Automated Category and Trend Analysis of Scientific Articles on Ophthalmology Using Large Language Models: Development and Usability Study

BACKGROUND

In this paper, we present an automated method for article classification, leveraging the power of large language models (LLMs).

OBJECTIVE

The aim of this study is to evaluate the applicability of various LLMs based on textual content of scientific ophthalmology papers.

METHODS

We developed a model based on natural language processing techniques, including advanced LLMs, to process and analyze the textual content of scientific papers. Specifically, we used zero-shot learning LLMs and compared Bidirectional and Auto-Regressive Transformers (BART) and its variants with Bidirectional Encoder Representations from Transformers (BERT) and its variants, such as distilBERT, SciBERT, PubmedBERT, and BioBERT. To evaluate the LLMs, we compiled a data set (retinal diseases [RenD] ) of 1000 ocular disease-related articles, which were expertly annotated by a panel of 6 specialists into 19 distinct categories. In addition to the classification of articles, we also performed analysis on different classified groups to find the patterns and trends in the field.

RESULTS

The classification results demonstrate the effectiveness of LLMs in categorizing a large number of ophthalmology papers without human intervention. The model achieved a mean accuracy of 0.86 and a mean F1-score of 0.85 based on the RenD data set.

CONCLUSIONS

The proposed framework achieves notable improvements in both accuracy and efficiency. Its application in the domain of ophthalmology showcases its potential for knowledge organization and retrieval. We performed a trend analysis that enables researchers and clinicians to easily categorize and retrieve relevant papers, saving time and effort in literature review and information gathering as well as identification of emerging scientific trends within different disciplines. Moreover, the extendibility of the model to other scientific fields broadens its impact in facilitating research and trend analysis across diverse disciplines.

Machine Learning-Based Approach for Identifying Research Gaps: COVID-19 as a Case Study

BACKGROUND

Research gaps refer to unanswered questions in the existing body of knowledge, either due to a lack of studies or inconclusive results. Research gaps are essential starting points and motivation in scientific research. Traditional methods for identifying research gaps, such as literature reviews and expert opinions, can be time consuming, labor intensive, and prone to bias. They may also fall short when dealing with rapidly evolving or time-sensitive subjects. Thus, innovative scalable approaches are needed to identify research gaps, systematically assess the literature, and prioritize areas for further study in the topic of interest.

OBJECTIVE

In this paper, we propose a machine learning-based approach for identifying research gaps through the analysis of scientific literature. We used the COVID-19 pandemic as a case study.

METHODS

We conducted an analysis to identify research gaps in COVID-19 literature using the COVID-19 Open Research (CORD-19) data set, which comprises 1,121,433 papers related to the COVID-19 pandemic. Our approach is based on the BERTopic topic modeling technique, which leverages transformers and class-based term frequency-inverse document frequency to create dense clusters allowing for easily interpretable topics. Our BERTopic-based approach involves 3 stages: embedding documents, clustering documents (dimension reduction and clustering), and representing topics (generating candidates and maximizing candidate relevance).

RESULTS

After applying the study selection criteria, we included 33,206 abstracts in the analysis of this study. The final list of research gaps identified 21 different areas, which were grouped into 6 principal topics. These topics were: "virus of COVID-19," "risk factors of COVID-19," "prevention of COVID-19," "treatment of COVID-19," "health care delivery during COVID-19," "and impact of COVID-19." The most prominent topic, observed in over half of the analyzed studies, was "the impact of COVID-19."

CONCLUSIONS

The proposed machine learning-based approach has the potential to identify research gaps in scientific literature. This study is not intended to replace individual literature research within a selected topic. Instead, it can serve as a guide to formulate precise literature search queries in specific areas associated with research questions that previous publications have earmarked for future exploration. Future research should leverage an up-to-date list of studies that are retrieved from the most common databases in the target area. When feasible, full texts or, at minimum, discussion sections should be analyzed rather than limiting their analysis to abstracts. Furthermore, future studies could evaluate more efficient modeling algorithms, especially those combining topic modeling with statistical uncertainty quantification, such as conformal prediction.

Temporal self-attention for risk prediction from electronic health records using non-stationary kernel approximation

Effective modeling of patient representation from electronic health records (EHRs) is increasingly becoming a vital research topic. Yet, modeling the non-stationarity in EHR data has received less attention. Most existing studies follow a strong assumption of stationarity in patient representation from EHRs. However, in practice, a patient's visits are irregularly spaced over a relatively long period of time, and disease progression patterns exhibit non-stationarity. Furthermore, the time gaps between patient visits often encapsulate significant domain knowledge, potentially revealing undiscovered patterns that characterize specific medical conditions. To address these challenges, we introduce a new method which combines the self-attention mechanism with non-stationary kernel approximation to capture both contextual information and temporal relationships between patient visits in EHRs. To assess the effectiveness of our proposed approach, we use two real-world EHR datasets, comprising a total of 76,925 patients, for the task of predicting the next diagnosis code for a patient, given their EHR history. The first dataset is a general EHR cohort and consists of 11,451 patients with a total of 3,485 unique diagnosis codes. The second dataset is a disease-specific cohort that includes 65,474 pregnant patients and encompasses a total of 9,782 unique diagnosis codes. Our experimental evaluation involved nine prediction models, categorized into three distinct groups. Group 1 comprises the baselines: original self-attention with positional encoding model, RETAIN model, and LSTM model. Group 2 includes models employing self-attention with stationary kernel approximations, specifically incorporating three variations of Bochner's feature maps. Lastly, Group 3 consists of models utilizing self-attention with non-stationary kernel approximations, including quadratic, cubic, and bi-quadratic polynomials. The experimental results demonstrate that non-stationary kernels significantly outperformed baseline methods for NDCG@10 and Hit@10 metrics in both datasets. The performance boost was more substantial in dataset 1 for the NDCG@10 metric. On the other hand, stationary Kernels showed significant but smaller gains over baselines and were nearly as effective as Non-stationary Kernels for Hit@10 in dataset 2. These findings robustly validate the efficacy of employing non-stationary kernels for temporal modeling of EHR data, and emphasize the importance of modeling non-stationary temporal information in healthcare prediction tasks.

The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis

BACKGROUND

Students usually encounter stress throughout their academic path. Ongoing stressors may lead to chronic stress, adversely affecting their physical and mental well-being. Thus, early detection and monitoring of stress among students are crucial. Wearable artificial intelligence (AI) has emerged as a valuable tool for this purpose. It offers an objective, noninvasive, nonobtrusive, automated approach to continuously monitor biomarkers in real time, thereby addressing the limitations of traditional approaches such as self-reported questionnaires.

OBJECTIVE

This systematic review and meta-analysis aim to assess the performance of wearable AI in detecting and predicting stress among students.

METHODS

Search sources in this review included 7 electronic databases (MEDLINE, Embase, PsycINFO, ACM Digital Library, Scopus, IEEE Xplore, and Google Scholar). We also checked the reference lists of the included studies and checked studies that cited the included studies. The search was conducted on June 12, 2023. This review included research articles centered on the creation or application of AI algorithms for the detection or prediction of stress among students using data from wearable devices. In total, 2 independent reviewers performed study selection, data extraction, and risk-of-bias assessment. The Quality Assessment of Diagnostic Accuracy Studies-Revised tool was adapted and used to examine the risk of bias in the included studies. Evidence synthesis was conducted using narrative and statistical techniques.

RESULTS

This review included 5.8% (19/327) of the studies retrieved from the search sources. A meta-analysis of 37 accuracy estimates derived from 32% (6/19) of the studies revealed a pooled mean accuracy of 0.856 (95% CI 0.70-0.93). Subgroup analyses demonstrated that the accuracy of wearable AI was moderated by the number of stress classes (P=.02), type of wearable device (P=.049), location of the wearable device (P=.02), data set size (P=.009), and ground truth (P=.001). The average estimates of sensitivity, specificity, and F1-score were 0.755 (SD 0.181), 0.744 (SD 0.147), and 0.759 (SD 0.139), respectively.

CONCLUSIONS

Wearable AI shows promise in detecting student stress but currently has suboptimal performance. The results of the subgroup analyses should be carefully interpreted given that many of these findings may be due to other confounding factors rather than the underlying grouping characteristics. Thus, wearable AI should be used alongside other assessments (eg, clinical questionnaires) until further evidence is available. Future research should explore the ability of wearable AI to differentiate types of stress, distinguish stress from other mental health issues, predict future occurrences of stress, consider factors such as the placement of the wearable device and the methods used to assess the ground truth, and report detailed results to facilitate the conduct of meta-analyses.

TRIAL REGISTRATION

PROSPERO CRD42023435051; http://tinyurl.com/3fzb5rnp.

Technological Challenges and Solutions in Emergency Remote Teaching for Nursing: An International Cross-Sectional Survey

OBJECTIVES

With the sudden global shift to online learning modalities, this study aimed to understand the unique challenges and experiences of emergency remote teaching (ERT) in nursing education.

