AI in medical diagnostics, including data quality, algorithm design, and computational power. Challenges to progress in the field include model explainability, robustness, and equality, which will require multi-stakeholder, interdisciplinary collaboration to tackle. Our study provides a holistic understanding of the path from task-specific, mono-modal AI toward general-purpose, multimodal AI for medical diagnostics. With the continuous improvement of AI technology and the accumulation of medical data, we believe that AI will play a greater role in medical diagnostics in the future.

Research and application of artificial intelligence in dentistry from lower-middle income countries - a scoping review

Artificial intelligence (AI) has been integrated into dentistry for improvement of current dental practice. While many studies have explored the utilization of AI in various fields, the potential of AI in dentistry, particularly in low-middle income countries (LMICs) remains understudied. This scoping review aimed to study the existing literature on the applications of artificial intelligence in dentistry in low-middle income countries. A comprehensive search strategy was applied utilizing three major databases: PubMed, Scopus, and EBSCO Dentistry & Oral Sciences Source. The search strategy included keywords related to AI, Dentistry, and LMICs. The initial search yielded a total of 1587, out of which 25 articles were included in this review. Our findings demonstrated that limited studies have been carried out in LMICs in terms of AI and dentistry. Most of the studies were related to Orthodontics. In addition gaps in literature were noted such as cost utility and patient experience were not mentioned in the included studies.

Artificial Intelligence in Kidney Disease: A Comprehensive Study and Directions for Future Research

Artificial intelligence (AI) has emerged as a promising tool in the field of healthcare, with an increasing number of research articles evaluating its applications in the domain of kidney disease. To comprehend the evolving landscape of AI research in kidney disease, a bibliometric analysis is essential. The purposes of this study are to systematically analyze and quantify the scientific output, research trends, and collaborative networks in the application of AI to kidney disease. This study collected AI-related articles published between 2012 and 20 November 2023 from the Web of Science. Descriptive analyses of research trends in the application of AI in kidney disease were used to determine the growth rate of publications by authors, journals, institutions, and countries. Visualization network maps of country collaborations and author-provided keyword co-occurrences were generated to show the hotspots and research trends in AI research on kidney disease. The initial search yielded 673 articles, of which 631 were included in the analyses. Our findings reveal a noteworthy exponential growth trend in the annual publications of AI applications in kidney disease. Nephrology Dialysis Transplantation emerged as the leading publisher, accounting for 4.12% (26 out of 631 papers), followed by the American Journal of Transplantation at 3.01% (19/631) and Scientific Reports at 2.69% (17/631). The primary contributors were predominantly from the United States (n = 164, 25.99%), followed by China (n = 156, 24.72%) and India (n = 62, 9.83%). In terms of institutions, Mayo Clinic led with 27 contributions (4.27%), while Harvard University (n = 19, 3.01%) and Sun Yat-Sen University (n = 16, 2.53%) secured the second and third positions, respectively. This study summarized AI research trends in the field of kidney disease through statistical analysis and network visualization. The findings show that the field of AI in kidney disease is dynamic and rapidly progressing and provides valuable information for recognizing emerging patterns, technological shifts, and interdisciplinary collaborations that contribute to the advancement of knowledge in this critical domain.

Impacts of the advancement in artificial intelligence on laboratory medicine in low- and middle-income countries: Challenges and recommendations-A literature review

Background and Aims

Artificial intelligence (AI) has emerged as a transformative force in laboratory medicine, promising significant advancements in healthcare delivery. This study explores the potential impact of AI on diagnostics and patient management within the context of laboratory medicine, with a particular focus on low- and middle-income countries (LMICs).

Methods

In writing this article, we conducted a thorough search of databases such as PubMed, ResearchGate, Web of Science, Scopus, and Google Scholar within 20 years. The study examines AI's capabilities, including learning, reasoning, and decision-making, mirroring human cognitive processes. It highlights AI's adeptness at processing vast data sets, identifying patterns, and expediting the extraction of actionable insights, particularly in medical imaging interpretation and laboratory test data analysis. The research emphasizes the potential benefits of AI in early disease detection, therapeutic interventions, and personalized treatment strategies.

