Early and reliable detection of pipeline leaks is essential for ensuring operational safety and minimizing environmental and economic losses. In practice, however, pipeline monitoring signals are inherently non-stationary and strongly influenced by operating conditions, making robust leak detection challenging, particularly when labeled fault data are scarce or unavailable. This paper presents a statistically grounded, signal-processing-based framework for pipeline leak detection that operates without reliance on machine learning or deep learning models. Pipeline signals are represented using a compact multi-domain feature set integrating time-domain statistics, frequency-domain spectral descriptors, and time-frequency features derived from wavelet packet decomposition. Instead of monitoring pointwise feature deviations, pipeline condition is assessed through distribution-level comparison between feature sets extracted from sliding monitoring windows and a reference distribution constructed under normal operation. Multiple complementary two-sample statistics energy distance, maximum mean discrepancy, and Hotelling's [Formula: see text] statistic are employed to capture distinct aspects of distributional divergence and fused into a unified health indicator (HI). Leak detection is achieved by comparing this indicator against statistically derived thresholds obtained exclusively from normal-condition data, enabling automated detection with controlled false-alarm behavior. The proposed framework is validated using experimental acoustic emission data collected from pipelines conveying gas and water at pressure levels of 13 bar and 18 bar. Results demonstrate stable normal-state behavior with false-alarm rates below 1%, rapid leak detection within 1-2 samples after leak onset, and detection accuracy exceeding 99% across all operating scenarios. Permutation-based statistical significance analysis confirms strong detection confidence with p-values in the range of [Formula: see text] to [Formula: see text], while robustness evaluation across more than 60 parameter configurations demonstrates consistent performance without operating-condition-specific tuning. The proposed approach provides an interpretable, data-efficient, and statistically rigorous solution for practical pipeline leak monitoring.
Smart Grids rely on robust communication infrastructures to monitor, control, and stabilize information in real time across geographically distributed energy resources. Trellis Coded Modulation (TCM) is a well-established technique for improving spectral efficiency and reliability, particularly in bandwidth-constrained and noisy channels. By combining convolutional coding with multilevel modulation, TCM achieves significant coding gains without increasing bandwidth, making it well suited for Smart Grid communication links. Turbo Trellis Coded Modulation (TTCM) extends TCM by incorporating parallel concatenated trellis encoders with iterative decoding, further enhancing performance and robustness under a wide range of channel distortions, including additive noise and fading. In this paper, we present the underlying mathematical framework for TCM and TTCM, simulation results under AWGN and Rayleigh fading channels, and comparisons to uncoded transmission. We also discuss future prospects of TCM, including integration with AI-driven adaptive coding and 5G-enabled Smart Grid infrastructures, highlighting the critical role of high-reliability communication systems in next-generation energy networks. Consequently, TTCM offers a hybrid solution that combines strong error correction with efficient bandwidth utilization, ensuring dependable communication for reliability-critical Smart Grid applications.
Cold object detection and classification allow reliable identification and categorization of low-temperature objects using non-contact thermal analysis, thereby complementing standard heat-focused techniques. It supports accurate monitoring of cooling behaviour, improves fault detection, quality control and remains powerful under poor lighting or visually challenging situations. However, cold object classification remains challenging when using conventional visible-light images due to the absence of discriminative temperature information. As of now, dedicated and systematic research on cold object detection and classification using thermal images are still very limited, highlighting a clear research gap. To address this limitation, this work proposes a thermal image-based cold object detection and classification framework using machine learning algorithms, designed to achieve effectiveness, reduced cost, and lower processing time. In addition, a dedicated dataset is developed by capturing time-dependent temperature variations of multiple cold object categories, enabling well ordered analysis and classification based on their thermal behaviour. Several machine learning models, including Decision Tree, Random Forest, XGBoost, and other classification algorithms, were developed and assessed using the proposed dataset. Among these models, the Random Forest classifier gives the highest classification accuracy of 99.35%, demonstrating its effectiveness in capturing temporal thermal variations for accurate cold object detection and identification. This work establishes a new research direction in thermal image analysis by shifting the focus from heat anomaly classification toward reliable cold object classification.
