Method For Early Detection Research Articles

Noninvasive, Presymptomatic Detection of Potato Cyst Nematode Infection in Tomato Using Chlorophyll Fluorescence Analysis.

Potato cyst nematodes (PCNs) are notorious pathogens in all major potato production areas worldwide. Mainly due to the low mobility of this soil pathogen, PCN infestations are mostly observed as patches ("foci") that only cover a fraction of the acreage. In-field presymptomatic localization of these pathogens is valuable, as it would allow for the localized application of control measures. Although the mapping of foci is technically feasible, it is unpractical, as it would require the analysis of numerous soil samples. We investigated whether chlorophyll fluorescence (Chl-F) could be suitable as a rapid, nondestructive method for early PCN detection. To this end, the impact of four Globodera pallida densities on the Chl-F of tomato was investigated in a phenotyping greenhouse for 26 days. Furthermore, the classical plant performance indicators of biomass and root surface area were compared with Chl-F. Thermal dissipation (NPQ) and an estimate of the photosynthetic rate (ΦPSII) responded at 1 day postinoculation, and ΦPSII was most sensitive to low PCN infection levels. Chl-F parameters responded more readily to PCN infection than biomass and root surface area. The maximum quantum yield of photosystem II (Fv/Fm) and the potential activity of photosystem II (Fv/F0) initially increased at low PCN infection levels, whereas a sharp decrease was observed at higher infestation levels. Hence, our data suggest that low PCN levels promoted plant performance before becoming detrimental at higher levels. Although Chl-F allowed for early and sensitive PCN detection, it remains to be investigated whether these signals can be distinguished from those produced by other belowground stressors in the field.

SVMVGGNet-16: A Novel Machine and Deep Learning Based Approaches for Lung Cancer Detection Using Combined SVM and VGGNet-16.

Lung cancer remains a leading cause of cancer-related mortality worldwide, necessitating early and accurate detection methods. Our study aims to enhance lung cancer detection by integrating VGGNet-16 form of Convolutional Neural Networks (CNNs) and Support Vector Machines (SVM) into a hybrid model (SVMVGGNet-16), leveraging the strengths of both models for high accuracy and reliability in classifying lung cancer types in different 4 classes such as adenocarcinoma (ADC), large cell carcinoma (LCC), Normal, and squamous cell carcinoma (SCC). Using the LIDC-IDRI dataset, we pre-processed images with a median filter and histogram equalization, segmented lung tumors through thresholding and edge detection, and extracted geometric features such as area, perimeter, eccentricity, compactness, and circularity. VGGNet-16 and SVM employed for feature extraction and classification, respectively. Performance matrices were evaluated using accuracy, AUC, recall, precision, and F1-score. Both VGGNet-16 and SVM underwent comparative analysis during the training, validation, and testing phases. The SVMVGGNet-16 model outperformed both, with a training accuracy (97.22%), AUC (99.42%), recall (94.22%), precision (95.28%), and F1- score (94.68%). In testing, our SVMVGGNet-16 model maintained high accuracy (96.72%), with an AUC (96.87%), recall (84.67%), precision (87.40%), and F1-score (85.73%). Our experimental results demonstrate the potential of SVMVGGNet-16 in improving diagnostic performance, leading to earlier detection and better treatment outcomes. Future work includes refining the model, expanding datasets, conducting clinical trials, and integrating the system into clinical practice to ensure practical usability.

Wastewater monitoring - passive sampling for the detection of SARS-CoV-2 and antibiotic resistance genes in wastewater.

As a lesson learned from the COVID-19 pandemic, wastewater-based epidemiology was recognised and used as an important method for surveillance and early detection of SARS-CoV-2. As a result, consideration of wastewater as a source of public health information has gained new prominence, and there is consensus that similar approaches can be used to detect the spread of other viral pathogens or antimicrobial resistance (AMR) in populations. However, the implementation of wastewater monitoring poses challenges in terms of obtaining representative and meaningful samples. In particular, it is difficult to sample small catchments, critical facilities (e.g. hospitals) or low-income countries where the use of automatic water samplers is not possible or the samplers are not available. To overcome these problems, this study developed a low-cost and easy-to-use passive sampler based on activated carbon as an adsorbent with a corresponding elution/extraction protocol that allows the detection of viruses and antibiotic resistance genes in wastewater. Monitoring of SARS-CoV-2 with these passive samplers at the influent of a wastewater treatment plant over a period of 1.5months showed a positive correlation with monitoring with 24-h composite samples in the catchment area. Analysis of the nucleic acid extracts for antibiotic resistance genes showed the presence of clinically relevant carbapenemase genes such as blaKPC-3 and blaNDM-1 in the wastewater samples, with these genes being detected more reliably by the passive samplers than in the 24-h composite samples. This study therefore demonstrated that passive samplers provide reproducible SARS-CoV-2 RNA and antibiotic resistance gene signals from wastewater and a time-integrated measurement of the sampled matrix with high sensitivity.

