-
NPJ Digital Medicine Dec 2023Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage,... (Review)
Review
Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage, there is a scarcity of comprehensive evaluations of their impact on mental health and well-being. This systematic review and meta-analysis aims to fill this gap by synthesizing evidence on the effectiveness of AI-based CAs in improving mental health and factors influencing their effectiveness and user experience. Twelve databases were searched for experimental studies of AI-based CAs' effects on mental illnesses and psychological well-being published before May 26, 2023. Out of 7834 records, 35 eligible studies were identified for systematic review, out of which 15 randomized controlled trials were included for meta-analysis. The meta-analysis revealed that AI-based CAs significantly reduce symptoms of depression (Hedge's g 0.64 [95% CI 0.17-1.12]) and distress (Hedge's g 0.7 [95% CI 0.18-1.22]). These effects were more pronounced in CAs that are multimodal, generative AI-based, integrated with mobile/instant messaging apps, and targeting clinical/subclinical and elderly populations. However, CA-based interventions showed no significant improvement in overall psychological well-being (Hedge's g 0.32 [95% CI -0.13 to 0.78]). User experience with AI-based CAs was largely shaped by the quality of human-AI therapeutic relationships, content engagement, and effective communication. These findings underscore the potential of AI-based CAs in addressing mental health issues. Future research should investigate the underlying mechanisms of their effectiveness, assess long-term effects across various mental health outcomes, and evaluate the safe integration of large language models (LLMs) in mental health care.
PubMed: 38114588
DOI: 10.1038/s41746-023-00979-5 -
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 -
American Journal of Human Biology : the... Mar 2022Digit ratio (2D:4D), a marker of prenatal testosterone exposure, is a weak negative correlate of sports/athletic/fitness performance. While numerous studies have... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Digit ratio (2D:4D), a marker of prenatal testosterone exposure, is a weak negative correlate of sports/athletic/fitness performance. While numerous studies have examined the relationship between 2D:4D and physical fitness, there has never been a comprehensive study that has synthesized studies examining relationships between 2D:4D and muscular fitness.
OBJECTIVES
To systematically review and meta-analyze the relationship between 2D:4D and muscular fitness measured as handgrip strength (HGS).
METHODS
We systematically searched five electronic databases, reference lists, topical systematic reviews/meta-analyses, and personal libraries in November 2020. Peer-reviewed, cross-sectional studies that reported Pearson's correlation coefficients between objectively measured 2D:4D and HGS were included. We used random-effects meta-analysis to estimate the pooled correlation and the 95% confidence interval (95%CI), and moderator analyses to estimate the influence of sex and age.
RESULTS
Data from 22 studies, representing 5271 individuals from 11 countries ranging in (mean) age from 10.4 to 58.0 years, were included. Overall, there was a weak negative correlation between 2D:4D and HGS (r = -0.15, 95%CI = -0.20 to -0.09), indicating that individuals with low 2D:4Ds had high HGS. We found substantial heterogeneity between studies (Q = 123.4, p < .0001; I = 74%), but neither sex (Q = 0.003, p = .96) nor age (Q = 0.46, p = .50) significantly moderated the pooled correlation.
CONCLUSIONS
We found a weak negative relationship between 2D:4D and HGS, which showed substantial heterogeneity between studies, but was neither moderated by sex nor age. Our finding probably reflects both the long-term (organizational) and short-term (activational) benefits of testosterone.
Topics: Adolescent; Adult; Athletic Performance; Child; Cross-Sectional Studies; Digit Ratios; Fingers; Hand Strength; Humans; Middle Aged; Testosterone; Young Adult
PubMed: 34331730
DOI: 10.1002/ajhb.23657 -
Journal of Hand and Microsurgery Aug 2020There is a lack of consensus on what the critical outcomes in replantation are and how best to measure them. This review aims to identify all reported outcomes and... (Review)
Review
There is a lack of consensus on what the critical outcomes in replantation are and how best to measure them. This review aims to identify all reported outcomes and respective outcome measures used in digital replantation. Randomized controlled trials, cohort studies, and single-arm observational studies of adults undergoing replantation with at least one well-described outcome or outcome measure were identified. Primary outcomes were classified into six domains, and outcome measures were classified into eight domains. The clinimetric properties were identified and reported. A total of 56 observational studies met the inclusion criteria. In total, 29 continuous and 29 categorical outcomes were identified, and 87 scales and instruments were identified. The most frequently used outcomes were survival of replanted digit, sensation, and time in hospital. Outcomes and measures were most variable in domains of viability, quality of life, and motor function. Only eight measures used across these domains were validated and proven reliable. Lack of consensus creates an obstacle to reporting, understanding, and comparing the effectiveness of various replantation strategies.
