Search Results (908)

Background and Objectives: Despite recent advancement, neovascular age-related macular degeneration (nAMD) remains a leading cause of irreversible vision loss. Undertreatment, fewer anti-VEGF injections and longer intervals than in clinical trials have been associated with sub-optimal visual outcomes. Visit-based regimens (Treat-and-Extend, PRN) may permit intervals of unrecognized retinal fluid between office visits. A home OCT system with near-daily self-imaging provides frequent structural retinal information between office visits that can support early detection of persistent or recurring fluid. The objective was to evaluate the duration and magnitude of fluid exposure between standard care visits and estimate the potential to shorten that exposure. Materials andMethods: Ad hoc analysis of three cohorts of treatment naïve and experienced nAMD eyes managed by standard care while participating in observational studies of the home OCT system, with treating physicians masked to home OCT data. AI-based analysis of fluid volume, rate of change and time of fluid onset was performed. Results: Data from 209 participants, mean age 76.4 years, 53% female, who performed 10,110 scans (6.0 scans/week) were analyzed. An amount of 119 eligible eyes provided data from 185 standard care intervals. Persistent or recurring fluid was identified in 121 (65%) intervals, on average 32 days prior to the next office visit. Of these, 84 (69%) had potential visit advancement within labeled minimal treatment intervals of 19 days. Mean fluid volume at the earliest possible notification was 26 nL and recurrence rate averaged 4.4 nL/day. Conclusions: A substantial proportion of patients experience unrecognized disease activity between visits. Home OCT monitoring provides adjunctive information to support early detection of fluid and may facilitate timely clinical evaluation. In this context, such monitoring may be considered reasonable and necessary to inform management of nAMD within established standards of care, while not replacing clinician-directed diagnosis or treatment decisions. Full article

Background: Dalbavancin (DBV) is a long-acting lipoglycopeptide with activity against Gram-positive pathogens approved for the treatment of acute bacterial skin and skin structure infections (ABSSSI). Its pharmacological profile supports use in infections requiring prolonged therapy, yet its role in osteomyelitis without implantable devices (OM-WoID) remains off-label. This study aims to describe real-world DBV use in a large tertiary care hospital, focusing on its effectiveness in OM-WoID. Methods: This is a monocentric, retrospective analysis including all patients receiving DBV at ASST Spedali Civili di Brescia, Italy, from April 2017 to July 2023. The statistical analysis focused on patients who received DBV for either ABSSSI or OM-WoID, with the latter transitioning to DBV after traditional daily intravenous therapy. Clinical, microbiological, and treatment data were extracted from electronic records and stored in REDCap. Effectiveness was defined as infection resolution or improvement; treatment failure encompassed clinical worsening, recurrence or suppressive therapy. Predictors of failure were identified through univariate and stepwise multivariate logistic regression. Results: During the study period, 157 patients (63.0% male; mean age 62.5 ± 20 years) received at least one dose of DBV, predominantly for off-label indications (66.2%). Early discharge was the most common reason for switching to DBV (66.3%). Focusing specifically on patients treated for ABSSSI (53) and OM-WoID (43), treatment success was achieved in 81.1% of ABSSSI and 90.7% of OM-WoID cases. In the stepwise multivariate logistic regression, older age was independently associated with an increased risk of treatment failure (OR 1.07, 95% CI 1.01–1.13; p = 0.028), while the presence of multimorbidity significantly reduced the risk (OR 0.07, 95% CI 0.01–0.77; p = 0.029). Discussion: Our study offers a comprehensive real-world analysis of DBV use in both approved and off-label indications. Although current clinical experience with DBV remains limited, DBV emerges as a valuable step-down option for the management of invasive Gram-positive infections in our setting. Consistent with previous evidence, older age independently increased the risk of treatment failure, whereas multimorbidity appeared protective, likely due to selection bias and the more intensive monitoring, earlier interventions, and tailored management such patients often receive. Our results support a broader range of approved indications for DBV to allow earlier discharge and more efficient use of healthcare resources. Full article

