Explore the vast range of titles available.

The global pandemic of coronavirus disease (COVID-19) has caused millions of deaths and affected the livelihood of many more people. Early and rapid detection of COVID-19 is a challenging task for the medical community, but it is also crucial in stopping the spread of the SARS-CoV-2 virus. Prior substantiation of artificial intelligence (AI) in various fields of science has encouraged researchers to further address this problem. Various medical imaging modalities including X-ray, computed tomography (CT) and ultrasound (US) using AI techniques have greatly helped to curb the COVID-19 outbreak by assisting with early diagnosis. We carried out a systematic review on state-of-the-art AI techniques applied with X-ray, CT, and US images to detect COVID-19. In this paper, we discuss approaches used by various authors and the significance of these research efforts, the potential challenges, and future trends related to the implementation of an AI system for disease detection during the COVID-19 pandemic.

Gut microbiota make up the largest microecosystem in the human body and are closely related to chronic metabolic diseases. Herein, 520 fecal samples are collected from different regions of China, the gut microbiome in chronic kidney disease (CKD) is characterized, and CKD classifiers based on microbial markers are constructed. Compared with healthy controls (HC, n = 210), gut microbial diversity is significantly decreased in CKD (n = 110), and the microbial community is remarkably distinguished from HC. Genera Klebsiella and Enterobacteriaceae are enriched, while Blautia and Roseburia are reduced in CKD. Fifty predicted microbial functions including tryptophan and phenylalanine metabolisms increase, while 36 functions including arginine and proline metabolisms decrease in CKD. Notably, five optimal microbial markers are identified using the random forest model. The area under the curve (AUC) reaches 0.9887 in the discovery cohort and 0.9512 in the validation cohort (49 CKD vs 63 HC). Importantly, the AUC reaches 0.8986 in the extra diagnosis cohort from Hangzhou. Moreover, Thalassospira and Akkermansia are increased with CKD progression. Thirteen operational taxonomy units are correlated with six clinical indicators of CKD. In conclusion, this study comprehensively characterizes gut microbiome in non‐dialysis CKD and demonstrates the potential of microbial markers as non‐invasive diagnostic tools for CKD in different regions of China. Compared with healthy controls, gut microbial diversity in CKD is significantly reduced, Klebsiella and Akkermansia are significantly increased, Roseburia and Faecalibacterium are significantly reduced, and the predictive function of gut microbiota such as ascorbate metabolism and lipopolysaccharide biosynthesis is significantly enhanced. Akkermansia increases along with the progression of CKD, which is positively correlated with serum creatinine and blood urea nitrogen, and negatively correlated with estimated glomerular filtration rate, and could be used as a therapeutic target to improve the prognosis of CKD. Importantly, gut microbial markers have strong diagnostic potential for CKD and achieve cross‐regional validation, which can be used as a non‐invasive diagnostic tool for CKD.

The premature ejaculation diagnostic tool （PEDT） is a brief diagnostic measure to assess premature ejaculation （PE）. However, there is insufficient evidence regarding its validity in the new evidence-based-defined PE. This study was performed to evaluate the validity of PEDT and its association with IIEF-15 in different types of evidence-based-defined PE. From June 2015 to January 2016, a total of 260 men complaining of PE and defined as lifelong PE （LPE）/acquired PE （APE） according to the evidence-based definition from Andrology Clinic of the First Affiliated Hospital of Anhui Medical University, along with 104 male healthy controls without PE from a medical examination center, were enrolled in this study. All individuals completed questionnaires including demographics, medical and sexual history, as well as PEDT and IIEF-15. After statistical analysis, it was found that men with PE reported higher PEDT scores （14.28 ± 3.05） and lower IIEF-15 （41.26 ± 8.20） than men without PE （PEDT： 5.32 ± 3.42, IIEF-15：52.66 ± 6.86, P 〈 0.001 for both）. It was suggested that a score of 〉9 indicated PE in both LPE and APE by sensitivity and specificity analyses （sensitivity： 0.875, 0.913; specificity： 0.865, 0.865, respectively）. In addition, IIEF-15 were higher in men with LPE （42.64 ± 8.11） than APE （39.43 ± 7.84, P 〈 0.001）. After adjusting for age, IIEF-15 was negatively related to PEDT in men with LPE （adjust r = -0.225, P 〈 0.001） and APE （adjust r = -0.378, P 〈 0.001）. In this study, we concluded that PEDT was valid in the diagnosis of evidenced-based-defined PE. Furthermore, IIEF-15 was negatively related to PEDT in men with different types of PE.