PubMed: 33335363
DOI: 10.1055/s-0040-1701324 -
Frontiers in Digital Health 2022Pain is a silent global epidemic impacting approximately a third of the population. Pharmacological and surgical interventions are primary modes of treatment.... (Review)
Review
IMPORTANCE
Pain is a silent global epidemic impacting approximately a third of the population. Pharmacological and surgical interventions are primary modes of treatment. Cognitive/behavioural management approaches and interventional pain management strategies are approaches that have been used to assist with the management of chronic pain. Accurate data collection and reporting treatment outcomes are vital to addressing the challenges faced. In light of this, we conducted a systematic evaluation of the current digital application landscape within chronic pain medicine.
OBJECTIVE
The primary objective was to consider the prevalence of digital application usage for chronic pain management. These digital applications included mobile apps, web apps, and chatbots.
DATA SOURCES
We conducted searches on PubMed and ScienceDirect for studies that were published between 1st January 1990 and 1st January 2021.
STUDY SELECTION
Our review included studies that involved the use of digital applications for chronic pain conditions. There were no restrictions on the country in which the study was conducted. Only studies that were peer-reviewed and published in English were included. Four reviewers had assessed the eligibility of each study against the inclusion/exclusion criteria. Out of the 84 studies that were initially identified, 38 were included in the systematic review.
DATA EXTRACTION AND SYNTHESIS
The AMSTAR guidelines were used to assess data quality. This assessment was carried out by 3 reviewers. The data were pooled using a random-effects model.
MAIN OUTCOMES AND MEASURES
Before data collection began, the primary outcome was to report on the standard mean difference of digital application usage for chronic pain conditions. We also recorded the type of digital application studied (e.g., mobile application, web application) and, where the data was available, the standard mean difference of pain intensity, pain inferences, depression, anxiety, and fatigue.
RESULTS
38 studies were included in the systematic review and 22 studies were included in the meta-analysis. The digital interventions were categorised to web and mobile applications and chatbots, with pooled standard mean difference of 0.22 (95% CI: -0.16, 0.60), 0.30 (95% CI: 0.00, 0.60) and -0.02 (95% CI: -0.47, 0.42) respectively. Pooled standard mean differences for symptomatologies of pain intensity, depression, and anxiety symptoms were 0.25 (95% CI: 0.03, 0.46), 0.30 (95% CI: 0.17, 0.43) and 0.37 (95% CI: 0.05, 0.69), respectively. A sub-group analysis was conducted on pain intensity due to the heterogeneity of the results ( = 82.86%; = 0.02). After stratifying by country, we found that digital applications were more likely to be effective in some countries (e.g., United States, China) than others (e.g., Ireland, Norway).
CONCLUSIONS AND RELEVANCE
The use of digital applications in improving pain-related symptoms shows promise, but further clinical studies would be needed to develop more robust applications.
SYSTEMATIC REVIEW REGISTRATION
https://www.crd.york.ac.uk/prospero/, identifier: CRD42021228343.
PubMed: 36405414
DOI: 10.3389/fdgth.2022.850601 -
Sleep Medicine: X Dec 2023Insomnia is a common disease, and the application of various types of sleeping pills for cognitive impairment is controversial, especially as different doses can lead to... (Review)
Review
BACKGROUND
Insomnia is a common disease, and the application of various types of sleeping pills for cognitive impairment is controversial, especially as different doses can lead to different effects. Therefore, it is necessary to evaluate the cognitive impairment caused by different sleeping pills to provide a theoretical basis for guiding clinicians in the selection of medication regimens.