METHODS

We conducted a comprehensive online international cross-sectional survey to capture the current state and firsthand experiences of ERT in the nursing discipline. Our analytical methods included a combination of traditional statistical analysis, advanced natural language processing techniques, latent Dirichlet allocation using Python, and a thorough qualitative assessment of feedback from open-ended questions.

RESULTS

We received responses from 328 nursing educators from 18 different countries. The data revealed generally positive satisfaction levels, strong technological self-efficacy, and significant support from their institutions. Notably, the characteristics of professors, such as age (p = 0.02) and position (p = 0.03), influenced satisfaction levels. The ERT experience varied significantly by country, as evidenced by satisfaction (p = 0.05), delivery (p = 0.001), teacher-student interaction (p = 0.04), and willingness to use ERT in the future (p = 0.04). However, concerns were raised about the depth of content, the transition to online delivery, teacher-student interaction, and the technology gap.

CONCLUSIONS

Our findings can help advance nursing education. Nevertheless, collaborative efforts from all stakeholders are essential to address current challenges, achieve digital equity, and develop a standardized curriculum for nursing education.

Artificial intelligence in glaucoma: opportunities, challenges, and future directions

Artificial intelligence (AI) has shown excellent diagnostic performance in detecting various complex problems related to many areas of healthcare including ophthalmology. AI diagnostic systems developed from fundus images have become state-of-the-art tools in diagnosing retinal conditions and glaucoma as well as other ocular diseases. However, designing and implementing AI models using large imaging data is challenging. In this study, we review different machine learning (ML) and deep learning (DL) techniques applied to multiple modalities of retinal data, such as fundus images and visual fields for glaucoma detection, progression assessment, staging and so on. We summarize findings and provide several taxonomies to help the reader understand the evolution of conventional and emerging AI models in glaucoma. We discuss opportunities and challenges facing AI application in glaucoma and highlight some key themes from the existing literature that may help to explore future studies. Our goal in this systematic review is to help readers and researchers to understand critical aspects of AI related to glaucoma as well as determine the necessary steps and requirements for the successful development of AI models in glaucoma.

Prevalence of stunting among under-five children in refugee and internally displaced communities: a systematic review and meta-analysis

Background

A pooled estimate of stunting prevalence in refugee and internally displaced under-five children can help quantify the problem and focus on the nutritional needs of these marginalized groups. We aimed to assess the pooled prevalence of stunting in refugees and internally displaced under-five children from different parts of the globe.

Methods

In this systematic review and meta-analysis, seven databases (Cochrane, EBSCOHost, EMBASE, ProQuest, PubMed, Scopus, and Web of Science) along with "preprint servers" were searched systematically from the earliest available date to 14 February 2023. Refugee and internally displaced (IDP) under-five children were included, and study quality was assessed using "National Heart, Lung, and Blood Institute (NHLBI)" tools.

Results

A total of 776 abstracts (PubMed = 208, Scopus = 192, Cochrane = 1, Web of Science = 27, Embase = 8, EBSCOHost = 123, ProQuest = 5, Google Scholar = 209, and Preprints = 3) were retrieved, duplicates removed, and screened, among which 30 studies were found eligible for qualitative and quantitative synthesis. The pooled prevalence of stunting was 26% [95% confidence interval (CI): 21-31]. Heterogeneity was high (I2 = 99%, p < 0.01). A subgroup analysis of the type of study subjects revealed a pooled stunting prevalence of 37% (95% CI: 23-53) in internally displaced populations and 22% (95% CI: 18-28) among refugee children. Based on geographical distribution, the stunting was 32% (95% CI: 24-40) in the African region, 34% (95% CI: 24-46) in the South-East Asian region, and 14% (95% CI: 11-19) in Eastern Mediterranean region.

Conclusion

The stunting rate is more in the internally displaced population than the refugee population and more in the South-East Asian and African regions. Our recommendation is to conduct further research to evaluate the determinants of undernutrition among under-five children of refugees and internally displaced populations from different regions so that international organizations and responsible stakeholders of that region can take effective remedial actions.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387156, PROSPERO [CRD42023387156].

Wearable Artificial Intelligence for Detecting Anxiety: Systematic Review and Meta-Analysis

BACKGROUND

Anxiety disorders rank among the most prevalent mental disorders worldwide. Anxiety symptoms are typically evaluated using self-assessment surveys or interview-based assessment methods conducted by clinicians, which can be subjective, time-consuming, and challenging to repeat. Therefore, there is an increasing demand for using technologies capable of providing objective and early detection of anxiety. Wearable artificial intelligence (AI), the combination of AI technology and wearable devices, has been widely used to detect and predict anxiety disorders automatically, objectively, and more efficiently.

OBJECTIVE

This systematic review and meta-analysis aims to assess the performance of wearable AI in detecting and predicting anxiety.

METHODS

Relevant studies were retrieved by searching 8 electronic databases and backward and forward reference list checking. In total, 2 reviewers independently carried out study selection, data extraction, and risk-of-bias assessment. The included studies were assessed for risk of bias using a modified version of the Quality Assessment of Diagnostic Accuracy Studies-Revised. Evidence was synthesized using a narrative (ie, text and tables) and statistical (ie, meta-analysis) approach as appropriate.

RESULTS

Of the 918 records identified, 21 (2.3%) were included in this review. A meta-analysis of results from 81% (17/21) of the studies revealed a pooled mean accuracy of 0.82 (95% CI 0.71-0.89). Meta-analyses of results from 48% (10/21) of the studies showed a pooled mean sensitivity of 0.79 (95% CI 0.57-0.91) and a pooled mean specificity of 0.92 (95% CI 0.68-0.98). Subgroup analyses demonstrated that the performance of wearable AI was not moderated by algorithms, aims of AI, wearable devices used, status of wearable devices, data types, data sources, reference standards, and validation methods.

CONCLUSIONS

Although wearable AI has the potential to detect anxiety, it is not yet advanced enough for clinical use. Until further evidence shows an ideal performance of wearable AI, it should be used along with other clinical assessments. Wearable device companies need to develop devices that can promptly detect anxiety and identify specific time points during the day when anxiety levels are high. Further research is needed to differentiate types of anxiety, compare the performance of different wearable devices, and investigate the impact of the combination of wearable device data and neuroimaging data on the performance of wearable AI.

TRIAL REGISTRATION

PROSPERO CRD42023387560; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387560.

Using artificial intelligence to improve body iron quantification: A scoping review

This scoping review explores the potential of artificial intelligence (AI) in enhancing the screening, diagnosis, and monitoring of disorders related to body iron levels. A systematic search was performed to identify studies that utilize machine learning in iron-related disorders. The search revealed a wide range of machine learning algorithms used by different studies. Notably, most studies used a single data type. The studies varied in terms of sample sizes, participant ages, and geographical locations. AI's role in quantifying iron concentration is still in its early stages, yet its potential is significant. The question is whether AI-based diagnostic biomarkers can offer innovative approaches for screening, diagnosing, and monitoring of iron overload and anemia.

A Strengths, Weaknesses, Opportunities, and Threats (SWOT) Analysis of ChatGPT Integration in Nursing Education: A Narrative Review

Amidst evolving healthcare demands, nursing education plays a pivotal role in preparing future nurses for complex challenges. Traditional approaches, however, must be revised to meet modern healthcare needs. The ChatGPT, an AI-based chatbot, has garnered significant attention due to its ability to personalize learning experiences, enhance virtual clinical simulations, and foster collaborative learning in nursing education. This review aims to thoroughly assess the potential impact of integrating ChatGPT into nursing education. The hypothesis is that valuable insights can be provided for stakeholders through a comprehensive SWOT analysis examining the strengths, weaknesses, opportunities, and threats associated with ChatGPT. This will enable informed decisions about its integration, prioritizing improved learning outcomes. A thorough narrative literature review was undertaken to provide a solid foundation for the SWOT analysis. The materials included scholarly articles and reports, which ensure the study's credibility and allow for a holistic and unbiased assessment. The analysis identified accessibility, consistency, adaptability, cost-effectiveness, and staying up-to-date as crucial factors influencing the strengths, weaknesses, opportunities, and threats associated with ChatGPT integration in nursing education. These themes provided a framework to understand the potential risks and benefits of integrating ChatGPT into nursing education. This review highlights the importance of responsible and effective use of ChatGPT in nursing education and the need for collaboration among educators, policymakers, and AI developers. Addressing the identified challenges and leveraging the strengths of ChatGPT can lead to improved learning outcomes and enriched educational experiences for students. The findings emphasize the importance of responsibly integrating ChatGPT in nursing education, balancing technological advancement with careful consideration of associated risks, to achieve optimal outcomes.

