Search

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance. [ABSTRACT FROM AUTHOR]

Background: Chronic ankle instability (CAI) is manifested by sensorimotor impairments in the sprained ankle, including deficits in sensation, motor function, and central integration or processing. These impairments have a significant impact on physical activities and daily life. Recently, some studies have suggested that bilateral deficits were observed in unilateral CAI, but contradictory evidence disputes this finding. Therefore, the objective of this study was to investigate whether bilateral sensorimotor deficits presented in individuals with unilateral CAI. Methods: Without language restriction, the following databases were retrieved from database inception up until 3 November 2023, including PubMed, WOS, EMBASE, Cochrane, SPORTDiscus and CINAHL. Case-control and cross-sectional studies that investigated bilateral sensorimotor functions in individuals with unilateral CAI were included. Sensorimotor functions contained static and dynamic balance, functional performance, muscle strength and activation, as well as sensation. Outcome measures contained centre-of-pressure parameters, normalised reach distance, activation time and magnitude of muscle, sensory errors and threshold. The risk of bias and quality assessment of included studies were evaluated using a standardised tool recommended by the Cochrane Collaboration and the Epidemiological Appraisal Instrument, respectively. To explore the potential bilateral deficits associated with unilateral CAI, a comprehensive meta-analysis was conducted using Review Manager version 5.4. The analysis compared the injured limb of unilateral CAI with healthy controls and the uninjured limb with healthy controls. The main focus of this study was to investigate the differences between the uninjured limb and healthy controls. A random-effects model was employed and effect sizes were estimated using the standardised mean difference (SMD) with 95% confidence intervals (CIs). Effect sizes were deemed as weak (0.2–0.5), moderate (0.5–0.8), or large (> 0.8). Results: A total of 11,442 studies were found; 30 studies were contained in the systematic review and 20 studies were included in the meta-analysis. Compared with healthy controls, those with unilateral CAI presented weak to moderate impairments in their uninjured limbs in static balance with eyes open (SMD = 0.32, 95% CI: 0.08 to 0.56), functional performance (SMD = 0.37; 95% CI: 0.08 to 0.67), kinesthesia (SMD = 0.52; 95% CI: 0.09 to 0.95) and tibialis anterior activation (SMD = 0.60, 95% CI: 0.19 to 1.01). There were no significant differences in other comparisons between the uninjured limb and healthy controls. Conclusions: Patients with unilateral CAI may present bilateral deficits in static balance with eyes open, functional performance and kinaesthesia. However, further evidence is required to confirm this point due to limited studies included in some analyses and small effect size. Registration: The protocol was registered in the International Prospective Register of Systematic Reviews platform (CRD: 42,022,375,855). Key Points This study conducted a meta-analysis to investigate bilateral functions in patients with unilateral chronic ankle instability (CAI). The analysis compared the injured limb of unilateral CAI with healthy control and the uninjured limb with healthy control. Patients with unilateral CAI may present bilateral deficits in static balance with eyes open, functional performance and kinesthesia. However, further large-scale studies are required to validate these findings. In future research, it is crucial to apply bilateral assessment in individuals with unilateral CAI and explore interventions targeting both limbs. Additionally, considering the differences between mechanical and functional ankle instability, future studies could explore the bilateral characteristics based on this classification to gain a better understanding of the variations between the two. This will provide more specific guidance for developing effective training methods. [ABSTRACT FROM AUTHOR]

