-
Digital Health 2023Due to the large volume of online health information, while quality remains dubious, understanding the usage of artificial intelligence to evaluate health information... (Review)
Review
BACKGROUND
Due to the large volume of online health information, while quality remains dubious, understanding the usage of artificial intelligence to evaluate health information and surpass human-level performance is crucial. However, the existing studies still need a comprehensive review highlighting the vital machine, and Deep learning techniques for the automatic health information evaluation process.
OBJECTIVE
Therefore, this study outlines the most recent developments and the current state of the art regarding evaluating the quality of online health information on web pages and specifies the direction of future research.
METHODS
In this article, a systematic literature is conducted according to the PRISMA statement in eight online databases PubMed, Science Direct, Scopus, ACM, Springer Link, Wiley Online Library, Emerald Insight, and Web of Science to identify all empirical studies that use machine and deep learning models for evaluating the online health information quality. Furthermore, the selected techniques are compared based on their characteristics, such as health quality criteria, quality measurement tools, algorithm type, and achieved performance.
RESULTS
The included papers evaluate health information on web pages using over 100 quality criteria. The results show no universal quality dimensions used by health professionals and machine or deep learning practitioners while evaluating health information quality. In addition, the metrics used to assess the model performance are not the same as those used to evaluate human performance.
CONCLUSIONS
This systemic review offers a novel perspective in approaching the health information quality in web pages that can be used by machine and deep learning practitioners to tackle the problem more effectively.
PubMed: 38025112
DOI: 10.1177/20552076231212296 -
Frontiers in Aging Neuroscience 2023Diagnostic classification systems and guidelines posit distinguishing patterns of impairment in Alzheimer's (AD) and vascular dementia (VaD). In our study, we aim to...
INTRODUCTION
Diagnostic classification systems and guidelines posit distinguishing patterns of impairment in Alzheimer's (AD) and vascular dementia (VaD). In our study, we aim to identify which diagnostic instruments distinguish them.
METHODS
We searched PubMed and PsychInfo for empirical studies published until December 2020, which investigated differences in cognitive, behavioral, psychiatric, and functional measures in patients older than 64 years and reported information on VaD subtype, age, education, dementia severity, and proportion of women. We systematically reviewed these studies and conducted Bayesian hierarchical meta-regressions to quantify the evidence for differences using the Bayes factor (BF). The risk of bias was assessed using the Newcastle-Ottawa-Scale and funnel plots.
RESULTS
We identified 122 studies with 17,850 AD and 5,247 VaD patients. Methodological limitations of the included studies are low comparability of patient groups and an untransparent patient selection process. In the digit span backward task, AD patients were nine times more probable (BF = 9.38) to outperform VaD patients ( = 0.33, 95% = 0.12, 0.52). In the phonemic fluency task, AD patients outperformed subcortical VaD (sVaD) patients ( = 0.51, 95% = 0.22, 0.77, BF = 42.36). VaD patients, in contrast, outperformed AD patients in verbal ( = -0.61, 95% = -0.97, -0.26, BF = 22.71) and visual ( = -0.85, 95% = -1.29, -0.32, BF = 13.67) delayed recall. We found the greatest difference in verbal memory, showing that sVaD patients outperform AD patients ( = -0.64, 95% = -0.88, -0.36, BF = 72.97). Finally, AD patients performed worse than sVaD patients in recognition memory tasks ( = -0.76, 95% = -1.26, -0.26, BF = 11.50).
CONCLUSION
Our findings show inferior performance of AD in episodic memory and superior performance in working memory. We found little support for other differences proposed by diagnostic systems and diagnostic guidelines. The utility of cognitive, behavioral, psychiatric, and functional measures in differential diagnosis is limited and should be complemented by other information. Finally, we identify research areas and avenues, which could significantly improve the diagnostic value of cognitive measures.
PubMed: 38020767
DOI: 10.3389/fnagi.2023.1267434 -
NPJ Digital Medicine Nov 2023Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most... (Review)
Review
Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.
PubMed: 38012349
DOI: 10.1038/s41746-023-00941-5 -
NPJ Digital Medicine Nov 2023Chronic obstructive pulmonary disease (COPD) is the third leading cause of death and is associated with multiple medical and psychological comorbidities. Therefore,...
Chronic obstructive pulmonary disease (COPD) is the third leading cause of death and is associated with multiple medical and psychological comorbidities. Therefore, future strategies to improve COPD management and outcomes are needed for the betterment of patient care. Wearable technology interventions offer considerable promise in improving outcomes, but prior reviews fall short of assessing their role in the COPD population. In this systematic review and meta-analysis we searched ovid-MEDLINE, ovid-EMBASE, CINAHL, CENTRAL, and IEEE databases from inception to April 2023 to identify studies investigating wearable technology interventions in an adult COPD population with prespecified outcomes of interest including physical activity promotion, increasing exercise capacity, exacerbation detection, and quality-of-life. We identified 7396 studies, of which 37 were included in our review. Meta-analysis showed wearable technology interventions significantly increased: the mean daily step count (mean difference (MD) 850 (494-1205) steps/day) and the six-minute walk distance (MD 5.81 m (1.02-10.61 m). However, the impact was short-lived. Furthermore, wearable technology coupled with another facet (such as health coaching or pulmonary rehabilitation) had a greater impact that wearable technology alone. Wearable technology had little impact on quality-of-life measures and had mixed results for exacerbation avoidance and prediction. It is clear that wearable technology interventions may have the potential to form a core part of future COPD management plans, but further work is required to translate this into meaningful clinical benefit.