An Exploration of Wearable Device Features Used in UK Hospital Parkinson Disease Care: Scoping Review

BACKGROUND

The prevalence of Parkinson disease (PD) is becoming an increasing concern owing to the aging population in the United Kingdom. Wearable devices have the potential to improve the clinical care of patients with PD while reducing health care costs. Consequently, exploring the features of these wearable devices is important to identify the limitations and further areas of investigation of how wearable devices are currently used in clinical care in the United Kingdom.

OBJECTIVE

In this scoping review, we aimed to explore the features of wearable devices used for PD in hospitals in the United Kingdom.

METHODS

A scoping review of the current research was undertaken and reported according to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. The literature search was undertaken on June 6, 2022, and publications were obtained from MEDLINE or PubMed, Embase, and the Cochrane Library. Eligible publications were initially screened by their titles and abstracts. Publications that passed the initial screening underwent a full review. The study characteristics were extracted from the final publications, and the evidence was synthesized using a narrative approach. Any queries were reviewed by the first and second authors.

RESULTS

Of the 4543 publications identified, 39 (0.86%) publications underwent a full review, and 20 (0.44%) publications were included in the scoping review. Most studies (11/20, 55%) were conducted at the Newcastle upon Tyne Hospitals NHS Foundation Trust, with sample sizes ranging from 10 to 418. Most study participants were male individuals with a mean age ranging from 57.7 to 78.0 years. The AX3 was the most popular device brand used, and it was commercially manufactured by Axivity. Common wearable device types included body-worn sensors, inertial measurement units, and smartwatches that used accelerometers and gyroscopes to measure the clinical features of PD. Most wearable device primary measures involved the measured gait, bradykinesia, and dyskinesia. The most common wearable device placements were the lumbar region, head, and wrist. Furthermore, 65% (13/20) of the studies used artificial intelligence or machine learning to support PD data analysis.

CONCLUSIONS

This study demonstrated that wearable devices could help provide a more detailed analysis of PD symptoms during the assessment phase and personalize treatment. Using machine learning, wearable devices could differentiate PD from other neurodegenerative diseases. The identified evidence gaps include the lack of analysis of wearable device cybersecurity and data management. The lack of cost-effectiveness analysis and large-scale participation in studies resulted in uncertainty regarding the feasibility of the widespread use of wearable devices. The uncertainty around the identified research gaps was further exacerbated by the lack of medical regulation of wearable devices for PD, particularly in the United Kingdom where regulations were changing due to the political landscape.

The performance of serious games for enhancing attention in cognitively impaired older adults

Attention, which is the process of noticing the surrounding environment and processing information, is one of the cognitive functions that deteriorate gradually as people grow older. Games that are used for other than entertainment, such as improving attention, are often referred to as serious games. This study examined the effectiveness of serious games on attention among elderly individuals suffering from cognitive impairment. A systematic review and meta-analyses of randomized controlled trials were carried out. A total of 10 trials ultimately met all eligibility criteria of the 559 records retrieved. The synthesis of very low-quality evidence from three trials, as analyzed in a meta-study, indicated that serious games outperform no/passive interventions in enhancing attention in cognitively impaired older adults (P < 0.001). Additionally, findings from two other studies demonstrated that serious games are more effective than traditional cognitive training in boosting attention among cognitively impaired older adults. One study also concluded that serious games are better than traditional exercises in enhancing attention. Serious games can enhance attention in cognitively impaired older adults. However, given the low quality of the evidence, the limited number of participants in most studies, the absence of some comparative studies, and the dearth of studies included in the meta-analyses, the results remain inconclusive. Thus, until the aforementioned limitations are rectified in future research, serious games should serve as a supplement, rather than a replacement, to current interventions.

Performance of Artificial Intelligence in Predicting Future Depression Levels

Depression is a prevalent mental condition that is challenging to diagnose using conventional techniques. Using machine learning and deep learning models with motor activity data, wearable AI technology has shown promise in reliably and effectively identifying or predicting depression. In this work, we aim to examine the performance of simple linear and non-linear models in the prediction of depression levels. We compared eight linear and non-linear models (Ridge, ElasticNet, Lasso, Random Forest, Gradient boosting, Decision trees, Support vector machines, and Multilayer perceptron) for the task of predicting depression scores over a period using physiological features, motor activity data, and MADRAS scores. For the experimental evaluation, we used the Depresjon dataset which contains the motor activity data of depressed and non-depressed participants. According to our findings, simple linear and non-linear models may effectively estimate depression scores for depressed people without the need for complex models. This opens the door for the development of more effective and impartial techniques for identifying depression and treating/preventing it using commonly used, widely accessible wearable technology.

Estimating Blood Glucose Levels Using Machine Learning Models with Non-Invasive Wearable Device Data

In 2019 alone, Diabetes Mellitus impacted 463 million individuals worldwide. Blood glucose levels (BGL) are often monitored via invasive techniques as part of routine protocols. Recently, AI-based approaches have shown the ability to predict BGL using data acquired by non-invasive Wearable Devices (WDs), therefore improving diabetes monitoring and treatment. It is crucial to study the relationships between non-invasive WD features and markers of glycemic health. Therefore, this study aimed to investigate accuracy of linear and non-linear models in estimating BGL. A dataset containing digital metrics as well as diabetic status collected using traditional means was used. Data consisted of 13 participants data collected from WDs, these participants were divided in two groups young, and Adult Our experimental design included Data Collection, Feature Engineering, ML model selection/development, and reporting evaluation of metrics. The study showed that linear and non-linear models both have high accuracy in estimating BGL using WD data (RMSE range: 0.181 to 0.271, MAE range: 0.093 to 0.142). We provide further evidence of the feasibility of using commercially available WDs for the purpose of BGL estimation amongst diabetics when using Machine learning approaches.

Wearable AI Reveals the Impact of Intermittent Fasting on Stress Levels in School Children During Ramadan

Intermittent fasting has been practiced for centuries across many cultures globally. Recently many studies have reported intermittent fasting for its lifestyle benefits, the major shift in eating habits and patterns is associated with several changes in hormones and circadian rhythms. Whether there are accompanying changes in stress levels is not widely reported especially in school children. The objective of this study is to examine the impact of intermittent fasting during Ramadan on stress levels in school children as measured using wearable artificial intelligence (AI). Twenty-nine school children (aged 13-17 years and 12M / 17F ratio) were given Fitbit devices and their stress, activity and sleep patterns analyzed 2 weeks before, 4 weeks during Ramadan fasting and 2 weeks after. This study revealed no statistically significant difference on stress scores during fasting, despite changes in stress levels being observed for 12 of the participants. Our study may imply intermittent fasting during Ramadan poses no direct risks in terms of stress, suggesting rather it may be linked to dietary habits, furthermore as stress score calculations are based on heart rate variability, this study implies fasting does not interfere the cardiac autonomic nervous system.

Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions

The integration of large language models (LLMs), such as those in the Generative Pre-trained Transformers (GPT) series, into medical education has the potential to transform learning experiences for students and elevate their knowledge, skills, and competence. Drawing on a wealth of professional and academic experience, we propose that LLMs hold promise for revolutionizing medical curriculum development, teaching methodologies, personalized study plans and learning materials, student assessments, and more. However, we also critically examine the challenges that such integration might pose by addressing issues of algorithmic bias, overreliance, plagiarism, misinformation, inequity, privacy, and copyright concerns in medical education. As we navigate the shift from an information-driven educational paradigm to an artificial intelligence (AI)-driven educational paradigm, we argue that it is paramount to understand both the potential and the pitfalls of LLMs in medical education. This paper thus offers our perspective on the opportunities and challenges of using LLMs in this context. We believe that the insights gleaned from this analysis will serve as a foundation for future recommendations and best practices in the field, fostering the responsible and effective use of AI technologies in medical education.

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

Given the limitations of traditional approaches, wearable artificial intelligence (AI) is one of the technologies that have been exploited to detect or predict depression. The current review aimed at examining the performance of wearable AI in detecting and predicting depression. The search sources in this systematic review were 8 electronic databases. Study selection, data extraction, and risk of bias assessment were carried out by two reviewers independently. The extracted results were synthesized narratively and statistically. Of the 1314 citations retrieved from the databases, 54 studies were included in this review. The pooled mean of the highest accuracy, sensitivity, specificity, and root mean square error (RMSE) was 0.89, 0.87, 0.93, and 4.55, respectively. The pooled mean of lowest accuracy, sensitivity, specificity, and RMSE was 0.70, 0.61, 0.73, and 3.76, respectively. Subgroup analyses revealed that there is a statistically significant difference in the highest accuracy, lowest accuracy, highest sensitivity, highest specificity, and lowest specificity between algorithms, and there is a statistically significant difference in the lowest sensitivity and lowest specificity between wearable devices. Wearable AI is a promising tool for depression detection and prediction although it is in its infancy and not ready for use in clinical practice. Until further research improve its performance, wearable AI should be used in conjunction with other methods for diagnosing and predicting depression. Further studies are needed to examine the performance of wearable AI based on a combination of wearable device data and neuroimaging data and to distinguish patients with depression from those with other diseases.

