Diagnostic Framework Research Articles

Exploration and verification a 13-gene diagnostic framework for ulcerative colitis across multiple platforms via machine learning algorithms

Ulcerative colitis (UC) is a chronic inflammatory bowel disease with intricate pathogenesis and varied presentation. Accurate diagnostic tools are imperative to detect and manage UC. This study sought to construct a robust diagnostic model using gene expression profiles and to identify key genes that differentiate UC patients from healthy controls. Gene expression profiles from eight cohorts, encompassing a total of 335 UC patients and 129 healthy controls, were analyzed. A total of 7530 gene sets were computed using the GSEA method. Subsequent batch correction, PCA plots, and intersection analysis identified crucial pathways and genes. Machine learning, incorporating 101 algorithm combinations, was employed to develop diagnostic models. Verification was done using four external cohorts, adding depth to the sample repertoire. Evaluation of immune cell infiltration was undertaken through single-sample GSEA. All statistical analyses were conducted using R (Version: 4.2.2), with significance set at a P value below 0.05. Employing the GSEA method, 7530 gene sets were computed. From this, 19 intersecting pathways were discerned to be consistently upregulated across all cohorts, which pertained to cell adhesion, development, metabolism, immune response, and protein regulation. This corresponded to 83 unique genes. Machine learning insights culminated in the LASSO regression model, which outperformed others with an average AUC of 0.942. This model's efficacy was further ratified across four external cohorts, with AUC values ranging from 0.694 to 0.873 and significant Kappa statistics indicating its predictive accuracy. The LASSO logistic regression model highlighted 13 genes, with LCN2, ASS1, and IRAK3 emerging as pivotal. Notably, LCN2 showcased significantly heightened expression in active UC patients compared to both non-active patients and healthy controls (P < 0.05). Investigations into the correlation between these genes and immune cell infiltration in UC highlighted activated dendritic cells, with statistically significant positive correlations noted for LCN2 and IRAK3 across multiple datasets. Through comprehensive gene expression analysis and machine learning, a potent LASSO-based diagnostic model for UC was developed. Genes such as LCN2, ASS1, and IRAK3 hold potential as both diagnostic markers and therapeutic targets, offering a promising direction for future UC research and clinical application.

Chronic Pain and Joint Hypermobility: A Brief Diagnostic Review for Clinicians and the Potential Application of Infrared Thermography in Screening Hypermobile Inflamed Joints.

Joint hypermobility syndromes, particularly chronic pain associated with this condition, including Hypermobile Ehlers-Danlos Syndrome (hEDS) and Hypermobility Spectrum Disorders (HSD), present diagnostic challenges due to their multifactorial origins and remain poorly understood from biomechanical and genomic-molecular perspectives. Recent diagnostic guidelines have differentiated hEDS, HSD, and benign joint hypermobility, providing a more objective diagnostic framework. However, incorrect diagnoses and underdiagnoses persist, leading to prolonged journeys for affected individuals. Musculoskeletal manifestations, chronic pain, dysautonomia, and gastrointestinal symptoms illustrate the multifactorial impact of these conditions, affecting both the physical and emotional well-being of affected individuals. Infrared thermography (IRT) emerges as a promising tool for joint assessment, especially in detecting inflammatory processes. Thermal distribution patterns offer valuable insights into joint dysfunctions, although the direct correlation between pain and inflammation remains challenging. The prevalence of neuropathies among hypermobile individuals accentuates the discordance between pain perception and thermographic findings, further complicating diagnosis and management. Despite its potential, the clinical integration of IRT faces challenges, with conflicting evidence hindering its adoption. However, studies demonstrate objective temperature disparities between healthy and diseased joints, especially under dynamic thermography, suggesting its potential utility in clinical practice. Future research focused on refining diagnostic criteria and elucidating the underlying mechanisms of hypermobility syndromes will be essential to improve diagnostic accuracy and enhance patient care in this complex and multidimensional context.