Background: Health literacy plays an important role in medication understanding, self-management, and engagement with healthcare services among older adults. Limited health literacy may contribute to medication-related problems and reduced utilization of pharmacist-led services in geriatric populations. Methods: A cross-sectional, questionnaire-based survey was conducted among geriatric outpatients (≥60 years) attending a tertiary-care teaching hospital in Saudi Arabia. Health literacy was assessed using a four-domain functional tool—covering prescription label comprehension, understanding of healthcare instructions, confidence in completing medical forms, and comprehension of written health information—developed in alignment with established health literacy frameworks, including the Health Literacy Survey—European Union (HLS-EU) model and Baker’s conceptual framework. Participants were classified as having higher health literacy (0–2 domains impaired) or lower health literacy (3–4 domains impaired). Sociodemographic characteristics, clinical burden, medication self-management behaviors, and awareness of clinical pharmacist services were recorded. Multivariable logistic regression was used to identify factors independently associated with lower health literacy. Results: A total of 200 participants were included. Impairment in three or more domains was observed in 55.5% of participants. Lower health literacy was independently associated with older age, lower educational attainment, lower income, female sex, multimorbidity, and polypharmacy. Participants with lower health literacy reported higher rates of missed or incorrect medication dosing and unreported adverse drug reactions and lower use of medication management aids. Awareness of clinical pharmacist services and prior exposure to pharmacist counseling were significantly lower among participants with lower health literacy. Willingness to receive pharmacist counseling was higher among participants with higher health literacy and greater awareness of pharmacist roles. Conclusions: Health-literacy impairment is common among geriatric outpatients and is associated with medication self-management behaviors and engagement with pharmacist-led services. These findings highlight the relevance of functional health literacy in geriatric medication use and support further research on literacy-sensitive pharmacist-led interventions. Full article

Approximately 30% of patients with tremor-dominant Parkinson’s disease (PD) have rest tremor that persists despite optimal dopaminergic therapy. When deep brain stimulation and focused ultrasound are unavailable or declined, the therapeutic options narrow. Botulinum toxin (BoNT) offers a targeted, titratable, reversible approach, but whether a peripheral neuromuscular blocking agent makes sense for a centrally generated tremor is a legitimate question that deserves a direct answer. This narrative critical review appraises what is currently known across PD and non-PD tremor conditions, defines the technical requirements for safe and effective injection, and provides a practical framework for patient selection and clinical management. The PD-specific literature rests on a single positive double-blind randomized controlled trial of 30 patients; all remaining data are open-label or extrapolated from other tremor conditions, and this narrative synthesis combines heterogeneous conditions, outcome scales, and toxin protocols. A recurring technical observation is that, in the available trials, individualized, EMG-guided injection has been associated with substantially lower rates of hand weakness than fixed-dose injection (reported reductions from roughly 30–70% to below 15%) while maintaining tremor reduction, although the degree of benefit and weakness risk vary with the tremor syndrome, injected muscles, baseline impairment, dose, and guidance method. The careful patient selection this approach requires helps the individual clinician and patient achieve tremor relief, but it departs from the unselected real-world PD population and introduces selection bias that makes a large, statistically representative cohort difficult to assemble. In well-selected patients at centers with the appropriate expertise, BoNT may be a clinically useful option, but routine adoption is not yet supported. Full article

