Clinical significance of peripheral blood UL16 and DR-70 for the early diagnosis and prognostic evaluation of colorectal cancer.

BACKGROUND: Early diagnosis of colorectal cancer (CRC) is of great significance to improve the survival rate and quality of life of patients, but early diagnosis of CRC requires more sensitive techniques. Peripheral blood UL16-binding protein 2 (ULBP2) and human fibrinogen degradation products (DR-70) are the main indicators for the diagnosis of malignant tumors. AIM: To assess ULBP2 and DR-70 potential for the early diagnosis and prognostic evaluation of CRC to provide a reference. METHODS: This study involved 60 patients with early-stage CRC (CRC group), 50 patients with benign colorectal tumors (benign group), and 50 healthy patients (control group) enrolled at the Affiliated Hospital of Jiangnan University and Jiangsu Province Official Hospital between January, 2020 and January, 2022. ULBP2 and DR-70 levels in the blood were determined and differences among the three groups and early diagnostic values for CRC were determined. Patients with CRC were divided into the good prognosis and poor prognosis groups, and ULBP2 and DR-70 levels in the blood and diagnostic values were compared. RESULTS: ULBP2 and DR-70 serum levels were significantly higher in the CRC group than in the control and benign groups (P < 0.05); however, no significant differences were observed between the benign and control groups (P > 0.05). Among the 60 patients with CRC followed up for two years, two died (3.33%) and 15 exhibited tumor metastasis, progression, or recurrence (25.00%). ULBP2 and DR-70 serum levels were significantly higher in the poor prognosis group than in the good prognosis group (P < 0.05). A receiver operating characteristic curve was plotted. Area under the curve, sensitivity, and specificity of serum ULBP2 with DR-70 for the early diagnosis of CRC were higher than those of the single serum indices (P < 0.05) in both the good and poor prognosis groups. CONCLUSION: ULBP2 and DR-70 serum levels were significantly high in patients with early-stage CRC. They improved the diagnostic rate of early-stage CRC and predicted patient prognosis, thereby showing clinical application potential.

Delayed diagnosis in inflammatory bowel disease: Time to consider solutions.

In this editorial, we discuss a recently published manuscript by Blüthner et al in the World Journal of Gastroenterology, with a specific focus on the delayed diagnosis of inflammatory bowel disease (IBD). IBD, which includes Crohn's disease and ulcerative colitis, is a chronic intestinal disorder. A time lag may exist between the onset of inflammation and the appearance of signs and symptoms, potentially leading to an incorrect or delayed diagnosis, a situation referred to as the delayed diagnosis of IBD. Early diagnosis is crucial for effective patient treatment and prognosis, yet delayed diagnosis remains common. The reasons for delayed diagnosis of IBD are numerous and not yet fully understood. One key factor is the nonspecific nature of IBD symptoms, which can easily be mistaken for other conditions. Additionally, the lack of specific diagnostic methods for IBD contributes to these delays. Delayed diagnosis of IBD can result in numerous adverse consequences, including increased intestinal damage, fibrosis, a higher risk of colorectal cancer, and a decrease in the quality of life of the patient. Therefore, it is essential to diagnose IBD promptly by raising physician awareness, enhancing patient education, and developing new diagnostic methods.

Early prediction of gestational diabetes mellitus using first trimester maternal serum pregnancy-associated plasma protein-a: A cross-sectional study.

Background and Aims: The oral glucose tolerance test with 75 g glucose is commonly regarded as the gold standard (GS) for the detection of gestational diabetes mellitus (GDM). However, one limitation of this test is its administration in the late second trimester of pregnancy in some countries (e.g., Iran). This study aimed to evaluate the accuracy of pregnancy-associated plasma protein-A (PAPP-A) for predicting GDM in the early first trimester of pregnancy using a novel statistical modeling technique. Methods: The study population consisted of 344 pregnant women who participated in the first trimester screening program for GDM. Maternal serum PAPP-A levels were measured between 11 and 13 gestational weeks for all participants. A Bayesian latent profile model (LPM) under the skew-t (ST) distribution was employed to estimate the diagnostic accuracy measures of PAPP-A in the absence of GS test outcomes. Results: The mean (standard deviation) age of the participants was 28.87 ± 5.20 years. The median (interquartile range (IQR)) PAPP-A MoM was 0.91 (0.69-1.34). Utilizing the LPM under the ST distribution while adjusting for covariates, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of PAPP-A were 92% (95% credible interval [CrI]: 0.89, 0.98), 81% (95% CrI: 0.76, 0.91), and 0.91 (95% CrI: 0.83, 0.97), respectively. Notably, the pregnant women with GDM had significantly lower PAPP-A values ( ß = -0.52, 95% CrI [-0.61, -0.46]). Conclusion: Generally, our findings confirmed that PAPP-A could serve as a potential screening tool for the identification of GDM in the early stages of pregnancy.