This study introduces a new 10-item, self-administered children's voice questionnaire (CVQ-10), designed to quantify children's voice handicap and assess its validity and reliability. Observational, prospective, cross-sectional study. The 10 items that comprise the new CVQ-10 were extracted from the full CVQ. The selected items were chosen based on their Cohen's d scores. The new questionnaire was administered to 208 children (80 dysphonic and 128 nondysphonic), aged 6-17 years. In addition, the parents of these children completed the Pediatric Voice Handicap Index (pVHI) and a brief anamnesis questionnaire. Furthermore, after 2 weeks, a subset of 30 randomly selected children (15 dysphonic and 15 nondysphonic) completed the CVQ-10 again, to examine test-retest reliability. At that time, another subset of 30 children was randomly selected to complete the full CVQ questionnaire to evaluate validity. The CVQ-10 demonstrated high reliability (Cronbach's α = 0.94). Test-retest reliability yielded a Pearson correlation coefficient of r = 0.91 (P < 0.001). A highly significant group difference was found between the dysphonic and nondysphonic groups of children (t[206] = 17.00, P < 0.001), with a calculated cutoff of nine points. A significant positive correlation was found between children's subjective self-evaluation on the CVQ-10 and their parents' responses on the pVHI questionnaire (r = 0.766, P < 0.001). The CVQ-10 is shown to be a valid and reliable instrument. Data confirms its single factor contract. This demonstrates that children are capable of providing a reliable and consistent description of their subjective voice handicap. The CVQ-10 differentiates dysphonic from nondysphonic children and can serve as a brief and easy to-use instrument for evaluating dysphonic children in clinical and research settings.
Engineered bacteria offer unique opportunities for biosensing because they combine genetically programmable biological activity with tunable surface interfaces. However, constructing living sensing systems that enable programmable recognition, reliable signal output, and robust performance in complex samples remains challenging. Here, we report an interfacially engineered bacterial sensing platform for dual-mode microRNA detection. Engineered Escherichia coli expressing enhanced green fluorescent protein (eGFP) were used as living signal carriers, and a polyphenol coating was deposited to create a stable, functionalizable interface. This coating preserved bacterial fluorescence while enabling immobilization of nucleic acid hairpin probes. Upon target recognition, catalytic hairpin assembly (CHA) was triggered, driving the programmable bridging and aggregation between bacteria and magnetic beads. This process converts molecular recognition into a magnetically separable assembly event, enabling target enrichment and background reduction. Meanwhile, enriched bacteria provide fluorescence output via intracellular eGFP, while Fe3+ released from the coating under acidic conditions generates a Prussian blue colorimetric signal. Together, these processes establish a fluorescence-colorimetric dual-mode sensing platform with limits of detection of 5.33 pM for the fluorescence mode and 14.1 pM for the colorimetric mode. In serum samples from glioma patients, the platform effectively distinguished patients from healthy controls, with dual-mode analysis showing improved discrimination performance compared to single-mode detection. This work demonstrates that interfacial engineering transforms engineered bacteria into multifunctional living sensing units and provides a practical strategy for developing reliable biosensing systems for liquid biopsy applications.
Weakly supervised video anomaly detection (WSVAD) is fundamentally constrained by the absence of frame-level annotations, which leads to noisy instance selection in Multiple Instance Learning (MIL) and weak correspondence between temporal video segments and semantic descriptions. Vision-language models address this by enabling cross-modal alignment between visual features and textual labels, but when these representations are learned in Euclidean space, they struggle to capture subtle semantic variations and often produce ambiguous instance ranking under weak supervision. To address this limitation, we propose PoinCLIP-VAD, a vision-language framework that performs cross-modal fusion in hyperbolic space. The model embeds visual and textual features into a shared Poincaré ball geometry, where non-linear distance scaling provides a more expressive representation of latent semantic relationships induced by cross-modal interactions, without relying on predefined hierarchical structures. This geometry-consistent formulation enables more reliable similarity estimation and better preserves distinctions between normal and anomalous patterns. The framework adopts a dual-block architecture consisting of a classification block for coarse anomaly scoring and a video-text alignment block for fine-grained correspondence using negative Poincaré distance. Extensive experiments on benchmark datasets demonstrate that PoinCLIP-VAD achieves an AUC of 90.62% on UCF-Crime and an AP of 86.93% on XD-Violence, confirming improved anomaly discrimination and more consistent cross-modal alignment under weak supervision.