Serious Games for Learning Among Older Adults With Cognitive Impairment: Systematic Review and Meta-analysis

BACKGROUND

Learning disabilities are among the major cognitive impairments caused by aging. Among the interventions used to improve learning among older adults are serious games, which are participative electronic games designed for purposes other than entertainment. Although some systematic reviews have examined the effectiveness of serious games on learning, they are undermined by some limitations, such as focusing on older adults without cognitive impairments, focusing on particular types of serious games, and not considering the comparator type in the analysis.

OBJECTIVE

This review aimed to evaluate the effectiveness of serious games on verbal and nonverbal learning among older adults with cognitive impairment.

METHODS

Eight electronic databases were searched to retrieve studies relevant to this systematic review and meta-analysis. Furthermore, we went through the studies that cited the included studies and screened the reference lists of the included studies and relevant reviews. Two reviewers independently checked the eligibility of the identified studies, extracted data from the included studies, and appraised their risk of bias and the quality of the evidence. The results of the included studies were summarized using a narrative synthesis or meta-analysis, as appropriate.

RESULTS

Of the 559 citations retrieved, 11 (2%) randomized controlled trials (RCTs) ultimately met all eligibility criteria for this review. A meta-analysis of 45% (5/11) of the RCTs revealed that serious games are effective in improving verbal learning among older adults with cognitive impairment in comparison with no or sham interventions (P=.04), and serious games do not have a different effect on verbal learning between patients with mild cognitive impairment and those with Alzheimer disease (P=.89). A meta-analysis of 18% (2/11) of the RCTs revealed that serious games are as effective as conventional exercises in promoting verbal learning (P=.98). We also found that serious games outperformed no or sham interventions (4/11, 36%; P=.03) and conventional cognitive training (2/11, 18%; P<.001) in enhancing nonverbal learning.

CONCLUSIONS

Serious games have the potential to enhance verbal and nonverbal learning among older adults with cognitive impairment. However, our findings remain inconclusive because of the low quality of evidence, the small sample size in most of the meta-analyzed studies (6/8, 75%), and the paucity of studies included in the meta-analyses. Thus, until further convincing proof of their effectiveness is offered, serious games should be used to supplement current interventions for verbal and nonverbal learning rather than replace them entirely. Further studies are needed to compare serious games with conventional cognitive training and conventional exercises, as well as different types of serious games, different platforms, different intervention periods, and different follow-up periods.

TRIAL REGISTRATION

PROSPERO CRD42022348849; https://tinyurl.com/y6yewwfa.

Artificial Intelligence for the Prediction and Early Diagnosis of Pancreatic Cancer: Scoping Review

BACKGROUND

Pancreatic cancer is the 12th most common cancer worldwide, with an overall survival rate of 4.9%. Early diagnosis of pancreatic cancer is essential for timely treatment and survival. Artificial intelligence (AI) provides advanced models and algorithms for better diagnosis of pancreatic cancer.

OBJECTIVE

This study aims to explore AI models used for the prediction and early diagnosis of pancreatic cancers as reported in the literature.

METHODS

A scoping review was conducted and reported in line with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. PubMed, Google Scholar, Science Direct, BioRXiv, and MedRxiv were explored to identify relevant articles. Study selection and data extraction were independently conducted by 2 reviewers. Data extracted from the included studies were synthesized narratively.

RESULTS

Of the 1185 publications, 30 studies were included in the scoping review. The included articles reported the use of AI for 6 different purposes. Of these included articles, AI techniques were mostly used for the diagnosis of pancreatic cancer (14/30, 47%). Radiological images (14/30, 47%) were the most frequently used data in the included articles. Most of the included articles used data sets with a size of <1000 samples (11/30, 37%). Deep learning models were the most prominent branch of AI used for pancreatic cancer diagnosis in the studies, and the convolutional neural network was the most used algorithm (18/30, 60%). Six validation approaches were used in the included studies, of which the most frequently used approaches were k-fold cross-validation (10/30, 33%) and external validation (10/30, 33%). A higher level of accuracy (99%) was found in studies that used support vector machine, decision trees, and k-means clustering algorithms.

CONCLUSIONS

This review presents an overview of studies based on AI models and algorithms used to predict and diagnose pancreatic cancer patients. AI is expected to play a vital role in advancing pancreatic cancer prediction and diagnosis. Further research is required to provide data that support clinical decisions in health care.

The Effectiveness of Wearable Devices Using Artificial Intelligence for Blood Glucose Level Forecasting or Prediction: Systematic Review

BACKGROUND

In 2021 alone, diabetes mellitus, a metabolic disorder primarily characterized by abnormally high blood glucose (BG) levels, affected 537 million people globally, and over 6 million deaths were reported. The use of noninvasive technologies, such as wearable devices (WDs), to regulate and monitor BG in people with diabetes is a relatively new concept and yet in its infancy. Noninvasive WDs coupled with machine learning (ML) techniques have the potential to understand and conclude meaningful information from the gathered data and provide clinically meaningful advanced analytics for the purpose of forecasting or prediction.

OBJECTIVE

The purpose of this study is to provide a systematic review complete with a quality assessment looking at diabetes effectiveness of using artificial intelligence (AI) in WDs for forecasting or predicting BG levels.

METHODS

We searched 7 of the most popular bibliographic databases. Two reviewers performed study selection and data extraction independently before cross-checking the extracted data. A narrative approach was used to synthesize the data. Quality assessment was performed using an adapted version of the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.

RESULTS

From the initial 3872 studies, the features from 12 studies were reported after filtering according to our predefined inclusion criteria. The reference standard in all studies overall (n=11, 92%) was classified as low, as all ground truths were easily replicable. Since the data input to AI technology was highly standardized and there was no effect of flow or time frame on the final output, both factors were categorized in a low-risk group (n=11, 92%). It was observed that classical ML approaches were deployed by half of the studies, the most popular being ensemble-boosted trees (random forest). The most common evaluation metric used was Clarke grid error (n=7, 58%), followed by root mean square error (n=5, 42%). The wide usage of photoplethysmogram and near-infrared sensors was observed on wrist-worn devices.

CONCLUSIONS

This review has provided the most extensive work to date summarizing WDs that use ML for diabetic-related BG level forecasting or prediction. Although current studies are few, this study suggests that the general quality of the studies was considered high, as revealed by the QUADAS-2 assessment tool. Further validation is needed for commercially available devices, but we envisage that WDs in general have the potential to remove the need for invasive devices completely for glucose monitoring in the not-too-distant future.

TRIAL REGISTRATION

PROSPERO CRD42022303175; https://tinyurl.com/3n9jaayc.

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

BACKGROUND

Anxiety and depression are the most common mental disorders worldwide. Owing to the lack of psychiatrists around the world, the incorporation of artificial intelligence (AI) into wearable devices (wearable AI) has been exploited to provide mental health services.

OBJECTIVE

This review aimed to explore the features of wearable AI used for anxiety and depression to identify application areas and open research issues.

METHODS

We searched 8 electronic databases (MEDLINE, PsycINFO, Embase, CINAHL, IEEE Xplore, ACM Digital Library, Scopus, and Google Scholar) and included studies that met the inclusion criteria. Then, we checked the studies that cited the included studies and screened studies that were cited by the included studies. The study selection and data extraction were carried out by 2 reviewers independently. The extracted data were aggregated and summarized using narrative synthesis.

RESULTS

Of the 1203 studies identified, 69 (5.74%) were included in this review. Approximately, two-thirds of the studies used wearable AI for depression, whereas the remaining studies used it for anxiety. The most frequent application of wearable AI was in diagnosing anxiety and depression; however, none of the studies used it for treatment purposes. Most studies targeted individuals aged between 18 and 65 years. The most common wearable device used in the studies was Actiwatch AW4 (Cambridge Neurotechnology Ltd). Wrist-worn devices were the most common type of wearable device in the studies. The most commonly used category of data for model development was physical activity data, followed by sleep data and heart rate data. The most frequently used data set from open sources was Depresjon. The most commonly used algorithm was random forest, followed by support vector machine.

CONCLUSIONS

Wearable AI can offer great promise in providing mental health services related to anxiety and depression. Wearable AI can be used by individuals for the prescreening assessment of anxiety and depression. Further reviews are needed to statistically synthesize the studies' results related to the performance and effectiveness of wearable AI. Given its potential, technology companies should invest more in wearable AI for the treatment of anxiety and depression.

Hepatic and cardiac iron overload quantified by magnetic resonance imaging in patients on hemodialysis: A systematic review and meta-analysis

INTRODUCTION

Few studies have reported hepatic and cardiac iron overload in patients with end-stage renal disease (ESRD), and the current evidence regarding the prevalence is still scarce.