Time from Diagnostic Suspicion to In-Person Evaluation in Skin Cancer Using Teledermatology.

Introduction: Early diagnosis of skin cancer is crucial for improving prognosis. Teledermatology (TD) usage can optimize referrals and reduce waiting times. This study aims to evaluate waiting times at the critical referral nodes in teleinterconsultations that raised suspicion of skin malignancy in the Chilean TD platform of the public health care system. Materials and Methods: A cross-sectional observational study that analyzed asynchronous teleinterconsultations and raised suspicion for skin malignancy following the teledermatologist evaluation was uploaded on the Chilean Ministry of Health's TD platform from January 1 to June 30, 2022. Results: Out of 20,522 teleinterconsultations, 1,853 raised suspicion of skin cancer. Among them, 1,119 patients were assessed by in-person examination, while 669 were still on the waiting list. Response times averaged 3.98 days for TD diagnostic suggestions. Overall referral times averaged 75.98 days from initial teleinterconsultation to the final specialist in-person evaluation. Waiting times showed significant differences among health care services and geographic regions. Discussion: In resource-limited settings, TD serves as a valuable tool to optimize referrals and manage the demand for oncologic dermatological consultation. The long waiting times emphasize the need for targeted interventions, especially in regions with longer delays. Conclusion: While TD has shown to be an effective tool in optimizing referrals, waiting times still exceed international recommendations, even in urban centers. The considerable heterogeneity in referral times within health care services and geographic regions highlights the necessity of establishing standardized referral protocols and explicit deadlines to fulfill teleinterconsultations that raise suspicion of skin malignancy in the Chilean public system.

Unlocking delays: revealing barriers to early diagnosis of childhood central nervous system tumors in an upper-middle-income country.

PURPOSE: Childhood central nervous system (CNS) tumors tend to have a longer time interval until diagnosis than other pediatric malignancies. The aim is to describe the time to diagnosis among Brazilian pediatric patients treated at a tertiary center and explore associated factors. METHODS: Cross-sectional study; application of questionnaires to parents of children with CNS tumors during outpatient visit or inpatient care. RESULTS: One hundred parents participated between August and November 2023. The median age of the children at diagnosis was 7.2 years old. Low-grade glioma (LGG) was the most common tumor type (37%), followed by medulloblastoma (24%). The most frequent symptoms were morning and/or persistent vomiting and headache. The mean prediagnostic symptomatic interval (PSI) was 150 days. The mean parental interval was shorter than the medical (58.1 days vs 92.8 days). LGGs and tumors located in the central area had longer intervals to diagnosis than other tumors (296 vs 54 days) (p = 0.005) and (206 vs 155 days) (p = 0.007), respectively. Despite 81% of the patients undergoing pediatric routine follow-up, 87% of them had been diagnosed at an emergency department. Children attended by the same physician had a shorter mean interval (18.2 vs 88.3 days) than those assisted by different professionals (p = 0.015). The mean time for referral to our specialized center was 23 days. CONCLUSIONS: This study is a crucial step in recognizing barriers to early diagnosis of CNS tumors in a middle-income country as low awareness of signs/symptoms by parents and health professionals, aiming to provide opportunities for intervention strategies to reduce the time to diagnosis.

The cellular signaling and regulatory role of protein phosphatase in tumor diagnosis: Upstream miRNAs of PTEN.