OBJECTIVE
To evaluate whether various different doses (low, medium and high) of anti-insomnia drugs, such as the dual-orexin receptor antagonist (DORA), zopiclone, eszopiclone and zolpidem, induce cognitive impairment.
METHODS
The PubMed, Embase, Scopus, Cochrane Library, and Google Scholar databases were searched from inception to September 20th, 2022 for keywords in randomized controlled trials (RCTs) to evaluate the therapeutic effects of DORA, eszopiclone, zopiclone and zolpidem on sleep and cognitive function. The primary outcomes were indicators related to cognitive characteristics, including scores on the Digit Symbol Substitution Test (DSST) and daytime alertness. The secondary outcomes were the indicators associated with sleep and adverse events. Continuous variables were expressed as the standard mean difference (SMD). Data were obtained through GetData 2.26 and analyzed by Stata v.15.0.
RESULTS
A total of 8702 subjects were included in 29 studies. Eszopiclone significantly increased the daytime alertness score (SMD = 3.00, 95 % CI: 1.86 to 4.13) compared with the placebo, and eszopiclone significantly increased the daytime alertness score (SMD = 4.21, 95 % CI: 1.65 to 6.77; SMD = 3.95, 95 % CI: 1.38 to 6.51; SMD = 3.26, 95 % CI: 0.38 to 6.15; and SMD = 3.23, 95 % CI: 0.34 to 6.11) compared with zolpidem, zolpidem, DORA, and eszopiclone, respectively. Compared with the placebo, zopiclone, zolpidem, and eszopiclone, DORA significantly increased the TST (SMD = 2.39, 95 % CI: 1.11 to 3.67; SMD = 6.00, 95 % CI: 2.73 to 9.27; SMD = 1.89, 95 % CI: 0.90 to 2.88; and SMD = 1.70, 95 % CI: 0.42 to 2.99, respectively).
CONCLUSION
We recommend DORA as the best intervention for insomnia because it was highly effective in inducing and maintaining sleep without impairing cognition. Although zolpidem had a more pronounced effect on sleep maintenance, this drug is better for short-term use. Eszopiclone and zopiclone improved sleep, but their cognitive effects have yet to be verified.
PubMed: 38149178
DOI: 10.1016/j.sleepx.2023.100094 -
Digital Health 2023Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for... (Review)
Review
OBJECTIVE
Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases.
METHODS
A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection.
RESULTS
The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance.
CONCLUSIONS
This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.
PubMed: 37214662
DOI: 10.1177/20552076231173569 -
Psychological Medicine Aug 2022Persons at clinical high-risk for psychosis (CHR) are characterised by specific neurocognitive deficits. However, the course of neurocognitive performance during the... (Meta-Analysis)
Meta-Analysis Review
Persons at clinical high-risk for psychosis (CHR) are characterised by specific neurocognitive deficits. However, the course of neurocognitive performance during the prodromal period and over the onset of psychosis remains unclear. The aim of this meta-analysis was to synthesise results from follow-up studies of CHR individuals to examine longitudinal changes in neurocognitive performance. Three electronic databases were systematically searched to identify articles published up to 31 December 2021. Thirteen studies met inclusion criteria. Study effect sizes (Hedges' ) were calculated and pooled for each neurocognitive task using random-effects meta-analyses. We examined whether changes in performance between baseline and follow-up assessments differed between: (1) CHR and healthy control (HC) individuals, and (2) CHR who did (CHR-T) and did not transition to psychosis (CHR-NT). Meta-analyses found that HC individuals had greater improvements in performance over time compared to CHR for letter fluency ( = -0.32, = 0.029) and digit span ( = -0.30, = 0.011) tasks. Second, there were differences in longitudinal performance of CHR-T and CHR-NT in trail making test A (TMT-A) ( = 0.24, = 0.014) and symbol coding ( = -0.51, = 0.011). Whilst CHR-NT improved in performance on both tasks, CHR-T improved to a lesser extent in TMT-A and had worsened performance in symbol coding over time. Together, neurocognitive performance generally improved in all groups at follow-up. Yet, evidence suggested that improvements were less pronounced for an overall CHR group, and specifically for CHR-T, in processing speed tasks which may be a relevant domain for interventions aimed to enhance neurocognition in CHR populations.