AIM

This review aims to estimate the prevalence of hepatic and/or cardiac iron overload quantified by magnetic resonance imaging (MRI) in patients with ESRD who receive hemodialysis (HD), peritoneal dialysis (PD), or have undergone a kidney transplant.

METHODS

A systematic review with meta-analysis was conducted and reported in line with PRISMA (Preferred Reporting Items for Systematic Review and Meta-Analysis) guidelines. MEDLINE and Embase bibliographic databases were searched using a comprehensive list of controlled vocabulary and keywords to identify relevant studies. All studies reporting the prevalence of hepatic and/or cardiac iron overload quantified by MRI in ESRD patients were considered. The Newcastle-Ottawa scale was used to assess the methodological quality of included studies. To investigate the heterogeneity between studies, random-effect meta-analyses for proportions were used.

RESULTS

The review comprised seven studies that included 339 patients. Using meta-analysis, the pooled prevalence of severe and mild to moderate hepatic iron overload quantified by MRI was 0.23 [95% CI: 0.08-0.43] and 0.52 [95% CI: 0.47-0.57], respectively. Only three studies included cardiac iron quantification, and none reported iron overload.

CONCLUSIONS

This review has revealed a high prevalence of severe hepatic iron overload in patients with ESRD treated by HD. Further studies with a larger sample size are needed to determine the impact of iron overload on vital organs in patients with ESRD and guide future research in this understudied field. Proper use of iron chelation and continuous monitoring will help in the early detection of unsolicited complications; however, the low renal clearance of most iron chelators limits the options for treating iron excess in patients with ESRD.

Wearable Artificial Intelligence for Assessing Physical Activity in High School Children

Eighty one percent of adolescents aged 11–17 years are inadequately physically active worldwide. Physical activity (PA) recommendations for high school children have not been studied previously in schools in the Qatar region. The objectives of the study were: (i) to assess the level of compliance of the recommended PA and to assess if there are any gender differences; and (ii) to analyze the recommended step count compliance during school and non-school days. An observational cross-sectional study was conducted. Twenty-nine children (12 boys and 17 girls) aged 13–17 years (15.24 ± 1.46) took part in this study. Participants wore Fitbit Charge 5 wrist bands for three weeks to collect various digital biomarkers including moderate-to-vigorous physical activity (MVPA) and step counts (tracking during out-of-school time and school time). Based on this study, high school children in the two Qatar region schools did not meet the MVPA and steps/day recommendation by the established agencies: 38% of the total study group met the recommended 60 min/day of activity (50% boys, 29% girls). Gender differences were also observed in PA levels and steps per day: for non-school days, 17% met the recommended 10,000 steps/day (25% boys, 12% girls). There was a pattern of greater PA performance and steps during the weekdays as opposed to the weekend, but these values showed no robust evidence in favor of H1 or statistical significance for step counts. However, the evidence was robust in favor of H1 (difference between weekend and weekday) due to a statistically significant difference for meeting the 60 min/day activity. While further studies are required to establish if this is a general trend in Qatari schools, this pilot study does highlight the need to design more effective programs and messaging strategies to improve PA levels in the high school population.

The Role of Artificial Intelligence in Decoding Speech from EEG Signals: A Scoping Review

Background: Brain traumas, mental disorders, and vocal abuse can result in permanent or temporary speech impairment, significantly impairing one's quality of life and occasionally resulting in social isolation. Brain-computer interfaces (BCI) can support people who have issues with their speech or who have been paralyzed to communicate with their surroundings via brain signals. Therefore, EEG signal-based BCI has received significant attention in the last two decades for multiple reasons: (i) clinical research has capitulated detailed knowledge of EEG signals, (ii) inexpensive EEG devices, and (iii) its application in medical and social fields. Objective: This study explores the existing literature and summarizes EEG data acquisition, feature extraction, and artificial intelligence (AI) techniques for decoding speech from brain signals. Method: We followed the PRISMA-ScR guidelines to conduct this scoping review. We searched six electronic databases: PubMed, IEEE Xplore, the ACM Digital Library, Scopus, arXiv, and Google Scholar. We carefully selected search terms based on target intervention (i.e., imagined speech and AI) and target data (EEG signals), and some of the search terms were derived from previous reviews. The study selection process was carried out in three phases: study identification, study selection, and data extraction. Two reviewers independently carried out study selection and data extraction. A narrative approach was adopted to synthesize the extracted data. Results: A total of 263 studies were evaluated; however, 34 met the eligibility criteria for inclusion in this review. We found 64-electrode EEG signal devices to be the most widely used in the included studies. The most common signal normalization and feature extractions in the included studies were the bandpass filter and wavelet-based feature extraction. We categorized the studies based on AI techniques, such as machine learning and deep learning. The most prominent ML algorithm was a support vector machine, and the DL algorithm was a convolutional neural network. Conclusions: EEG signal-based BCI is a viable technology that can enable people with severe or temporal voice impairment to communicate to the world directly from their brain. However, the development of BCI technology is still in its infancy.

Overview of Artificial Intelligence-Driven Wearable Devices for Diabetes: Scoping Review

Background

Prevalence of diabetes has steadily increased over the last few decades with 1.5 million deaths reported in 2012 alone. Traditionally, analyzing patients with diabetes has remained a largely invasive approach. Wearable devices (WDs) make use of sensors historically reserved for hospital settings. WDs coupled with artificial intelligence (AI) algorithms show promise to help understand and conclude meaningful information from the gathered data and provide advanced and clinically meaningful analytics.

Objective

This review aimed to provide an overview of AI-driven WD features for diabetes and their use in monitoring diabetes-related parameters.

Methods

We searched 7 of the most popular bibliographic databases using 3 groups of search terms related to diabetes, WDs, and AI. A 2-stage process was followed for study selection: reading abstracts and titles followed by full-text screening. Two reviewers independently performed study selection and data extraction, and disagreements were resolved by consensus. A narrative approach was used to synthesize the data.

Results

From an initial 3872 studies, we report the features from 37 studies post filtering according to our predefined inclusion criteria. Most of the studies targeted type 1 diabetes, type 2 diabetes, or both (21/37, 57%). Many studies (15/37, 41%) reported blood glucose as their main measurement. More than half of the studies (21/37, 57%) had the aim of estimation and prediction of glucose or glucose level monitoring. Over half of the reviewed studies looked at wrist-worn devices. Only 41% of the study devices were commercially available. We observed the use of multiple sensors with photoplethysmography sensors being most prevalent in 32% (12/37) of studies. Studies reported and compared >1 machine learning (ML) model with high levels of accuracy. Support vector machine was the most reported (13/37, 35%), followed by random forest (12/37, 32%).

Conclusions

This review is the most extensive work, to date, summarizing WDs that use ML for people with diabetes, and provides research direction to those wanting to further contribute to this emerging field. Given the advancements in WD technologies replacing the need for invasive hospital setting devices, we see great advancement potential in this domain. Further work is needed to validate the ML approaches on clinical data from WDs and provide meaningful analytics that could serve as data gathering, monitoring, prediction, classification, and recommendation devices in the context of diabetes.

Clinical Trials on Alternative Medicines for COVID-19

In this study, we addressed the alternative medications that have been targeted in the clinical trials (CTs) to be evidenced as an adjuvant treatment against COVID-19. Based on the outcomes from CTs, we found that dietary supplements such as Lactoferrin, and Probiotics (as SivoMixx) can play a role enhancing the immunity thus can be used as prophylactics against COVID-19 infection. Vitamin D was proven as an effective adjuvant treatment against COVID-19, while Vitamin C role is uncertain and needs more investigation. Herbals such as Guduchi Ghan Vati can be used as prophylactic, while Resveratrol can be used to reduce the hospitalization risk of COVID-19 patients. On the contrary, there were no clinical improvements demonstrated when using Cannabidiol. This study is a part of a two-phase research study. In the first phase, we gathered evidence-based information on alternative therapeutics for COVID-19 that are under CT. In the second phase, we plan to build a mobile health application that will provide evidence based alternative therapy information to health consumers.

Artificial Intelligence-Based Mobile Application for Sensing Children Emotion Through Drawings

Children go through varied emotions such as happiness, sadness, and fear. At times, it may be difficult for children to express their emotions. Detecting and understanding the unexpressed emotions of children is very important to address their needs and prevent mental health issues. In this paper, we develop an artificial intelligence (AI) based Emotion Sensing Recognition App (ESRA) to help parents and teachers understand the emotions of children by analyzing their drawings. We collected 102 drawings from a local school in Doha and 521 drawings from Google and Instagram. Four different experiments were conducted using a combination of the two datasets. The deep learning model was trained using the Fastai library in Python. The model classifies the drawings into positive or negative emotions. The model accuracy ranged from 55% to 79% in the four experiments. This study showed that ESRA has the potential in identifying the emotions of children. However, the underlying algorithm needs to be trained and evaluated using more drawings to improve its current accuracy and to be able to identify more specific emotions.

