SEARCH · Search PubMed

Results for “Velocity-based training”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

1,086 records · Page 9Linked to original sources

PubMed2026

Integration of ear and hearing care services in low- and middle-income health systems: a systematic review and qualitative synthesis.

Hearing loss is a global public health burden and mostly affects those living in low- and middle-income countries (LMICs). One approach to address ongoing challenges is the World Health Organization's recommendation for the integration of ear and hearing care (EHC) services into healthcare packages. However, little is known about EHC integration approaches, particularly in LMICs additionally, these approaches have not been investigated through a health systems lens. This qualitative review aimed to describe the various approaches to the EHC service integration in LMICs and to identify enabling and constraining factors. We reviewed 17 studies, with a focus on LMICs, using adaptations of the Valentijn integration and World Health Organization EHC frameworks, following the PRISMA guidelines. Our investigation showed that most integration approaches were at micro or individual level. Enabling factors for integration of EHC services were training, mentorship, collaboration, technology, inclusion of EHC in healthcare packages and investment in EHC services. Barriers were challenges with training, facilities and equipment, policy implementation and resourcing of EHC services. We further described factors influencing healthcare seeking behaviour and the use of integrated EHC services, such as access and ability to pay, referral systems and communication and awareness. This study describes the complex nature of EHC integration and ways to support integration. Key considerations are the level of integration, training to address workforce issues and factors influencing service utilisation as we work towards health system strengthening.

Humans↗

PubMed2026

Home-Based Cardiac Rehabilitation Using a Smart Ring and Telephone Counselling: A Randomized Controlled Trial.

BACKGROUND: Home-based cardiac rehabilitation (HB-CR) is a promising alternative to center-based cardiac rehabilitation as it can address several barriers impeding CR implementation because of its enhanced accessibility. However, to date, HB-CR has not garnered adequate attention due to a lack of communication between patients and medical staff. In this study, we aimed to investigate the effectiveness of HB-CR by monitoring the pulse rate (PR) using a smart ring equipped with photoplethysmography. METHODS: Patients with cardiovascular disease were educated on structured HB-CR methods following a symptom-limited cardiopulmonary exercise test (CPET), and were instructed to wear the device during the exercise session. The recorded PR was uploaded to a website via a smartphone and monitored by medical staff. Patients were randomly assigned to one of two groups: intervention or control group. The intervention group received weekly telephone counselling and was encouraged to maintain optimal levels of physical activity. In contrast, the control group only recorded their exercise data without additional interventions. After 3 months of training, the CPET was performed. RESULTS: Among the 64 randomized patients (32 in each group), an intention-to-treat analysis showed that peak oxygen consumption increased over time in both the groups, with a significantly greater improvement in the intervention group. The group-by-time interaction for peak oxygen consumption was statistically significant (estimated mean difference, 2.0 mL/kg/min; 95% confidence interval, 0.7-3.3; P = 0.004). CONCLUSION: HB-CR using a smart device was effective in improving oxygen consumption. However, appropriate monitoring and timely counselling by medical professionals are important for improved outcomes. TRIAL REGISTRATION: Clinical Research Information Service Identifier: KCT0005893.

Humans↗

PubMed2026

Understanding and Usefulness of Effect Size and Certainty of Evidence: A Cross-Sectional Survey of Evidence-Based Practice Competencies Among US Registered Dietitians.

