Search Results (4,051)

The rapid advancement of machine learning and artificial intelligence (AI) has created new opportunities to enhance diagnostic accuracy in dermatology, particularly within primary care settings. Computer-aided diagnosis (CAD) systems have demonstrated potential to support General Practitioners (GPs) by enabling earlier and more consistent identification of skin diseases. This review critically examines the literature on explainable artificial intelligence (XAI) for skin disease classification, with a specific focus on the evolution of explainability frameworks and the methodological implications of dataset selection. A comprehensive review of studies published between 2020 and 2025 was conducted across multiple academic databases, encompassing research on skin lesion detection, classification, and monitoring. The analysis reveals that deep learning architectures, particularly those leveraging transfer learning with models such as EfficientNet, ResNet, and Xception, frequently report high classification accuracies—often exceeding 90% when evaluated on single benchmark datasets. However, studies employing multiple datasets consistently demonstrate more stable and generalisable performance, albeit with modest reductions in reported accuracy, highlighting a critical trade-off between performance optimisation and real-world robustness. The review further identifies a clear temporal progression in the adoption of XAI techniques. Early studies relied on a broader range of post hoc explainability while later work increasingly consolidated around Grad-CAM, SHAP, and related attribution techniques, followed by gradual diversification into more specialised frameworks such as TCAVs (Testing with Concept Activation Vectors) and Prototype-based Networks. Despite these advances, the lack of clinically grounded explanations, limited integration of ethical considerations, and reliance on non-clinical imagery continue to constrain clinical applicability which we have explored using a GRADE-style narrative. Notably, evidence suggests that CAD systems can improve GP diagnostic accuracy for conditions such as melanoma and seborrhoeic keratosis; however, sustained clinical adoption remains contingent on transparent, reliable, and context-aware explainability mechanisms. Full article

Background: Aerobic vaginitis (AV) is characterized by dysbiotic vaginal microflora with overgrowth of aerobic pathogens of enteric origin, presence of vaginal inflammation and immature epithelial cells. This study aimed to evaluate, over a period of 10 years, women of reproductive age (non-pregnant and pregnant) as well as menopausal women affected by AV. Methods: We included non-pregnant, pregnant and menopausal women diagnosed with AV over a period of 10 years. Diagnosis of AV was determined according to the criteria proposed by Donders in 2002. The isolated pathogens were identified with the rapid identification system I-dOne (Alifax S.r.l, Polverara, Italy) and the automated system VITEK2 (Biomerieux, Marcy l’Etoile, France), which was used for antimicrobial susceptibility testing. Results: The overall aerobic vaginitis prevalence rate during the studied period was 9.5%. The most common isolated pathogens were Escherichia coli 27.3%, Enterococcus faecalis 25.0%, Streptococcus agalactiae 22.2%, Klebsiella pneumoniae 8.9%, Proteus spp 4.7%, and Staphylococcus aureus 3.5%. E. coli infection significantly increased the odds of mild AV by 1.65 times (p = 0.002) and Proteus species infection was over 6 times more likely to progress to severe disease (p < 0.001). Furthermore, pregnant women were more likely to be infected with E. faecalis (p < 0.001) while menopausal women were diagnosed significantly more with severe AV (p < 0.001) compared to the other groups. Conclusions: The prevalence of aerobic vaginitis in the population studied was in concordance with global rates. Menopausal women displayed increased severe AV cases while, in contrast, mild cases were recorded during pregnancy. The most commonly isolated pathogens were of enteric origin. Full article