Hybrid physics-infused 1D-CNN based deep learning framework for diesel engine fault diagnostics

Hybrid physics-infused 1D-CNN based deep learning framework for diesel engine fault diagnostics

Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis – a proof of concept study

IntroductionProsthetic valve endocarditis (PVE) is a serious complication of prosthetic valve implantation, with an estimated yearly incidence of at least 0.4-1.0%. The Duke criteria and subsequent modifications have been developed as a diagnostic framework for infective endocarditis (IE) in clinical studies. However, their sensitivity and specificity are limited, especially for PVE. Furthermore, their most recent versions (ESC2015 and ESC2023) include advanced imaging modalities, e.g., cardiac CTA and [18F]FDG PET/CT as major criteria. However, despite these significant changes, the weighing system using major and minor criteria has remained unchanged. This may have introduced bias to the diagnostic set of criteria. Here, we aimed to evaluate and improve the predictive value of the modified Duke/ESC 2015 (MDE2015) criteria by using machine learning algorithms.MethodsIn this proof-of-concept study, we used data of a well-defined retrospective multicentre cohort of 160 patients evaluated for suspected PVE. Four machine learning algorithms were compared to the prediction of the diagnosis according to the MDE2015 criteria: Lasso logistic regression, decision tree with gradient boosting (XGBoost), decision tree without gradient boosting, and a model combining predictions of these (ensemble learning). All models used the same features that also constitute the MDE2015 criteria. The final diagnosis of PVE, based on endocarditis team consensus using all available clinical information, including surgical findings whenever performed, and with at least 1 year follow up, was used as the composite gold standard.ResultsThe diagnostic performance of the MDE2015 criteria varied depending on how the category of ‘possible’ PVE cases were handled. Considering these cases as positive for PVE, sensitivity and specificity were 0.96 and 0.60, respectively. Whereas treating these cases as negative, sensitivity and specificity were 0.74 and 0.98, respectively. Combining the approaches of considering possible endocarditis as positive and as negative for ROC-analysis resulted in an excellent AUC of 0.917. For the machine learning models, the sensitivity and specificity were as follows: logistic regression, 0.92 and 0.85; XGBoost, 0.90 and 0.85; decision trees, 0.88 and 0.86; and ensemble learning, 0.91 and 0.85, respectively. The resulting AUCs were, in the same order: 0.938, 0.937, 0.930, and 0.941, respectively.DiscussionIn this proof-of-concept study, machine learning algorithms achieved improved diagnostic performance compared to the major/minor weighing system as used in the MDE2015 criteria. Moreover, these models provide quantifiable certainty levels of the diagnosis, potentially enhancing interpretability for clinicians. Additionally, they allow for easy incorporation of new and/or refined criteria, such as the individual weight of advanced imaging modalities such as CTA or [18F]FDG PET/CT. These promising preliminary findings warrant further studies for validation, ideally in a prospective cohort encompassing the full spectrum of patients with suspected IE.

Retrieval-Based Diagnostic Decision Support: Mixed Methods Study.

Diagnostic errors pose significant health risks and contribute to patient mortality. With the growing accessibility of electronic health records, machine learning models offer a promising avenue for enhancing diagnosis quality. Current research has primarily focused on a limited set of diseases with ample training data, neglecting diagnostic scenarios with limited data availability. This study aims to develop an information retrieval (IR)-based framework that accommodates data sparsity to facilitate broader diagnostic decision support. We introduced an IR-based diagnostic decision support framework called CliniqIR. It uses clinical text records, the Unified Medical Language System Metathesaurus, and 33 million PubMed abstracts to classify a broad spectrum of diagnoses independent of training data availability. CliniqIR is designed to be compatible with any IR framework. Therefore, we implemented it using both dense and sparse retrieval approaches. We compared CliniqIR's performance to that of pretrained clinical transformer models such as Clinical Bidirectional Encoder Representations from Transformers (ClinicalBERT) in supervised and zero-shot settings. Subsequently, we combined the strength of supervised fine-tuned ClinicalBERT and CliniqIR to build an ensemble framework that delivers state-of-the-art diagnostic predictions. On a complex diagnosis data set (DC3) without any training data, CliniqIR models returned the correct diagnosis within their top 3 predictions. On the Medical Information Mart for Intensive Care III data set, CliniqIR models surpassed ClinicalBERT in predicting diagnoses with <5 training samples by an average difference in mean reciprocal rank of 0.10. In a zero-shot setting where models received no disease-specific training, CliniqIR still outperformed the pretrained transformer models with a greater mean reciprocal rank of at least 0.10. Furthermore, in most conditions, our ensemble framework surpassed the performance of its individual components, demonstrating its enhanced ability to make precise diagnostic predictions. Our experiments highlight the importance of IR in leveraging unstructured knowledge resources to identify infrequently encountered diagnoses. In addition, our ensemble framework benefits from combining the complementary strengths of the supervised and retrieval-based models to diagnose a broad spectrum of diseases.