INTRODUCTION: Understanding of absolute and relative effect estimates, and determining effect size and certainty of evidence corresponding to effect estimates, represent fundamental evidence-based practice competencies that promote informed clinical decision-making. While research has been conducted in the medical profession, based on our literature review there is no published research on these competencies in the nutrition and dietetics profession. METHODS: Among registered dietitians, our main objectives were to assess (1) their understanding and perceived usefulness of three absolute and two relative effect estimate approaches to determine effect size, (2) their perceived usefulness of certainty of evidence, and (3) factors influencing their understanding and perceived usefulness. We conducted a web-based, cross-sectional survey by recruiting dietitians from the Academy of Nutrition and Dietetics (United States). Participants received effect estimates based on hypothetical dietary interventions vs. usual diet for reducing myocardial infarction risk. RESULTS: Of the 11,050 dietitians who received the survey link, 210 participated, and only completers (n = 114) were included in our analysis. Participants demonstrated a similar understanding of the relative (27.6%) and absolute (27.5%) effect estimates, with Risk Difference being the best understood approach and Number Needed to Treat being the least (30.7% vs. 24.6% correct responses). While perceived usefulness scores were similar between five approaches, they were highest when data was presented as Relative Risk [mean (SD): 4.82 (1.50)]. Dietitians rated the usefulness of certainty of evidence favorably [mean (SD): 5.07 (1.83), on a 7-point scale], and no factors were associated with correct understanding. CONCLUSION: Dietitians may have limited understanding of effect size thresholds presented in our survey, a finding mostly consistent with surveys of other health professionals. To optimize informed decision-making between dietitians and clients, dietetic programs and continuing education platforms should consider additional training on effect estimate approaches (relative and absolute), and determining effect sizes and certainty of evidence for effect estimates.

Clinical nutrition↗

PubMed2026

A multi-scale fusion model based on multi-phase contrast-enhanced CT for predicting pancreatic cancer resectability.

Purpose.Develop a multi-scale fusion model (MSFM) based on multi-phase contrast-enhanced computed tomography (CECT) to predict pancreatic cancer (PC) resectability, thereby assisting expert decision-making.Methods.This retrospective study enrolled 280 patients with PC from four institutions, which were randomly divided into a training cohort (202 patients) and an independent test cohort (78 patients). Three-phase CECT images (arterial, venous, and delayed phases) were used for modeling. The MSFM comprises two sub-networks: (1) a multi-phase fusion network for extracting cross-phase shared fusion features, (2) a phase-specific branch network for capturing phase-specific features; and a post-fusion strategy to generate the final predictive score by integrating the shared fusion features and three groups of phase-specific features. Additionally, a human-machine fusion deep learning model (HMfDL) was constructed by fusing the predictive score of the MSFM with expert assessments.Results.In the independent test, the MSFM achieved an AUC (area under the receiver operating characteristic curve) of 0.8385 (95% CI: 0.7521-0.9249), accuracy of 84.62%, sensitivity of 72.00%, and specificity of 90.57%. This performance outperformed single-phase models (AUC range: 0.7638-0.7781), two-phase models (AUC range: 0.7826-0.7864), and ten states-of-the-art classifiers (AUC range: 0.7404-0.7796). The HMfDL further improved the performance, reaching an AUC of 0.8626 (95% CI: 0.7853-0.9400), accuracy of 91.03%, sensitivity of 80.00%, and specificity of 96.23%. Notably, the HMfDL corrected 58.82% of misdiagnosis made by experts.Conclusions. The MSFM effectively fuses multi-phase CECT to enable highly accurate predictions of PC resectability, and provides valuable support for expert decision-making through HMfDL.

Humans↗

PubMed2026

A systematic review of the impact of Mental Health First Aid on medical, nursing and allied healthcare professional students.

BACKGROUND: Healthcare professional (HCP) students are at high risk of mental health problems, but stigma and fear of career repercussions often deter them from seeking help. Mental Health First Aid (MHFA) is a globally disseminated course teaching the public to identify and respond to people experiencing mental health problems. MHFA training may address some of the challenges faced by HCP students, by improving mental health knowledge and by enhancing well-being and peer support. AIMS: To systematically review the available literature regarding the impact of MHFA training on HCP students' mental health literacy, confidence and intentions to provide help, stigma, peer support and self-care. METHOD: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines (International Prospective Register of Systematic Reviews ID: CRD42024589509), five databases were searched. Primary studies evaluating the above outcome measures in HCP students were included. Two authors independently screened references and extracted data. Quality was assessed using the Modified Medical Education Research Study Quality Instrument and Cochrane Risk of Bias tools. A narrative synthesis was performed. RESULTS: Of 2367 records screened, 26 met inclusion criteria. Confidence in supporting others and mental health literacy showed the most consistent improvements following MHFA training, whereas evidence for changes in stigma was mixed. Peer support, self-care and student well-being were infrequently examined, although qualitative data suggested that MHFA had improved openness to help-seeking. CONCLUSIONS: MHFA shows promise in enhancing mental health literacy, confidence and intentions, and in reducing stigma, particularly when supplemented with experiential learning. HCP students may benefit from tailoring of such courses to their specific needs, fostering a culture of peer support, enhancing well-being and introducing basic concepts in mental health.