Background: The management of diabetic foot disease and knee osteoarthritis (OA) with smart orthotics holds significant importance during the early stages of these conditions, given their potential consequences, including functional impairment, chronic pain, and economic burden. Real-time monitoring of plantar foot pressure enables early detection of abnormal force distribution and gait biomechanics, allowing for the redirection of forces away from affected ulcers or arthritic joints. This is the first systematic review to synthesise clinical evidence for smart orthotics technology with real-time plantar pressure sensor biofeedback across both diabetic foot ulcer prevention and knee osteoarthritis management simultaneously. A search of the PROSPERO register confirmed no existing registration covers this specific combination. Objectives: To examine the clinical evidence for the use of standard and smart orthotics in the prevention and management of diabetic foot ulcers (DFUs) and knee OA, and to evaluate their impact on plantar pressure redistribution, ulcer recurrence, pain, biomechanics, and economic burden. Eligibility criteria: Studies published in English involving human adult participants (≥18 years) with a clinical diagnosis of diabetes mellitus (at risk of DFU or with peripheral neuropathy) or knee OA, where the intervention involved any orthotic device or smart/intelligent insole with clinical outcomes reported, were included. Studies on healthy individuals only, those not reporting participant age, and non-weight-bearing protocols not differentiated from weight-bearing were excluded. Information sources: Five databases were searched: CINAHL (EBSCO Information Services, Ipswich, MA, USA), PubMed Advanced (National Library of Medicine, Bethesda, MD, USA), Wiley Online Library (John Wiley & Sons, Hoboken, NJ, USA), Cochrane Library (Cochrane Collaboration, London, UK), and Google Scholar (Google LLC, Mountain View, CA, USA). Searches were completed in May 2026. Methods: We conducted a comprehensive literature review. This review was structured and reported with reference to the PRISMA 2020 statement (Preferred Reporting Items for Systematic Reviews and Meta-Analysis; University of Ottawa, Ottawa, ON, Canada) to guide transparency of reporting. It does not constitute a full Cochrane-style systematic review; risk of bias assessment was applied to key included studies and GRADE (Grading of Recommendations Assessment, Development and Evaluation; McMaster University, Hamilton, ON, Canada) certainty ratings were applied informally and narratively rather than as formal per-outcome evidence profiles. Five databases were searched yielding 92,637 records. After removal of 398 duplicates by Rayyan, 92,239 records remained. A subsequent automated keyword-based relevance filter applied within Rayyan (Rayyan AI, Doha, Qatar), prior to human screening, excluded 84,572 records that did not contain any terms related to orthotics, diabetic foot, or knee osteoarthritis, yielding 7667 records for human title/abstract screening. A narrative synthesis approach was adopted owing to the heterogeneity of study designs and outcome measures across included studies, which precluded meta-analysis. This review was not prospectively registered. A complete list of all 78 included studies, including those not individually discussed in the results and discussion. Results: The available clinical studies report promising findings for orthotics and smart orthotics in pain reduction, ulcer prevention, and potential reduction in economic burden, though conclusions are limited by small sample sizes, heterogeneity, and predominantly open-label designs. Recent research found that orthotics can be used to alter the gait pattern that influences knee OA by reducing excessive force on the affected joint. A randomised controlled trial demonstrated an 80% relative risk reduction in DFU recurrence (RR = 0.20; 95% CI: 0.06–0.79; p = 0.022), with absolute event rates of 6.3% in the intervention group versus 30.8% in controls (ARR = 24.5%); a second trial reported a 71% reduction in ulcer incidence over 18 months; and a third randomised controlled trial demonstrated statistically significant plantar pressure reduction (p < 0.01) in patients with diabetic neuropathy. Conclusions: The available evidence suggests that orthotics may be associated with improved pressure redistribution, reduced ulcer incidence, and benefit in the management of knee OA. Although the number of studies directly comparing smart orthotics with standard orthotics remains limited, the limited comparative studies suggested that smart orthotics showed promising results in reducing ulcer incidence, providing the patient with real-time feedback to offload via their electronic devices. These findings, while preliminary, highlight the potential of smart orthotic technology as an adjunct to standard orthotic care in reducing the overall burden of diabetic foot disease and knee osteoarthritis. Limitations: The primary methodological limitation of this review is the open-label design of all included smart orthotic trials, which precludes participant blinding and introduces performance bias. However, this limitation is structural and inherent to the wearable technology field—analogous to surgical trials—and is substantially mitigated by the use of objective primary outcome measures (plantar pressure and ulcer recurrence) across the three included RCTs, the consistency of effect direction across independent RCTs conducted in different countries, and a narrative sensitivity analysis confirming robustness of findings (Risk of Bias Across Studies Section). Formal per-outcome GRADE evidence profiles were not produced; overall certainty of evidence was assessed narratively with reference to GRADE domains and is judged to be low to moderate for smart orthotics in DFU prevention and low for knee OA management, consistent with the Level 2–3 evidence base and open-label study designs. Future adequately powered, multi-site RCTs with standardised outcome reporting, minimum 24-month follow-up, and integrated health economic modelling are the highest priority to extend these preliminary findings. Registration: This review was not prospectively registered. Full article