A feature-aware multimodal framework with auto-fusion for Alzheimer’s disease diagnosis

Alzheimer’s disease (AD), one of the most common dementias, has about 4.6 million new cases yearly worldwide. Due to the significant amount of suspected AD patients, early screening for the disease has become particularly important. There are diversified types of AD diagnosis data, such as cognitive tests, images, and risk factors, many prior investigations have primarily concentrated on integrating only high-dimensional features and simple fusion concatenation, resulting in less-than-optimal outcomes for AD diagnosis. Therefore, We propose an enhanced multimodal AD diagnostic framework comprising a feature-aware module and an automatic model fusion strategy (AMFS). To preserve the correlation and significance features within a low-dimensional space, the feature-aware module employs a low-dimensional SHapley Additive exPlanation (SHAP) boosting feature selection as the initial step, following this analysis, diverse tiers of low-dimensional features are extracted from patients’ biological data. Besides, in the high-dimensional stage, the feature-aware module integrates cross-modal attention mechanisms to capture subtle relationships among different cognitive domains, neuroimaging modalities, and risk factors. Subsequently, we integrate the aforementioned feature-aware module with graph convolutional networks (GCN) to address heterogeneous data in multimodal AD, while also possessing the capability to perceive relationships between different modalities. Lastly, our proposed AMFS autonomously learns optimal parameters for aligning two sub-models. The validation tests using two ADNI datasets show the high accuracies of 95.9% and 91.9% respectively, in AD diagnosis. The methods efficiently select features from multimodal AD data, optimizing model fusion for potential clinical assistance in diagnostics.

The shift to authenticity: a framework for analysis of political truth claims

Abstract It is often claimed that political disinformation is more abundant than ever, that populists are particularly prone to lying, and that we live in an era of post-truth or epistemic relativism. Contrary to these views, we interpret this historical trend as a shift from objective to authentic forms of political truth claims. We develop a diagnostic framework that captures different types of political truth claims and their distinct elements. This framework enables interrogation and understanding of the current state of epistemic contestation and change. The rise of both populist and deliberative approaches to democracy, which we use as key examples, are indicators of a gradual shift towards a greater importance of authenticity in the public sphere. We nuance this proposition by distinguishing between different forms of authenticity employed by populist and deliberative politics: communicative authenticity in deliberative politics and original and personal authenticity in populist politics.

Evaluating 15-minute walkable life circles for the senior: a case study of Jiande, China

ABSTRACT Walking is the primary travel mode for daily errands, leisure, and accessing local services, particularly for most seniors. Sufficient and diverse facilities within walking distance help improve seniors’ well-being. Countries today face the challenge of providing enough facilities for more seniors and adopt some possible solutions, such as China’s 15-minute community life circle. Focused on Jiande, a medium-sized city in southeast China, we propose an assessment framework with three dimensions: availability, diversity, and balance among medical, living, and leisure facilities. Using GIS network analysis, this study reveals disparities in facility provision at the household-level between earlier and newer developed urban areas, which are closely related to geographical factors and gated communities. This is common in Chinese cities, suggesting the cumulative effects of urban development sequences. To alleviate and prevent serious service inequity, we propose the following two strategies to achieve an equally walkable city: increasing landscape services to overcome geographical obstacles and implementing open-gated community strategies. Furthermore, the limitations of relying solely on big data to calculate walking routes were noted. This diagnostic framework for assessing city environments for seniors is straightforward yet comprehensive and potentially promotes cooperation between planning professionals, policymakers, and the public.