Although liver biopsy in patients with acute cellular rejection (ACR) is the gold standard for diagnosis, its invasive nature highlights the need for reliable noninvasive biomarkers. With evidence suggesting that peripheral blood eosinophil levels may be associated with rejection, we evaluated the relationship between eosinophil levels and ACR to determine whether eosinophil dynamics reflect rejection severity. We retrospectively analyzed 151 liver transplant recipients who underwent 398 liver biopsies between 2012 and 2022. To analyze eosinophil changes, we collected data on eosinophil counts, eosinophil percentages, liver enzymes, bilirubin, international normalized ratio, and rejection activity index (RAI) scores from biopsy day (day 0) and day 5 after treatment; patients with and without rejection (established histopathologically with RAI) were compared. We analyzed correlations between RAI severity and eosinophil levels. Liver enzyme levels were significantly higher in patients with versus without ACR (P < .05). In the rejection group, eosinophil count and percentage decreased markedly after treatment (P < .001), whereas no significant change was observed in the non-rejection group. Higher RAI scores were associated with increased eosinophil count (P = .029) and percentage (P = .021) on day 0 and a more pronounced decline on day 5 (both P < .001). Peripheral blood eosinophil levels were associated with ACR and exhibited characteristic changes that reflected rejection severity and therapeutic response. Eosinophil monitoring may be a useful noninvasive adjunct in the early detection and follow-up of ACR. Larger prospective multicenter studies are needed to validate these findings.
Accurate quantification of hormone concentrations using clinical immunoassays is often limited by minimum specimen volume requirements, particularly with microvolume collection devices such as microtainers and capillary microsampling systems. When volume is insufficient to meet assay requirements, dilution is necessary; however, conventional dilution with analyte-free diluent proportionally reduces analyte concentration and may result in measurements falling below the assay's functional sensitivity, preventing reliable quantification. We evaluated an analyte-containing diluent strategy designed to preserve measurable signal and enable accurate hormone quantification from minimal serum volumes. Pooled human serum specimens were serially diluted and analyzed for estradiol (E2), luteinizing hormone (LH), and human chorionic gonadotropin (hCG) using the Beckman Coulter DxI 600 platform. Reverse-calculated concentrations from analyte-free and analyte-containing dilutions were compared with undiluted measurements using Passing-Bablok regression and recovery analysis. Analyte-containing dilution kept the measured concentration above the limit of quantitation at dilution factors up to 1:128, exceeding the dilution range over which conventional analyte-free dilution remained quantifiable. A hybrid correction model restored agreement with undiluted measurements, yielding recovery rates of 95.5% for hCG, 116.5% for E2, and 105.3% for LH across evaluable dilution ranges. This approach extends the functional analytical range of immunoassays and enables accurate hormone quantification from substantially reduced specimen volumes. Analyte-containing dilution provides a practical method compatible with existing clinical laboratory workflows and may enhance diagnostic testing reliability in microvolume and minimally invasive sampling applications.
Workplace gender discrimination against female nurses is a critical issue requiring evidence-based investigation and documentation. This study aimed to validate the Persian version of the Scale to Measure the Perception of Workplace Gender Discrimination for Female Nurses and ensure its psychometric robustness for clinical and research applications. Employing a cross-sectional methodological design, the study recruited 535 female nurses in Iran through convenience sampling. The Persian translation of the scale was developed in accordance with World Health Organization (WHO) guidelines. Validity and reliability were assessed using exploratory factor analysis (EFA), confirmatory factor analysis (CFA), and internal consistency measures. The EFA and CFA confirmed a five-factor structure with 29 items, accounting for 51.029% of the total variance. Model fit was excellent, as indicated by CFI, GFI, TLI, RMSEA, and SRMR values. The scale exhibited acceptable internal consistency, with Cronbach's alpha and McDonald's ω coefficients of 0.905 and 0.916, respectively. These findings establish the Persian version of the scale as a valid and reliable instrument, addressing a significant gap in the assessment of workplace gender discrimination for female nurses.
