-
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 -
Journal of the American Academy of... Oct 2020Patients with dementia commonly have problems processing speech in the presence of competing background speech or noise. This difficulty can be present from the very... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Patients with dementia commonly have problems processing speech in the presence of competing background speech or noise. This difficulty can be present from the very early stages of dementia, and may be a preclinical feature of Alzheimer's disease.
PURPOSE
This study investigates whether people with dementia perform worse on the dichotic digit test (DDT), an experimental probe of speech processing in the presence of competing speech, and whether test performance may predict dementia onset.
RESEARCH DESIGN
Systematic review and meta-analysis.
DATA COLLECTION AND ANALYSIS
A literature search was conducted in Medline, Embase, Scopus, and Psycinfo. We included (1) studies that included people with a diagnosis of dementia and a healthy control group with no cognitive impairment; (2) studies that reported results from a DDT in a free-recall response task; and (3) studies that had the dichotic digit mean correct percentage score or right-ear advantage, as outcome measurements.
RESULTS
People with dementia had a lower DDT total score, with a pooled mean difference of 18.6% (95% confidence interval [CI]: 21.2-15.9). Patients with dementia had an increased right-ear advantage relative to controls with a pooled difference of 24.4% (95% CI: 21.8-27.0).
CONCLUSION
The DDT total scores are lower and the right-ear advantage increased in cognitively impaired versus normal control participants. The findings also suggest that the reduction of dichotic digit total score and increase of right-ear advantage progress as cognitive impairment increases. Whether abnormalities in dichotic digit scores could predict subsequent dementia onset should be examined in further longitudinal studies.
Topics: Alzheimer Disease; Dichotic Listening Tests; Hearing; Hearing Disorders; Humans; Mental Recall
PubMed: 33296935
DOI: 10.1055/s-0040-1718700 -
Digital Health 2020To date the application of eHealth strategies among adults and adolescents undergoing metabolic and bariatric surgery (MBS) has not been systematically reviewed. This... (Review)
Review
OBJECTIVE
To date the application of eHealth strategies among adults and adolescents undergoing metabolic and bariatric surgery (MBS) has not been systematically reviewed. This study comprehensively examines eHealth intervention studies among MBS patients within the RE-AIM framework to assess reach, effectiveness, adoption, implementation and maintenance of these efforts.
METHODS
A search was conducted using PubMed, EMBASE, CINAHL, PsycNET and SCOPUS of original research relating to eHealth strategies for MBS patients published in peer-reviewed journals and revealed 38 published articles between 2011 and 2019.
RESULTS
Studies varied widely in terms of design (qualitative to randomized controlled trials) and eHealth delivery method (telemedicine to blog post content) with a balance of pre- or post-MBS use. No studies included adolescents and very few reported (1) a conceptual framework to support study design/outcomes; and (2) race/ethnicity composition.
CONCLUSIONS
Although some studies report that eHealth strategies/interventions are effective in producing post-MBS weight loss and other positive health outcomes, most are pilot studies or have study design limitations. There is an opportunity for development of (1) tailored eHealth interventions to support pre- and post-MBS sustained behavior change and improved outcomes; and (2) rigorous studies that employ robust conceptual frameworks so dissemination and implementation efforts can be mapped to construct-driven outcomes.
PubMed: 32030193
DOI: 10.1177/2055207619898987 -
NPJ Digital Medicine 2020Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to... (Review)
Review
Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.
PubMed: 32195365
DOI: 10.1038/s41746-020-0229-3 -
Frontiers in Digital Health 2022Digital health interventions (DHIs) have increased exponentially all over the world. Furthermore, the interest in the sustainability of digital health interventions is... (Review)
Review
BACKGROUND
Digital health interventions (DHIs) have increased exponentially all over the world. Furthermore, the interest in the sustainability of digital health interventions is growing significantly. However, a systematic synthesis of digital health intervention sustainability challenges is lacking. This systematic review aimed to identify the barriers and facilitators for the sustainability of digital health intervention in low and middle-income countries.
METHODS
Three electronic databases (PubMed, Embase and Web of Science) were searched. Two independent reviewers selected eligible publications based on inclusion and exclusion criteria. Data were extracted and quality assessed by four team members. Qualitative, quantitative or mixed studies conducted in low and middle-income countries and published from January 2000 to May 2022 were included.
RESULTS
The sustainability of digital health interventions is very complex and multidimensional. Successful sustainability of digital health interventions depends on interdependent complex factors that influence the implementation and scale-up level in the short, middle and long term. Barriers identified among others are associated with infrastructure, equipment, internet, electricity and the DHIs. As for the facilitators, they are more focused on the strong commitment and involvement of relevant stakeholders: Government, institutional, sectoral, stakeholders' support, collaborative networks with implementing partners, improved satisfaction, convenience, privacy, confidentiality and trust in clients, experience and confidence in using the system, motivation and competence of staff. All stakeholders play an essential role in the process of sustainability. Digital technology can have long term impacts on health workers, patients, and the health system, by improving data management for decision-making, the standard of healthcare service delivery and boosting attendance at health facilities and using services. Therefore, management changes with effective monitoring and evaluation before, during, and after DHIs are essential.