AI-Assisted Body Composition Assessment Using CT Imaging in Colorectal Cancer Patients: Predictive Capacity for Sarcopenia and Malnutrition Diagnosis.

(1) Background: The assessment of muscle mass is crucial in the nutritional evaluation of patients with colorectal cancer (CRC), as decreased muscle mass is linked to increased complications and poorer prognosis. This study aims to evaluate the utility of AI-assisted L3 CT for assessing body composition and determining low muscle mass using both the Global Leadership Initiative on Malnutrition (GLIM) criteria for malnutrition and the European Working Group on Sarcopenia in Older People (EWGSOP2) criteria for sarcopenia in CRC patients prior to surgery. Additionally, we aim to establish cutoff points for muscle mass in men and women and propose their application in these diagnostic frameworks. (2) Methods: This retrospective observational study included CRC patients assessed by the Endocrinology and Nutrition services of the Regional University Hospitals of Malaga, Virgen de la Victoria of Malaga, and Vall d'Hebrón of Barcelona from October 2018 to July 2023. A morphofunctional assessment, including anthropometry, bioimpedance analysis (BIA), and handgrip strength, was conducted to apply the GLIM criteria for malnutrition and the EWGSOP2 criteria for sarcopenia. Body composition evaluation was performed through AI-assisted analysis of CT images at the L3 level. ROC analysis was used to determine the predictive capacity of variables derived from the CT analysis regarding the diagnosis of low muscle mass and to describe cutoff points. (3) Results: A total of 586 patients were enrolled, with a mean age of 68.4 ± 10.2 years. Using the GLIM criteria, 245 patients (41.8%) were diagnosed with malnutrition. Applying the EWGSOP2 criteria, 56 patients (9.6%) were diagnosed with sarcopenia. ROC curve analysis for the skeletal muscle index (SMI) showed a strong discriminative capacity of muscle area to detect low fat-free mass index (FFMI) (AUC = 0.82, 95% CI 0.77-0.87, p < 0.001). The identified SMI cutoff for diagnosing low FFMI was 32.75 cm2/m2 (Sn 77%, Sp 64.3%; AUC = 0.79, 95% CI 0.70-0.87, p < 0.001) in women, and 39.9 cm2/m2 (Sn 77%, Sp 72.7%; AUC = 0.85, 95% CI 0.80-0.90, p < 0.001) in men. Additionally, skeletal muscle area (SMA) showed good discriminative capacity for detecting low appendicular skeletal muscle mass (ASMM) (AUC = 0.71, 95% CI 0.65-0.76, p < 0.001). The identified SMA cutoff points for diagnosing low ASMM were 83.2 cm2 (Sn 76.7%, Sp 55.3%; AUC = 0.77, 95% CI 0.69-0.84, p < 0.001) in women and 112.6 cm2 (Sn 82.3%, Sp 58.6%; AUC = 0.79, 95% CI 0.74-0.85, p < 0.001) in men. (4) Conclusions: AI-assisted body composition assessment using CT is a valuable tool in the morphofunctional evaluation of patients with colorectal cancer prior to surgery. CT provides quantitative data on muscle mass for the application of the GLIM criteria for malnutrition and the EWGSOP2 criteria for sarcopenia, with specific cutoff points established for diagnostic use.