MHFA↗

PubMed2026

Mul-PheG2P: decoupled learning and prediction-space fusion enables robust and interpretable multi-phenotype genomic prediction.

Genomic prediction of multiple phenotypes is crucial in modern plant breeding; however, existing methods struggle with negative transfer and lack interpretability, particularly across high-dimensional small-sample data and diverse species. To address this, we propose Mul-PheG2P, a novel paradigm based on decoupled learning and predictive space fusion. It employs a two-stage design: first training phenotype-specific encoders using genetic data, then decoupling phenotype-specific learning from cross-phenotype aggregation via an interpretable prediction layer. Mul-PheG2P outperforms existing methods across diverse crop datasets, including maize (Zea mays), wheat (Triticum aestivum), and tomato (Solanum lycopersicum). It provides a multi-scale interpretability chain: at the macro level, it quantifies phenotypic contributions via attention-based weighting; at the micro level, Integrated Gradients reveal the genetic basis of predictions. Notably, the model successfully identified the CCT (CONSTANS, CO-like, and TOC) motif regulating photoperiodism and the SQUAMOSA (SQUAMOSA promoter binding protein) promoter for inflorescence development, confirming its ability to capture functional biological mechanisms. These results highlight the high performance and interpretability of Mul-PheG2P, showcasing its value for low-cost, large-scale screening to advance precision breeding.

Phenotype↗

PubMed2026

Whole cell inactivated poly-bacterial preparation MV130 effect on nasal mucosal immunity and experimental human pneumococcal carriage: double-blind randomised controlled trial with controlled human infection model.

BACKGROUND: Bacterial mucosal immunotherapy has shown protection of children and adults from both viral and bacterial respiratory infections, offering the potential to reduce antimicrobial use, and hence also control antimicrobial resistance (AMR). Pneumococcal carriage of vaccine type Streptococcus pneumoniae remains high in Malawi despite infant conjugate vaccination and AMR is increasing. We compared nasal inflammation following sublingual bacterial immunotherapy including S. pneumoniae (MV130, Inmunotek, Spain) or placebo and determined the effect in an experimental human pneumococcal carriage model. METHODS: A double-blind, randomised, placebo-controlled trial in healthy adult volunteers was conducted at Queen Elizabeth Central Hospital in Blantyre, Malawi. Participants were randomly allocated to receive MV130 or placebo sublingually once daily for 42 days. Mucosal inflammation (neutrophil to T cell ratio, NTR) was measured in nasal micro-biopsies. Post-treatment, participants were challenged with 160,000 CFU/naris S. pneumoniae 6B (Spn6b). Experimental pneumococcal carriage rates post inoculation were compared between the two arms. All participants completing the study were included in the analysis. Prospective trial registration: PACTR202403820001276. FINDINGS: 107 participants were enrolled and randomised to MV130/placebo between May and December 2024. There were no serious adverse events, complete compliance was good (72%) and all adverse events were mild. 96 participants (53 male, 43 female) completed the study with 52 participants randomised to MV130 and 44 to placebo. There was no difference in mucosal inflammation (neutrophil to T cell ratio) at day 14 of the intervention MV130 NTR median = 0.737 (IQR 0.294, 2.059) and placebo NTR = 0.831 (IQR 0.450, 2.073), p = 0.64. Secondary analyses showed a rise in mucosal neutrophils after MV130 treatment and after experimental pneumococcal inoculation. There was no difference in nasal or serum anti-pneumococcal immunoglobulin or in experimental pneumococcal carriage proportion between MV130 (12/52, 23%) and placebo (10/44, 23%) groups (unadjusted risk ratio 1.02 (CI 0.49-2.12) p = 1.0). INTERPRETATION: MV130 induced non-specific mild neutrophil inflammation of the nasal mucosa but had no protective effect against experimental human pneumococcal carriage. FUNDING: Wellcome Trust.