CONCLUSION
The sustainability of digital health interventions is crucial to maintain good quality healthcare, especially in low and middle-income countries. Considering potential barriers and facilitators for the sustainability of digital health interventions should inform all stakeholders, from their planning until their scaling up. Besides, it would be appropriate at the health facilities level to consolidate facilitators and efficiently manage barriers with the participation of all stakeholders.
PubMed: 36518563
DOI: 10.3389/fdgth.2022.1014375 -
Digital Health 2023Cystic fibrosis causes mucus to build up in the lungs, digestive tract, and other areas. It is the most common chronic lung disease in children and young adults. It... (Review)
Review
BACKGROUND
Cystic fibrosis causes mucus to build up in the lungs, digestive tract, and other areas. It is the most common chronic lung disease in children and young adults. It requires daily medical care. Before the COVID-19 pandemic, telerehabilitation and telehealth were used, but it was after this that there was a boom in these types of assistance in order to continue caring for cystic fibrosis patients.
OBJECTIVE
The objective is to evaluate the effect of telemedicine programs in people with cystic fibrosis.
METHODS
For the search, the PubMed, Scopus, Web of Science, PEDro, Cochrane, and CINAHL databases were used. Randomized controlled trials, pilot studies, and clinical trials have been included. The exclusion criteria have considered that the population did not have another active disease or that telemedicine was not used as the main intervention. This study follows the PRISMA statement and has been registered in the PROSPERO database (CRD42021257647).
RESULTS
A total of 11 articles have been included in the systematic review. No improvements have been found in quality of life, forced expiratory volume, and forced vital capacity. Good results have been found in increasing physical activity and early detection of exacerbations. Adherence and satisfaction are very positive and promising.
CONCLUSIONS
Despite not obtaining significant improvements in some of the variables, it should be noted that the adherence and satisfaction of both patients and workers reinforce the use of this type of care. Future studies are recommended in which to continue investigating this topic.
PubMed: 37654722
DOI: 10.1177/20552076231197023 -
NPJ Digital Medicine Nov 2022In view of the staggering disease and economic burden of mental disorders, internet and mobile-based interventions (IMIs) targeting mental disorders have often been...
In view of the staggering disease and economic burden of mental disorders, internet and mobile-based interventions (IMIs) targeting mental disorders have often been touted to be cost-effective; however, available evidence is inconclusive and outdated. This review aimed to provide an overview of the cost-effectiveness of IMIs for mental disorders and symptoms. A systematic search was conducted for trial-based economic evaluations published before 10th May 2021. Electronic databases (including MEDLINE, PsycINFO, CENTRAL, PSYNDEX, and NHS Economic Evaluations Database) were searched for randomized controlled trials examining IMIs targeting mental disorders and symptoms and conducting a full health economic evaluation. Methodological quality and risk of bias were assessed. Cost-effectiveness was assumed at or below £30,000 per quality-adjusted life year gained. Of the 4044 studies, 36 economic evaluations were reviewed. Guided IMIs were likely to be cost-effective in depression and anxiety. The quality of most evaluations was good, albeit with some risks of bias. Heterogeneity across studies was high because of factors such as different costing methods, design, comparison groups, and outcomes used. IMIs for anxiety and depression have potential to be cost-effective. However, more research is needed into unguided (preventive) IMIs with active control conditions (e.g., treatment as usual) and longer time horizon across a wider range of disorders.Trial registration: PROSPERO Registration No. CRD42018093808.
PubMed: 36424463
DOI: 10.1038/s41746-022-00702-w -
Surgical and Radiologic Anatomy : SRA Apr 2015The tendon of the extensor indicis (EI) is frequently used to restore the loss of function in other digits. However, it shows many variations which include splitting of... (Meta-Analysis)
Meta-Analysis Review
The tendon of the extensor indicis (EI) is frequently used to restore the loss of function in other digits. However, it shows many variations which include splitting of the extensor indicis proprius (EIP) into two or three distal slips, attachment to fingers other than the index such as the extensor medii proprius (EMP), attachment onto the index and the third finger such as the extensor indicis et medii communis, or attachment to both the index and the thumb such as the extensor pollicis et indicis (EPI). This systematic review gathers the available data on the prevalence of EI tendon and its variation in the hand. Twenty-nine cadaveric studies met the inclusion criteria with a total of 3858 hands. Meta-analysis results yielded an overall pooled prevalence estimate (PPE) of EI of 96.5% and PPEs of 92.6, 7.2 and 0.3% for the single-, double- and triple-slip EIP, respectively. The single-slip EIP is frequently inserted on the ulnar side of the extensor digitorum communis of the index (EDC-index) in 98.3%. The double-slip EIP is located on the ulnar side of the EDC-index in 53.5%, on its radial side in 17% and on both sides in 28.7%. Indian populations showed the highest rate of single-slip EIP and the lowest rate of double-slip EIP when compared to Japanese, Europeans and North Americans. The pooled prevalence of EMP, EMIC and EPI were 3.7, 1.6 and 0.75%, respectively. Knowledge of the variants of the EI tendon and their prevalence should help surgeons in correctly choosing the tendon to transfer in hand surgery.