Comprehensive transcriptomic analysis unveils macrophage-associated genes for establishing an abdominal aortic aneurysm diagnostic model and molecular therapeutic framework

BackgroundAbdominal aortic aneurysm (AAA) is a highly lethal cardiovascular disease. The aim of this research is to identify new biomarkers and therapeutic targets for the treatment of such deadly diseases.MethodsSingle-sample gene set enrichment analysis (ssGSEA) and CIBERSORT algorithms were used to identify distinct immune cell infiltration types between AAA and normal abdominal aortas. Single-cell RNA sequencing data were used to analyse the hallmark genes of AAA-associated macrophage cell subsets. Six macrophage-related hub genes were identified through weighted gene co-expression network analysis (WGCNA) and validated for expression in clinical samples and AAA mouse models. We screened potential therapeutic drugs for AAA through online Connectivity Map databases (CMap). A network-based approach was used to explore the relationships between the candidate genes and transcription factors (TFs), lncRNAs, and miRNAs. Additionally, we also identified hub genes that can effectively identify AAA and atherosclerosis (AS) through a variety of machine learning algorithms.ResultsWe obtained six macrophage hub genes (IL-1B, CXCL1, SOCS3, SLC2A3, G0S2, and CCL3) that can effectively diagnose abdominal aortic aneurysm. The ROC curves and decision curve analysis (DCA) were combined to further confirm the good diagnostic efficacy of the hub genes. Further analysis revealed that the expression of the six hub genes mentioned above was significantly increased in AAA patients and mice. We also constructed TF regulatory networks and competing endogenous RNA networks (ceRNA) to reveal potential mechanisms of disease occurrence. We also obtained two key genes (ZNF652 and UBR5) through a variety of machine learning algorithms, which can effectively distinguish abdominal aortic aneurysm and atherosclerosis.ConclusionOur findings depict the molecular pharmaceutical network in AAA, providing new ideas for effective diagnosis and treatment of diseases.

Diagnostic and prognostic for prescriptive maintenance and control of PEMFC systems in an industrial framework

This paper designed and defined the framework of prescriptive maintenance and its four axes, for hydrogen-energy systems, considering the constraints of actual systems, to improve durability, availability, reliability, performance, safety and operating costs of these systems. Different data-driven approaches for diagnostic and different approaches for prognostic of Remaining Useful Life (RUL) for Proton Exchange Membrane Fuel Cell (PEMFC) systems are discussed. The use of measures always available on actual systems allows to validate the approach in an industrial framework. Several diagnostic algorithms (classification and clustering) are compared to find the best compromise between computation time and accuracy in an online diagnostic framework. For the prognostic part, the data set comes from experimental tests performed under steady load for a PEMFC stack. A degradation trend of PEMFC stack voltage is extracted from these data and two well-known prediction algorithms namely Bidirectional Echo State Network (BiESN) and Bidirectional Long-Short Term Memory network (BiLSTM) are tested and compared to evaluate the robustness of the PEMFC voltage prediction for RUL estimation. The diagnostic and prognostic approaches proposed in this paper are first steps towards future work related to prescriptive maintenance for hydrogen-energy systems (PEMFC, Proton Exchange Membrane Water Electrolyzer and hybridization of the two).

Salmonellosis in Ukraine: An analysis of food products contamination, Salmonella transmission, and serovar diversity during 2012–2023

A laboratory-based surveillance was conducted to study the transmission of Salmonella infection in Ukraine during the period 2012-2023. The study focused on the different categories of food products, feed, and animals as the main transmission factors and tried to analyze the relationship between them. The serological profile of Salmonella was predominantly observed in samples from objects of veterinary control, including biological/pathological material from animals and biomaterials from poultry within the National Poultry Salmonellosis Control Program. The study found that the most frequently isolated serovars were S. Enteritidis (20.03%), followed by S. Typhimurium (14.76%), S. Pullorum (without biovar identification;10.71%), S. Pullorum biovar Pullorum (10.50%), S. Pullorum var. Gallinarum (6.62%), S. Choleraesuis (5.79%), S. Livingstone (2.53%), and S. Infantis (1.70%). In 2021, an isolate of monophasic S. Typhimurium was identified for the first time in pathological material from pigs. The study also found that the most frequent Salmonella-positive categories of food products in Ukraine were meat and meat products (78.16%), eggs and egg products (11.75%); dairy products (3.319%), fish products (2.71%), ready-to-eat food products (1.96%). The largest specific share of Salmonella isolates from food products and feed was S. Enteritidis, followed by serotypes such as S. Infantis, S. Typhimurium, S. Livingstone, S. Virchow, and rare serotypes such as S. Nigeria and S. Thompson. The dominance of certain serovars such as S. Enteritidis, S. Typhimurium, S. Infantis, S. Livingstone, and S. Virchow in biomaterials from sick animals indicates their primary role in the infection of food products of animal origin. Hence, a stress to enhance diagnostic and monitoring frameworks at animal herd levels. The findings of this study can be used as a basis for evidence-based epidemiology, as well as for the implementation of joint steps to improve the effectiveness of control measures against salmonellosis in each region.