PubMed: 38012218
DOI: 10.1038/s41746-023-00962-0 -
PLOS Digital Health Nov 2023The exponential growth of artificial intelligence (AI) in the last two decades has been recognized by many as an opportunity to improve the quality of patient care....
The exponential growth of artificial intelligence (AI) in the last two decades has been recognized by many as an opportunity to improve the quality of patient care. However, medical education systems have been slow to adapt to the age of AI, resulting in a paucity of AI-specific education in medical schools. The purpose of this systematic review is to evaluate the current evidence-based recommendations for the inclusion of an AI education curriculum in undergraduate medicine. Six databases were searched from inception to April 23, 2022 for cross sectional and cohort studies of fair quality or higher on the Newcastle-Ottawa scale, systematic, scoping, and integrative reviews, randomized controlled trials, and Delphi studies about AI education in undergraduate medical programs. The search yielded 991 results, of which 27 met all the criteria and seven more were included using reference mining. Despite the limitations of a high degree of heterogeneity among the study types and a lack of follow-up studies evaluating the impacts of current AI strategies, a thematic analysis of the key AI principles identified six themes needed for a successful implementation of AI in medical school curricula. These themes include ethics, theory and application, communication, collaboration, quality improvement, and perception and attitude. The themes of ethics, theory and application, and communication were further divided into subthemes, including patient-centric and data-centric ethics; knowledge for practice and knowledge for communication; and communication for clinical decision-making, communication for implementation, and communication for knowledge dissemination. Based on the survey studies, medical professionals and students, who generally have a low baseline knowledge of AI, have been strong supporters of adding formal AI education into medical curricula, suggesting more research needs to be done to push this agenda forward.
PubMed: 38011214
DOI: 10.1371/journal.pdig.0000255 -
The Lancet. Digital Health Dec 2023As the number and availability of digital mental health tools increases, patients and clinicians see benefit only when these tools are engaging and well integrated into... (Review)
Review
As the number and availability of digital mental health tools increases, patients and clinicians see benefit only when these tools are engaging and well integrated into care. Digital navigators-ie, members of health-care teams who are dedicated to supporting patient use of digital resources-offer one solution and continue to be piloted in behavioural health; however, little is known about the core features of this position. The aims of this systematic review were to assess how digital navigators are implemented in behavioural health, and to provide a standardised definition of this position. In January, 2023, we conducted a systematic literature search resulting in 48 articles included in this systematic review. Results showed high heterogeneity between four attributes of digital navigators: training specifications, educational background, frequency of communication, and method of communication with patients. Reported effect sizes for depression and anxiety were medium to large, but could not be synthesised due to study heterogeneity and small study sample size. This systematic review was registered with PROSPERO (CRD42023391696). Results suggest that digital navigator support can probably increase access to, engagement with, and clinical integration of digital health technology, with standards for training and defined responsibilities now emerging.
Topics: Humans; Mental Health; Anxiety Disorders; Communication; Biomedical Technology
PubMed: 38000876
DOI: 10.1016/S2589-7500(23)00152-8 -
The Lancet. Digital Health Dec 2023Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease... (Meta-Analysis)
Meta-Analysis
Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis.
BACKGROUND
Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps.
METHODS
We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052).
FINDINGS
We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias.
INTERPRETATION
There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility.
FUNDING
None.
Topics: Adult; Humans; Reproducibility of Results; Deep Learning; Quality of Life; Pulmonary Disease, Chronic Obstructive; Prognosis
PubMed: 38000872
DOI: 10.1016/S2589-7500(23)00177-2 -
International Journal of Digital Earth 2023Geospatial social media (GSM) data has been increasingly used in public health due to its rich, timely, and accessible spatial information, particularly in infectious...
Geospatial social media (GSM) data has been increasingly used in public health due to its rich, timely, and accessible spatial information, particularly in infectious disease research. This review synthesized 86 research articles that use GSM data in infectious diseases published between December 2013 and March 2022. These articles cover 12 infectious disease types ranging from respiratory infectious diseases to sexually transmitted diseases with spatial levels varying from the neighborhood, county, state, and country. We categorized these studies into three major infectious disease research domains: surveillance, explanation, and prediction. With the assistance of advanced statistical and spatial methods, GSM data has been widely and deeply applied to these domains, particularly in surveillance and explanation domains. We further identified four knowledge gaps in terms of contextual information use, application scopes, spatiotemporal dimension, and data limitations and proposed innovation opportunities for future research. Our findings will contribute to a better understanding of using GSM data in infectious diseases studies and provide insights into strategies for using GSM data more effectively in future research.