Protein phosphatases have demonstrated considerable promise in the realm of early tumor diagnosis across various malignancies. These enzymes play a critical role in modulating the PI3K-Akt signaling pathway, which is integral to cellular processes such as proliferation, survival, and migration. When the activity of protein phosphatases becomes abnormal, it can disrupt these essential signaling pathways, potentially leading to the initiation and progression of tumors. Consequently, monitoring for abnormal expression and activity levels of protein phosphatases could serve as a vital biomarker for early cancer detection. By identifying these alterations, clinicians may be better equipped to diagnose tumors at an earlier stage, significantly improving patient outcomes.In summary, our study highlights the multifaceted and significant role of PTEN in various forms of cancer, including esophageal squamous cell carcinoma (ESCA). Further analysis showed that the expression levels of protein phosphatase and PTEN protein were significantly associated with the early diagnosis of tumors, especially in the early stage of tumors, and their detection sensitivity and specificity were high. Therefore, by detecting the expression of protein phosphatase and PTEN protein, the early diagnosis of tumor can be achieved, and the therapeutic effect and prognosis of patients can be improved.

Effectiveness of Multifaceted Lifestyle Interventions in Prediabetic Adults: A Field Study in an Urban Slum Population of Pune, India.

Introduction Adults with diabetes have an increased risk of hypertension, heart attack, and stroke than those without diabetes. Diagnosing prediabetes at an early stage can significantly reduce the risk of diabetes through simple interventions such as lifestyle modifications. Lifestyle modifications such as weight loss combined with regular physical exercise and a healthy diet can help delay or prevent the progression of diabetes. This study aims to estimate the prevalence of prediabetes among the urban slum population and to assess the effect of lifestyle modifications on blood sugar levels, glycated hemoglobin (HbA1c), and lipid profile among the participants. Methods A quasi-experimental field study was conducted among the urban slum population. Participants were randomly selected from previous health screening data. Pre-intervention blood evaluations were performed, and those who fulfilled the criteria were enrolled for interventions. The follow-up period lasted three months and included telephonic and in-person meetings for support and motivation. All variables were reevaluated at the end of the follow-up period. Results Out of 34 participants included in the study, 20 completed the three-month follow-up. Statistically significant changes were observed after three months of intervention in weight, fasting blood sugar, HbA1c, BMI, triglycerides, and high-density lipoprotein (HDL) cholesterol levels. However, decreases in systolic blood pressure (BP), diastolic BP, total cholesterol, and low-density lipoprotein (LDL) cholesterol were not statistically significant. Conclusion The study revealed that lifestyle intervention programs promoting healthy diets, physical activity, and body weight reduction can prevent or delay the onset of diabetes among high-risk populations. The effectiveness of interventions across community settings depends on delivery formats, implementers, and the level of motivation of participants.

A Deep Learning System to Predict Epithelial Dysplasia in Oral Leukoplakia.

Oral leukoplakia (OL) has an inherent disposition to develop oral cancer. OL with epithelial dysplasia (OED) is significantly likely to undergo malignant transformation; however, routine OED assessment is invasive and challenging. This study investigated whether a deep learning (DL) model can predict dysplasia probability among patients with leukoplakia using oral photographs. In addition, we assessed the performance of the DL model in comparison with clinicians' ratings and in providing decision support on dysplasia assessment. Retrospective images of leukoplakia taken before biopsy/histopathology were obtained to construct the DL model (n = 2,073). OED status following histopathology was used as the gold standard for all images. We first developed, fine-tuned, and internally validated a DL architecture with an EfficientNet-B2 backbone that outputs the predicted probability of OED, OED status, and regions-of-interest heat maps. Then, we tested the performance of the DL model on a temporal cohort before geographical validation. We also assessed the model's performance at external validation with opinions provided by human raters on OED status. Performance evaluation included discrimination, calibration, and potential net benefit. The DL model achieved good Brier scores, areas under the curve, and balanced accuracies of 0.124 (0.079-0.169), 0.882 (0.838-0.926), and 81.8% (76.5-87.1) at testing and 0.146 (0.112-0.18), 0.828 (0.792-0.864), and 76.4% (72.3-80.5) at external validation, respectively. In addition, the model had a higher potential net benefit in selecting patients with OL for biopsy/histopathology during OED assessment than when biopsies were performed for all patients. External validation also showed that the DL model had better accuracy than 92.3% (24/26) of human raters in classifying the OED status of leukoplakia from oral images (balanced accuracy: 54.8%-79.7%). Overall, the photograph-based intelligent model can predict OED probability and status in leukoplakia with good calibration and discrimination, which shows potential for decision support to select patients for biopsy/histopathology, obviate unnecessary biopsy, and assist in patient self-monitoring.