Pediatric acute liver failure (PALF) is a rare but life-threatening condition characterized by rapid clinical deterioration and high mortality. Viral infections represent a major etiology of PALF, although the causative agent remains unidentified in a substantial proportion of cases. Human Enteroviruses (EVs) are typically associated with self-limiting illnesses; however, they may rarely cause severe systemic disease, including fulminant hepatitis, particularly in neonates and young children. We describe the case of a 4-year-old previously healthy male who presented with acute fulminant hepatitis secondary to systemic Echovirus 25 (E25) infection, with concomitant Epstein–Barr virus (EBV) co-infection of recent onset. The diagnosis was established through multiplex PCR on cerebrospinal fluid, blood, stool, and nasopharyngeal aspirate, with serotype confirmation by the Italian National Institute of Health. The patient required intensive supportive care including therapeutic plasma exchange (TPE), continuous kidney replacement therapy (CKRT), and intravenous immunoglobulins (IGIV). Despite initial clinical deterioration and placement on the liver transplant list, the patient achieved complete hepatic recovery and was discharged after fourteen days of hospitalization without requiring transplantation. This case highlights the importance of prompt virological workup including enterovirus PCR in children presenting with acute liver failure of undetermined etiology and supports the use of extracorporeal therapies as a bridge to recovery. Full article

Viral hemorrhagic fevers (VHFs) are severe infectious diseases caused by RNA viruses of the families Arenaviridae, Filoviridae, Flaviviridae, and Hantaviridae, characterized by high morbidity, significant case fatality rates, and frequent diagnostic uncertainty in early disease stages. For military medical services, timely clinical recognition and laboratory confirmation are essential to guide patient management, prevent nosocomial transmission, and maintain operational continuity, particularly in endemic or resource-limited deployment settings. This review critically examines current diagnostic approaches to VHF-causative agents, emphasizing their use in clinical and field medical settings. The diagnostic process, from exposure through specimen collection, laboratory testing, and result interpretation is analyzed, including the use of molecular, serological, and antigen-based assays. Particular attention is given to deployable diagnostic platforms and their role in bridging the gap between frontline clinical suspicion and definitive laboratory confirmation. Biosafety requirements and infection prevention measures are discussed as integral components of clinical diagnostic workflows, aligned with guidance from the World Health Organization and the Centers for Disease Control and Prevention. Comparative analyses of virus-specific diagnostic timelines and laboratory requirements are presented to support differential diagnosis and clinical decision-making. Emerging technologies, including rapid molecular assays and genomic methods, are evaluated for their potential to improve early diagnosis and patient outcomes. This review highlights the central role of diagnostic readiness in clinical management of the VHFs and provides evidence-based considerations to support military clinicians facing high-risk febrile illnesses in operational environments. Full article

High-dynamic amusement ride conditions involving impacts, rapid rotations, and abrupt posture changes introduce severe motion artifacts that degrade vital sign quality and destabilize physiological state recognition. This study aims to develop an engineering-ready closed-loop framework for robust passenger monitoring and intelligent diagnosis. A multimodal sensing and modeling pipeline was designed to jointly leverage physiological signals such as heart rate and SpO₂ and kinematic measurements, including acceleration, angular rate, velocity, and attitude. Inertial and PPG signals were preprocessed into supervised samples through wavelet multiresolution denoising and coordinate frame unification, while a strapdown inertial navigation system was used to propagate a 12-channel physical quantity sequence. To ensure interpretability and standards compliance, constraints from GB 8408-2018 were translated into executable threshold rules, enabling standards-driven auto-labeling and rule-based early warning. Building on this foundation, three learning modules were developed: a fusion model for high-dynamic heart rate estimation, a CNN–LSTM dynamic-threshold-enhanced network TAPNet for rapid kinematic anomaly screening, and an attention-augmented hybrid model HS-BANet integrating one-dimensional residual blocks, bidirectional LSTM, and multi-head attention for fine-grained arrhythmia classification. Experimental results demonstrated accurate and consistent heart rate estimation with RMSE of 1.18 bpm on HSSH-I and 1.24 bpm on the independent HSSH-II set, strong agreement with training and testing correlations of 0.9928 and 0.9865, and near-zero bias in Bland–Altman analysis. TAPNet achieved 96.9% validation accuracy and 98.2% test accuracy for kinematic anomaly recognition, maintaining robust generalization under class imbalance. HS-BANet enabled multi-class identification of PVC, PAC, VT, SVT, and AF, achieving an accuracy of 92.37%, an F1-score of 86.87%, a precision of 88.45%, a sensitivity of 88.14%, and a specificity of 89.42%. Overall, the proposed two-stage multimodal closed-loop—fast, interpretable early warning based on physical quantity thresholds followed by fine-grained diagnosis from physiological signals—supports stable feature extraction and reliable decision-making under strong motion artifacts and non-stationary dynamics, balancing responsiveness and diagnostic credibility, while showing potential for practical safety early warning and future deployment-oriented operational support in amusement ride scenarios. Full article