Effectiveness of Serious Games for Visuospatial Abilities in Elderly Population with Cognitive Impairment: A Systematic Review and Meta-Analysis

We explore the effectiveness of serious games for visuospatial abilities among older adults with cognitive impairment by conducting a systematic review. Out of 548 identified publications, seven randomized controlled trials (RCTs) were included in this review. According to a meta-analysis of four RCTs, there is no statistically significant difference (p=0.28) in visuospatial abilities between serious game and control groups. Further, the included RCTs noted no statistically significant difference in the visuospatial ability when comparing serious games to conventional exercise (one study) and other serious games (two studies). One RCT demonstrated a statistically significant effect of serious games on the visuospatial ability when compared with conventional cognitive training. This review could not prove the effectiveness of serious games in enhancing visuospatial abilities for older adults with cognitive impairment. Thus, serious games should not be offered or used for enhancing visuospatial abilities amongst the elderly population with cognitive impairment. More robust RCTs are needed to make firm conclusions on the efficacy of serious games.

Effectiveness of Serious Games for Language Processing Amongst Elderly Population with Cognitive Impairment: A Systematic Review and Meta-Analysis

This article intended to carry out a systematic review on the effectiveness of serious games for language processing among older adults with cognitive impairment. Out of 548 retrieved records, six randomized controlled trials (RCTs) eventually met the eligibility criteria. A meta-analysis of four studies showed that serious games are more effective than no/passive interventions in enhancing language processing among older adults with cognitive impairment (p=0.008). Further, a statistically significant effect of serious games on language processing when compared with conventional cognitive activities and conventional exercises was reported in two RCTs. Other RCTs found that exergames are as effective as computerized cognitive training games in improving language processing. Serious games should be offered or used as complementary (i.e., not a substitute) to the current interventions. For there to be definitive conclusions about the efficacy of serious games on language processing more trials are needed.

Artificial Intelligence Solutions to Detect Fraud in Healthcare Settings: A Scoping Review

Over the past decade, Artificial Intelligence (AI) technologies have quickly become implemented in protecting data, including detecting fraud in healthcare organizations. This scoping review aims to explore AI solutions utilized in fraud detection occurring in treatment settings. To find relevant literature, PubMed and Google Scholar were searched. Out of 183 retrieved studies, 31 met all inclusion criteria. This review found that AI has been used to detect different types of fraud such as identify theft and kickbacks in healthcare. Additionally, this review discusses how AI techniques used in network mapping fraud can detect and visualize the hacker's network. A proper system must be implemented in healthcare settings for successful fraud detection, which may overall improve the healthcare system.

Artificial Intelligence in Kidney Transplantation: A Scoping Review

Artificial Intelligence (AI) technologies are increasingly being used to enhance kidney transplant outcomes. In this review, we explore the use of AI in kidney transplantation (KT) in the existing literature. Four databases were searched to identify a total of 33 eligible studies. AI technologies were used to help in diagnostic, predictive and medication management purposes for kidney transplant patients. AI is an emerging tool in KT, however, there is a research gap exploring the limitations associated with implementing AI technologies in the field. Research is also needed to recognize clinical educational needs and other barriers to promote adoption and standardization of care for KT patients amongst clinicians.

Artificial Intelligence and the diagnosis of lung cancer in early stage: scoping review. (Preprint).. [DOI: 10.2196/preprints.38773] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Lung cancer is considered to be the most fatal out of all diagnoseable cancers. This is, in part, due to the difficulty in detecting lung cancer at an early stage. Moreover, approximately one in five individuals who will develop lung cancer will pass away due to a misdiagnosis. Fortunately, Machine Learning (ML) and Deep Learning (DL) is considered to be a promising solution for detection of lung cancer through developments in radiology.

OBJECTIVE

The purpose of this paper is to is to review how AI can assist identifying and diagnosing of lung cancer in an early stage.

METHODS

PRISMA was utilized and were retrieved from 4 databases: Google Scholar, PubMed, EMBASE, and Institute of Electrical and Electronics Engineers (IEEE). In addition, two phases of screening were implemented in order to determine relevant literature. The first phase was reading the title and abstract, and the second stage was reading the full text. These two steps were independently conducted by three reviewers. Finally, the three authors use a narrative synthesis to present the data.

RESULTS

Overall, 543 potential studies were extracted from four databases. After screening, 26 articles that met the inclusion criteria were included in this scoping review. Several articles utilized privet data including patients’ data and other public sources. 15 articles used data from UCI repository dataset (58%). However, CT scan images was utilized on 9 studies (normal CT was mentioned in 5 articles (19%), two studies used CT scan with PET (7.7%), and two articles used FDG with CT (7.7%). While two articles used demographic data such as age, sex, and educational background (7.7%).

CONCLUSIONS

This scoping review illustrates recent studies that utilize AI models to diagnose lung cancer. The literature currently relies on private and public databases and compare models with physicians or other machine learning technology. Additional studies should be conducted to explore the efficacy of these technologies in clinical settings.

The Effectiveness of Supervised Machine Learning in Screening and Diagnosing Voice Disorders: A Systematic Review and Meta-Analysis (Preprint).. [DOI: 10.2196/preprints.38472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Voice screening and diagnosis are processes that are used during voice disorders investigations. Both have limited standardized tests, which are affected by the clinician’s experience and subjective judgment. Machine learning (ML) algorithms were introduced and employed in screening/diagnosing patients’ voices as an objective tool. The effectiveness of ML algorithms in assessing and diagnosing voice disorders has been investigated by numerous studies.

OBJECTIVE

This systematic review aims to assess the effectiveness of ML algorithms in screening and diagnosing voice disorders.

METHODS

An electronic search was conducted in five databases. We included studies that examined the performance (accuracy, sensitivity, and specificity) of any ML algorithms in detecting abnormal voice samples. Two reviewers independently selected the studies, extracted data from the included studies, and assessed the risk of bias in the included studies. The methodological quality of each study was assessed using the QUADAS-2 tool. Characteristics of studies, population, and index tests were extracted. Meta-analyses were conducted for pooling accuracy, sensitivity, and specificity of ML techniques. Sources of heterogeneity were addressed by excluding some studies and discussing the possible sources of it.

RESULTS

Out of 1409 records retrieved, 13 studies were included (participants: 4079) in this review. Thirteen machine learning techniques were used in the included studies, but the most commonly used technique was SVM. The pooled accuracy, sensitivity, and specificity of ML techniques in screening voice disorders were 93%, 96%, and 93%, respectively. LS-SVM had the highest accuracy (99%) while K-NN had the highest sensitivity (98%) and specificity (98%). Quadric Discriminant analysis (QDA) achieved the lowest accuracy (91%), sensitivity (89%), and specificity (89%).

CONCLUSIONS

ML showed promising findings in screening voice disorders. However, the findings could not be conclusive in diagnosing voice disorders due to the limited number of studies that used ML for diagnosing purposes, thus, more investigations need to be made. Accordingly, it might not be possible to use ML as a substitution for the current diagnostic tools. Instead, it might be used as a decision support tool for clinicians to assess their patients, this could improve the management process for voice disorders assessment.

The Effectiveness of Supervised Machine Learning in Screening and Diagnosing Voice Disorders: A Systematic Review and Meta-Analysis (Preprint)

Background

Objective

Methods

Results

Conclusions

Trial Registration

Thematic Analysis on User Reviews for Depression and Anxiety Chatbot Apps: Machine Learning Approach

BACKGROUND

Anxiety and depression are among the most commonly prevalent mental health disorders worldwide. Chatbot apps can play an important role in relieving anxiety and depression. Users' reviews of chatbot apps are considered an important source of data for exploring users' opinions and satisfaction.

OBJECTIVE

This study aims to explore users' opinions, satisfaction, and attitudes toward anxiety and depression chatbot apps by conducting a thematic analysis of users' reviews of 11 anxiety and depression chatbot apps collected from the Google Play Store and Apple App Store. In addition, we propose a workflow to provide a methodological approach for future analysis of app review comments.

METHODS

We analyzed 205,581 user review comments from chatbots designed for users with anxiety and depression symptoms. Using scraper tools and Google Play Scraper and App Store Scraper Python libraries, we extracted the text and metadata. The reviews were divided into positive and negative meta-themes based on users' rating per review. We analyzed the reviews using word frequencies of bigrams and words in pairs. A topic modeling technique, latent Dirichlet allocation, was applied to identify topics in the reviews and analyzed to detect themes and subthemes.

RESULTS

Thematic analysis was conducted on 5 topics for each sentimental set. Reviews were categorized as positive or negative. For positive reviews, the main themes were confidence and affirmation building, adequate analysis, and consultation, caring as a friend, and ease of use. For negative reviews, the results revealed the following themes: usability issues, update issues, privacy, and noncreative conversations.