Topics: Cadaver; Dissection; Female; Finger Joint; Hand; Hand Deformities, Congenital; Humans; Male; Musculoskeletal Abnormalities; Prevalence; Tendons
PubMed: 25096501
DOI: 10.1007/s00276-014-1352-0 -
Digital Health 2023mHealth can help with healthcare service delivery for various health issues, but there's a significant gap in the availability and use of mHealth systems between... (Review)
Review
BACKGROUND
mHealth can help with healthcare service delivery for various health issues, but there's a significant gap in the availability and use of mHealth systems between sub-Saharan Africa and Europe, despite the ongoing digitalization of the global healthcare system.
OBJECTIVE
This work aims to compare and investigate the use and availability of mHealth systems in sub-Saharan Africa and Europe, and identify gaps in current mHealth development and implementation in both regions.
METHODS
The study adhered to the PRISMA 2020 guidelines for article search and selection to ensure an unbiased comparison between sub-Saharan Africa and Europe. Four databases (Scopus, Web of Science, IEEE Xplore, and PubMed) were used, and articles were evaluated based on predetermined criteria. Details on the mHealth system type, goal, patient type, health concern, and development stage were collected and recorded in a Microsoft Excel worksheet.
RESULTS
The search query produced 1020 articles for sub-Saharan Africa and 2477 articles for Europe. After screening for eligibility, 86 articles for sub-Saharan Africa and 297 articles for Europe were included. To minimize bias, two reviewers conducted the article screening and data retrieval. Sub-Saharan Africa used SMS and call-based mHealth methods for consultation and diagnosis, mainly for young patients such as children and mothers, and for issues such as HIV, pregnancy, childbirth, and child care. Europe relied more on apps, sensors, and wearables for monitoring, with the elderly as the most common patient group, and the most common health issues being cardiovascular disease and heart failure.
CONCLUSION
Wearable technology and external sensors are heavily used in Europe, whereas they are seldom used in sub-Saharan Africa. More efforts should be made to use the mHealth system to improve health outcomes in both regions, incorporating more cutting-edge technologies like wearables internal and external sensors. Undertaking context-based studies, identifying determinants of mHealth systems use, and considering these determinants during mHealth system design could enhance mHealth availability and utilization.
PubMed: 37377558
DOI: 10.1177/20552076231180972 -
Digital Health 2023Although the pedometer- and accelerometer-based interventions (PABI) have demonstrated efficacy in improving physical activity (PA) and health-related outcomes, the... (Review)
Review
Effectiveness of pedometer- and accelerometer-based interventions in improving physical activity and health-related outcomes among college students: A systematic review and meta-analysis.
BACKGROUND
Although the pedometer- and accelerometer-based interventions (PABI) have demonstrated efficacy in improving physical activity (PA) and health-related outcomes, the dearth of empirical evidence in college students warrants further investigation.
OBJECTIVE
This systematic review and meta-analysis aim to examine the effects of PABI on improving PA and health-related outcomes among college students.
METHODS
PubMed, Web of Science, Embase, Cochrane Library, and PsycINFO were searched for relevant literature from inception to 20 February 2022. Randomized controlled trials (RCTs) conducted among college students with PABI to increase objectively measured PA as the primary outcome were included in this study.
RESULTS
A total of nine RCTs with 527 participants were included in this study. The combined results showed that PABI significantly improved PA (standardized mean difference = 0.41, 95% confidence interval (CI): 0.08, 0.74, = 0.016) and significantly contributed to weight loss (mean differences (MD) = -1.56 kg, 95% CI: -2.40 kg, -0.73 kg, < 0.01), and lower body mass index (MD = -0.33 kg/m, 95% CI: -0.66 kg/m, 0.00 kg/m, = 0.05) compared to the control group, but no significant effects were observed on improvements of body fat (%) and exercise self-efficacy. Interventions in the group of step, general students, pedometer-based intervention, theory, and developed region were significantly more effective in subgroup analyses.
CONCLUSIONS
PABI was found to be effective in promoting PA and weight loss among college students. Future research is needed to further explore the long-term effects of PABI and the characteristics of multiple intervention models.
PubMed: 37492032
DOI: 10.1177/20552076231188213