The fetal echocardiogram is useful for monitoring and diagnosing cardiovascular diseases in the fetus in utero. Importantly, it can be used for assessing prenatal congenital heart disease, for which timely intervention can improve the unborn child’s outcomes. In this regard, artificial intelligence (AI) can be used for the automatic analysis of fetal heart ultrasound images. This study reviews nondeep and deep learning approaches for assessing the fetal heart using standard four-chamber ultrasound images. The state-of-the-art techniques in the field are described and discussed. The compendium demonstrates the capability of automatic assessment of the fetal heart using AI technology. This work can serve as a resource for research in the field.

The aim of the study was to evaluate the long-term outcomes of pelvic floor muscle (PFM) rehabilitation in males with lifelong premature ejaculation (PE), using intravaginal ejaculatory latency time (IELT) and the self-report Premature Ejaculation Diagnostic Tool (PEDT) as primary outcomes. A total of 154 participants were retrospectively reviewed in this study, with 122 completing the training protocol. At baseline, all participants had an IELT ≤60 s and PEDT score >11. Participants completed a 12-week program of PFM rehabilitation, including physio-kinesiotherapy treatment, electrostimulation, and biofeedback, with three sessions per week, with 20 min for each component completed at each session. The effectiveness of intervention was evaluated by comparing the change in the geometric mean of IELT and PEDT values, from baseline, at 3, 6, and 12 months during the intervention, and at 24 and 36 months postintervention, using a paired sample 2-tailed t-test, including the associated 95% confidence intervals. Of the 122 participants who completed PFM rehabilitation, 111 gained control of their ejaculation reflex, with a mean IELT of 161.6 s and PEDT score of 2.3 at the 12-week endpoint of the intervention, representing an increase from baseline of 40.4 s and 17.0 scores, respectively, for IELT and PEDT (P < 0.0001). Of the 95 participants who completed the 36-month follow-up, 64% and 56% maintained satisfactory ejaculation control at 24 and 36 months postintervention, respectively.

Background The use of in vivo and ex vivo diagnostic tools for delayed hypersensitivity reactions (DHRs) associated with iodinated contrast media (ICM) is currently ill-defined. Objective To evaluate the role of in vivo and ex vivo diagnostic tools for DHRs occurring >6 h following intravenous low-osmolality ICM. Methods We conducted a prospective, multicenter, international cohort study. The patients were recruited from two tertiary care adult allergy clinics, Austin Health, Australia and the McGill University Health Centre, Canada. Eligible participants were adults who reported a DHR after receiving ICM. In vivo testing (skin testing and intravenous challenge) was performed to identify an alternative agent. Ex vivo testing using interferon-γ enzyme-linked ImmunoSpot assay was performed in four Australian patients to explore its diagnostic performance. Results The culprit ICM was identified by dIDT in 17/20 (85%) while in 3/20 (15%) a challenge was necessary to confirm delayed hypersensitivity. All patients with a positive dIDT to iohexol were positive to iodixanol (15/15; 100%) while 3/4 (75%), 3/4 (75%), 4/6 (67%), and 3/5 (60%) were positive to iopromide, ioversol, iopamidol, and iobitridol, respectively. Overall, 7/20 (35%) patients tolerated a challenge with an alternative ICM. The IFN-γ release assay was negative for the implicated ICM in 4 patients with confirmed DHR through a positive dIDT. Conclusion dIDT allowed confirmation of T cell-mediated allergy to the implicated ICM in 85% of patients with a strong clinical suspicion of DHR and identification of non-cross-reactive ICM in 35% of patients. The IFN-y ELISpot was not useful in the four patients tested.