Humans↗

PubMed2026

Ten years on, still out of reach: barriers to PrEP access and retention in France according to frontline actors (QualiPrEP Study).

Pre-exposure prophylaxis (PrEP) for HIV has been available in France since 2014, and reimbursed since 2016, with general practitioners allowed to prescribe it since 2021. Despite these policy advances, uptake remains low among some of the most affected populations. This community-based qualitative study explored barriers to PrEP access and retention ten years into its implementation.Interviews were conducted with 28 PrEP frontline actors (healthcare professionals and community-based workers involved in promoting, prescribing, or supporting PrEP). The sample included one group discussion (n = 5), two triads (n = 6), two dyads (n = 4), and nine individual interviews (n = 13). Thematic analysis was inductive, with barriers classified across four main domains.Participants were mostly cisgender men, median age 48, born in France and abroad, and employed by NGOs in Paris. Thirteen barriers and four major themes emerged: (1) Internal psychosocial barriers: lack of knowledge, negative health-related reactions; HIV stigma; STI risk perception, taboos; (2) Internal pragmatic barriers: perceived limits of protection, usage and follow-up constraints; (3) External psychosocial barriers: limited physician knowledge and reluctance; (4) External pragmatic barriers: communication failures; structural constraints, lack of human and financial resources.Findings call for more targeted messaging, simplified care models and provider training. They highlight the need to address social and symbolic dimensions of PrEP, with insights from those supporting users to ensure more equitable implementation.

Humans↗

PubMed2026

Construction of precision clinical-proteomics risk model based on machine learning for predicting heart failure in type II diabetes mellitus.

BACKGROUND AND AIMS: Heart failure (HF) is a severe complication in type 2 diabetes mellitus (T2DM), but current risk stratification scores have limited predictive accuracy. We aimed to develop novel prediction tools integrating clinical variables with proteomics to improve risk stratification of hospitalization for HF in T2DM. METHODS AND RESULTS: In this study, we included 2111 UK Biobank participants with T2DM but no prior HF, and profiled 2920 proteins to predict 10-year incident HF hospitalization. Participants were randomly divided into training (70%), tuning (10%), and validation (20%) sets.Three prediction models were developed: a Clinical model based on demographic characteristics, comorbidities, medication use, and laboratory indices; a Protein model based on 40 proteins selected by the Light Gradient Boosting Machine (LGBM); and the Clinical OMics and Protein ASSessment for Heart Failure (COMPASS-HF) model, which integrated both clinical variables and the LGBM-selected proteins. Models were evaluated for area under the curve (AUC), sensitivity, and specificity. During follow-up, 168 participants (7.96%) developed incident HF. The COMPASS-HF model showed better discrimination than the Clinical model, with an AUC of 0.897 (95% CI: 0.850-0.945) versus 0.790 (95% CI: 0.723-0.856). It also demonstrated higher sensitivity (0.882; 95% CI: 0.725-0.967) and consistent performance in subgroups. COMPASS-HF effectively stratified risk of hospitalization for HF, with cumulative incidence rates of 31.9% in the high-risk group and 1.2% in the low-risk group. CONCLUSIONS: By combining clinical and proteomic variables, we developed a high-performance HF prediction model for T2DM, enabling precise risk stratification and informing early intervention strategies.

Humans↗

PubMed2026

Implementing Prolonged Exposure Therapy in a Community Substance Use Treatment Program: A Qualitative Study.