Engineering of Kidney-Targeting Fluorophores with Tunable Emission from NIR-I to NIR-II for Early Diagnosis of Kidney Disease.

The development of rapidly distributed and retained probes within the kidneys is important for accurately diagnosing kidney diseases. Although molecular imaging shows the potential for non-intrusively interrogating kidney disease-related biomarkers, the limited kidney contrast of many fluorophores, owing to their relatively low distribution in the kidney, hinders their effectiveness for kidney disease detection. Herein, for the first time, an amino-functionalization strategy is proposed to construct a library of kidney-targeting fluorophores NHcy with tunable emissions from NIR-I to NIR-II. Among these, NHcy-8 is the first small-molecule NIR-II dye without a renal clearance moiety, designed specifically for kidney-targeting imaging. Building on this class of NIR-II fluorophore, the first NIR-II small-molecule kidney-targeting pH probe NIR-II-pH is developed, which exhibits a desirable kidney distribution after intravenous injection and is fluorescent only after activation by acidosis. NIR-II in vivo fluorescence/photoacoustic imaging of kidney disease models induced by cisplatin and renal I/R injury using NIR-II-pH reveals increasingly severe metabolic acidosis as the disease progressed, enabling sensitive detection of the onset of acidosis 36 h (cisplatin group) earlier than clinical methods. Thus, this study introduces a practical NIR-II kidney-targeting probe and provides a useful molecular blueprint for guiding kidney-targeting NIR-II fluorophores as diagnostic aids for kidney diseases.

Nanozyme-Based Pump-free Microfluidic Chip for Colorectal Cancer Diagnosis via Circulating Cancer Stem Cell Detection.

Circulating cancer stem cells (CCSCs) are subpopulations of cancer cells with high tumorigenicity, chemoresistance, and metastatic potential, which are also major drivers of disease progression. Herein, to achieve the prediction of tumor diagnosis and progression in colorectal cancer (CRC), a new, automated, and portable lateral displacement patterned pump-free (LP) microfluidic chip (LP-chip) with the CoPt3 nanozyme was established for CCSC capture and detection in peripheral blood and feces samples ex vivo. In this design, CoPt3@HA probes with functions of magnetic separation and colorimetric signal transduction by peroxidase-mimicking activity were applied for the capture of CCSCs and signal output in clinical samples. The generated colors of polydopamine (PDA) were quantifiable through the smartphone APP and visualizable by the naked eye in the test line (T line) and control line (C line) of the LP-chip. In the optimal experimental conditions, the CCSC concentration was sensitive to change in the range 0-105 cells mL-1, with a detection limit of 3 cells mL-1 (S/N = 3). Preliminary studies of clinical samples suggest that the platform has the potential for prediction of colorectal cancer progression and poor prognosis. Overall, the LP-chip provides potential strategies for timely diagnosis, therapeutic monitoring, and recurrence prediction to improve home-based patient care.

The Value of Topological Radiomics Analysis in Predicting Malignant Risk of Pulmonary Ground-Glass Nodules: A Multi-Center Study.