Mental health disorders (MHDs) remain a leading cause of the global burden of diseases. Early identification of neurobiological mechanisms mediating a risk for MHDs is key to reducing a lifetime burden. Recent findings emphasize the locus coeruleus-norepinephrine (LC-NE) system as a neuromodulator of arousal translating acute stress responses into neuronal excitability. We propose that individual differences in LC-NE functioning can explain a differential susceptibility to psychological adversity, which mediates the development of transdiagnostic psychopathology in early childhood. The primary objective of LOCUS-MENTAL is to assess LC-NE functioning in preschoolers as a predictor of later psychopathology. This will be applied to generate an objective tool of individual early risk prediction, supporting targeted prevention of MHD. LOCUS-MENTAL includes 4 work packages. The centerpiece is an accelerated longitudinal study, in which a cohort of 300 preschool-aged children (aged 4-6 years) will be recruited and followed up across 3 assessment waves, each one year apart. This will characterize developmental trajectories from 4 to 8 years of age. The primary outcome is the prediction of transdiagnostic psychopathology by pupillometry-derived LC-NE functioning. Transdiagnostic psychopathology is assessed by the Child Behavior Checklist (CBCL), while LC-NE functioning is assessed with pupillometry that includes core metrics of baseline pupil size (BPS) and stimulus-evoked pupillary response (SEPR). Cross-lagged panel models will be applied to the longitudinal data for quantifying causal effects between LC-NE functioning, childhood adversity, and psychopathology. Normative modeling and classification approaches will estimate an individual risk prediction based on pupillometric metrics of LC-NE functioning. The pupillometric battery has 4 passive auditory and visual paradigms. This battery will be validated with a multitrait-multimethod design that combines pupillometry with neurophysiological measures in electroencephalography, behavioral and cognitive measures, and neurocognitive paradigms. The study was approved by the Ethics Committee of the Faculty of Medicine at Goethe University Hospital (2024-2160). Written informed consent will be obtained from caregivers and verbal assent by the children. The study was funded in September 2024. Participant enrollment for the validation phase commenced in August 2025. As of February 2026, 82 participants were assessed, with a target of reaching 90 by the end of February 2026. Statistical analysis of the validation phase is planned for March 2026, with results aimed for publication in a peer-reviewed journal by the end of 2026. The longitudinal study is scheduled to start in April 2026 with completion in March 2029. The LOCUS-MENTAL study will establish whether LC-NE functioning provides a validated biomarker for detecting early psychopathology. The associated pupillometry provides a feasible and scalable test for identifying high-risk developmental trajectories in preschool children, which can be translated to clinical practice. The resulting risk assessment tool could facilitate a shift toward objective screening for mental health risks that enables targeted prevention with evidence-based treatment before diagnosis onset. This could prevent sequential comorbidity and reduce the lifetime burden of MHDs.

Autism spectrum disorder (ASD) is a prevalent neurodevelopmental condition that can be quite difficult to diagnose due to a lack of objective diagnostic methods in the currently used behavioral assessments. Recent work has shown that children with ASD have a higher incidence of motor control differences. A compilation of studies indicates that between 50% and 88% of the children with ASD have issues with movement control based on standardized motor assessments or parent-reported questionnaires. In this study, we assess a variety of deep learning approaches for the classification of ASD, utilizing data collected via inertial measurement unit (IMU) hand tracking during goal-directed arm movements. IMU hand tracking data were recorded from 41 school-aged children both with and without an ASD diagnosis to track their arm movements during a reach-to-clean up task. The IMU data were then preprocessed using a moving average and z score normalization to prepare the data for deep learning models. We evaluated the effectiveness of different deep learning models using the preprocessed data and a k-fold validation approach, as well as a patient-separated approach. The best result was achieved with a convolutional autoencoder combined with long short-term memory layers, reaching an accuracy of 90.21% and an F1-score of 90.02%. Once the convolutional autoencoder+long short-term memory was determined to be the most effective model for this datatype, it was retrained and evaluated with a patient-separated dataset to assess the generalization capability of the model, achieving an accuracy of 91.87% and an F1-score of 93.66%. Our deep learning approach demonstrates that our models hold potential for facilitating ASD diagnosis in clinical settings. This work validates that there are significant differences between the physical movements of typically developing children and children with ASD, and these differences can be identified by analyzing hand-eye coordination skills. Additionally, we have validated that small-scale models can still achieve a high accuracy and good generalization when classifying medical data, opening the door for future research into diagnostic models that may not require massive amounts of data.