Alterations of the Gut Microbiome and Metabolome Following: A Opportunity for Early Detection of Colorectal Cancer

Abstract: Colorectal cancer (CRC) is a commonly diagnosed cancer responsible for numerous deaths worldwide. In recent decades, technological advances implicated in considering the molecular pathways underlying CRC pathogenesis. Several investigations have identified various mechanisms involved in CRC and have paved the way for new therapeutics and early diagnosis. Gut microbiome play a crucial role in intestinal inflammation and can be associated with colitis colorectal cancer. In this review, we narrated the role of the microbiome population and their metabolome profile as a new screening method for early detection of CRC.

Artificial intelligence in gastrointestinal cancers: diagnostic, prognostic, and surgical strategies.

GI (Gastrointestinal) malignancies are one of the most common and lethal cancers globally. The dawn of precision medicine and developing technologies have reduced the mortality rates for GI malignancies, underscoring the main role of early detection methods for survival rate improvement. Artificial intelligence (AI) is a new technology that may improve GI cancer screening, treatment, and therapeutic efficiency for better patient care. AI could accelerate the development of targeted therapies by analyzing considerable data from the genome and identifying biomarkers connected with GI tumors. This opens up new avenues toward more tailored and personalized approaches, raising efficacy while reducing undesired side effects. For instance, AI may improve treatment outcomes by accurately predicting patient responses to therapeutic regimens, helping oncologists choose the most effective treatment options. This review will outline the transformative potential of AI in GI oncology by emphasizing the incorporation of AI-based technologies to enhance patient care.

Deteksi Anemia dan Edukasi Gizi Remaja

Stunting is a chronic malnutrition issue resulting from prolonged inadequate nutrient intake, and adolescents, as future parents, play a crucial role in its prevention. Data from the Riset Kesehatan Dasar (Riskesdas) surveys in 2007, 2013, and 2018 show a rising trend in anemia prevalence among adolescents. In 2018, 32% of adolescents in Indonesia were anemic, and in 2017, the prevalence in West Sumatra was 18.1%. Hemoglobin (Hb) testing is a vital method for early anemia detection. Additionally, providing nutritional education to teenage girls is essential for addressing anemia. This community service project aimed to detect anemia and offer nutritional education to teenage girls as a stunting prevention strategy. Conducted at SMA Negeri 12 Padang, the project involved Hb testing and nutritional education. Results revealed that 12% of 12th-grade female students were anemic. Nutritional education improved their knowledge, with average scores increasing from 19.97 before the intervention to 26.92 afterward. In conclusion, Hb testing and nutritional education are effective for early anemia detection and enhancing nutritional knowledge, crucial for preventing stunting.

Immune Cell Profiling Reveals a Common Pattern in Premetastatic Niche Formation Across Various Cancer Types

ABSTRACTBackgroundMetastasis is the major cause of cancer‐related mortality. The premetastatic niche is a promising target for its prevention. However, the generality and cellular dynamics in premetastatic niche formation have remained unclear.AimsThis study aimed to elucidate the generality and cellular dynamics in premetastatic niche formation.Materials and MethodsWe performed comprehensive flow cytometric analysis of lung and peripheral immune cells at three time points (early premetastatic, late premetastatic, and micrometastatic phases) for mice with subcutaneous implants of three types of cancer cells (breast cancer, lung cancer, or melanoma cells). The immuno‐cell profiles were then used to predict the metastatic phase by machine learning.ResultsWe found a common pattern of changes in both lung and peripheral immune cell profiles across the three cancer types, including a decrease in the proportion of eosinophils in the early premetastatic phase, an increase in that of regulatory T cells in the late premetastatic phase, and an increase in that of polymorphonuclear myeloid‐derived suppressor cells and a decrease in that of B cells in the micrometastatic phase. Machine learning using immune cell profiles could predict the metastatic phase with approximately 75% accuracy.DiscussionValidation of our findings in humans will require data on the presence or absence of micrometastases in patients and the accumulation of comprehensive and temporal information on immune cells. In addition, blood proteins, extracellular vesicles, DNA, RNA, or metabolites may be useful for more accurate prediction.ConclusionThe discovery of generalities in premetastatic niche formation allow prediction of metastatic phase and provide a basis for the development of methods for early detection and prevention of cancer metastasis in a cancer type‐independent manner.