Rapid and non-destructive detection of nitrogen content in greenhouse cucumber leaves is essential for precision fertilization, yet traditional chemical methods are destructive and time-consuming, and existing spectral technologies suffer from high cost and poor field adaptability. This study aims to propose a high-precision detection scheme for cucumber leaf nitrogen content based on a lightweight model, suitable for complex scenarios. A total of 698 cucumber leaf images covering three growth stages were collected to build a segmentation dataset. Four categories and eight types of deep learning segmentation models were optimized and compared, and the optimal one was selected to extract leaf regions. Nine color features were extracted and combined with Kjeldahl-measured nitrogen content to construct and optimize three machine learning models, forming a deep learning segmentation–color feature extraction–machine learning prediction process. The results showed that YOLOv11n achieved the best segmentation accuracy, with an IoU of 0.9212 and AP of 0.9998 for high-resolution images. The optimized XGBoost had the highest prediction accuracy, with an MAE of 0.469, MSE of 0.461, and RMSE of 0.679, which are 10.15%, 8.71%, and 4.36% lower than Support Vector Regression with Radial Basis Function kernel (SVR_RBF) respectively, and its predicted nitrogen content aligned well with true values. The proposed scheme integrating YOLOv11n and XGBoost offers a lightweight technical solution for nitrogen nutrition diagnosis and precise fertilization of greenhouse cucumbers. Full article

In modern power systems such as new energy generation and smart grids, inverters serve as core equipment for electrical energy conversion and transmission. Their operational reliability directly impacts system power supply quality and safety stability. Currently, research on inverter fault diagnosis technology primarily focuses on linear load conditions, with diagnostic method design and validation based on linear load characteristics. However, with the rapid advancement of power electronics technology, power electronic loads such as variable frequency drives, charging stations, and distributed power sources are increasingly prevalent in power systems. These loads exhibit nonlinear and time-varying characteristics under complex operating conditions, leading to a growing variety of inverter faults with significantly diversified and complex fault signatures. Traditional diagnostic methods fail to adapt to the unique characteristics of power electronic loads, making it difficult to accurately identify various faults. Consequently, they no longer meet the diagnostic demands of practical engineering scenarios. In addition, current diagnostic methods for open-circuit power transistors, intermittent faults, and sensor faults often employ different approaches, which consume significant controller resources and are prone to mutual interference, leading to false triggers. This paper takes a three-phase four-wire inverter as the research subject. Targeting the challenge of fault diagnosis under power electronic load conditions, it proposes a comprehensive diagnostic method capable of simultaneously diagnosing power switch open circuits, intermittent faults, and current sensor faults. First, the characteristics of various faults are analyzed. Subsequently, fault diagnosis variables are constructed using the actual arm voltage of the inverter and the ideal arm voltage. Logical rules for each type of fault are established, and diagnosis is performed through fuzzy logic inference. Finally, experiments validated the effectiveness of this fault diagnosis scheme, with open-circuit faults detected in less than 2 ms, intermittent faults in less than 0.5 ms, and sensor faults in less than 3 ms. Full article