Checkpoint inhibitor (CPI) therapy has emerged as treatment option in selected patients with resectable head and neck squamous cell carcinoma. Recent phase III data have led to approval of perioperative pembrolizumab for patients with PD-L1-positive (CPS ≥ 1). With emerging data on adjuvant checkpoint inhibitor therapy the selection of the optimal treatment strategy is becoming increasingly complex. Several clinical phase II/III trials have evaluated neoadjuvant immunotherapy in resectable head and neck cancer, demonstrating both clinical and immunological benefits. This review summarizes current data on neoadjuvant and perioperative checkpoint inhibitors in resectable head and neck cancer and addresses main immunological advantages. In addition, potential strategies to optimize treatment efficacy and to overcome resistance mechanisms of CPI therapy are discussed. Further trials are needed to define optimal treatment protocols, determinate the best timing of surgery, and identify reliable biomarkers for patient selection, to guide evidence-based therapeutic decision-making in routine clinical practice.
Diffusion magnetic resonance imaging (dMRI) provides powerful insights into brain microstructure, but conventional microstructural modeling methods require long acquisition times for covering sufficient diffusion directions and are computationally intensive. While deep learning has shown promise in reducing the direction requirement and accelerating the modeling, traditional architectures such as CNNs often struggle to capture the highly nonlinear relationships between multi-shell diffusion signals and microstructural properties. We present MicroKAN, a novel framework built upon Kolmogorov-Arnold Networks with adaptive spline-based activations, specifically designed to represent complex biophysical models with enhanced flexibility and efficiency. MicroKAN supports both supervised and self-supervised paradigms: the supervised variant learns mappings from data to reference metrics, while the self-supervised variant estimates model parameters directly by reconstructing signals through the forward diffusion process, eliminating the need for ground-truth labels. Evaluated on diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) across multiple datasets, MicroKAN substantially accelerates acquisition and improves the fidelity of microstructural parameter estimation. Beyond supervised training, its self-supervised formulation shows strong robustness to distribution shifts, enabling reliable performance even without annotations. Furthermore, transfer learning with minimal labeled data preserves high accuracy, underscoring the framework's adaptability to diverse scenarios. These advances establish MicroKAN as a versatile and efficient tool for dMRI analysis, offering new opportunities to accelerate neuroscience research and expand the clinical utility of microstructural imaging. Our source code is available at https://github.com/JustlfC03/MicroKAN.
Large language models (LLMs) are increasingly applied in clinical communication, yet their reliability depends on high-quality conversational corpora. Real-world doctor-patient recordings are frequently degraded by noise, transcription errors, speaker overlap, and fragmented dialogue structure, limiting their usability for downstream model training. Here, we present an agent-based transcription framework that autonomously converts raw unstructured conversation transcriptions (RUCT) into structured conversation transcriptions (SCT) suitable for LLM fine-tuning. The system integrates three coordinated modules-Planner, Memory, and Executor-to orchestrate noise removal, content correction, speaker identification, and dialogue segmentation within a self-correcting workflow. Applied to 7197 minutes of Chinese clinical recordings across eight departments, with an additional 240 minutes of English-language dialogues used as a limited portability check, the agent achieved high reconstruction accuracy (94.7% denoising, 96.9% content correction, 88.6% speaker identification, 92.7% segmentation) and operated 3.6× faster than manual processing. In controlled comparisons against a cascaded deep-learning pipeline, a sequential non-agent execution, and an end-to-end large-context model, the agent achieved consistently higher performance across all four processing tasks. Architectural ablation further revealed marked degradation when Planner or Memory modules were removed (e.g., up to 47.6% reduction in speaker identification), supporting the contribution of coordinated task decomposition and cross-step state retention. To assess downstream impact, we fine-tuned an independent open-weight model (Qwen3-32B) on agent-generated SCT versus RUCT derived from an identical training set. Agent-generated SCT fine-tuning significantly improved overall quality scores (3.1 to 3.7; P < 0.001; Fleiss' κ = 0.82) in blinded expert evaluation across six clinically grounded dimensions, and also yielded higher scores on an external medical dialogue benchmark (HealthBench) than both RUCT fine-tuning and the non-fine-tuned baseline. These findings indicate that agent-structured clinical corpora enhance LLM fine-tuning performance and provide a scalable framework for reliable medical conversational AI development.