Results

In the realm of laboratory medicine, AI demonstrates remarkable precision in interpreting medical images such as radiography, computed tomography, and magnetic resonance imaging. Its predictive analytical capabilities extend to forecasting patient trajectories and informing personalized treatment strategies using comprehensive data sets comprising clinical outcomes, patient records, and laboratory results. The study underscores the significance of AI in addressing healthcare challenges, especially in resource-constrained LMICs.

Conclusion

While acknowledging the profound impact of AI on laboratory medicine in LMICs, the study recognizes challenges such as inadequate data availability, digital infrastructure deficiencies, and ethical considerations. Successful implementation necessitates substantial investments in digital infrastructure, the establishment of data-sharing networks, and the formulation of regulatory frameworks. The study concludes that collaborative efforts among stakeholders, including international organizations, governments, and nongovernmental entities, are crucial for overcoming obstacles and responsibly integrating AI into laboratory medicine in LMICs. A comprehensive, coordinated approach is essential for realizing AI's transformative potential and advancing health care in LMICs.

Strategies for Implementing Machine Learning Algorithms in the Clinical Practice of Radiology

Despite recent advancements in machine learning (ML) applications in health care, there have been few benefits and improvements to clinical medicine in the hospital setting. To facilitate clinical adaptation of methods in ML, this review proposes a standardized framework for the step-by-step implementation of artificial intelligence into the clinical practice of radiology that focuses on three key components: problem identification, stakeholder alignment, and pipeline integration. A review of the recent literature and empirical evidence in radiologic imaging applications justifies this approach and offers a discussion on structuring implementation efforts to help other hospital practices leverage ML to improve patient care. Clinical trial registration no. 04242667 © RSNA, 2024 Supplemental material is available for this article.

Feasibility and accuracy of the screening for diabetic retinopathy using a fundus camera and an artificial intelligence pre-evaluation application

AIMS

Periodical screening for diabetic retinopathy (DR) by an ophthalmologist is expensive and demanding. Automated DR image evaluation with Artificial Intelligence tools may represent a clinical and cost-effective alternative for the detection of retinopathy. We aimed to evaluate the accuracy and reliability of a machine learning algorithm.

METHODS

This was an observational diagnostic precision study that compared human grader classification with that of DAIRET®, an algorithm nested in an electronic medical record powered by Retmarker SA. Retinal images were taken from 637 consecutive patients attending a routine annual diabetic visit between June 2021 and February 2023. They were manually graded by an ophthalmologist following the International Clinical Diabetic Retinopathy Severity Scale and the results were compared with those of the AI responses. The main outcome measures were screening performance, such as sensitivity and specificity and diagnostic accuracy by 95% confidence intervals.

RESULTS

The rate of cases classified as ungradable was 1.2%, a figure consistent with the literature. DAIRET® sensitivity in the detection of cases of referable DR (moderate and above, "sight-threatening" forms of retinopathy) was equal to 1 (100%). The specificity, that is the true negative rate of absence of DR, was 80 ± 0.04.

CONCLUSIONS

DAIRET® achieved excellent sensitivity for referable retinopathy compared with that of human graders. This is undoubtedly the key finding of the study and translates into the certainty that no patient in need of the ophthalmologist is misdiagnosed as negative. It also had sufficient specificity to represent a cost-effective alternative to manual grade alone.

Existing Barriers Faced by and Future Design Recommendations for Direct-to-Consumer Health Care Artificial Intelligence Apps: Scoping Review

BACKGROUND

Direct-to-consumer (DTC) health care artificial intelligence (AI) apps hold the potential to bridge the spatial and temporal disparities in health care resources, but they also come with individual and societal risks due to AI errors. Furthermore, the manner in which consumers interact directly with health care AI is reshaping traditional physician-patient relationships. However, the academic community lacks a systematic comprehension of the research overview for such apps.