Current status and perspectives of esophageal cancer: a comprehensive review.

Esophageal cancer (EC) continues to be a significant global health concern, with two main subtypes: esophageal squamous cell carcinoma and esophageal adenocarcinoma. Prevention and changes in etiology, improvements in early detection, and refinements in the treatment have led to remarkable progress in the outcomes of EC patients in the past two decades. This seminar provides an in-depth analysis of advances in the epidemiology, disease biology, screening, diagnosis, and treatment landscape of esophageal cancer, focusing on the ongoing debate surrounding multimodality therapy. Despite significant advancements, EC remains a deadly disease, underscoring the need for continued research into early detection methods, understanding the molecular mechanisms, and developing effective treatments.

Ezrin Polarization as a Diagnostic Marker for Circulating Tumor Cells in Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the sixth most common cancer and the third leading cause of cancer-related death worldwide, with no precise method for early detection. Circulating tumor cells (CTCs) expressing the dynamic polarity of the cytoskeletal membrane protein, ezrin, have been proposed to play a crucial role in tumor progression and metastasis. This study investigated the diagnostic and prognostic potential of polarized circulating tumor cells (p-CTCs) in HCC patients. CTCs were isolated from the peripheral blood of 20 HCC patients and 18 patients with nonmalignant liver disease (NMLD) via an OncoQuick® kit and immunostained with Ezrin-Alexa Fluor 488®, CD146-PE, and CD45-APC. A fluorescence microscopy was then performed for analysis. The HCC group exhibited significantly higher levels of p-CTCs, with median values of 0.56 p-CTCs/mL, compared to 0.02 p-CTCs/mL (p = 0.03) in the NMLD group. CTCs were detected in 95% of the HCC patients, with a sensitivity of 95% and specificity of 89%. p-CTCs were present in 75% of the HCC patients, with a sensitivity of 75% and a specificity of 94%. Higher p-CTC counts were associated with the significantly longer overall survival in HCC patients (p = 0.05). These findings suggest that p-CTCs could serve as valuable diagnostic and prognostic markers for HCC. The incorporation of p-CTCs into diagnostic strategies could enhance therapeutic decision-making and improve patient outcomes.

The inter-reader agreement in the interpretation of mammography images according to BI-RADS by Moscow radiologists

Background: Breast malignancies take a leading position among incident cancers in women. Mammography has been recognized as the main method for early detection of breast cancer. However, mammogram assessments are based on a subjective opinion of the radiologist, which could lead to diagnostic disagreement. According to the literature, inter-radiologist agreement on mammograms varies from 0.450 to 0.888. Aim: To assess the inter-reader agreement in mammogram interpretation with BI-RADS (Breast Imaging Reporting and Data System) by radiologists of the Moscow city (Russia). Methods: The study included 741 mammography images done from January 15, 2020, to June 25, 2023. All mammograms were downloaded from the Unified Radiology Information Service of the Unified Medical Information and Analytical System (EMIAS) of the Moscow city and included radiologist reports with a BI-RADS score (the initial assessment). Each mammogram was further analyzed by two radiologists (with their job experience from 2 to 5 years) (this was the first revision) and thereafter by two more radiologists (with their job experience above 5 years and scientific degree) as a part of the expert review. The inter-reader agreement was assessed using an intra-class correlation coefficient. Results: The inter-reader agreement for the full BI-RADS score between radiologists who performed the initial assessment and those performing the first revision ranged from 0.836 [95% confidence interval (CI) 0.801–0.865] to 0.875 [95% CI 0.848–0.897]. Similar agreement was observed between radiologists who performed the initial assessment and the experts: 0.838 [95% CI 0.804–0.866] to 0.879 [95% CI 0.854–0.901]. The agreement on the full BI-RADS scale between radiologists who performed the first revision and the experts was significantly higher (p 0.001) than with those performing the initial assessment and ranged from 0.890 [95% CI 0.866–0.910] to 0.963 [95% CI 0.954–0.970]. Conclusion: The inter-reader agreement between radiologists of the Moscow city in the assessment of mammography study results on the full BI-RADS scale is high. The agreement between the radiologists who performed the revision is higher than their agreement with the radiologists who performed the initial assessment, which may indicate better and more stable results obtained during the revision.