Background: Breastfeeding enhances infant and maternal health, but global breastfeeding rates remain suboptimal. Virtual reality (VR) emerges as a promising tool for breastfeeding education. The objective of this review was to assess the effectiveness of VR-based interventions on breastfeeding outcomes in pregnant and postpartum women. Methods: PubMed, Embase, Web of Science, Scopus, and CENTRAL were searched until 10 January 2026, for randomized controlled trials (RCTs) and quasi-experimental studies comparing VR-based interventions (immersive simulations, 360° videos, or head-mounted displays) with standard care or non-VR comparators in pregnant or postpartum women. Primary outcomes included breastfeeding self-efficacy, motivation, and breastfeeding technique (LATCH score). Secondary outcomes included exclusive breastfeeding rates, milk production, and maternal anxiety. Risk of bias was assessed using the RoB 2.0 and ROBINS-I tools for RCTs and non-RCTs, respectively. A random-effects meta-analysis was conducted, with results reported as mean differences (MD) or risk ratios (RR), along with 95% confidence intervals (CIs). Certainty of the evidence was assessed using the GRADE approach. Results: Five studies (4 RCTs and 1 quasi-experimental; n = 344) were included. VR improved prenatal breastfeeding self-efficacy (2 studies, MD: 13.93; 95% CI: 10.96–16.90), motivation (1 study, MD: 2.88; 95% CI: 1.66–4.10), and LATCH score (1 study, MD: 1.72; 95% CI: 1.37–2.07), and reduced time to breastfeeding initiation (1 study, MD: −22.4 min; 95% CI: −29 to −15.9), the certainty of evidence was low to very low for these outcomes. No significant effects were observed for postnatal self-efficacy, exclusive breastfeeding, or maternal anxiety. Formal assessment of publication bias could not be done. The small sample sizes for most outcomes, heterogeneity, the open-label nature of the trials, and the subjective nature of the outcomes should be considered when interpreting these results. Conclusions: VR-based interventions may improve process outcomes, such as prenatal breastfeeding self-efficacy, motivation, breastfeeding technique, and early breastfeeding initiation; the certainty of evidence is low to very low. Evidence for clinically important outcomes, including exclusive breastfeeding and maternal anxiety, remains inconsistent. Larger, well-designed RCTs are warranted before these interventions can be considered in routine practice. Full article

Background: Telemedicine is increasingly used in inflammatory bowel disease (IBD), but its effects on quality of life (QoL) and psychological outcomes remain unclear. Objectives: This study aimed to evaluate the impact of 6-month telemonitoring on QoL, disease activity, treatment adherence, psychological well-being, patient satisfaction, and healthcare utilization. Methods: This randomized, open-label, single-center study conducted in Russia (July 2023–December 2024) included adults with ulcerative colitis or Crohn’s disease, who were assigned 1:1 to telemonitoring or standard care. The intervention involved monthly remote assessments and access to a web-based platform containing educational information, disease activity assessment, and a chat with a gastroenterologist. The primary outcome was health-related QoL (SIBDQ). Exploratory outcomes included general QoL (WHOQOL-26), psychological well-being (HADS), alexithymia (TAS-26), visceral sensitivity (VSI), treatment adherence (GMAS), patient satisfaction (PSQ-18), achievement of clinical remission, and healthcare utilization. Results: Sixty-eight patients completed the study (32 intervention, 36 control). Telemonitoring was associated with lower anxiety levels (β = −1.76, p = 0.021), reduced visceral sensitivity (β = −5.08, p = 0.039), and higher medication adherence (β = 1.75, p = 0.008). No significant associations were observed for SIBDQ, WHOQOL-26 domains, depressive symptoms, alexithymia, achievement of clinical remission, or patient satisfaction with care (p > 0.05). Patients in the telemonitoring group also required fewer outpatient visits (p < 0.001), with no difference in hospitalizations. Within-group analysis demonstrated improvements in QoL, treatment adherence, visceral sensitivity, and disease activity in the telemonitoring group, but not in the controls. Conclusions: Six-month telemonitoring in IBD was associated with lower anxiety, reduced visceral sensitivity, improved treatment adherence, and fewer outpatient visits. The health-related QoL assessed by the SIBDQ did not differ compared to standard care. No clear clinical disadvantage compared with standard care was detected during the study period. Full article