Topics: Humans; Neuropsychological Tests; Disease Progression; Psychotic Disorders; Prodromal Symptoms; Cognition Disorders; Longitudinal Studies
PubMed: 35821623
DOI: 10.1017/S0033291722001830 -
NPJ Digital Medicine Jan 2022Machine learning (ML) is a rapidly advancing field with increasing utility in health care. We conducted a systematic review and critical appraisal of ML applications in... (Review)
Review
Machine learning (ML) is a rapidly advancing field with increasing utility in health care. We conducted a systematic review and critical appraisal of ML applications in vascular surgery. MEDLINE, Embase, and Cochrane CENTRAL were searched from inception to March 1, 2021. Study screening, data extraction, and quality assessment were performed by two independent reviewers, with a third author resolving discrepancies. All original studies reporting ML applications in vascular surgery were included. Publication trends, disease conditions, methodologies, and outcomes were summarized. Critical appraisal was conducted using the PROBAST risk-of-bias and TRIPOD reporting adherence tools. We included 212 studies from a pool of 2235 unique articles. ML techniques were used for diagnosis, prognosis, and image segmentation in carotid stenosis, aortic aneurysm/dissection, peripheral artery disease, diabetic foot ulcer, venous disease, and renal artery stenosis. The number of publications on ML in vascular surgery increased from 1 (1991-1996) to 118 (2016-2021). Most studies were retrospective and single center, with no randomized controlled trials. The median area under the receiver operating characteristic curve (AUROC) was 0.88 (range 0.61-1.00), with 79.5% [62/78] studies reporting AUROC ≥ 0.80. Out of 22 studies comparing ML techniques to existing prediction tools, clinicians, or traditional regression models, 20 performed better and 2 performed similarly. Overall, 94.8% (201/212) studies had high risk-of-bias and adherence to reporting standards was poor with a rate of 41.4%. Despite improvements over time, study quality and reporting remain inadequate. Future studies should consider standardized tools such as PROBAST and TRIPOD to improve study quality and clinical applicability.
PubMed: 35046493
DOI: 10.1038/s41746-021-00552-y -
Journal of Clinical Neuroscience :... Jan 2024Considering the different results regarding the correlation between Magnetic Resonance Imaging (MRI) structural measures and cognitive dysfunction in patients with MS,... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Considering the different results regarding the correlation between Magnetic Resonance Imaging (MRI) structural measures and cognitive dysfunction in patients with MS, we aimed to perform a systematic review and meta-analysis study to investigate the correlation between T1 and T2 weighted lesions and cognitive scores to find the most robust MRI markers for cognitive function in MS population.
METHODS
The literature of this paper was identified through a comprehensive search of electronic datasets including PubMed, Scopus, Web of Science, and Embase in February 2022. Studies that reported the correlation between cognitive status and T1 and T2 weighted lesions in MS patients were selected.
RESULTS
21 studies with a total of 3771 MS patients with mean ages ranging from 30 to 57 years were entered into our study. Our analysis revealed that the volume of T1 lesions was significantly correlated with Symbol Digit Modality test (SDMT) (r: -0.30, 95 %CI: -0.59, -0.01) and Paced Auditory Serial-Addition Task (PASAT) scores (r: -0.23, 95 %CI: -0.36, -0.10). We investigated the correlation between T2 lesions and cognitive scores. The pooled estimates of z scores were significant for SDMT (r: -0.27, 95 %CI: -0.51, -0.03) and PASAT (r: -0.27, 95 %CI: -0.41, -0.13).
CONCLUSION
In conclusion, our systematic review and meta-analysis study provides strong evidence of the correlation between T1 and T2 lesions and cognitive function in MS patients. Further research is needed to explore the potential mechanisms underlying this relationship and to develop targeted interventions to improve cognitive outcomes in MS patients.
Topics: Humans; Adult; Middle Aged; Multiple Sclerosis; Cognition; Cognitive Dysfunction; Magnetic Resonance Imaging; Neuropsychological Tests
PubMed: 37952373
DOI: 10.1016/j.jocn.2023.11.014