OBJECTIVE

This paper systematically delineated and analyzed the characteristics of included studies, identified existing barriers and design recommendations for DTC health care AI apps mentioned in the literature and also provided a reference for future design and development.

METHODS

This scoping review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines and was conducted according to Arksey and O'Malley's 5-stage framework. Peer-reviewed papers on DTC health care AI apps published until March 27, 2023, in Web of Science, Scopus, the ACM Digital Library, IEEE Xplore, PubMed, and Google Scholar were included. The papers were analyzed using Braun and Clarke's reflective thematic analysis approach.

RESULTS

Of the 2898 papers retrieved, 32 (1.1%) covering this emerging field were included. The included papers were recently published (2018-2023), and most (23/32, 72%) were from developed countries. The medical field was mostly general practice (8/32, 25%). In terms of users and functionalities, some apps were designed solely for single-consumer groups (24/32, 75%), offering disease diagnosis (14/32, 44%), health self-management (8/32, 25%), and health care information inquiry (4/32, 13%). Other apps connected to physicians (5/32, 16%), family members (1/32, 3%), nursing staff (1/32, 3%), and health care departments (2/32, 6%), generally to alert these groups to abnormal conditions of consumer users. In addition, 8 barriers and 6 design recommendations related to DTC health care AI apps were identified. Some more subtle obstacles that are particularly worth noting and corresponding design recommendations in consumer-facing health care AI systems, including enhancing human-centered explainability, establishing calibrated trust and addressing overtrust, demonstrating empathy in AI, improving the specialization of consumer-grade products, and expanding the diversity of the test population, were further discussed.

CONCLUSIONS

The booming DTC health care AI apps present both risks and opportunities, which highlights the need to explore their current status. This paper systematically summarized and sorted the characteristics of the included studies, identified existing barriers faced by, and made future design recommendations for such apps. To the best of our knowledge, this is the first study to systematically summarize and categorize academic research on these apps. Future studies conducting the design and development of such systems could refer to the results of this study, which is crucial to improve the health care services provided by DTC health care AI apps.

Are physicians ready for precision antibiotic prescribing? A qualitative analysis of the acceptance of artificial intelligence-enabled clinical decision support systems in India and Singapore

OBJECTIVES

Artificial intelligence (AI)-driven clinical decision support systems (CDSSs) can augment antibiotic decision-making capabilities, but physicians' hesitancy in adopting them may undermine their utility. We conducted a cross-country comparison of physician perceptions on the barriers and facilitators in accepting an AI-enabled CDSS for antibiotic prescribing.

METHODS

We conducted in-depth interviews with physicians from the National Centre for Infectious Diseases (NCID), Singapore, and Christian Medical College Vellore (CMCV), India, between April and December 2022. Our semi-structured in-depth interview guides were anchored on Venkatesh's UTAUT model. We used clinical vignettes to illustrate the application of AI in clinical decision support for antibiotic prescribing and explore medico-legal concerns.

RESULTS

Most NCID physicians felt that an AI-enabled CDSS could facilitate antibiotic prescribing, while most CMCV physicians were sceptical about the tool's utility. The hesitancy in adopting an AI-enabled CDSS stems from concerns about the lack of validated and successful examples, fear of losing autonomy and clinical skills, difficulty of use, and impediment in work efficiency. Physicians from both sites felt that a user-friendly interface, integration with workflow, transparency of output, a guiding medico-legal framework, and training and technical support would improve the uptake of an AI-enabled CDSS.

CONCLUSION

In conclusion, the acceptance of AI-enabled CDSSs depends on the physician's confidence with the tool's recommendations, perceived ease of use, familiarity with AI, the organisation's digital culture and support, and the presence of medico-legal governance of AI. Progressive implementation and continuous feedback are essential to allay scepticism around the utility of AI-enabled CDSSs.