INTRODUCTION: Post-traumatic stress disorder (PTSD) commonly co-occurs with substance use disorders (SUD), yet few community-based SUD programs incorporate evidence-based trauma-focused. Prolonged exposure (PE), including its massed format (M-PE) with session frequency of 3-4 times per week, is a gold standard intervention for PTSD; however, concerns about client readiness, logistical demands and relapse risk have limited its adoption within SUD settings. This study examined staff perspectives on the feasibility and acceptability of integrating M-PE into a community-based SUD program. METHODS: Prior to launching a Hybrid Type 1 effectiveness-implementation trial (Project COMET), we conducted semi-structured virtual interviews with 15 community clinic staff: providers (n = 8), administrators (n = 2) and peer specialists (n = 5). Interviews were recorded, transcribed and analysed using a rapid qualitative analysis framework with matrix techniques to compare themes across roles. RESULTS: Four overarching themes captured staff perspectives on integrating M-PE: (Theme 1) Prior Knowledge and Experiences: Most staff were familiar with EMDR, while direct knowledge of PE/M-PE was limited. (Theme 2) Perceptions of M-PE: M-PE was widely viewed as a promising, structured intervention that fits the pacing and duration of SUD care. (Theme 3) Symptom Reduction and Client Impact: Staff anticipated improvements in PTSD and SUD symptoms through trauma-focused treatment. (Theme 4) Barriers and Constraints: Participants identified several potential implementation challenges, including logistical barriers and client readiness. DISCUSSION AND CONCLUSIONS: Findings suggest that staff generally viewed M-PE favourably but emphasised the importance of ensuring client readiness and organisational support. Enhancing feasibility and long-term sustainability may require expanded psychoeducation, targeted provider training and flexible delivery models. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT06968832.

Adult↗

PubMed2026

Reliability-aware hierarchical learning for Chagas disease screening from 12-lead ECGs: tackling label uncertainty and class imbalance.

Objective.Chagas disease, a neglected tropical disease (NTD) with significant cardiovascular impact, remains underdiagnosed in resource-limited regions. Electrocardiogram (ECG) screening offers a low-cost tool for detecting cardiac involvement, yet algorithm development is challenged by label noise, data scarcity, and the latent nature of infection. This study proposes a robust ECG-based screening framework that explicitly addresses these constraints.Approach.We introduce aReliability-Aware Hierarchical Learningstrategy that calibrates supervision according to data provenance, prioritizing serology-confirmed labels over noisy self-reports. To mitigate data scarcity, we compare a specialized convolutional neural network (CNN) trained from scratch with a transfer learning approach based on a Spatio-Temporal ECG foundation Model (FM). Performance is evaluated across varying data scales, and the representation structure is analyzed to interpret model behavior.Main results.On the official hidden test set of the George B. Moody PhysioNet/Computing in Cardiology Challenge 2025, our approach achieved a Challenge Score of 0.163. We observe that while the specialized CNN performs competitively in data-rich regimes, the FM exhibits superior robustness in extreme low-resource settings. Furthermore, performance reaches a plateau imposed by underlying disease physiology. Bimodal score distributions suggest that models distinguish established cardiomyopathy from indeterminate infection, which remains electrophysiologically indistinguishable from healthy controls.Significance.These findings clarify both the potential and intrinsic limits of ECG-based AI screening for NTD-associated cardiac involvement. Reliability-aware supervision and data-efficient transfer learning provide a practical framework toward scalable and clinically meaningful ECG screening systems in resource-constrained environments.

Humans↗

PubMed2026

The value of international collaborations for supporting neuroanesthesia practice, education, and research in resource-constrained settings.

PURPOSE OF REVIEW: Neuroanesthesia practice in low- and middle-income countries is constrained by workforce shortages, limited infrastructure, and variability in clinical practice. Growing global interest in collaboration makes it timely to evaluate how international partnerships can address these gaps and improve equity in care, education, and research. RECENT FINDINGS: Recent literature highlights substantial variability in neuroanesthesia practice and limited access to context-appropriate guidelines and advanced technologies. International collaborations, including training partnerships, scholarship programs, and research networks, have improved knowledge exchange, workforce development, and the adoption of standardized practices. Evidence suggests that specialized training is associated with improved clinical outcomes. However, persistent inequities in research participation, authorship, and leadership, as well as concerns regarding sustainability and 'parachute research', remain. SUMMARY: International collaboration is a key strategy for advancing neuroanesthesia in resource-constrained settings. Sustainable, equitable partnerships that prioritize local ownership, capacity building, and contextual adaptation are essential to improving clinical practice, strengthening education, and enhancing global research representation.