Background/Objectives: Prepubertal localized aggressive periodontitis/LPP is an extremely rare but extremely fast-progressing form of periodontal disease involving systemically healthy children, starting in primary and mixed dentition. Our aim is to synthesize the data (January 2014–April 2026) on LPP progression description in systemically healthy children aged 2–13 years; clinical and biological responses to available treatment strategies, focusing on disease progression pattern, treatment efficacy and factors influencing treatment outcomes; and correlating findings with a report of a 24-month follow-up of a female prepubertal Caucasian patient during the primary and early stages of mixed dentition. Methods: A total of 489 studies were found after deduplication for the selected period. Due to the eligibility criteria, 9 studies plus another 10 contextual publications were included. Additionally, a 24-month follow-up of a previous LPP case was correlated. Results: LPP displayed rapid tissular destruction in primary dentition with risks to transfers to mixed and permanent dentition. The systemic antibiotic treatment reduced tissue loss, enabling fast periodontal regeneration. LPP is rare but severe, with a continuous biological trajectory, and with the window of opportunity remaining when the first symptoms appear. A few months (4–6 months) delay in diagnosis leads to irreversible tooth loss even in young patients with high biological healing potential. Conclusions: Systemic antibiotic treatment is mandatory in LPP/C-MIP cases from the primary dentition phase but does not reset host susceptibility. The Amoxicillin/Augmentin–Metronidazole association is recommended, with caution regarding dosage (adverse reactions). Periodontal gains are radiologically and clinically proven, but rebounding is possible. Full article

The Eastern equine encephalitis virus (EEEV) complex comprises mosquito-borne neurotropic alphaviruses maintained in nature by mosquitoes. Although rare, human infections caused by these viruses can lead to febrile illness that may progress to severe encephalitis, for which there are no vaccines for prevention and no specific therapeutics for treatment. Moreover, a high percentage of human cases show long-term neurological sequelae. Here, we review the literature on cases, diagnosis, and management. Current gaps in clinical care include an urgent need to develop rapid diagnostic tests, new therapeutics, and vaccines. Full article

Grapevine black-foot disease is a destructive trunk disease with a complex pathogen composition that often involves mixed and latent infections, making timely field diagnosis challenging. To improve rapid field detection, we developed a rapid, sensitive, and low instrument-dependent nucleic acid assay. The assay integrates recombinase polymerase amplification (RPA) and clustered regularly interspaced short palindromic repeats (CRISPR)–Cas12a for the detection of Ilyonectria and Dactylonectria, two genera associated with grapevine black-foot disease. Conserved regions of the histone H3 and β-tubulin genes were selected for the design of specific RPA primers and corresponding CRISPR RNAs (crRNAs) for Ilyonectria and Dactylonectria, respectively. A workflow integrating RPA, Cas12a-mediated recognition, and lateral flow assay (LFA)-based visualization was established. The reaction conditions were optimized to enhance amplification efficiency and Cas12a recognition stability. Specificity was evaluated using DNA from target and non-target fungi, and sensitivity was determined using serially diluted templates. Under optimized conditions, the assay detected Ilyonectria DNA at concentrations as low as 3.6 ng/μL within 1 h at 39 °C. For Dactylonectria, the detection limit reached 80 fg/μL within 50 min at 41 °C. No cross-reactivity was observed. The LFA strips exhibited positive and negative bands within minutes, enabling rapid visual interpretation. This RPA-CRISPR/Cas12a-LFA system provides a rapid, visually interpretable approach for detecting selected grapevine black-foot disease-associated species in China. The workflow reduces the requirement for specialized thermocycling and fluorescence detection equipment during amplification and readout, following DNA extraction. Full article

Due to the low inertia and small internal resistance of the DC line, the short-circuit fault is more harmful to the DC microgrid than the AC microgrid. Therefore, rapid and accurate detection of faults in DC microgrids plays an important role in ensuring the stable operation of DC microgrids. In this paper, the residual generator is designed based on the state observer, and the fault diagnosis of the DC microgrid is achieved by analyzing and processing the residual signal. Firstly, a mathematical model is established for a single line, and the corresponding residual generator is designed by using the unknown input observer to achieve the fault detection of a single key protection line. Secondly, considering the high cost of fault detection for each line alone, a residual generator is established for the entire DC microgrid to achieve fault detection of the entire DC microgrid, which effectively reduces the cost of fault detection. Finally, the radial DC microgrid and the ring DC microgrid are simulated and verified respectively to ensure that the designed fault diagnosis method is applicable to both topologies. Full article