Safety-critical Industrial Internet of Things (IIoT) sensor networks deployed in disaster scenarios require intelligent routing mechanisms that prioritize mission-critical packets without relying on centralized coordination. Federated learning on resource-constrained edge nodes presents three primary challenges: the absence of an interpretable supervisory signal, the inability to act conservatively based on per-inference confidence, and vulnerability to partial node availability. The proposed FedCARE framework addresses these issues by employing a Mamdani Fuzzy Inference System to generate traceable criticality labels from multi-modal sensor telemetry, a dropout-aware aggregation protocol that normalizes over only reachable nodes, and a confidence-gated resolver that defers to symbolic fuzzy classification when model confidence is insufficient, otherwise applying an auditable maximization rule to prevent under-prioritization of safety-critical data. Evaluation on 50-, 100-, and 200-node Watts–Strogatz topologies under fault rates up to 50%, using the Edge-IIoTset and WUSTL-IIoT-2021 benchmarks, demonstrates 99.00% critical recall and up to $1.8\times$ higher overall-packet delivery compared to RPL-RP under severe fault conditions. Routing improvements are primarily attributed to fuzzy criticality labeling and multi-path replication. These findings indicate that fuzzy-supervised federated inference offers a practical and interpretable solution for safety-critical IIoT routing, with an observed energy overhead of 7.8% per delivered packet. Full article

Objective: Based on the Person-Centered Approach, this study targeted parents of very preterm (VPT) infants in Neonatal Intensive Care Units (NICUs) from Italy and Portugal. The primary aim was to classify parents by identifying latent classes of perceived risks (NICU stressors) and resources (sources of social support). Potential specificities in class membership according to Country of Belonging and sociodemographic factors were also investigated. Methods: Overall, 303 parents (92 Italian; 211 Portuguese) completed a survey including sociodemographic factors, Parental-Stressor-Scale-NICU, and Multidimensional-Scale-of-Perceived-Social-Support. Data were analyzed by multigroup latent class analysis and multinomial logistic regression. Results: Three statistically valid and cross-country classes were identified and labelled as Class 1, Adjusted/Beneficial-and-Supported-System, Class 2, Stressed-and-Supported-System, and Class 3, Parental-Role-Alteration-with-Family-Supported-System. Portuguese parents were mainly grouped in Classes 1 and 2, while Italian parents were in Class 3. Men were less likely to belong to Classes 2 and 3, while older parents having another child were more likely to belong to Class 3. Conclusions: The experience of parents of VPT infants in NICUs is inherently challenging, yet identifying specific risk profiles featured by the unique nuances of stressors and sources of support while accounting for further factors (Country of Belonging, Gender, Age, Having another child) can foster the customization of interventions aimed at providing parents with the necessary resources for adjusting to this extremely demanding experience. Full article

Shelter organisations take responsibility for the care, assessment and homing of large numbers of domestic cats from diverse backgrounds. However, not all cats that come under shelter care are suited to close human-cohabitation or to certain types of human-domestic lifestyles. Shelter stakeholders may undertake decision-making processes to determine how each cat should be managed and where they should go next. These processes may lead to different cat welfare experiences and long-term outcomes depending on how they occur, yet little is known about current approaches. The aim of this study was to characterise current approaches to cat and adopter assessments, behaviour management and homing decisions across the British Isles shelter sector, considering reported practices against sector minimum standards where applicable. A total of 393 quantitative and qualitative responses from employees and volunteers were received. Responses indicated that overall, stakeholders were consistently undertaking cat and prospective adopter assessments, with subsequent information used to support cat management, decision-making and homing. However, the degree of standardisation and objectivity associated with these processes was unclear, with considerable variation in approaches, including certain practices potentially associated with poor cat welfare outcomes identified. Examples include exposure to stressful handling and behavioural interventions and assessment ‘tests’, prolonged stays for harder-to-home cats and potentially suboptimal homing decisions for cats not suited to domestic ‘pet’ lifestyles. Identified opportunities to support welfare-friendly processes at the individual level include more consistent use of cats’ within-shelter behavioural presentations as grounds for ‘pet’-suitability assessments, and careful and consistent application of cat-labelling and terminology. It is also recommended that care is taken to ensure methods of cat assessments, behavioural interventions and homing decisions are pragmatic and optimised to positive cat welfare outcomes. Full article