Sudden cardiac death after myocardial infarction (MI) remains a major clinical problem, partly driven by complex electromechanical feedback mechanisms that are not fully understood. In particular, the interplay between scar stiffness, border zone (BZ) remodeling, mechano-electric feedback (MEF) through stretch-activated channels (SACs), and cross-bridge formation, can strongly influence ventricular function and arrhythmogenic risk. In this study, we developed a 3D finite element model of human ventricular electromechanics coupled with a closed-loop circulation model to investigate the impact of scar size on cardiac function. Before addressing scar effects, we first analyzed the spatial resolution of the mesh to ensure reliable electromechanical predictions. Within the present electromechanical framework and mechanical discretization, spatial resolutions of approximately 1.0-1.3 mm were required to capture SAC-driven depolarizations in the BZ. Using this confirmed to be suitable resolution, we examined infarct volume fractions (IVFs) from 5-20% of the left ventricle (LV). Increasing IVF progressively impaired contractility and ejection fraction, with a nonlinear threshold emerging between 10% and 15% IVF in the primary models studied here, above which SACs elicited premature activations which disrupted sinus-driven dynamics, and produced irregular multi-beat PV-loop patterns. These findings highlight two key insights: spatial resolution is critical for capturing SAC-mediated feedback accurately, and scar extent strongly influences the severity of this feedback, with larger scars significantly altering ventricular dynamics. Together, this work provides mechanistic understanding of how scar enlargement can accelerate heart failure progression and arrhythmic risk through nonlinear MEF.
Bedaquiline, classified as a WHO 2019 group A drug, is a core component of BPaLM, revolutionizing the treatment of MDR/RR tuberculosis (TB). Since 2015, however, concerns about acquired and primary bedaquiline resistance have emerged. We report a diagnostically challenging case of a young asylum seeker from Afghanistan, previously treated for pulmonary TB with standard therapy for five months about four years earlier. After arriving in Switzerland, he presented with chronic dry cough, weight loss, and small upper-lobe nodular lesions. Rifampicin mono-resistant pulmonary TB was diagnosed, and BPaLM was initiated. Five weeks later, phenotypic antimicrobial susceptibility testing showed bedaquiline/clofazimine resistance. Next-generation sequencing revealed an IS6110 insertion in mmpR5. The patient had never received bedaquiline. An individualized regimen with pretomanid, linezolid, moxifloxacin, isoniazid, and pyrazinamide led to clinical and radiological improvement. Treatment was stopped after 9 months, with outcome classified as completed (not cured due to absent sputum production). The patient remains well 1.5 years after treatment completion. This case highlights the diagnostic and therapeutic challenges of primary bedaquiline resistance. Faster, reliable phenotypic and genotypic diagnostic methods, along with clear treatment recommendations, are urgently needed to identify bedaquiline-resistant patients promptly, treat them appropriately, and preserve the effectiveness of the BPaLM regimen.
Malignant melanoma is responsible for most skin cancer-related deaths due to its unpredictable behavior. Serum biomarkers have been widely investigated to improve prognostic assessment, yet their clinical utility remains inconclusive. This systematic review and meta-analysis evaluated the prognostic significance of serum biomarkers in melanoma. Following PRISMA guidelines and a registered protocol (PROSPERO: CRD42023486532), PubMed, EMBASE, and CENTRAL were searched for studies assessing biomarkers and survival outcomes. Univariate analyses revealed that elevated levels of LDH (HR 2.29, 95%-CI:1.97-2.67), S100B (HR 2.52, 95%-CI:1.59-3.99), circulating tumor DNA (ctDNA) (HR 2.61, 95%-CI:1.90-3.58), neutrophil-to-lymphocyte ratio (NLR) (HR 2.34, 95%-CI:1.86-2.93), and interleukin-6 (HR 3.11, 95%-CI:2.44-3.96) were significantly associated with reduced overall survival. Similarly, higher levels of LDH (HR 2.04, 95%-CI:1.68-2.47), S100B (HR 1.94, 95%-CI:1.39-2.70), ctDNA (HR 2.57, 95%-CI:1.95-3.39), and NLR (HR 2.38, 95%-CI:1.52-3.73) predicted shorter progression-free survival. These associations persisted in multivariable-adjusted analyses for LDH, ctDNA, NLR, IL-6, S100B, and CRP supporting their predictive relevance. LDH remains a reliable and cost-effective biomarker, while NLR may provide complementary prognostic information in patients receiving immune checkpoint inhibitors. Emerging biomarkers such as ctDNA demonstrate promising prognostic potential, but further evaluation is required before routine clinical implementation.