PubMed: 37997607
DOI: 10.1080/17538947.2022.2161652 -
Systematic Reviews Nov 2023Symbrachydactyly is a rare congenital malformation of the hand characterized by short or even absent fingers with or without syndactyly, mostly unilaterally present. The...
Symbrachydactyly is a rare congenital malformation of the hand characterized by short or even absent fingers with or without syndactyly, mostly unilaterally present. The hand condition can vary from a small hand to only nubbins on the distal forearm. This study aims to systematically review the surgical management options for symbrachydactyly and compare functional and aesthetic outcomes.The review was performed according to the PRISMA guidelines. Literature was systematically assessed searching the Cochrane Library, PubMed, Embase, and PROSPERO databases up to January 1, 2023. Studies were identified using synonyms for 'symbrachydactyly' and 'treatment'. Inclusion criteria were the report of outcomes after surgical treatment of symbrachydactyly in humans. Studies were excluded if they were written in another language than English, German, or French. Case reports, letters to the editor, studies on animals, cadaveric, in vitro studies, biomechanical reports, surgical technique description, and papers discussing traumatic or oncologic cases were excluded.Twenty-four studies published were included with 539 patients (1037 digit corrections). Only one study included and compared two surgical techniques. The quality of the included studies was assessed using the Modified Coleman Methodology Score and ranged from 25 to 47. The range of motion was the main reported outcome and demonstrated modest results in all surgical techniques. The report on aesthetics of the hand was limited in non-vascularized transfers to 2/8 studies and in vascularized transfers to 5/8 studies, both reporting satisfactory results. On average, there was a foot donor site complication rate of 22% in non-vascularized transfers, compared to 2% in vascularized transfers. The hand-related complication rate of 54% was much higher in the vascularized group than in the non-vascularized transfer with 16%.No uniform strategy to surgically improve symbrachydactyly exists. All discussed techniques show limited functional improvement with considerable complication rates, with the vascularized transfer showing relative high hand-related complications and the non-vascularized transfer showing relative high foot-related complications.There were no high-quality studies, and due to a lack of comparing studies, the data could only be analysed qualitatively. Systematic assessment of studies showed insufficient evidence to determine superiority of any procedure to treat symbrachydactyly due to inadequate study designs and comparative studies. This systematic review was registered at the National Institute for Health Research PROSPERO International Prospective Register of Systematic Reviews number: CRD42020153590 and received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.Level of evidenceI.Systematic review registrationPROSPERO CRD42020153590.
PubMed: 37974291
DOI: 10.1186/s13643-023-02362-7 -
Frontiers in Digital Health 2023Virtual fracture clinics (VFC) involve a consultant-led multidisciplinary team meeting where cases are reviewed before a telephone consultation with the patient. VFCs... (Review)
Review
INTRODUCTION
Virtual fracture clinics (VFC) involve a consultant-led multidisciplinary team meeting where cases are reviewed before a telephone consultation with the patient. VFCs have the advantages of reducing waiting times, outpatient appointments and time off school compared to face-to-face (F2F) fracture clinics. There has been a surge in VFC use since the COVID-19 pandemic but there are still concerns over safety in the paediatric population. Fractures make up a large burden of paediatric injuries, therefore research is required on the safety and efficacy of paediatric VFCs. This systematic review will look at the safety and effectiveness of paediatric VFCs, as well as determine the cost-effectiveness and parent preferences.
METHODS
As per the PRISMA guidelines two independent reviewers searched the following databases: Medline, Embase and Web of Science. Studies were included if children under 18 years old presented to A&E with a suspected or confirmed simple un-displaced fracture and were referred to a VFC. The primary outcomes assessed were effectiveness and safety, with the secondary outcomes of cost-effectiveness and parent satisfaction.
RESULTS
Six studies met the inclusion criteria for this systematic review. There was a high rate of direct discharge from the VFC leading to reduced outpatient appointments. All patients were seen within 72 h of presentation. There were limited incidences of missed fractures and the rates of re-presentation were similar to that of F2F orthopaedic clinics. There were significant cost savings for the hospitals and high parent satisfaction.
DISCUSSION
VFCs have shown to be safe and effective at managing most stable, low operative risk paediatric fractures. Safety must be ensured with a telephone helpline and an open return to fracture clinic policy. More research is needed into specific paediatric fracture types to be managed in the VFC.
SYSTEMATIC REVIEW REGISTRATION
https://www.crd.york.ac.uk/PROSPERO/#searchadvanced, identifier: CRD42023423795.
PubMed: 37964895
DOI: 10.3389/fdgth.2023.1261035