Global Access to Comprehensive Care for Paediatric and Congenital Heart Disease

Paediatric and congenital heart disease (PCHD) is common but remains forgotten on the global health agenda. Congenital heart disease is the most frequent major congenital anomaly, affecting approximately 1 in every 100 live births. In high-income countries, most children now live into adulthood, whereas in low- and middle-income countries, over 90% of patients do not get the care they need. Rheumatic heart disease is the most common acquired cardiovascular disease in children and adolescents. While almost completely eradicated in high-income countries, over 30-40 million people live with rheumatic heart disease in low- and middle-income countries. Challenges exist in the care for PCHD and, increasingly, adult congenital heart disease (ACHD) worldwide. In this review, we summarize the current status of PCHD and ACHD care through the health systems lens of workforce, infrastructure, financing, service delivery, information management and technology, and governance. We further highlight gaps in knowledge and opportunities moving forward to improve access to care for all those living with PCHD or ACHD worldwide.

ChatGPT: promise and challenges for deployment in low- and middle-income countries

In low- and middle-income countries (LMICs), the fields of medicine and public health grapple with numerous challenges that continue to hinder patients' access to healthcare services. ChatGPT, a publicly accessible chatbot, has emerged as a potential tool in aiding public health efforts in LMICs. This viewpoint details the potential benefits of employing ChatGPT in LMICs to improve medicine and public health encompassing a broad spectrum of domains ranging from health literacy, screening, triaging, remote healthcare support, mental health support, multilingual capabilities, healthcare communication and documentation, medical training and education, and support for healthcare professionals. Additionally, we also share potential concerns and limitations associated with the use of ChatGPT and provide a balanced discussion on the opportunities and challenges of using ChatGPT in LMICs.

Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review

OBJECTIVE

This study aims to summarize the research literature evaluating machine learning (ML)-based clinical decision support (CDS) systems in healthcare settings.

MATERIALS AND METHODS

We conducted a review in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta Analyses extension for Scoping Review). Four databases, including PubMed, Medline, Embase, and Scopus were searched for studies published from January 2016 to April 2021 evaluating the use of ML-based CDS in clinical settings. We extracted the study design, care setting, clinical task, CDS task, and ML method. The level of CDS autonomy was examined using a previously published 3-level classification based on the division of clinical tasks between the clinician and CDS; effects on decision-making, care delivery, and patient outcomes were summarized.

RESULTS

Thirty-two studies evaluating the use of ML-based CDS in clinical settings were identified. All were undertaken in developed countries and largely in secondary and tertiary care settings. The most common clinical tasks supported by ML-based CDS were image recognition and interpretation (n = 12) and risk assessment (n = 9). The majority of studies examined assistive CDS (n = 23) which required clinicians to confirm or approve CDS recommendations for risk assessment in sepsis and for interpreting cancerous lesions in colonoscopy. Effects on decision-making, care delivery, and patient outcomes were mixed.

CONCLUSION

ML-based CDS are being evaluated in many clinical areas. There remain many opportunities to apply and evaluate effects of ML-based CDS on decision-making, care delivery, and patient outcomes, particularly in resource-constrained settings.

ChatGPT, GPT-4, and Other Large Language Models: The Next Revolution for Clinical Microbiology?

ChatGPT, GPT-4, and Bard are highly advanced natural language process-based computer programs (chatbots) that simulate and process human conversation in written or spoken form. Recently released by the company OpenAI, ChatGPT was trained on billions of unknown text elements (tokens) and rapidly gained wide attention for its ability to respond to questions in an articulate manner across a wide range of knowledge domains. These potentially disruptive large language model (LLM) technologies have a broad range of conceivable applications in medicine and medical microbiology. In this opinion article, I describe how chatbot technologies work and discuss the strengths and weaknesses of ChatGPT, GPT-4, and other LLMs for applications in the routine diagnostic laboratory, focusing on various use cases for the pre- to post-analytical process.

Conversational AI and Vaccine Communication: Systematic Review of the Evidence

BACKGROUND

Since the mid-2010s, use of conversational artificial intelligence (AI; chatbots) in health care has expanded significantly, especially in the context of increased burdens on health systems and restrictions on in-person consultations with health care providers during the COVID-19 pandemic. One emerging use for conversational AI is to capture evolving questions and communicate information about vaccines and vaccination.