Evaluation of Calcarenite Degradation by X-ray Photoelectron Spectroscopy Analysis inside the Rupestrian Church of San Pietro Barisano (Matera, Southern Italy)

We report on the XPS analysis of degraded surfaces inside San Pietro Barisano, the rupestrian church carved into the calcarenite rock of ancient Matera, which has been a UNESCO World Heritage Site since 1993. As reported in previous works, the “Sassi” district and the park of rupestrian churches were available as open laboratories for the National Smart Cities SCN_00520 research project dedicated to the sustainable recovery of this remarkable architectural heritage. In that context, XPS functionality was shown to reside in the possibility of analyzing surfaces by feasible sampling, acquiring spectra without any preliminary sample treatment, and processing data using a well-established curve fitting procedure. The obtained results allowed us to identify the degradation products of the investigated surfaces, thus contributing to defining a diagnostic framework for subsequent actions. Accordingly, the samples here considered, collected from the internal wall surfaces of the church, were all analyzed in comparison with the reference calcarenite, and the XPS results were evaluated as a function of local environmental factors and the historical context of the church itself. The final aim was to provide, for each sample, the most representative indicator(s) of biotic and/or abiotic degradation for reliable use, in a multidisciplinary context, in planning care interventions for building heritage.

Task-based EEG and fMRI paradigms in a multimodal clinical diagnostic framework for disorders of consciousness.

Disorders of consciousness (DoC) are generally diagnosed by clinical assessment, which is a predominantly motor-driven process and accounts for up to 40 % of non-communication being misdiagnosed as unresponsive wakefulness syndrome (UWS) (previously known as prolonged/persistent vegetative state). Given the consequences of misdiagnosis, a more reliable and objective multimodal protocol to diagnosing DoC is needed, but has not been produced due to concerns regarding their interpretation and reliability. Of the techniques commonly used to detect consciousness in DoC, task-based paradigms (active paradigms) produce the most unequivocal result when findings are positive. It is well-established that command following (CF) reliably reflects preserved consciousness. Task-based electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) can detect motor-independent CF and reveal preserved covert consciousness in up to 14 % of UWS patients. Accordingly, to improve the diagnostic accuracy of DoC, we propose a practical multimodal clinical decision framework centered on task-based EEG and fMRI, and complemented by measures like transcranial magnetic stimulation (TMS-EEG).

Salience Network Segregation Mediates the Effect of Tau Pathology on Mild Behavioral Impairment.

A recently developed mild behavioral impairment (MBI) diagnostic framework standardizes the early characterization of neuropsychiatric symptoms in older adults. However, the links between MBI, brain function, and Alzheimer's disease (AD) biomarkers are unclear. Using data from 128 participants with diagnosis of amnestic mild cognitive impairment and mild dementia - Alzheimer's type, we test a novel model assessing direct relationships between AD biomarker status and MBI symptoms, as well as mediated effects through segregation of the salience and default-mode networks. We identified a mediated effect of tau positivity on MBI through functional segregation of the salience network from the other high-level, association networks. There were no direct effects of AD biomarkers status on MBI. Our findings suggest an indirect role of tau pathology in MBI through brain network dysfunction and emphasize the role of the salience network in mediating relationships between neuropathological changes and behavioral manifestations.