Though machine learning is widely used in wireless edge networks, the transmission of raw data still suffers from security and privacy leakage. Federated learning (FL) addresses these privacy concerns by enabling model training without sharing raw data. However, traditional centralized FL is vulnerable to a single point of failure. Blockchain-based federated learning (BFL) technology can provide FL with a more reliable and secure environment. In wireless edge networks with limited resources, BFL systems encounter challenges related to computing demands and network transmission overhead. To address these issues, we propose a BFL framework for wireless edge networks, which includes local client training, a consensus process, and edge server aggregation. A client selection policy is designed to exclude low-quality clients that could degrade training efficiency and accuracy. Additionally, a joint client selection and resource allocation scheme is implemented to optimize the allocation of computing and bandwidth resources necessary for BFL training and consensus. Simulation results demonstrate that the proposed approach improves BFL system accuracy while reducing delay.
Idiopathic pulmonary fibrosis (IPF) is a progressive debilitating lung disease which affects physical and mental well-being. The IPF Patient-Reported Outcome Measure (IPF-PROM) scale is a validated and reliable tool for the self-report of physical and psychological well-being in IPF. This study aimed to validate a Greek version of the IPF-PROM scale and further investigate its correlation with clinical features of IPF patients and its interrelation with depressive symptoms and health-related quality of life (HRQoL). This was a two-centre, observational, cross-sectional study, in which IPF patients completed three scales: IPF-PROM, Patient Health Questionnaire-9 (PHQ-9), an index of depressive symptoms, and Health Survey Questionnaire Short Form-12 (SF-12), an index of HRQoL, at the IPF Outpatient Clinics of two University Hospitals in Greece during 2023-2024. Logistic regression analysis was conducted to assess severe status of IPF-PROM compared with mild/moderate status. The study involved 136 IPF patients (87.9% males) with a mean age of 73.5±7.9 years. Patients were classified overall with moderate disease according to IPF-PROM mean scores (41.7±31.3), particularly in the combined Breathlessness/Fatigue and the Psychological well-being components (40.1 and 43.8, respectively, p>0.050). Patients with severe symptoms, as measured by IPF-PROM, scored higher levels of depressive symptoms on PHQ-9 compared with those with moderate or mild symptoms (17.1, 12.3 and 1.4, respectively, p<0.001) and lower levels of HRQoL in physical (32.6, 34.7 and 47.9, p<0.001) and mental health on SF-12 (23.9, 34.5 and 50.3, p<0.001). Patients with incrementally higher levels of oxygen saturation had lower odds for severe health status according to IPF-PROM (OR=0.83, p=0.018). A significant percentage of IPF patients present with impaired health status and symptoms suggestive of depression. The IPF-PROM scale represents a useful tool that may predict impairment of mental health and HRQoL in IPF, with potential utility for clinical practice and research.