OBJECTIVE

The objective of this systematic review was to examine documented uses and evidence on the effectiveness of conversational AI for vaccine communication.

METHODS

This systematic review was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. PubMed, Web of Science, PsycINFO, MEDLINE, Scopus, CINAHL Complete, Cochrane Library, Embase, Epistemonikos, Global Health, Global Index Medicus, Academic Search Complete, and the University of London library database were searched for papers on the use of conversational AI for vaccine communication. The inclusion criteria were studies that included (1) documented instances of conversational AI being used for the purpose of vaccine communication and (2) evaluation data on the impact and effectiveness of the intervention.

RESULTS

After duplicates were removed, the review identified 496 unique records, which were then screened by title and abstract, of which 38 were identified for full-text review. Seven fit the inclusion criteria and were assessed and summarized in the findings of this review. Overall, vaccine chatbots deployed to date have been relatively simple in their design and have mainly been used to provide factual information to users in response to their questions about vaccines. Additionally, chatbots have been used for vaccination scheduling, appointment reminders, debunking misinformation, and, in some cases, for vaccine counseling and persuasion. Available evidence suggests that chatbots can have a positive effect on vaccine attitudes; however, studies were typically exploratory in nature, and some lacked a control group or had very small sample sizes.

CONCLUSIONS

The review found evidence of potential benefits from conversational AI for vaccine communication. Factors that may contribute to the effectiveness of vaccine chatbots include their ability to provide credible and personalized information in real time, the familiarity and accessibility of the chatbot platform, and the extent to which interactions with the chatbot feel "natural" to users. However, evaluations have focused on the short-term, direct effects of chatbots on their users. The potential longer-term and societal impacts of conversational AI have yet to be analyzed. In addition, existing studies do not adequately address how ethics apply in the field of conversational AI around vaccines. In a context where further digitalization of vaccine communication can be anticipated, additional high-quality research will be required across all these areas.

Artificial intelligence and digital health in global eye health: opportunities and challenges

Global eye health is defined as the degree to which vision, ocular health, and function are maximised worldwide, thereby optimising overall wellbeing and quality of life. Improving eye health is a global priority as a key to unlocking human potential by reducing the morbidity burden of disease, increasing productivity, and supporting access to education. Although extraordinary progress fuelled by global eye health initiatives has been made over the last decade, there remain substantial challenges impeding further progress. The accelerated development of digital health and artificial intelligence (AI) applications provides an opportunity to transform eye health, from facilitating and increasing access to eye care to supporting clinical decision making with an objective, data-driven approach. Here, we explore the opportunities and challenges presented by digital health and AI in global eye health and describe how these technologies could be leveraged to improve global eye health. AI, telehealth, and emerging technologies have great potential, but require specific work to overcome barriers to implementation. We suggest that a global digital eye health task force could facilitate coordination of funding, infrastructural development, and democratisation of AI and digital health to drive progress forwards in this domain.

Disease Assessments in Patients with Glioblastoma

PURPOSE OF REVIEW

The neuro-oncology team faces a unique challenge when assessing treatment response in patients diagnosed with glioblastoma. Magnetic resonance imaging (MRI) remains the standard imaging modality for measuring therapeutic response in both clinical practice and clinical trials. However, even for the neuroradiologist, MRI interpretations are not straightforward because of tumor heterogeneity, as evidenced by varying degrees of enhancement, infiltrating tumor patterns, cellular densities, and vasogenic edema. The situation is even more perplexing following therapy since treatment-related changes can mimic viable tumor. Additionally, antiangiogenic therapies can dramatically decrease contrast enhancement giving the false impression of decreasing tumor burden. Over the past few decades, several approaches have emerged to augment and improve visual interpretation of glioblastoma response to therapeutics. Herein, we summarize the state of the art for evaluating the response of glioblastoma to standard therapies and investigational agents as well as challenges and future directions for assessing treatment response in neuro-oncology.