Humans↗

PubMed2026

Predicting ACL injury risk in athletes: A systematic review of machine learning-based models.

BACKGROUND: Early ACL injury risk identification in athletes is essential. This systematic review examines machine learning (ML) models for predicting ACL injuries, evaluating their methodological quality, performance, and reliability. METHOD: A comprehensive electronic search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore databases, supplemented by Google Scholar for grey literature, covering articles published between January 1, 2015, and August 30, 2025. Eligible studies were appraised using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST) for methodological quality and risk of bias, and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines for quality of evidence. RESULTS: Ten studies were included. PROBAST showed eight studies had moderate risk of bias and two low risk. TRIPOD found only two studies met quality criteria. ML models included logistic regression (n = 5), support vector machines (n = 4), k-nearest neighbor (n = 3), decision trees (n = 3), random forests (n = 5), neural networks (n = 2), linear discriminant analysis (n = 1), and pre-trained CNNs (n = 1). AUC ranged from 0.63 to 0.98. Accuracy (reported in six studies) ranged from 26% to 95%; however, these values should be interpreted with caution due to the absence of confidence intervals, lack of class imbalance handling, and limited external validation across studies. Tree-based ensemble methods such as random forest achieved competitive accuracy (74-86%), while SVM, a non-ensemble classifier, reported accuracy ranging from 71% to 95%; however, the highest values were obtained in studies with notably small sample sizes (n = 12 to n = 39), raising concerns about overfitting and generalizability. CONCLUSION: Current ML algorithms show promise for identifying athletes at high ACL injury risk and detecting relevant risk factors. Although study quality was generally satisfactory, future research should prioritize external validation and model interpretability to support clinical translation.

Humans↗

PubMed2026

Weight-bearing locomotion mitigates the progression of post-traumatic knee osteoarthritis in male rodents: A systematic review and meta-analysis.

OBJECTIVE: Although knee post-traumatic osteoarthritis (PTOA) has been associated with altered loading, how weight-bearing (WB) activities should be modulated post-injury to preserve knee health remains unknown. This systematic review and meta-analysis examined the effects of WB locomotion on knee PTOA in rodents to provide insight into potential clinical implications. DESIGN: Studies published in PubMed, Cochrane Library, Embase, and CINAHL through 02/2025 and meeting the following criteria were included: 1) rodents with knee PTOA, 2) compared locomotor exercises (treadmill/wheel) to no exercise, 3) outcome measures of PTOA (OARSI/Mankin OA scores, bone quality, osteophyte condition, cartilage quality/morphology). If significant heterogeneity across studies was observed, locomotion speed, time/number of intervention sessions, frequency and duration of intervention, exercise initiation, follow-up time, animal species, PTOA model were analyzed as potential moderator variables that may influence findings. RESULTS: Twenty-two studies met the criteria, resulting in a total of 156 effect sizes (ESs) for meta-analysis (all males). A positive ES denotes less PTOA. Based on the CAMARADES checklist, 5 studies were ranked low risk of bias and 14 studies were ranked moderate risk of bias. Locomotion significantly reduced PTOA severity evaluated using OARSI/Mankin scores (ES=0.927, 95% CI: [0.590, 1.264]) and improved bone quality (ES=0.379, 95% CI: [-0.023, 0.780]) with substantial heterogeneity across studies. Follow-up analyses indicated that greater ESs for reducing OA scores were associated with a shorter duration of each training session, more training sessions, longer intervention duration, and longer follow-up time (all P≤0.004). Greater ESs for improving bone quality were associated with a longer follow-up time and later exercise initiation post-injury (both P≤0.014). Locomotion resulted in small to moderate but non-significant positive effects for isolated measures assessing osteophyte condition (ES=0.379, 95% CI: [-0.023, 0.780]), cartilage quality (ES=0.430, 95% CI: [-0.034, 0.893]), and cartilage morphology (ES=0.464, 95% CI: [-0.006, 0.934]). CONCLUSION: WB locomotion reduced the overall degree of knee PTOA in male rodents. Composite knee OA scores may be more responsive to exercise interventions than isolated cartilage/osteophyte measures. The benefits of locomotion may be more prominent with a longer follow-up time or with exercise protocols consisting of shorter but more individual sessions and longer overall intervention durations.