Nanotheranostics for gynecological cancers: a path forward for Africa.

Nanoparticle-based therapies represent a transformative approach to managing gynecological cancers, offering targeted treatment strategies that minimize harm to healthy tissues while maximizing therapeutic efficacy. Despite their potential, implementing these advanced treatments in Africa is needed by a complex interplay of technological, economic, regulatory, and ethical challenges. This paper examines the current landscape of nanoparticle-based therapies, identifying critical barriers to their adoption, including inadequate infrastructure, high costs, and insufficient regulatory frameworks. Technological deficiencies manifest as a need for advanced nanoparticle synthesis, delivery, and diagnostics equipment, impeding research and clinical applications. Economically, the high production costs of nanoparticles, compounded by limited access to advanced diagnostic and treatment facilities, create significant financial barriers for healthcare systems and patients alike. Additionally, the regulatory environment needs to be more cohesive, characterized by a lack of established protocols and expertise to evaluate the unique properties of nanomedicines. However, opportunities for advancement exist through focused research and development initiatives. Targeted drug delivery systems, early detection methods, and immunotherapy integration are promising avenues to enhance treatment outcomes. Collaborative partnerships between African institutions and international research entities, alongside public-private collaborations, could bolster local capabilities in nanomedicine. To facilitate the integration of nanoparticle-based therapies, African governments must prioritize funding for nanomedicine research, create robust regulatory frameworks, and ensure equitable access to these innovative treatments. A concerted effort involving policy reforms, investment, and collaboration is essential for overcoming existing barriers and realizing the full potential of nanoparticle-based therapies in improving health outcomes for gynecological cancer patients across Africa.

Aging and head and neck cancer insights from single cell and spatial transcriptomic analyses

BackgroundHead and neck squamous cell carcinoma(HNSCC) is the sixth most common malignancy worldwide, with more than 890,000 new cases and 450,000 deaths annually. Its major risk factors include smoking, alcohol abuse, aging, and poor oral hygiene. Due to the lack of early and effective detection and screening methods, many patients are diagnosed at advanced stages with a five-year survival rate of less than 50%. In this study, we deeply explored the expression of Aging-related genes(ARGs) in HNSCC and analyzed their prognostic significance using single-cell sequencing and spatial transcriptomics analysis. This research aims to provide new theoretical support and directions for personalized treatment.Annually, more than 890,000 new cases of head and neck squamous cell carcinoma (HNSCC) are diagnosed globally, leading to 450,000 deaths, making it the sixth most common malignancy worldwide. The primary risk factors for HNSCC include smoking, alcohol abuse, aging, and poor oral hygiene. Many patients are diagnosed at advanced stages due to the absence of early and effective detection and screening methods, resulting in a five-year survival rate of less than 50%. In this research, single cell sequencing and spatial transcriptome analysis were used to investigate the expression of Aging-related genes (ARGs) in HNSCC and to analyse their prognostic significance. This research aims to provide new theoretical support and directions for personalized treatment.MethodsIn this study, we investigated the association between HNSCC and AGRs by utilizing the GSE139324 series in the GEO database alongside the TCGA database, combined with single-cell sequencing and spatial transcriptomics analysis. The data were analyzed using Seurat and tSNE tools to reveal intercellular communication networks. For the spatial transcriptome data, SCTransform and RunPCA were applied to examine the metabolic activities of the cells. Gene expression differences were determined through spacerxr and RCTD tools, while the limma package was employed to identify differentially expressed genes and to predict recurrence rates using Cox regression analysis and column line plots. These findings underscore the potential importance of molecular classification, prognostic assessment, and personalized treatment of HNSCC.ResultsThis study utilized HNSCC single-cell sequencing data to highlight the significance of ARGs in the onset and prognosis of HNSCC. It revealed that the proportion of monocytes and macrophages increased, while the proportion of B cells decreased. Notably, high expression of the APOE gene in monocytes was closely associated with patient prognosis. Additionally, a Cox regression model was developed based on GSTP1 and age to provide personalized prediction tools for clinical use in predicting patient survival.ConclusionsWe utilized single-cell sequencing and spatial transcriptomics to explore the cellular characteristics of HNSCC and its interaction with the tumor microenvironment. Our findings reveal that HNSCC tissues show increased mononuclear cells and demonstrate enhanced activity in ARGs, thereby advancing our understanding of HNSCC development mechanisms.