RECENT FINDINGS

Monitoring glioblastoma responses to standard therapy and novel agents has been fraught with many challenges and limitations over the past decade. Excitingly, new promising methods are emerging to help address these challenges. Recently, the Response Assessment in Neuro-Oncology (RANO) working group proposed an updated response criteria (RANO 2.0) for the evaluation of all grades of glial tumors regardless of IDH status or therapies being evaluated. In addition, advanced neuroimaging techniques, such as histogram analysis, parametric response maps, morphometric segmentation, radio pharmacodynamics approaches, and the integrating of amino acid radiotracers in the tumor evaluation algorithm may help resolve equivocal lesion interpretations without operative intervention. Moreover, the introduction of other techniques, such as liquid biopsy and artificial intelligence could complement conventional visual assessment of glioblastoma response to therapies. Neuro-oncology has evolved over the past decade and has achieved significant milestones, including the establishment of new standards of care, emerging therapeutic options, and novel clinical, translational, and basic research. More recently, the integration of histopathology with molecular features for tumor classification has marked an important paradigm shift in brain tumor diagnosis. In a similar manner, treatment response monitoring in neuro-oncology has made considerable progress. While most techniques are still in their inception, there is an emerging body of evidence for clinical application. Further research will be critically important for the development of impactful breakthroughs in this area of the field.

Health Equity in Clinical Research Informatics

OBJECTIVES

Through a scoping review, we examine in this survey what ways health equity has been promoted in clinical research informatics with patient implications and especially published in the year of 2021 (and some in 2022).

METHOD

A scoping review was conducted guided by using methods described in the Joanna Briggs Institute Manual. The review process consisted of five stages: 1) development of aim and research question, 2) literature search, 3) literature screening and selection, 4) data extraction, and 5) accumulate and report results.

RESULTS

From the 478 identified papers in 2021 on the topic of clinical research informatics with focus on health equity as a patient implication, 8 papers met our inclusion criteria. All included papers focused on artificial intelligence (AI) technology. The papers addressed health equity in clinical research informatics either through the exposure of inequity in AI-based solutions or using AI as a tool for promoting health equity in the delivery of healthcare services. While algorithmic bias poses a risk to health equity within AI-based solutions, AI has also uncovered inequity in traditional treatment and demonstrated effective complements and alternatives that promotes health equity.

CONCLUSIONS

Clinical research informatics with implications for patients still face challenges of ethical nature and clinical value. However, used prudently-for the right purpose in the right context-clinical research informatics could bring powerful tools in advancing health equity in patient care.

Widening the lens of population-based health research to climate change impacts and adaptation: the climate change and health evaluation and response system (CHEERS)

Background

Climate change significantly impacts health in low-and middle-income countries (LMICs), exacerbating vulnerabilities. Comprehensive data for evidence-based research and decision-making is crucial but scarce. Health and Demographic Surveillance Sites (HDSSs) in Africa and Asia provide a robust infrastructure with longitudinal population cohort data, yet they lack climate-health specific data. Acquiring this information is essential for understanding the burden of climate-sensitive diseases on populations and guiding targeted policies and interventions in LMICs to enhance mitigation and adaptation capacities.

Objective

The objective of this research is to develop and implement the Change and Health Evaluation and Response System (CHEERS) as a methodological framework, designed to facilitate the generation and ongoing monitoring of climate change and health-related data within existing Health and Demographic Surveillance Sites (HDSSs) and comparable research infrastructures.

Methods

CHEERS uses a multi-tiered approach to assess health and environmental exposures at the individual, household, and community levels, utilizing digital tools such as wearable devices, indoor temperature and humidity measurements, remotely sensed satellite data, and 3D-printed weather stations. The CHEERS framework utilizes a graph database to efficiently manage and analyze diverse data types, leveraging graph algorithms to understand the complex interplay between health and environmental exposures.

Results

The Nouna CHEERS site, established in 2022, has yielded significant preliminary findings. By using remotely-sensed data, the site has been able to predict crop yield at a household level in Nouna and explore the relationships between yield, socioeconomic factors, and health outcomes. The feasibility and acceptability of wearable technology have been confirmed in rural Burkina Faso for obtaining individual-level data, despite the presence of technical challenges. The use of wearables to study the impact of extreme weather on health has shown significant effects of heat exposure on sleep and daily activity, highlighting the urgent need for interventions to mitigate adverse health consequences.