Animals↗

PubMed2026

Protocol for project FIERCE: A randomized controlled trial to evaluate a positive emotion-focused meditation intervention for physicians with elevated stress.

INTRODUCTION: Nearly 80% of healthcare providers experience adverse psychological symptoms (e.g., depression, burnout, sleep disturbance) stemming from workplace stressors. Elevated levels of stress have been associated with unfavorable occupational, patient, and provider-related outcomes, imposing a heavy burden on a strained system. Given the impact of stress on both employee and patient health, effective interventions are urgently needed to reduce distress and promote well-being among healthcare professionals. Mindfulness-based interventions show promise for addressing these challenges. We developed a six-week, remotely delivered mindfulness intervention, the Building Emotional Strength Training (BEST) program, based on the Buddhist Four Immeasurables practice to cultivate the distinct emotional qualities of loving-kindness, compassion, joy, and equanimity. The present study aims to evaluate the feasibility and efficacy of a Four Immeasurables-based mindfulness intervention on perceived stress (primary outcome), burnout, depressive symptoms, and inflammatory biomarkers, while enhancing psychological well-being and sleep quality (secondary outcomes) in physicians. We will also investigate potential mediators of intervention effects, including compassion, positive affect, equanimity, and mindfulness. METHOD: We will enroll 90 full-time physicians in a remote, two-arm randomized controlled trial with 1:1 allocation to either the meditation intervention or waitlist control. Participants will complete self-report questionnaires and provide blood samples at baseline, mid-course, and post-intervention to assess outcomes and mediators. DISCUSSION: The project aims to advance the study of mindfulness-based interventions that reduce distress and promote well-being through practices that cultivate prosocial and altruistic feelings toward oneself and others. While mindfulness interventions have gained considerable interest, none have specifically drawn from the Four Immeasurables practice to target loving-kindness, compassion, joy, and equanimity. This novel investigation could expand our understanding of practices that foster kindness and compassion to reduce distress in an at-risk population. TRIAL REGISTRATION: ClinicalTrials.gov NCT07283744, registered on 2025/10/14. The Open Science Framework, registered on 2026/06/26.

Humans↗

PubMed2026

The Role of Artificial Intelligence for Intimate Partner Violence Prevention: A Systematic Review.

INTRODUCTION: Intimate partner violence (IPV), encompassing physical, sexual, emotional and economic abuse, remains a pervasive global health concern. Traditional prevention efforts face obstacles such as underreporting, delayed detection and limited personalised support. Emerging artificial intelligence (AI) approaches offer new opportunities to enhance IPV prevention. AIM: This systematic review maps and synthesises evidence on AI-driven tools in IPV prevention based on studies published between 2004 and 2024. METHODS: Following PRISMA 2020 guidelines and PROSPERO registration, we searched PubMed, Embase, CINAHL, PsycINFO, IEEE Xplore and Web of Science. Eligible studies explicitly evaluated AI technologies targeting IPV prediction, screening, intervention or support delivery. Study quality was appraised using the Mixed Methods Appraisal Tool (MMAT). RESULTS: Of 1304 records initially identified, 41 studies met eligibility criteria. AI applications ranged from machine learning (ML) for risk prediction and natural language processing (NLP) for IPV detection in clinical and social media data, to image analysis for forensic evaluation and chatbot-based support. Predictive modelling demonstrated strong discriminative performance, while NLP-based screening detected IPV with notable sensitivity. Chatbots showed feasibility and user acceptability, but evidence of their direct impact on reducing IPV incidence was limited, with one randomised controlled trial showing a modest reduction. Key challenges identified included algorithmic bias, data privacy risks and barriers to integration across health and social care systems. DISCUSSION: AI-informed interventions show promise for improving IPV detection, risk assessment, and scalable support, but questions remain about long-term effectiveness, ethical fairness, transparency and equitable implementation. Future interdisciplinary research should address these concerns to responsibly deploy AI in IPV prevention. RELEVANCE TO CLINICAL PRACTICE: The findings highlight the importance of trauma-informed, culturally responsive care and provider training in AI applications. Nurse-led innovation and policy advocacy will be crucial for safe, equitable integration of AI in IPV prevention.