BACKGROUND: Early detection and accurate differentiation of malignant ground-glass nodules (GGNs) in lung CT scans are crucial for the effective treatment of lung adenocarcinoma. However, existing imaging diagnostic methods often struggle to distinguish between benign and malignant GGNs in the early stages. This study aims to predict the malignancy risk of GGNs observed in lung CT scans by applying two radiomics methods: topological data analysis and texture analysis. METHODS: A retrospective analysis was conducted on 3223 patients from two centers between January 2018 and June2023. The dataset was divided into training, testing, and validation sets to ensure robust model development and validation. We developed topological features applied to GGNs using radiomics analysis based on homology. This innovative approach emphasizes the integration of topological information, capturing complex geometric and spatial relationships within GGNs. By combining machine learning and deep learning algorithms, we established a predictive model that integrates clinical parameters, previous radiomics features, and topological radiomics features. RESULTS: Incorporating topological radiomics into our model significantly enhanced the ability to distinguish between benign and malignant GGNs. The topological radiomics model achieved areas under the curve (AUC) of 0.85 and 0.862 in two independent validation sets, outperforming previous radiomics models. Furthermore, this model demonstrated higher sensitivity compared to models based solely on clinical parameters, with sensitivities of 80.7% in validation set 1 and 82.3% in validation set 2. The most comprehensive model, which combined clinical parameters, previous radiomics features, and topological radiomics features, achieved the highest AUC value of 0.879 across all datasets. CONCLUSION: This study validates the potential of topological radiomics in improving the predictive performance for distinguishing between benign and malignant GGNs. By integrating topological features with previous radiomics and clinical parameters, our comprehensive model provides a more accurate and reliable basis for developing treatment strategies for patients with GGNs.

Optimal cut-off values and diagnostic significance of clinical laboratory indicators in newly diagnosed multiple myeloma.

OBJECTIVE: This study aims to identify clinical laboratory parameters for the diagnosis of newly diagnosed multiple myeloma (NDMM), establish optimal cutoffs for early screening, and develop a diagnostic model for precise diagnosis. METHODS: The study conducted a retrospective analysis of 279 NDMM patients and 553 healthy subjects at Zhejiang Province People's Hospital between January 2008 and June 2023. Multifactor LR was employed to explore clinical laboratory indicators with diagnostic value for NDMM, determine optimal cutoff values and contract a diagnostic model. The diagnostic efficacy and clinical utility were evaluated using receiver operating characteristic curves (ROC), sensitivity, specificity, and other indicators. RESULTS: Multifactor analysis revealed that hemoglobin (Hb), albumin (Alb), and platelet distribution width (PDW) were significant diagnostic factors for NDMM. Optimal cutoff values for Hb, Alb, and PDW in MM diagnosis were determined, and the results showed a significant increase in the probability of NDMM diagnosis when Alb was below 39.3 g/L, Hb was below 11.6 g/dL, and PDW was below 14.1 fL. The diagnostic model constructed from the development cohort demonstrated a high area under the ROC curve of 0.960 (95% CI 0.942-0.978) and exhibited good sensitivity (0.860), specificity (0.957). The area under the curve (AUC) value of the diagnostic model in the external validation cohort was 0.979, confirming its good diagnostic efficacy and generalization. CONCLUSIONS: The optimal cutoff values for Hb, Alb, and PDW and the diagnostic model designed in the study provided good accuracy and sensitivity for the initial screening and diagnosis of NDMM.

Implementation of Machine Learning-Based System for Early Diagnosis of Feline Mammary Carcinomas through Blood Metabolite Profiling.

Background: Feline mammary carcinoma (FMC) is a prevalent and fatal carcinoma that predominantly affects unspayed female cats. FMC is the third most common carcinoma in cats but is still underrepresented in research. Current diagnosis methods include physical examinations, imaging tests, and fine-needle aspiration. The diagnosis through these methods is sometimes delayed and unreliable, leading to increased chances of mortality. Objectives: The objective of this study was to identify the biomarkers, including blood metabolites and genes, related to feline mammary carcinoma, study their relationships, and develop a machine learning (ML) model for the early diagnosis of the disease. Methods: We analyzed the blood metabolites of felines with mammary carcinoma using the pathway analysis feature in MetaboAnalyst software, v. 5.0. We utilized machine-learning (ML) methods to recognize FMC using the blood metabolites of sick patients. Results: The metabolic pathways that were elucidated to be associated with this disease include alanine, aspartate and glutamate metabolism, Glutamine and glutamate metabolism, Arginine biosynthesis, and Glycerophospholipid metabolism. Furthermore, we also elucidated several genes that play a significant role in the development of FMC, such as ERBB2, PDGFA, EGFR, FLT4, ERBB3, FIGF, PDGFC, PDGFB through STRINGdb, a database of known and predicted protein-protein interactions, and MetaboAnalyst 5.0. The best-performing ML model was able to predict metabolite class with an accuracy of 85.11%. Conclusion: Our findings demonstrate that the identification of the biomarkers associated with FMC and the affected metabolic pathways can aid in the early diagnosis of feline mammary carcinoma.