Because injuries are often vague and easily unnoticed, missed diagnosis of scaphoid fractures on emergency radiographs reveals a critical limitation of acute care imaging. In addition, owing to unremarkable radiographic features, scaphoid fractures are particularly challenging. Therefore, a deep learning-based scaphoid fracture detection (DLSFD) framework is developed in this study for predicting scaphoid fractures on anteroposterior wrist radiographs. A ten-year retrospective cohort of wrist radiographs including both fractures and non-fractures were collected and analyzed in the study. Furthermore, data augmentation and labeling were used to improve model performance. The proposed deep learning-based scaphoid fracture detection framework first applies the YOLOv8 algorithm to localize and segment the scaphoid region in anteroposterior wrist radiographs. Then, a U-Net-based classifier is employed to predict the fracture or non-fracture with 5-fold cross-validation to prevent overfitting. Instead of using heat maps to represent the regions of scaphoid fractures, this study carries out pixel-level segmentation and generates pixel-wise masks to clearly locate scaphoid fracture area. Numerical results indicate that the proposed DLSFD framework is a feasible and promising alternative in predicting scaphoid fractures in terms of classification performance. Moreover, overlay segmentation masks generated by the developed DLSFD framework provide visual assistance for clinical interpretation. Thus, the designed DLSFD framework is able to successfully identify scaphoid fractures and may be useful in clinical practice for assisting clinical assessment. Full article

Background/Objectives: HbA1c is widely used to identify adults at increased risk of type 2 diabetes mellitus (T2DM), but major guidance differs on whether the lower limit of an HbA1c-defined risk range should be 5.7% (39 mmol/mol) or 6.0% (42 mmol/mol). This systematic review evaluated the prognostic and screening utility of HbA1c 5.7–6.4% compared with HbA1c 6.0–6.4% and examined whether available evidence supports threshold-based allocation of preventive interventions. Methods: The review was reported in accordance with PRISMA 2020 and registered in PROSPERO (CRD42019134344). PubMed/MEDLINE, Embase and the Cochrane Library were searched for studies published from 1 January 2016 to 1 January 2026. Eligible evidence comprised human studies in English, French, Hebrew, Italian or Spanish that evaluated HbA1c ranges below the diabetes diagnostic threshold in adults aged at least 40 years or younger adults with established risk factors. Two reviewers independently screened records and extracted data. Risk of bias was assessed using an adapted QUADAS-2 framework for threshold-performance evidence, supplemented by CASP-informed appraisal, and certainty was rated with GRADE domains. Narrative synthesis was selected because populations, thresholds, comparator tests, follow-up and outcome ascertainment were heterogeneous. Results: Seven studies were included. Evidence consistently supported a graded risk continuum rather than a single biological cut point. HbA1c 5.7–6.4% identifies more adults but includes many at low short-term absolute risk, whereas HbA1c 6.0–6.4%, especially 6.2–6.4% or combined HbA1c and fasting glucose abnormality, identifies fewer adults at higher near-term risk. Direct evidence comparing 5.7% versus 6.0% thresholds came mainly from one UK cohort, with supportive but indirect evidence from meta-analysis, routine-care cohorts and reversion studies. No trial randomized adults to intervention by HbA1c threshold, and eligible evidence did not directly address early diabetes-related morbidity by threshold. Conclusions: HbA1c below the diabetes diagnostic threshold should be interpreted as risk strata, not as a binary disease label. HbA1c 5.7–6.4% is defensible for broad, low-intensity preventive advice, while HbA1c 6.0–6.4% can be used to prioritize structured prevention and closer follow-up. The proposed tiered approach is a pragmatic, hypothesis-generating interpretation of the available evidence rather than a trial-validated intervention algorithm. Full article