Conclusion

Implementing the CHEERS in research infrastructures can advance climate change and health research, as large and longitudinal datasets have been scarce for LMICs. This data can inform health priorities, guide resource allocation to address climate change and health exposures, and protect vulnerable communities in LMICs from these exposures.

Sustainable development goals applied to digital pathology and artificial intelligence applications in low- to middle-income countries

Digital Pathology (DP) and Artificial Intelligence (AI) can be useful in low- and middle-income countries; however, many challenges exist. The United Nations developed sustainable development goals that aim to overcome some of these challenges. The sustainable development goals have not been applied to DP/AI applications in low- to middle income countries. We established a framework to align the 17 sustainable development goals with a 27-indicator list for low- and middle-income countries (World Bank/WHO) and a list of 21 essential elements for DP/AI. After categorization into three domains (human factors, IT/electronics, and materials + reagents), we permutated these layers into 153 concatenated statements for prioritization on a four-tiered scale. The two authors tested the subjective ranking framework and endpoints included ranked sum scores and visualization across the three layers. The authors assigned 364 points with 1.1-1.3 points per statement. We noted the prioritization of human factors (43%) at the indicator layer whereas IT/electronic (36%) and human factors (35%) scored highest at the essential elements layer. The authors considered goal 9 (industry, innovation, and infrastructure; average points 2.33; sum 42), goal 4 (quality education; 2.17; 39), and goal 8 (decent work and economic growth; 2.11; 38) most relevant; intra-/inter-rater variability assessment after a 3-month-washout period confirmed these findings. The established framework allows individual stakeholders to capture the relative importance of sustainable development goals for overcoming limitations to a specific problem. The framework can be used to raise awareness and help identify synergies between large-scale global objectives and solutions in resource-limited settings.

Recent Advancements and Challenges of AIoT Application in Smart Agriculture: A Review

As the most popular technologies of the 21st century, artificial intelligence (AI) and the internet of things (IoT) are the most effective paradigms that have played a vital role in transforming the agricultural industry during the pandemic. The convergence of AI and IoT has sparked a recent wave of interest in artificial intelligence of things (AIoT). An IoT system provides data flow to AI techniques for data integration and interpretation as well as for the performance of automatic image analysis and data prediction. The adoption of AIoT technology significantly transforms the traditional agriculture scenario by addressing numerous challenges, including pest management and post-harvest management issues. Although AIoT is an essential driving force for smart agriculture, there are still some barriers that must be overcome. In this paper, a systematic literature review of AIoT is presented to highlight the current progress, its applications, and its advantages. The AIoT concept, from smart devices in IoT systems to the adoption of AI techniques, is discussed. The increasing trend in article publication regarding to AIoT topics is presented based on a database search process. Lastly, the challenges to the adoption of AIoT technology in modern agriculture are also discussed.

A transparent artificial intelligence framework to assess lung disease in pulmonary hypertension

Recent studies have recognized the importance of characterizing the extent of lung disease in pulmonary hypertension patients by using Computed Tomography. The trustworthiness of an artificial intelligence system is linked with the depth of the evaluation in functional, operational, usability, safety and validation dimensions. The safety and validation of an artificial tool is linked to the uncertainty estimation of the model's prediction. On the other hand, the functionality, operation and usability can be achieved by explainable deep learning approaches which can verify the learning patterns and use of the network from a generalized point of view. We developed an artificial intelligence framework to map the 3D anatomical models of patients with lung disease in pulmonary hypertension. To verify the trustworthiness of the framework we studied the uncertainty estimation of the network's prediction, and we explained the learning patterns of the network. Therefore, a new generalized technique combining local explainable and interpretable dimensionality reduction approaches (PCA-GradCam, PCA-Shape) was developed. Our open-source software framework was evaluated in unbiased validation datasets achieving accurate, robust and generalized results.