Patients' recollection about the onset of Sjögren's disease - a mixed methods study on the patients' perspective.

BACKGROUND: Little is known about the symptoms at the onset of Sjögren's Disease (SjD) and it is unclear whether SjD starts with characteristic symptoms that could be differentiated from dryness of other origin (sicca syndrome). The aim of this study was to investigate patients' recollection of initial events and first symptoms of SjD. The second aim was to verify and quantify these aspects in a representative cohort. METHODS: All SjD patients fulfilled the EULAR/ACR 2016 classification criteria. In the first part of the study, consecutive SjD patients were recruited for individual, semi-structured interviews. All interviews were audio-recorded and transcribed verbatim, and an inductive thematic data analysis was performed. In the second part, the identified aspects of the qualitative analysis were grouped into a checklist with ten items. RESULTS: One-hundred and thirty-four patients participated in the study. 31 SjD patients completed the qualitative part. Major aspects emerged of how patients experienced the beginning and first symptoms of SjD: (1) "classic" SjD symptoms (fatigue, pain, dryness) (2), sicca symptoms started after initial swelling of parotid and/or lymph nodes (3), after hormonal transition or infections before the onset of SjD symptoms. In the second part of the study, the previous identified major aspects were verified in an independent cohort of 103 SjD patients. The main symptom before diagnosis was dryness (n = 77, 74.8%) with migratory joint pain (n = 51, 49.5%) and fatigue (n = 47, 45.6%). In 38.8% (n = 40), patients reported a swelling/inflammation of the parotid gland at the onset of disease. CONCLUSIONS: We describe patients' recollection of the onset of SjD. Raising awareness of the symptoms identified among physicians and among the general public may allow earlier diagnosis of SjD.

Screening COPD-Related Biomarkers and Traditional Chinese Medicine Prediction Based on Bioinformatics and Machine Learning.

Purpose: To employ bioinformatics and machine learning to predict the characteristics of immune cells and genes associated with the inflammatory response and ferroptosis in chronic obstructive pulmonary disease (COPD) patients and to aid in the development of targeted traditional Chinese medicine (TCM). Mendelian randomization analysis elucidates the causal relationships among immune cells, genes, and COPD, offering novel insights for the early diagnosis, prevention, and treatment of COPD. This approach also provides a fresh perspective on the use of traditional Chinese medicine for treating COPD. Methods: R software was used to extract COPD-related data from the Gene Expression Omnibus (GEO) database, differentially expressed genes were identified for enrichment analysis, and WGCNA was used to pinpoint genes within relevant modules associated with COPD. This analysis included determining genes linked to the inflammatory response in COPD patients and analyzing their correlation with ferroptosis. Further steps involved filtering core genes, constructing TF-miRNA‒mRNA network diagrams, and employing three types of machine learning to predict the core miRNAs, key immune cells, and characteristic genes of COPD patients. This process also delves into their correlations, single-gene GSEA, and diagnostic model predictions. Reverse inference complemented by molecular docking was used to predict compounds and traditional Chinese medicines for treating COPD; Mendelian randomization was applied to explore the causal relationships among immune cells, genes, and COPD. Results: We identified 2443 differential genes associated with COPD through the GEO database, along with 8435 genes relevant to WGCNA and 1226 inflammation-related genes. A total of 141 genes related to the inflammatory response in COPD patients were identified, and 37 core genes related to ferroptosis were selected for further enrichment analysis and analysis. The core miRNAs predicted for COPD include hsa-miR-543, hsa-miR-181c, and hsa-miR-200a, among others. The key immune cells identified were plasma cells, activated memory CD4 T cells, gamma delta T cells, activated NK cells, M2 macrophages, and eosinophils. Characteristic genes included EGF, PLG, PTPN22, and NR4A1. A total of 78 compounds and 437 traditional Chinese medicines were predicted. Mendelian randomization analysis revealed a causal relationship between 36 types of immune cells and COPD, whereas no causal relationship was found between the core genes and COPD. Conclusion: A definitive causal relationship exists between immune cells and COPD, while the prediction of core miRNAs, key immune cells, characteristic genes, and targeted traditional Chinese medicines offers novel insights for the early diagnosis, prevention, and treatment of COPD.