Background: Multiparameter flow cytometry is widely used in the diagnosis of acute leukemia, allowing for rapid identification of leukemic cells based on their immunophenotype. The EuroFlow Acute Leukemia Orientation Tube was designed as a standardized screening tool to support early diagnostic orientation and guide further, more targeted testing. In this study, we assessed the diagnostic performance of the ALOT panel in pediatric patients with suspected acute leukemia. Methods: A total of 254 pediatric patients (0–18 years) with suspected acute leukemia were analyzed. Bone marrow samples were assessed using multiparameter flow cytometry with the EuroFlow ALOT panel, comprising eight markers (MPO, cyCD79a, CD34, CD19, CD3, cyCD3, CD7, and CD45). Final diagnoses were established using extended immunophenotypic panels and additional diagnostic methods when required. Samples were processed according to EuroFlow standard operating procedures and acquired on FACSCanto II and FACSCanto 10-color flow cytometers (BD Biosciences). Diagnostic performance was assessed by calculating sensitivity, specificity, precision, accuracy, and negative predictive value. Results: Among 254 patients, 234 were diagnosed with hematologic disorders, while 20 had normal bone marrow findings. The ALOT panel correctly identified all pathological samples and did not misclassify any normal sample, resulting in 100% sensitivity, specificity, positive predictive value, negative predictive value, and accuracy for discrimination between abnormal and normal samples. In terms of exact diagnostic orientation, ALOT correctly classified 244 of 254 cases (96.1%) using a single-tube approach. The remaining 10 cases (3.9%), including rare entities such as Burkitt leukemia, chronic myeloid leukemia, and transient myeloproliferative syndrome, required extended immunophenotypic evaluation. Importantly, these cases were not false negative results, as all were correctly identified as abnormal. Conclusions: The EuroFlow ALOT panel is a reliable screening tool for rapid diagnostic orientation in pediatric acute leukemia. Its implementation facilitates targeted selection of extended immunophenotypic panels, improving the efficiency and cost-effectiveness of diagnostic workflows. Full article

Background/Objectives: Pes planus and pes cavus are common foot deformities, which may lead to pain, functional limitations, and impairment of foot biomechanics. While calcaneal pitch, talar declination, and Meary angles, commonly used in diagnosis, provide objective information, their lack of a gold standard and the observer’s dependence on manual measurements limit their reliability. Therefore, in this study, these angles obtained from weight-bearing lateral foot radiographs were evaluated according to literature references, and the aim was to determine the model that provides the most accurate prediction in the diagnosis of pes planus using machine learning algorithms. It should be emphasized that, because the diagnostic labels were derived from literature-based thresholds of these same angles, the machine-learning task addressed here is the automated reproduction and standardization of expert, angle-threshold-based classification, rather than an independent clinical diagnosis from raw images. Methods: This retrospective study was conducted using weight-bearing lateral foot radiographs of 697 male patients obtained from the archives of public hospitals in Gaziantep. Calcaneal pitch, Meary angle, and talar declination angles were evaluated in both feet, and the data were labeled as normal, pes planus, and pes cavus. The dataset, consisting of a total of 1394 feet, was divided into training and test groups and analyzed using Random Forest, XGBoost, Logistic Regression, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) algorithms; the diagnostic performance of the models was compared using measures such as accuracy, F1 score, sensitivity, and specificity. Results: A total of 1394 feet from 697 male patients (mean age 24.8 ± 5.57 years) were analyzed using five machine learning algorithms with calcaneal pitch angle (CPA), Meary angle (MA), and talar declination angle (TDA) as reference labels. Ensemble-based methods showed superior performance, with XGBoost achieving perfect classification (Accuracy = 1.000) under all three labels for the left foot and 0.996–1.000 for the right foot, while Random Forest reached 0.986–1.000 across all experiments. Logistic Regression and SVM yielded moderate accuracies (0.905–0.973), whereas KNN consistently performed the weakest (0.905–0.964), particularly in the pes cavus subgroup. The near-perfect accuracy obtained when the labeling angle was itself included among the predictors reflects, at least in part, the algebraic reconstruction of the threshold rule from a same-source variable rather than genuine diagnostic generalization; results should therefore be interpreted with this in mind. Conclusions: This study demonstrates that machine learning, particularly ensemble methods such as XGBoost and Random Forest, provides high accuracy and consistency in diagnosing foot arch deformities based on radiographic angle measurements. Traditional models, such as Logistic Regression, still hold value in terms of clinical interpretability despite their lower performance. The findings suggest that machine learning-based approaches can offer objective, rapid, and reliable decision support tools for diagnosing pes planus and pes cavus, but external validation studies are necessary for clinical generalizability. Full article