CONCLUSIONS

Using a machine learning approach, we were able to analyze ≥200,000 comments and categorize them into themes, allowing us to observe users' expectations effectively despite some negative factors. A methodological workflow is provided for the future analysis of review comments.

The Effectiveness of Mobile Phone Messaging-Based Interventions to Promote Physical Activity in Type 2 Diabetes Mellitus: Systematic Review and Meta-analysis

Background

The prevalence of type 2 diabetes mellitus (T2DM) is increasing worldwide. Physical activity (PA) is an important aspect of self-care and first line management for T2DM. SMS text messaging can be used to support self-management in people with T2DM, but the effectiveness of mobile text message–based interventions in increasing PA is still unclear.

Objective

This study aims to assess the effectiveness of mobile phone messaging on PA in people with T2DM by summarizing and pooling the findings of previous literature.

Methods

A systematic review was conducted to accomplish this objective. Search sources included 5 bibliographic databases (MEDLINE, Cochrane Library, CINAHL, Web of Science, and Embase), the search engine Google Scholar (Google Inc), and backward and forward reference list checking of the included studies and relevant reviews. A total of 2 reviewers (MA and AA) independently carried out the study selection, data extraction, risk of bias assessment, and quality of evidence evaluation. The results of the included studies were synthesized narratively and statistically, as appropriate.

Results

We included 3.8% (6/151) of the retrieved studies. The results of individual studies were contradictory regarding the effectiveness of mobile text messaging on PA. However, a meta-analysis of the results of 5 studies showed no statistically significant effect (P=.16) of text messages on PA in comparison with no intervention. A meta-analysis of the findings of 2 studies showed a nonsignificant effect (P=.14) of text messages on glycemic control. Of the 541 studies, 2 (0.4%) found a nonsignificant effect of text messages on anthropometric measures (weight and BMI).

Conclusions

We could not draw a definitive conclusion regarding the effectiveness of text messaging on PA, glycemic control, weight, or BMI among patients with T2MD, given the limited number of included studies and their high risk of bias. Therefore, there is a need for more high-quality primary studies.

Trial Registration

PROSPERO International Prospective Register of Systematic Reviews CRD42020156465; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=156465

The effectiveness of serious games on the cognitive processing speed among elderly people with cognitive impairment: A systematic review and meta-analysis (Preprint)

Background

Human cognitive processing speed is known to decline with age. Human cognitive processing speed refers to the time that an individual takes from receiving a stimulus to reacting to it. Serious games, which are video games used for training and educational purposes, have the potential to improve processing speed. Numerous systematic reviews have summarized the evidence regarding the effectiveness of serious games in improving processing speed, but they are undermined by some limitations.

Objective

This study aimed to examine the effectiveness of serious games on the cognitive processing speed of an older adult population living with cognitive impairment.

Methods

A systematic review of randomized controlled trials (RCTs) was conducted. Two search sources were used in this review: 8 electronic databases and backward and forward reference list checking. A total of 2 reviewers independently checked the eligibility of the studies, extracted data from the included studies, and appraised the risk of bias and quality of the evidence. Evidence from the included studies was synthesized using a narrative and statistical approach (ie, meta-analysis), as appropriate.

Results

Of the 548 publications identified, 16 (2.9%) RCTs eventually met all eligibility criteria. Very-low-quality evidence from 50% (8/16) and 38% (6/16) of the RCTs showed no statistically significant effect of serious games on processing speed compared with no or passive intervention groups (P=.77) and conventional exercises (P=.58), respectively. A subgroup analysis showed that both types of serious games (cognitive training games: P=.26; exergames: P=.88) were as effective as conventional exercises in improving processing speed.

Conclusions

There is no superiority of serious games over no or passive interventions and conventional exercises in improving processing speed among older adults with cognitive impairment. However, our findings remain inconclusive because of the low quality of the evidence, the small sample size in most of the included studies, and the paucity of studies included in the meta-analyses. Therefore, until more robust evidence is published, serious games should be offered or used as an adjunct to existing interventions. Further trials should be undertaken to investigate the effect of serious games that specifically target processing speed rather than cognitive abilities in general.

Trial Registration

PROSPERO CRD42022301667; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=301667

Evaluation of Meditation Apps Available on Google Play and Apple Store: An App Review

Many meditation apps have been used to improve the mental wellbeing of individuals. However, little information is available regarding the quality of the applications. This study aims to evaluate meditation apps using the Mobile Applications Rating Scale (MARS). A systematic search for meditation apps was performed on both Android Google Play and Apple iOS Store. We used two keywords to search both app stores: meditation and mindfulness. Out of 623 apps identified, 334 apps were excluded due to language, containing only reminders to meditate, or for not being accessible. A total number of 289 apps remained, of which 280 apps were excluded for being information-only focused, containing religious practices, eating habits, exercises, or for not being free. Therefore, nine apps were included in this review for evaluation. The MARS ratings used in this app review were based on scores from a prior study conducted. The mobile app Headspace had the highest average (4), which is rated as 'good' based on MARS. The remaining apps were rated as acceptable with averages that ranged from 3.2-3.7.

Contribution of Artificial Intelligence in Pregnancy: A Scoping Review

For the past ten years, the healthcare sector and industry has witnessed a surge in Artificial Intelligence (AI) technologies being used in many different medical specialties. Recently, AI-driven technologies have been utilized in medical care for pregnancy. In this work, we present a scoping review that explores the features of AI-driven technologies used in caring for pregnant patients. This review was conducted using the Preferred Reporting Items for Systematic review and Meta-Analyses extension for Scoping Reviews. Our analysis revealed that AI techniques were used in predicting pregnancy disorders such as preeclampsia and gestational diabetes, along with managing and treating ectopic pregnancies. We also found that AI technologies were used to assess risk factors and safety surveillance of pregnant women. We believe that AI-driven technologies have the potential to improve the healthcare provided to pregnant women.

The Effectiveness of Serious Games for Alleviating Depression: Systematic Review and Meta-analysis

BACKGROUND

Depression is a common mental disorder characterized by disturbances in mood, thoughts, or behaviors. Serious games, which are games that have a purpose other than entertainment, have been used as a nonpharmacological therapeutic intervention for depression. Previous systematic reviews have summarized evidence of effectiveness of serious games in reducing depression symptoms; however, they are limited by design and methodological shortcomings.

OBJECTIVE

This study aimed to assess the effectiveness of serious games in alleviating depression by summarizing and pooling the results of previous studies.

METHODS

A systematic review of randomized controlled trials (RCTs) was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. The search sources included 6 bibliographic databases (eg, MEDLINE, PsycINFO, IEEE Xplore), the search engine "Google Scholar," and backward and forward reference list checking of the included studies and relevant reviews. Two reviewers independently carried out the study selection, data extraction, risk of bias assessment, and quality of evidence appraisal. Results of the included studies were synthesized narratively and statistically, as appropriate, according to the type of serious games (ie, exergames or computerized cognitive behavioral therapy [CBT] games).

RESULTS

From an initial 966 citations retrieved, 27 studies met the eligibility criteria, and 16 studies were eventually included in meta-analyses. Very low-quality evidence from 7 RCTs showed no statistically significant effect of exergames on the severity of depressive symptoms as compared with conventional exercises (P=.12). Very low-quality evidence from 5 RCTs showed a statistically and clinically significant difference in the severity of depressive symptoms (P=.004) between exergame and control groups, favoring exergames over no intervention. Very low-quality evidence from 7 RCTs showed a statistically and clinically significant effect of computerized CBT games on the severity of depressive symptoms in comparison with no intervention (P=.003).

CONCLUSIONS

Serious games have the potential to alleviate depression as other active interventions do. However, we could not draw definitive conclusions regarding the effectiveness of serious games due to the high risk of bias in the individual studies examined and the low quality of meta-analyzed evidence. Therefore, we recommend that health care providers consider offering serious games as an adjunct to existing interventions until further, more robust evidence is available. Future studies should assess the effectiveness of serious games that are designed specifically to alleviate depression and deliver other therapeutic modalities, recruit participants with depression, and avoid biases by following recommended guidelines for conducting and reporting RCTs.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42021232969; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=232969.

Electronic Health Records and Physician Burnout: A Scoping Review

This scoping review aims to identify the causes and consequences of physician burnout resulting from using Electronic Health Records (EHRs), as reported by current literature. We identified studies by searching PubMed, Wiley Online Library, and Google Scholar. Study selection and data extraction were conducted by three reviewers independently. Extracted data was then synthesized narratively. Out of 500 references retrieved, 30 studies met all eligibility criteria. We identified six main causes that lead to physician burnout related to the use of EHRs: EHRs' documentation and related tasks, EHRs' poor design, workload, overtime work, inbox alerts, and alert fatigue. We also identified the following consequences of physician burnout: low-quality care, behavioral issues, mental health complications, substance abuse, career dissatisfaction, costly turnover, and a decline in patient safety and satisfaction.