The burden of alcohol use among patients with trauma and the relative injury risks is not routinely measured in South Africa. Given the prominent burden of alcohol on hospital trauma departments, South Africa needs practical, cost-effective, and accurate alcohol diagnostic tools for testing, surveillance, and clinical management of patients with trauma. This study aims to validate alcohol diagnostics for injury-related trauma and assess its use for improving national health practice and policy. The Alcohol Diagnostic Validation for Injury-Related Trauma study will use mixed methods across 3 work packages. Five web-based focus group discussions will be conducted with 6 to 8 key stakeholders, each across 4 areas of expertise (clinical, academic, policy, and operational) to determine the type of alcohol information that will be useful for different stakeholders in the injury prevention and health care sectors. We will then conduct a small pilot study followed by a validation study of alcohol diagnostic tools (clinical assessment, breath analysis, and fingerprick blood) against enzyme immunoassay blood concentration analysis in a tertiary hospital trauma setting with 1000 patients. Finally, selected alcohol diagnostic tools will be tested in a district hospital setting with a further 1000 patients alongside community-based participatory research on the use of the selected tools. Pilot data are being collected, and the protocol will be modified based on the results. Through this project, we hope to identify and validate the most appropriate methods of diagnosing alcohol-related injury and violence in a clinical setting. The findings from this study are likely to be highly relevant and could influence our primary beneficiaries-policy makers and senior health clinicians-to adopt new practices and policies around alcohol testing in injured patients. The findings will be disseminated to relevant national and provincial government departments, policy experts, and clinicians. Additionally, we will engage in media advocacy and with our stakeholders, including community representatives, work through several nonprofit partners to reach civil society organizations and share findings. In addition, we will publish findings in scientific journals. DERR1-10.2196/52949.

Attention deficit/hyperactivity disorder (ADHD) is the most prevalent neurodevelopmental disorder worldwide, affecting approximately 5%-7% of school-aged children and 2%-5% of adults worldwide. However, there is still no reliable diagnostic tool for it. The lack of specific biomarkers further complicates the accurate diagnosis of ADHD. The SINCRONIA study seeks to develop and optimize an electroencephalogram (EEG)-based ADHD diagnostic classification algorithm by identifying biomarkers that provide optimal diagnostic performance. This protocol introduces a single-center, case-control study involving at least 165 participants, aged between 7 and 12 years, that is being conducted at the Puerta de Hierro University Hospital in Madrid, Spain. Participants will be allocated to 3 groups, including ADHD predominantly inattentive, ADHD predominantly combined or hyperactive/impulsive, and a control group, according to the best estimated diagnosis based on clinical interviews and a neuropsychological assessment that includes the Conners Continuous Performance Test. In addition, an EEG recording will be conducted separately, and functional connectivity metrics will be used to characterize brain networks associated with inhibitory control. The index test is expected to match or improve the clinical diagnosis of ADHD in children aged between 7 and 12 years and provide a set of eventual biomarkers that maximize diagnostic performance and provide pathophysiological clues. The SINCRONIA study began screening and recruitment in March 2023. Recruitment ended on December 11, 2024. A total of 165 eligible participants were enrolled. The SINCRONIA project is a high-quality, large-scale, unicenter study devoted to improving the objective diagnosis of ADHD by using EEG biomarkers. The EEG-based ADHD diagnosis is expected to have greater sensitivity and specificity than the Conners Continuous Performance Test.