Human activity recognition—HAR—plays a crucial role in the lives of patients battling neurodegenerative diseases. These debilitating conditions, such as Alzheimer’s or Parkinson’s, affect individuals’ ability to perform daily tasks autonomously and safely. HAR technology offers an invaluable solution by enabling real-time monitoring and assistance, helping to maintain independence and quality of life for patients. Additionally, this technology provides a valuable data source for doctors and caregivers, allowing for more precise and personalized care, which can make a difference in managing and treating these neurodegenerative diseases. The objective of this review is to identify the contribution of Transfer Learning and Reinforcement Learning in supporting the processes of daily activity recognition, thus enhancing the quality of life for patients. As this is a trending topic, the literature surrounding it is quite dispersed, which is why this review aims to present the current line of research in this field. To carry out this analysis, the science tree paradigm was used, which establishes two fundamental stages of analysis. The first is delimited by scientometrics, where the leading countries in the application of such technologies can be identified. This review highlights the evolution in the use of transfer learning and reinforcement learning in HAR in the healthcare field, where these techniques have significantly improved the accuracy and adaptability of real-time monitoring systems. The studies reviewed indicate that transfer learning has allowed models to adapt to data variations without requiring large volumes of manual labeling, which is essential in clinical and patient monitoring contexts. Additionally, reinforcement learning has optimized decision-making in complex scenarios, enabling activity recognition systems to dynamically adjust monitoring parameters, enhancing detection and response to critical or unusual activities in multi-user environments. These advances demonstrate that, by integrating these approaches, greater personalization and robustness can be achieved in human activity recognition, thereby improving the quality of life for patients in clinical settings. Full article

Sepsis is life-threatening organ dysfunction caused by a dysregulated host response to infection, making early detection critical for improving outcomes in intensive care units (ICUs). This study presents a retrospective comparative evaluation of deep learning architectures for predicting sepsis up to 6 h before the PhysioNet/Computing in Cardiology 2019 Challenge onset label using hourly structured electronic health record (EHR) variables, including vital signs, laboratory measurements, and demographics. Evaluated architectures include Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory (Bi-LSTM), Temporal Convolutional Network (TCN), Transformer, and hybrid Convolutional Neural Network–Vision Transformer (CNN-ViT) models. Median imputation and class-weighted loss were applied to address missing values and severe class imbalance, while Shapley Additive Explanations (SHAP) and attention analyses were used as complementary interpretability approaches. Among the evaluated models, CNN-ViT achieved the strongest overall minority-class performance, with 88.25% accuracy, 0.7480 recall, a 0.454 F1-score, and a 0.48 area under the precision–recall curve (AUPRC), although the numerical gains over other advanced temporal and hybrid architectures were modest. Leave-one-unit-out evaluation further demonstrated relatively stable performance under internal distribution shifts. The results suggest that combining local feature extraction with temporal and attention-based modeling can improve early sepsis prediction from structured ICU data. However, the study represents a retrospective computational benchmark using a public dataset and does not constitute prospective clinical validation or real-world deployment assessment. Full article

Approximately 10% of the general population reports a penicillin allergy, making it one of the most commonly documented drug allergies in clinical practice. Yet formal evaluation confirms true hypersensitivity in fewer than 10% of these cases. This gap has practical consequences. Patients who carry an inaccurate allergy label are more likely to receive broader-spectrum alternative antibiotics, with downstream effects on cost, adverse drug events, and antimicrobial resistance. Although primary care physicians are often the first to record these labels and the ones who face their consequences most often in daily prescribing, they have remained peripheral to most systematic delabeling efforts. In this narrative review, we examine how antibiotic allergy labels arise, why they persist, and what they cost—clinically, economically, and from a stewardship perspective. We also discuss emerging approaches to reassessment in primary care, including risk stratification tools and international guideline recommendations, along with the possible role of digital health tools and patient education in improving the accuracy of allergy documentation. Full article