Features of Meditation Apps: A Scoping Review

This review aims to provide an overview of the features of meditation apps as described in empirical literature. Nine databases were searched for this review. Search terms were related to all types of meditation. Study selection and data extraction of the included studies were conducted by two reviewers. We included 93 studies in this review. Headspace was the most common app among studies and the most common type of meditation was mindfulness. Stress was the most targeted health condition by the studies. Future research needs to focus on different mental conditions other than stress to understand the effect of meditation apps on mental health.

The effectiveness of serious games in improving executive functions among older adults with cognitive impairment: A systematic review and meta-analysis (Preprint)

Background

Executive functions are one of the known cognitive abilities that decline with age. They are the high-order cognitive processes that enable an individual to concentrate, plan, and take action. Serious games, which are games developed for specific purposes other than entertainment, could play a positive role in improving executive functions. Several systematic reviews have pooled the evidence about the effectiveness of serious games in improving executive functions; however, they are limited by some weaknesses.

Objective

This study aims to investigate the effectiveness of serious games for improving executive functions among older adults with cognitive impairment.

Methods

A systematic review of randomized controlled trials (RCTs) was conducted. To retrieve relevant studies, 8 electronic databases were searched. Further, reference lists of the included studies and relevant reviews were screened, and we checked studies that cited our included studies. Two reviewers independently checked the eligibility of the studies, extracted data from the included studies, assessed the risk of bias, and appraised the quality of the evidence. We used a narrative and statistical approach, as appropriate, to synthesize results of the included studies.

Results

Of 548 publications identified, 16 RCTs were eventually included in this review. Of the 16 studies, 14 studies were included in 6 meta-analyses. Our meta-analyses showed that serious games are as effective as no or passive interventions at improving executive functions (P=.29). Surprisingly, conventional exercises were more effective than serious games at improving executive functions (P=.03). Our subgroup analysis showed that both types of serious games (cognitive training games, P=.08; exergames, P=.16) are as effective as conventional exercises at improving executive functions. No difference was found between adaptive serious games and nonadaptive serious games for improving executive functions (P=.59).

Conclusions

Serious games are not superior to no or passive interventions and conventional exercises at improving executive functions among older adults with cognitive impairment. However, our findings remain inconclusive due to the low quality of the evidence, the small sample size in most included studies, and the paucity of studies included in the meta-analyses. Accordingly, until more robust evidence is available, serious games should not be offered by health care providers nor used by patients for improving executive functions among older adults with cognitive impairment. Further reviews are needed to assess the long-term effect of serious games on specific executive functions or other cognitive abilities among people from different age groups with or without cognitive impairment.

Trial Registration

PROSPERO CRD42021272757; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=272757

The effectiveness of serious games in improving memory among the elderly with cognitive impairment: A systematic review and meta-analysis (Preprint)

Background

Objective

Methods

Results

Conclusions

Artificial Intelligence for Skin Cancer Detection: Scoping Review

Background

Skin cancer is the most common cancer type affecting humans. Traditional skin cancer diagnosis methods are costly, require a professional physician, and take time. Hence, to aid in diagnosing skin cancer, artificial intelligence (AI) tools are being used, including shallow and deep machine learning–based methodologies that are trained to detect and classify skin cancer using computer algorithms and deep neural networks.

Objective

The aim of this study was to identify and group the different types of AI-based technologies used to detect and classify skin cancer. The study also examined the reliability of the selected papers by studying the correlation between the data set size and the number of diagnostic classes with the performance metrics used to evaluate the models.

Methods

We conducted a systematic search for papers using Institute of Electrical and Electronics Engineers (IEEE) Xplore, Association for Computing Machinery Digital Library (ACM DL), and Ovid MEDLINE databases following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. The studies included in this scoping review had to fulfill several selection criteria: being specifically about skin cancer, detecting or classifying skin cancer, and using AI technologies. Study selection and data extraction were independently conducted by two reviewers. Extracted data were narratively synthesized, where studies were grouped based on the diagnostic AI techniques and their evaluation metrics.

Results

We retrieved 906 papers from the 3 databases, of which 53 were eligible for this review. Shallow AI-based techniques were used in 14 studies, and deep AI-based techniques were used in 39 studies. The studies used up to 11 evaluation metrics to assess the proposed models, where 39 studies used accuracy as the primary evaluation metric. Overall, studies that used smaller data sets reported higher accuracy.

Conclusions

This paper examined multiple AI-based skin cancer detection models. However, a direct comparison between methods was hindered by the varied use of different evaluation metrics and image types. Performance scores were affected by factors such as data set size, number of diagnostic classes, and techniques. Hence, the reliability of shallow and deep models with higher accuracy scores was questionable since they were trained and tested on relatively small data sets of a few diagnostic classes.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

Background

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

Objective

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

Methods

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

Results

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

Conclusions

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

The effectiveness and safety of serious games in improving cognitive abilities among elderly people with cognitive impairment: A systematic review and meta-analysis (Preprint)

Background

Cognitive impairment is a mental disorder that commonly affects elderly people. Serious games, which are games that have a purpose other than entertainment, have been used as a nonpharmacological intervention for improving cognitive abilities. The effectiveness and safety of serious games for improving cognitive abilities have been investigated by several systematic reviews; however, they are limited by design and methodological weaknesses.

Objective

This study aims to assess the effectiveness and safety of serious games for improving cognitive abilities among elderly people with cognitive impairment.

Methods

A systematic review of randomized controlled trials (RCTs) was conducted. The following 8 electronic databases were searched: MEDLINE, Embase, CINAHL, PsycINFO, ACM Digital Library, IEEE Xplore, Scopus, and Google Scholar. We also screened reference lists of the included studies and relevant reviews, as well as checked studies citing our included studies. Two reviewers independently carried out the study selection, data extraction, risk of bias assessment, and quality of evidence appraisal. We used a narrative and statistical approach, as appropriate, to synthesize the results of the included studies.

Results

Fifteen studies met the eligibility criteria among 466 citations retrieved. Of those, 14 RCTs were eventually included in the meta-analysis. We found that, regardless of their type, serious games were more effective than no intervention (P=.04) and conventional exercises (P=.002) for improving global cognition among elderly people with cognitive impairment. Further, a subgroup analysis showed that cognitive training games were more effective than no intervention (P=.05) and conventional exercises (P<.001) for improving global cognition among elderly people with cognitive impairment. Another subgroup analysis demonstrated that exergames (a category of serious games that includes physical exercises) are as effective as no intervention and conventional exercises (P=.38) for improving global cognition among elderly people with cognitive impairment. Although some studies found adverse events from using serious games, the number of adverse events (ie, falls and exacerbations of pre-existing arthritis symptoms) was comparable between the serious game and control groups.

Conclusions

Serious games and specifically cognitive training games have the potential to improve global cognition among elderly people with cognitive impairment. However, our findings remain inconclusive because the quality of evidence in all meta-analyses was very low, mainly due to the risk of bias raised in the majority of the included studies, high heterogeneity of the evidence, and imprecision of total effect sizes. Therefore, psychologists, psychiatrists, and patients should consider offering serious games as a complement and not a substitute to existing interventions until further more robust evidence is available. Further studies are needed to assess the effect of exergames, the safety of serious games, and their long-term effects.

Evaluation Metrics for Health Chatbots: A Delphi Study

BACKGROUND

 In recent years, an increasing number of health chatbots has been published in app stores and described in research literature. Given the sensitive data they are processing and the care settings for which they are developed, evaluation is essential to avoid harm to users. However, evaluations of those systems are reported inconsistently and without using a standardized set of evaluation metrics. Missing standards in health chatbot evaluation prevent comparisons of systems, and this may hamper acceptability since their reliability is unclear.

OBJECTIVES

 The objective of this paper is to make an important step toward developing a health-specific chatbot evaluation framework by finding consensus on relevant metrics.

METHODS

 We used an adapted Delphi study design to verify and select potential metrics that we retrieved initially from a scoping review. We invited researchers, health professionals, and health informaticians to score each metric for inclusion in the final evaluation framework, over three survey rounds. We distinguished metrics scored relevant with high, moderate, and low consensus. The initial set of metrics comprised 26 metrics (categorized as global metrics, metrics related to response generation, response understanding and aesthetics).

RESULTS

 Twenty-eight experts joined the first round and 22 (75%) persisted to the third round. Twenty-four metrics achieved high consensus and three metrics achieved moderate consensus. The core set for our framework comprises mainly global metrics (e.g., ease of use, security content accuracy), metrics related to response generation (e.g., appropriateness of responses), and related to response understanding. Metrics on aesthetics (font type and size, color) are less well agreed upon-only moderate or low consensus was achieved for those metrics.

CONCLUSION

 The results indicate that experts largely agree on metrics and that the consensus set is broad. This implies that health chatbot evaluation must be multifaceted to ensure acceptability.