Background/Objectives: Therapeutic plasma exchange (TPE) is an extracorporeal treatment used in thrombotic microangiopathies (TMAs) and various autoimmune and neurological disorders. However, data regarding its use during early pregnancy remain limited. This study aimed to evaluate maternal laboratory response and perinatal outcomes in pregnant women who underwent TPE before 26 weeks of gestation. Methods: This retrospective case series included 10 pregnant women diagnosed before 26 weeks of gestation who underwent TPE between 2010 and 2023. Clinical and laboratory parameters before and after TPE were compared. Results: Indications for TPE included HELLP syndrome (n = 4), thrombotic thrombocytopenic purpura (n = 3), presumed atypical haemolytic uremic syndrome (n = 1), neuromyelitis optica (n = 1), and Guillain–Barré syndrome (n = 1). The mean gestational age at diagnosis was 22.1 ± 3.1 weeks, and the mean gestational age at delivery was 27.1 ± 6.9 weeks. Five fetuses (50%) died and five (50%) survived to discharge. In patients with TMAs, TPE was associated with significant decreases in LDH, INR, APTT, ALT, AST, and total bilirubin levels, along with a significant increase in platelet count and ADAMTS13 activity (p < 0.01). No maternal complications occurred in neurological cases, all of which resulted in term deliveries with healthy neonates. Conclusions: In this uncontrolled case series, TPE was associated with rapid maternal clinical and laboratory improvement in selected pregnant women with TMAs, although a causal effect cannot be established from these data. However, perinatal outcomes were primarily determined by gestational age at delivery: all fetal losses occurred before 26 weeks, whereas all infants survived when delivery occurred after 26 weeks. Larger studies are needed to confirm these findings. Full article

Intracranial hemorrhage (ICH) is a life-threatening neurological condition that requires rapid and accurate diagnosis to reduce mortality and improve patient health. Computed tomography (CT) imaging is widely used for ICH detection. However, manual interpretation can be time-consuming and prone to errors, particularly in high-volume clinical settings. Recent studies have demonstrated the effectiveness of deep learning techniques in automating medical image analysis and improving diagnostic accuracy. In this study, we propose a novel deep learning model, MGiT-X, for the automated detection of intracranial hemorrhage using head CT images. The MGiT-X model is a hybrid deep learning architecture that uses dual scale Swin Transformer modules to extract features at multiple scales, capturing local and global contextual information on CT images. It has a Gradient Fusion mechanism to enhance feature representation by combining complementary features to distinguish between hemorrhagic and healthy tissue. In addition, to further improve feature representation, the use of Jensen–Shannon divergence is used to provide better mutual alignment and consistency between the distribution of features. An adaptive weight strategy is also employed to provide refinement to the importance of features for classification. MGiT-X is evaluated on two publicly available datasets including the Head CT Hemorrhage dataset and the Brain CT Hemorrhage dataset. The proposed approach leverages advanced feature extraction and classification capabilities to distinguish between hemorrhage and healthy cases effectively. Experimental results demonstrate that the proposed MGiT-X achieves high performance across both datasets. On Dataset 1, the model attains an overall accuracy of 95.87% and a Kappa score of 91.80%, while on Dataset 2, it achieves an improved accuracy of 99.12% with a Kappa score of 98.20%. Class-wise evaluation further shows strong performance, with F1-scores exceeding 95% for both hemorrhage and healthy classes across datasets. Full article