The Evolving Role of Genomic Testing in Early Breast Cancer: Implications for Diagnosis, Prognosis, and Therapy.

Multigene prognostic genomic assays have become indispensable in managing early breast cancer (EBC), offering crucial information for risk stratification and guiding adjuvant treatment strategies in conjunction with traditional clinicopathological parameters. The American Society of Clinical Oncology (ASCO) guidelines endorse these assays, though some clinical contexts still lack definitive recommendations. The dynamic landscape of EBC management demands further refinement and optimization of genomic assays to streamline their incorporation into clinical practice. The breast cancer community is poised at the brink of transformative advances in enhancing the clinical utility of genomic assays, aiming to significantly improve the precision and effectiveness of both diagnosis and treatment for women with EBC. This article methodically examines the testing methodologies, clinical validity and utility, costs, diagnostic frameworks, and methodologies of the established genomic tests, including the Oncotype Dx Breast Recurrence Score®, MammaPrint, Prosigna®, EndoPredict®, and Breast Cancer Index (BCI). Among these tests, Prosigna and EndoPredict® have at present been validated only on a prognostic level, while Oncotype Dx, MammaPrint, and BCI hold both a prognostic and predictive role. Oncologists and pathologists engaged in the management of EBC will find in this review a thorough comparison of available genomic assays, as well as strategies to optimize the utilization of the information derived from them.

Trauma and resistance in Niger's emergency transit mechanism: A life narrative study

This qualitative exploratory research delves into the intricate life narratives of forcibly displaced individuals residing within the Emergency Transit Mechanism in Niger, employing a methodology grounded in life narrative analysis. The primary objective is to gain a comprehensive understanding of the potential stressors and traumatic experiences encountered by these individuals, encompassing both psychological and physiological dimensions, while also examining the dynamics of resilience and elements contributing to their overall well-being. The findings, derived through thematic content analysis, underscore the cumulative nature of traumatic events experienced by migrants throughout their lifetimes and across various stages of the migration continuum. The study, in alignment with extant scholarly literature, identifies thematic categories such as “A scenario of conflict and mourning, " everyday experience of violence and discrimination,” “health at risk”, and " Seeking security.” Refugees recount enduring multiple traumas, including familial bereavements and losses resulting from conflicts and militarized violence. Furthermore, the analysis elucidates a profound interplay between traumatic occurrences, subjective well-being, and resilience among the studied population. Despite confronting adverse living circumstances, refugees demonstrate indicators of subjective well-being, hinting at the potential for resilience and recovery. This challenges conventional diagnostic frameworks such as Post-Traumatic Stress Disorder (PTSD) and underscores the necessity for a nuanced understanding of trauma's multifaceted impacts. Nevertheless, the study underscores the urgent need for a more robust and contextually attuned mental health support infrastructure, advocating for a deeper exploration of the socio-political determinants underpinning forced migration. By comprehending the root causes of displacement through a socio-political lens, policymakers and practitioners can devise comprehensive strategies and interventions aimed at both prevention and mitigation of factors precipitating forced migration. This approach seeks to foster a global landscape wherein compassionate and well-informed interventions proactively address the underlying drivers of displacement.

Intelligent crop management system for improving yield in maize production: evidence from India