Objective: To compare the outcomes associated with the use of lasmiditan, rimegepant, ubrogepant, and zavegepant for the acute management of migraine headaches. Methods: We searched four electronic databases from database inception to August 31, 2023, to identify randomized controlled trials (RCTs) that report efficacy and safety for the acute treatment of migraine. The risk of bias in the included RCTs was evaluated according to the Cochrane tool, and the certainty of evidence using the CINeMA approach. We conducted frequentist network meta-analyses (NMA) to summarise the evidence. Data were analyzed using R-4.3.1. Results: A total of 18 eligible studies including 10 different types of interventions with 22,429 migraine patients were included. NMA results showed that compared to ubrogepant (25 mg and 50 mg) and zavegepant, lasmiditan (100 mg and 200 mg) exhibits an elevated probability of achieving pain relief within a 2-hour interval. Similarly, relative to zavegepant, rimegepant (75 mg) and ubrogepant (50 mg and 100 mg) demonstrate an enhanced likelihood of sustaining pain relief over a 24-hour period. Furthermore, in contrast to ubrogepant (25 mg) and lasmiditan (50 mg), rimegepant (75 mg) presents a heightened probability of achieving freedom from photophobia within 2 h. Regarding safety, lasmiditan carries the highest risk of adverse events, which are associated with an increased incidence of adverse effects, including dizziness, somnolence, asthenia, paresthesia, and fatigue. Conclusions: In this NMA, a spectrum of evidence ranging from very low to high levels underscores the favorable efficacy and tolerability of rimegepant 75 mg and ubrogepant 100 mg, positioning them as potential candidates for the acute management of migraine. Concurrently, lasmiditan (100 mg and 200 mg) exhibits notable efficacy, albeit accompanied by an increased susceptibility to adverse events. These findings should still be approached with caution, primarily due to the intrinsic limitations associated with indirect comparisons. [ABSTRACT FROM AUTHOR]

Background: Despite the increasing number of research studies examining the effects of age on the control of posture, the number of annual fall-related injuries and deaths continues to increase. A better understanding of how old age affects the neural mechanisms of postural control and how countermeasures such as balance training could improve the neural control of posture to reduce falls in older individuals is therefore necessary. The aim of this review is to determine the effects of age on the neural correlates of balance skill learning measured during static (standing) and dynamic (walking) balance tasks in healthy individuals. Methods: We determined the effects of acute (1–3 sessions) and chronic (> 3 sessions) balance skill training on balance in the trained and in untrained, transfer balance tasks through a systematic review and quantified these effects by robust variance estimation meta-analysis in combination with meta-regression. We systematically searched PubMed, Web of Science, and Cochrane databases. Balance performance and neural plasticity outcomes were extracted and included in the systematic synthesis and meta-analysis. Results: Forty-two studies (n = 622 young, n = 699 older individuals) were included in the systematic synthesis. Seventeen studies with 508 in-analysis participants were eligible for a meta-analysis. The overall analysis revealed that acute and chronic balance training had a large effect on the neural correlates of balance skill learning in the two age groups combined (g = 0.79, p < 0.01). Both age groups similarly improved balance skill performance in 1–3 training sessions and showed little further improvements with additional sessions. Improvements in balance performance mainly occurred in the trained and less so in the non-trained (i.e., transfer) balance tasks. The systematic synthesis and meta-analysis suggested little correspondence between improved balance skills and changes in spinal, cortical, and corticospinal excitability measures in the two age groups and between the time courses of changes in balance skills and neural correlates. Conclusions: Balance skill learning and the accompanying neural adaptations occur rapidly and independently of age with little to no training dose-dependence or correspondence between behavioral and neural adaptations. Of the five types of neural correlates examined, changes in only spinal excitability seemed to differ between age groups. However, age or training dose in terms of duration did not moderate the effects of balance training on the changes in any of the neural correlates. The behavioral and neural mechanisms of strong task-specificity and the time course of skill retention remain unclear and require further studies in young and older individuals. Registration: PROSPERO registration number: CRD42022349573. Key Points: We examined the effects of balance training on balance performance, and its neural correlates in healthy younger (n = 21 studies) and older individuals (n = 18 studies) Balance training improves the trained balance skill rapidly, i.e., 30–40 min Balance training improves the non-trained balance skills (i.e., transfer tasks) much less or not at all Balance training improves neural measures independently of age and training dose Age and training duration do not moderate the training-induced changes in the neural correlates of balance learning There is little-to-no temporal correspondence between improvements in balance skills and the neural correlates examined [ABSTRACT FROM AUTHOR]