Nursing Students' Knowledge, Attitudes and Beliefs About Testicular Cancer and Testicular Self‐Examination

ABSTRACTWhat are the levels of knowledge, attitudes and beliefs of nursing students regarding testicular cancer and testicular self‐examination (TSE)? Is there a significant difference between male and female nursing students in terms of their knowledge, attitudes and beliefs about testicular cancer and TSE? Testicular cancer is the most common cancer affecting young men, yet awareness and knowledge about the disease and early detection methods, such as TSE, remain insufficient among men. Nurses play a critical role in raising awareness and addressing gaps in knowledge about testicular cancer and TSE. This study aims to assess nursing students' knowledge, attitudes and health beliefs concerning testicular cancer and TSE, as well as the factors influencing these outcomes. Nursing students are the future of the nursing profession, and it is essential to address any gaps in their knowledge during their training to ensure they are well‐prepared for their roles in patient education and care. This study employed a descriptive, correlational and multicentred design. The sample consisted of 524 nursing students. The inclusion criteria were being enrolled in the 2nd, 3rd or 4th year of a nursing program. Data were collected through an online survey using Google Forms. Statistical analysis was conducted using chi‐squared tests, independent t‐tests, correlation coefficients, and multiple linear regression to examine the relationships between the variables. The study revealed that both female and male nursing students had low average knowledge scores concerning testicular cancer and TSE. However, a significant gender difference was observed in previous awareness of testicular cancer, with females demonstrating higher levels of awareness compared to their male counterparts. Among the independent variables included in the model, perceived benefits and health motivation had a significant positive effect on male students' knowledge about testicular cancer (β = 0.039, p = 0.018), while perceived barriers had a significant negative effect (β = −0.064, p = 0.002). These variables were statistically significant predictors of male students' knowledge about testicular cancer. The study determined that nursing students' knowledge and attitudes regarding testicular cancer and TSE were low. Among the subscales of the Health Beliefs Scale, the highest mean score was observed for the ‘seriousness’ subscale, while the lowest was for the ‘health motivation’ subscale. Due to the structure of the scale, it was only applicable to male students, which prevented the assessment of female students' beliefs and influencing factors, representing a significant limitation of this research. To ensure nursing students graduate with sufficient knowledge about testicular cancer and TSE, it is recommended to integrate educational and awareness initiatives, such as projects, seminars and public service announcements, into undergraduate nursing curricula.

Review and Analysis of XAI Methods for Addressing Geoecological Zoning and Public Health Prevention Challenges

This study focuses on the application of Explainable Artificial Intelligence (XAI) in geoecological zoning tasks to support sustainable development and public health prevention. Amid increasing anthropogenic pressures on ecosystems and rising disease rates due to environmental degradation, emphasis is placed on early risk detection methods. The study highlights the importance of XAI in analyzing ecological data to mitigate the impacts of adverse factors on population health. Integrating XAI with Geographic Information Systems (GIS) not only provides high accuracy in geoecological forecasting but also enhances the transparency of these forecasts for experts, aiding informed decision-making in the fields of geoecology and healthcare. Special attention is given to early diagnosis of health risks, such as respiratory and oncological diseases, through the use of XAI in analyzing environmental data and medical images. Explainable AI enhances the transparency and understandability of diagnostic processes for medical professionals, fostering trust in analytical outcomes. Implementing XAI in healthcare can not only improve diagnostic accuracy but also optimize healthcare resources by reallocating them toward disease prevention. A review of existing decision support systems (DSS) demonstrates the efficacy of hybrid models combining neural networks and fuzzy logic to enhance the precision and interpretability of medical forecasts. These models open new prospects for personalized medicine, improving preventive strategies and providing individual recommendations based on comprehensive analyses of environmental and medical data. A critical aspect of the study is territorial zoning aimed at managing environmental risks and disease prevention. This approach not only reduces the burden on healthcare systems but also promotes sustainable territorial development, taking into account the influence of environmental and social factors on population health.