PurposeManaging weeds and pests in cropland is one of the major concerns in agriculture that greatly affects the quantity and quality of the produce. While the success of preventing potential weeds and pests is not guaranteed, early detection and diagnosis help manage them effectively to ensure crops’ growth and healthDesign/methodology/approachWe propose a diagnostic framework for crop management with automatic weed and pest detection and identification in maize crops using residual neural networks. We train two models, one for weed detection with a labeled image dataset of maize and commonly occurring weed plants, and another for leaf disease detection using a labeled image dataset of healthy and infected maize leaves. The global and local explanations of image classification are obtained and presentedFindingsWeed and disease detection and identification can be accurately performed using deep-learning neural networks. Weed detection is accurate up to 97%, and disease detection up to 95% is made on average and the results are presented. Further, using this crop management system, we can detect the presence of weeds and pests in the maize crop early, and the annual yield of the maize crop can potentially increase by 90% theoretically with suitable control actionsPractical implicationsThe proposed diagnostic models can be further used on farms to monitor the health of maize crops. Images obtained from drones and robots can be fed to these models, which can then automatically detect and identify weed and disease attacks on maize farms. This offers early diagnosis, which enables necessary treatment and control of crops at the early stages without affecting the yield of the maize cropSocial implicationsThe proposed crop management framework allows treatment and control of weeds and pests only in the affected regions of the farms and hence minimizes the use of harmful pesticides and herbicides and their related health effects on consumers and farmers.Originality/valueThis study presents an integrated weed and disease diagnostic framework, which is scarcely reported in the literature

Clinical Presentation, Diagnosis, and Management of Hyperinsulinemic Hypoglycemia in Adults: A Single-center Experience.

Hyperinsulinemic Hypoglycemia (HH) is a rare condition characterized by inappropriately elevated insulin levels in the presence of low glucose levels. A proper diagnostic framework is fundamental to avoid patients undergoing unnecessary diagnostic and therapeutic invasive procedures. The study aimed to assess the clinical presentation, diagnostic work-up, and treatment of a single-center cohort of patients affected by HH. We conducted a retrospective analysis of data collected from January 2000-2023. Our study included 104 patients: 81 (58% F) affected by insulinoma, 11 (91% F) by autoimmune hypoglycemia, 7 (71% M) by post-gastric surgery hypoglycemia, and 5 (80% F) by factitious hypoglycemia. HH was more frequent in females (63 F vs. 41 M, p-value 0.039). The median age at diagnosis was lower in insulinoma than in the autoimmune group (52.7 vs. 63.7 y, p < 0.001). During the hypoglycemic event, insulin and C-peptide levels were significantly higher in autoimmune hypoglycemia than in insulinoma (insulin 324.6 vs. 36.4 μU/ml, p-value 0.033; C-peptide 14.25 vs. 3.99 ng/ml, p-value 0.003). Specifically, C-peptide levels <9.6 ng/ml and insulin levels <75 μU/ml exhibited 97.3% vs. 93.4% sensitivity and 80% vs. 90% specificity for insulinoma diagnosis, respectively. Regarding insulinoma, the sensitivity of localizing imaging was 88% for Endoscopic Ultrasound (EUS), 86% for Magnetic Resonance Imaging (MRI), 82% for Computed Tomography (CT) scan, 52% for nuclear imaging, and 100% for angiography with the Doppman test. Among insulinoma patients, 79% received surgical treatment while 4% radiofrequency ablation. Symptomatic remission occurred in 100% of cases. We have confirmed insulinoma as the primary cause of HH. The autoimmune form should be suspected when insulin and C-peptide levels are markedly elevated.

Current and flux correlation analysis for detection, location, and phase identification of stator inter-turn short-circuit fault in doubly-fed induction generator

This study proposes an innovative method for identifying and locating inter-turn short-circuit faults in doubly-fed induction generators (DFIGs), commonly used in wind-energy production. Our approach uniquely integrates data from both current and magnetic-flux monitoring, offering a complete framework for fault diagnostics. We effectively distinguish between normal and abnormal conditions in the generators by observing the patterns in current and flux waveforms. Normal conditions are marked by uniform waveforms, whereas faults create noticeable imbalances. A key feature of our research is the development of a technique to accurately determine which phase of the generator is affected by the fault, facilitating quicker and more effective repairs. To pinpoint the exact location of the fault, we use a set of four magnetic-flux sensors strategically placed around the generator. These sensors detect variations in magnetic flux, enabling the precise location of the fault. By focusing on these three essential elements—fault detection, phase identification, and exact fault localisation—our proposed algorithm significantly improves the dependability of DFIGs in wind-power applications.