Artificial Intelligence↗

PubMed2026

Machine learning-based prediction of unplanned readmission and construction of an online calculator for elderly patients with mild ischemic stroke.

OBJECTIVE: To screen for independent risk factors for unplanned readmission in elderly patients with mild ischemic stroke, and to construct and validate an online risk prediction calculator based on an interpretable machine learning model, thereby providing a promising practical tool for accurate clinical assessment of 30‑day all‑cause unplanned readmission risk in this population. METHODS: A prospective cohort study was conducted, including 1050 patients aged ≥ 60 years with mild ischemic stroke admitted between August 2023 and September 2024. Participants were randomly divided into a training set (840 cases) and a test set (210 cases) at a ratio of 8:2. Risk factors were screened by univariate analysis and multivariable Logistic regression. Four machine learning models, namely LightGBM, XGBoost, Random Forest, and K‑Nearest Neighbors (KNN), were developed and their performance was evaluated using AUC, accuracy, sensitivity, and specificity as metrics. The SHAP framework was used for interpretability analysis, and an online calculator was subsequently developed based on the optimal model. RESULTS: Univariate analysis showed significant differences (P < 0.05) in 13 factors including age, smoking, AIP, TyG index, HALP score, etc. Multivariable Logistic regression identified age (OR = 9.752), smoking (OR = 5.171), AIP (OR = 6.691), TyG index (OR = 4.393), HALP score (OR = 2.831), and ≥ 2 comorbidities (OR = 3.664) as independent risk factors. All four machine learning models demonstrated good predictive performance. Based on a comprehensive evaluation of multiple metrics and computational efficiency, the LightGBM model exhibited the best predictive performance (AUC = 0.884, accuracy = 0.829, sensitivity = 0.812, specificity = 0.875). SHAP analysis showed that age, AIP, TyG index, smoking, and HALP score were key predictors. An online calculator developed based on this model enables individualized risk predictions. CONCLUSION: Key risk factors associated with 30‑day unplanned readmission in elderly patients with mild ischemic stroke were identified. The LightGBM model demonstrated high predictive accuracy, and together with the interpretability analysis and online calculator, offers a practical tool to support clinical risk assessment. However, this tool requires future external validation.

Humans↗

PubMed2026

Exploring Primary Care Clinicians' Sexual and Reproductive Health Care Delivery to Male Adolescents and Young Adults.

INTRODUCTION: Despite existing guidance for adolescent sexual and reproductive health (SRH) care, male adolescent SRH care receipt is inadequate. Limited research has explored factors affecting clinicians' provision of SRH care to male adolescents, specifically. METHODS: This mixed-method study with 12 primary care clinicians included a brief survey assessing care delivery practices and confidence, followed by an in-depth interview to explore factors affecting SRH care delivery. RESULTS: Clinicians reported high confidence delivering male adolescent SRH care (mean ± SD: 8.31 ± 1.71 out of 10), but delivered only about half the recommended services (20 items out of 38). Factors influencing care delivery included gaps in education/training, assumptions about male SRH care, and behavioral constraints at various levels. DISCUSSION: Findings underscore the need to strengthen male adolescent SRH care by enhancing provider training, increasing clinic-level supports, and addressing structural barriers. CONCLUSIONS: Findings can inform strategies to improve the quality and comprehensiveness of SRH services for male adolescents in primary care settings.

Humans↗