Clinical Evaluation of an Electronic Guidance System for Optimizing the Ultrasound Screening for Developmental Hip Dysplasia in Newborns.

Background: Graf ultrasound screening is considered an established method for early detection of developmental dysplasia of the hip (DDH). Although characterized by a high degree of standardization to allow for good reproducibility of results, examination-related factors may still affect sonographic measurements. The relative tilt angle between the hip and the probe is a potential pitfall as it significantly influences sonographic measurements and consequently classification of DDH according to Graf. Objectives: Evaluation of an electronic guidance system developed to reduce relative tilt angles and increase reliability and comparability in ultrasound screening of DDH. Materials and Methods: Twenty-five newborns were examined using a prototype guidance system, which tracks the position of the transducer and the pelvis to calculate the relative tilt angles. Two ultrasound images were obtained, one conventionally and the other one using the guidance system. Subsequently, relative roll and pitch angles and sonographic measurements were determined and analyzed. Results: The relative inclination angles in the conventional group ranged from -12.6° to 14.3° (frontal plane) and -23.8° to 32.5° (axial plane). vs. -3.7° to 3.0° and -3.2° to 4.5° in the guidance system group. The variances were significantly lower in the guidance system-assisted group for both planes (p < 0.001 and p < 0.001, respectively). The optimized transducer position showed significant effects and consequently significantly reduced alpha angles were observed (p = 0.001, and p = 0.003). Conclusions: The guidance system allowed a significant reduction in the relative tilt angles, supporting optimal positioning of the transducer, resulting in significant effects on Graf sonographic measurements. This technique shows great potential for enhancing the reproducibility and reliability of ultrasound screening for DDH.

Early Wildfire Smoke Detection Method Based on EDA

Early wildfire smoke detection faces challenges such as limited datasets, small target sizes, and interference from smoke-like objects. To address these issues, we propose a novel approach leveraging Efficient Channel and Dilated Convolution Spatial Attention (EDA). Specifically, we develop an experimental dataset, Smoke-Exp, consisting of 6016 images, including real-world and Cycle-GAN-generated synthetic wildfire smoke images. Additionally, we introduce M-YOLO, an enhanced YOLOv5-based model with a 4× downsampling detection head, and MEDA-YOLO, which incorporates the EDA mechanism to filter irrelevant information and suppress interference. Experimental results on Smoke-Exp demonstrate that M-YOLO achieves a mean Average Precision (mAP) of 96.74%, outperforming YOLOv5 and Faster R-CNN by 1.32% and 3.26%, respectively. MEDA-YOLO further improves performance, achieving an mAP of 97.58%, a 2.16% increase over YOLOv5. These results highlight the potential of the proposed models for precise and real-time early wildfire smoke detection.

Diagnostic value of SAT-TB in smear-negative pulmonary tuberculosis: A diagnostic accuracy study.

This study aimed to evaluate the diagnostic value of rapid simultaneous RNA amplification and testing for tuberculosis (SAT-TB) in smear-negative pulmonary tuberculosis (PTB). We performed a multicenter prospective analysis of 206 patients with smear-negative suspected PTB between December 2018 and March 2022. We collected sputum or bronchoalveolar lavage fluid (BALF) for simultaneous SAT-TB and Xpert Mycobacterium tuberculosis/rifampin (MTB/RIF) assays. The efficiency of SAT-TB detection was also evaluated. The final analysis included 161 patients with smear-negative suspected PTB, of whom 114 provided sputum specimens and 47 provided BALF specimens. In sputum samples, the area under the curve, sensitivity, and specificity of SAT-TB for diagnosing PTB were 0.75, 50.7%, and 100.0%, respectively, and those of the Xpert MTB/RIF assay were 0.81, 62.3%, and 100.0%, respectively. The kappa coefficient k of the consistency between SAT-TB and Xpert MTB/RIF in sputum specimens was 0.686. In BALF specimens, the area under the curve, sensitivity, and specificity of SAT-TB for diagnosing PTB were 0.79, 57.1%, and 100.0%, respectively, and those of Xpert MTB/RIF were 0.86, 76.2%, and 96.2%, respectively. The kappa coefficient k of the consistency between SAT-TB and Xpert MTB/RIF in BALF specimens was 0.656. The SAT-TB and Xpert MTB/RIF assays were highly consistent in diagnosing smear-negative PTB. It is a valuable method for early detection, prevention, and managing smear-negative PTB suspects. Meanwhile, the detection efficiency and cost-effectiveness of SAT-TB are more suitable for the rapid diagnosis of smear-negative PTB in low- and middle-income countries.

Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications.

Mild cognitive impairment and early-stage dementia significantly impact healthcare utilization and costs, yet more than half of affected patients remain underdiagnosed. This study leverages audio-recorded patient-nurse verbal communication in home healthcare settings to develop an artificial intelligence-based screening tool for early detection of cognitive decline. To develop a speech processing algorithm using routine patient-nurse verbal communication and evaluate its performance when combined with electronic health record (EHR) data in detecting early signs of cognitive decline. We analyzed 125 audio-recorded patient-nurse verbal communication for 47 patients from a major home healthcare agency in New York City. Out of 47 patients, 19 experienced symptoms associated with the onset of cognitive decline. A natural language processing algorithm was developed to extract domain-specific linguistic and interaction features from these recordings. The algorithm's performance was compared against EHR-based screening methods. Both standalone and combined data approaches were assessed using F1-score and area under the curve (AUC) metrics. The initial model using only patient-nurse verbal communication achieved an F1-score of 85 and an AUC of 86.47. The model based on EHR data achieved an F1-score of 75.56 and an AUC of 79. Combining patient-nurse verbal communication with EHR data yielded the highest performance, with an F1-score of 88.89 and an AUC of 90.23. Key linguistic indicators of cognitive decline included reduced linguistic diversity, grammatical challenges, repetition, and altered speech patterns. Incorporating audio data significantly enhanced the risk prediction models for hospitalization and emergency department visits. Routine verbal communication between patients and nurses contains critical linguistic and interactional indicators for identifying cognitive impairment. Integrating audio-recorded patient-nurse communication with EHR data provides a more comprehensive and accurate method for early detection of cognitive decline, potentially improving patient outcomes through timely interventions. This combined approach could revolutionize cognitive impairment screening in home healthcare settings.

Autoencoder and Mahalanobis distance-based monitoring indicator estimation for early clinkering detection in boiler

Abstract The performance of coal-fired boilers has a significant impact on the overall yield of thermal power plants. Among the various boiler faults, the clinkering fault diagnosis is one of the most crucial and scarcely addressed topics in literature. Existing clinkering detection methods are boiler-specific and require both healthy and faulty data for training, which is difficult to acquire. To overcome these drawbacks, a generalized method for early clinkering detection is proposed that only requires normal operation data for training. A stacked-denoising-autoencoder is trained such that the reconstruction error departs from the expected value when clinkering occurs. Mahalanobis distance of this error gives the monitoring indicator for clinkering detection, whose threshold is determined as 385.817 using kernel density estimation. The method is validated using real-time boiler data containing clinkering events, which shows that the obtained threshold clearly demarcates between healthy and clinkering conditions with 99.29% accuracy, providing early alert to operators.

HybridFusionNet: Deep Learning for Multi-Stage Diabetic Retinopathy Detection

Diabetic retinopathy (DR) is one of the most common causes of visual impairment worldwide and requires reliable automated detection methods. Numerous research efforts have developed various conventional methods for early detection of DR. Research in the field of DR remains insufficient, indicating the potential for advances in diagnosis. In this paper, a hybrid model (HybridFusionNet) that integrates vision transformer (VIT) and attention processes is presented. It improves classification in the binary (Bcl) and multi-class (Mcl) stages by utilizing deep features from the DR stages. As a result, both the SAN and VIT models improve the recognition accuracy (Acc) in both stages.The HybridFusionNet mechanism achieves a competitive improvement in multi-stage and binary stages, which is Acc in Bcl and Mcl, with 91% and 99%, respectively. This illustrates that this model is suitable for a better diagnosis of DR.