Accurate identification of frontal sinus boundaries is a critical step in anterior skull base surgery, particularly in transsinusal approaches, as it allows optimization of the surgical bony window while minimizing unnecessary bone removal. To describe a simple and reproducible technique of external frontal bone transillumination for intraoperative frontal sinus mapping. After bicoronal exposure of the frontal bone, a standard fiber-optic light cable connected to the operating room light source is applied in direct contact with the frontal squama under low ambient light conditions. When properly applied, the frontal sinus appears as a brighter translucent area, allowing accurate delineation of its margins. Postoperative CT imaging was retrospectively reviewed to assess correspondence between the intraoperatively identified margins and the actual anatomical boundaries. Between 2015 and 2024, the technique was applied in 14 consecutive patients undergoing anterior skull base surgery, including olfactory groove meningiomas, post-traumatic anterior skull base cerebrospinal fluid fistulas, and one case of intrasinusal osteoma. In all cases, external transillumination enabled clear identification of frontal sinus boundaries and facilitated creation of an adequate surgical window. Postoperative imaging confirmed correspondence between the planned opening and the actual anatomical extent of the frontal sinus opening. No sinus-related complications or postoperative cerebrospinal fluid leaks were observed. External frontal bone transillumination is a simple, fast, and reliable method for intraoperative frontal sinus mapping during anterior skull base surgery. Its ease of adoption and use of routinely available equipment make it a useful adjunct to preoperative imaging for optimizing surgical exposure.
Parkinson's disease (PD) presents significant challenges due to its intricate symptoms and often delayed diagnosis. Therefore, early detection is vital for effective management and slowing the disease progression. Recently, machine learning based methods show high performance in this purpose. This research introduces a new machine learning approach that combines Residual-Shuffle Network (ResNet) with an advanced metaheuristic, the Improved Dandelion Optimizer (IDO) by integrating adaptive parameter control and enhanced exploration-exploitation balance, to provide an accessible and precise solution for automated PD detection. The proposed framework addresses previous limitations by effectively adjusting model hyperparameters and network weights without the need for expensive or sophisticated data collection devices. The proposed IDO-ResShuffle framework achieved strong performance on the HandPD dataset, obtaining 97.6% accuracy, 96.9% F1-score, 97.2% sensitivity, and 97.1% specificity. These results demonstrate the effectiveness of jointly optimizing the network architecture and hyperparameters through the Improved Dandelion Optimizer, enabling more reliable identification of Parkinson's disease from handwriting patterns. These enhancements empower healthcare professionals to make informed decisions about patient care sooner and potentially slow down the progression of symptoms. By enhancing accessibility and reliability, this approach can enhance clinical decision-making and support timely intervention in PD management.
Uric acid is a critical metabolic biomarker for gout, kidney dysfunction, and cardiovascular disease. Persistent hyperuricemia promotes monosodium urate crystal deposition, triggering recurrent gout flares, chronic joint damage, and systemic inflammation, while early and continuous uric acid monitoring enables timely therapeutic intervention and improved disease outcomes. However, conventional blood tests and enzymatic sensors, although reliable, remain invasive, laboratory-bound, and unsuitable for continuous or point-of-care monitoring. Herein, we report a sustainable one-step strategy to fabricate a non-enzymatic uric acid sensor by direct laser writing on cobalt-treated paper with 455 nm irradiation, producing cobalt oxide-infused graphene. Unlike conventional metal-functionalized laser-induced graphene (LIG), which typically requires multi-step processing and non-biodegradable polymeric substrates, the present approach employs a biomass-derived paper substrate and simultaneously generates conductive graphene and redox-active cobalt oxide nanostructures in a single photothermal process. Furthermore, the incorporated multivalent Co2⁺/Co3⁺ redox couples act as biomimetic active sites for uric acid oxidation, enabling a flexible low-energy electron-hopping mechanism and enhanced interfacial charge transfer. The resulting porous hybrid electrode provides abundant electroactive sites for efficient sensing performance. Integrated into a flexible near-field communication (NFC) tag, the resulting platform enables wireless, battery-free uric acid monitoring in human sweat. The fabricated sensor achieved a sensitivity of 9.96 µA·μM-1 and a detection limit of 1.08 μM for uric acid sensing. The mechanical robustness is confirmed by minimal resonance frequency variation under bending, shifting only from 13.525 MHz at 0° to 13.575 MHz at 180° (~ 0.37% relative change). This work establishes a low-cost, scalable, and environmentally sustainable route toward metal oxide-carbon hybrid biosensors, offering a promising pathway for wearable uric acid monitoring and next-generation point-of-care diagnostics.