SwAV-driven diagnostics: new perspectives on grading diabetic retinopathy from retinal photography.

Diabetic Retinopathy (DR) is a serious eye condition that occurs due to high blood sugar levels in patients with Diabetes Mellitus. If left untreated, DR can potentially result in blindness. Using automated neural network-based methods to grade DR shows potential for early detection. However, the uneven and non-quadrilateral forms of DR lesions provide difficulties for traditional Convolutional Neural Network (CNN)-based architectures. To address this challenge and explore a novel algorithm architecture, this work delves into the usage of contrasting cluster assignments in retinal fundus images with the Swapping Assignments between multiple Views (SwAV) algorithm for DR grading. An ablation study was made where SwAV outperformed other CNN and Transformer-based models, independently and in ensemble configurations with an accuracy of 87.00% despite having fewer parameters and layers. The proposed approach outperforms existing state-of-the-art models regarding classification metrics, complexity, and prediction time. The findings offer great potential for medical practitioners, allowing for more accurate diagnosis of DR and earlier treatments to avoid visual loss.

Detection and diagnosis of diabetic eye diseases using two phase transfer learning approach.

Background: Early diagnosis and treatment of diabetic eye disease (DED) improve prognosis and lessen the possibility of permanent vision loss. Screening of retinal fundus images is a significant process widely employed for diagnosing patients with DED or other eye problems. However, considerable time and effort are required to detect these images manually. Methods: Deep learning approaches in machine learning have attained superior performance for the binary classification of healthy and pathological retinal fundus images. In contrast, multi-class retinal eye disease classification is still a difficult task. Therefore, a two-phase transfer learning approach is developed in this research for automated classification and segmentation of multi-class DED pathologies. Results: In the first step, a Modified ResNet-50 model pre-trained on the ImageNet dataset was transferred and learned to classify normal diabetic macular edema (DME), diabetic retinopathy, glaucoma, and cataracts. In the second step, the defective region of multiple eye diseases is segmented using the transfer learning-based DenseUNet model. From the publicly accessible dataset, the suggested model is assessed using several retinal fundus images. Our proposed model for multi-class classification achieves a maximum specificity of 99.73%, a sensitivity of 99.54%, and an accuracy of 99.67%.

Extracellular Vesicle miRNAs in Diagnostics of Gastric Cancer.

Gastric cancer (GC) poses a significant global health challenge because of its high mortality rate attributed to the late-stage diagnosis and lack of early symptoms. Early cancer diagnostics is crucial for improving the survival rates in GC patients, which emphasizes the importance of identifying GC markers for liquid biopsy. The review discusses a potential use of extracellular vesicle microRNAs (EV miRNAs) as biomarkers for the diagnostics and prognostics of GC. Methods. Original articles on the identification of EV miRNA as GC markers published in the Web of Science and Scopus indexed issues were selected from the PubMed and Google Scholar databases. We focused on the methodological aspects of EV analysis, including the choice of body fluid, methods for EV isolation and validation, and approaches for EV miRNA analysis. Conclusions. Out of 33 found articles, the majority of authors investigated blood-derived extracellular vesicles (EVs); only a few utilized EVs from other body fluids, including tissue-specific local biofluids (washing the tumor growth areas), which may be a promising source of EVs in the context of cancer diagnostics. GC-associated miRNAs identified in different studies using different methods of EV isolation and analysis varied considerably. However, three miRNAs (miR-10b, miR-21, and miR-92a) have been found in several independent studies and shown to be associated with GC in experimental models. Further studies are needed to determine the optimal miRNA marker panel. Another essential step necessary to improve the reliability and reproducibility of EV-based diagnostics is standardization of methodologies for EV handling and analysis of EV miRNA.