Diagnostics最新文献

{"title":"A Comparative Analysis of SegFormer, FabE-Net and VGG-UNet Models for the Segmentation of Neural Structures on Histological Sections.","authors":"Igor Makarov, Elena Koshevaya, Alina Pechenina, Galina Boyko, Anna Starshinova, Dmitry Kudlay, Taiana Makarova, Lubov Mitrofanova","doi":"10.3390/diagnostics15182408","DOIUrl":"10.3390/diagnostics15182408","url":null,"abstract":"<p><p><b>Background:</b> Segmenting nerve fibres in histological images is a tricky job because of how much the tissue looks can change. Modern neural network architectures, including U-Net and transformers, demonstrate varying degrees of effectiveness in this area. The aim of this study is to conduct a comparative analysis of the SegFormer, VGG-UNet, and FabE-Net models in terms of segmentation quality and speed. <b>Methods:</b> The training sample consisted of more than 75,000 pairs of images of different tissues (original slice and corresponding mask), scaled from 1024 × 1024 to 224 × 224 pixels to optimise computations. Three neural network architectures were used: the classic VGG-UNet, FabE-Net with attention and global context perception blocks, and the SegFormer transformer model. For an objective assessment of the quality of the models, expert validation was carried out with the participation of four independent pathologists, who evaluated the quality of segmentation according to specified criteria. Quality metrics (precision, recall, F1-score, accuracy) were calculated as averages based on the assessments of all experts, which made it possible to take into account variability in interpretation and increase the reliability of the results. <b>Results:</b> SegFormer achieved stable stabilisation of the loss function faster than the other models-by the 20-30th epoch, compared to 45-60 epochs for VGG-UNet and FabE-Net. Despite taking longer to train per epoch, SegFormer produced the best segmentation quality, with the following metrics: precision 0.84, recall 0.99, F1-score 0.91 and accuracy 0.89. It also annotated a complete histological section in the fastest time. Visual analysis revealed that, compared to other models, which tended to produce incomplete or excessive segmentation, SegFormer more accurately and completely highlights nerve structures. <b>Conclusions:</b> Using attention mechanisms in SegFormer compensates for morphological variability in tissues, resulting in faster and higher-quality segmentation. Image scaling does not impair training quality while significantly accelerating computational processes. These results confirm the potential of SegFormer for practical use in digital pathology, while also highlighting the need for high-precision, immunohistochemistry-informed labelling to improve segmentation accuracy.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468733/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Criteria and Protocol: Assessing Generative AI Efficacy in Perceiving EULAR 2019 Lupus Classification.","authors":"Gerald H Lushington, Sandeep Nair, Eldon R Jupe, Bernard Rubin, Mohan Purushothaman","doi":"10.3390/diagnostics15182409","DOIUrl":"10.3390/diagnostics15182409","url":null,"abstract":"<p><p><b>Background/Objectives:</b> In clinical informatics, the term 'information overload' is increasingly used to describe the operational impediments of excessive documentation. While electronic health records (EHRs) are growing in abundance, many medical records (MRs) remain in legacy formats that impede efficient, systematic processing, contributing to the extenuating challenges of care fragmentation. Thus, there is a growing interest in using generative AI (genAI) for automated MR summarization and characterization. <b>Methods:</b> MRs for a set of 78 individuals were digitized. Some were known systemic lupus erythematosus (SLE) cases, while others were under evaluation for possible SLE classification. A two-pass genAI assessment strategy was implemented using the Claude 3.5 large language model (LLM) to mine MRs for information relevant to classifying SLE vs. undifferentiated connective tissue disorder (UCTD) vs. neither via the 22-criteria EULAR 2019 model. <b>Results:</b> Compared to clinical determination, the antinuclear antibody (ANA) criterion (whose results are crucial for classifying SLE-negative cases) exhibited favorable sensitivity 0.78 ± 0.09 (95% confidence interval) and a positive predictive value 0.85 ± 0.08 but a marginal performance for specificity 0.60 ± 0.11 and uncertain predictivity for the negative predictive value 0.48 ± 0.11. Averaged over the remaining 21 criteria, these four performance metrics were 0.69 ± 0.11, 0.87 ± 0.04, 0.54 ± 0.10, and 0.93 ± 0.03. <b>Conclusions:</b> ANA performance statistics imply that genAI yields confident assessments of SLE negativity (per high sensitivity) but weaker positivity. The remaining genAI criterial determinations support (per specificity) confident assertions of SLE-positivity but tend to misclassify a significant fraction of clinical positives as UCTD.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468409/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Relapsed AML Case Featuring MYC and MECOM Rearrangements.","authors":"Kevin A Murgas, Pons Materum, Luke Z Li, Jacob Rocha, Michael Schuster, Tahmeena Ahmed, Carlos A Tirado","doi":"10.3390/diagnostics15182410","DOIUrl":"10.3390/diagnostics15182410","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Relapsed acute myeloid leukemia (AML) is often characterized by clonal evolution and acquired genomic abnormalities, which can inform prognosis and direct therapeutic decisions. The emergence of high-risk chromosomal rearrangements during relapse is of particular significance, yet the impact of rare and complex events remains poorly understood. This report details a case of relapsed AML that demonstrated rare <i>MYC</i> and <i>MECOM</i> rearrangements and additional features that were not observed at initial diagnosis, emphasizing the clinical relevance of serial cytogenetic assessments. <b>Case Description:</b> A 70-year-old man was initially diagnosed with AML, exhibiting monocytic differentiation, an 11q23 deletion involving <i>KMT2A</i> loss, and a <i>U2AF1</i> mutation. After achieving remission with azacitidine and venetoclax, the patient relapsed within ten months, necessitating reevaluation and modification of therapy. Repeat cytogenetic analysis at relapse revealed a distinct t(3;8)(q26.2;q24.3) exhibiting <i>MYC</i> and <i>MECOM</i> rearrangements, features that were absent at initial diagnosis. <b>Conclusions:</b> This case underscores the importance of serial cytogenetic and molecular profiling in relapsed AML. The emergence of new abnormalities upon relapse suggested underlying genomic instability and clonal evolution. <i>MYC</i> rearrangements are notably rare in AML, especially with concurrent <i>MECOM</i> rearrangements, highlighting a unique feature of this case. The identification of novel abnormalities at relapse may carry prognostic and therapeutic significance and may be used to refine risk stratification. Thus, ongoing cytogenetic monitoring is essential to adapt management approaches in evolving disease contexts.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468068/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Contingency of Reported sST2 Serum Concentrations with a Protein Detection System (ELISA) from the Same Manufacturer (R&D Biotechne, 2002-2025): An Explanatory Effort by Applied Medical Researchers.","authors":"Marie-Therese Lingitz, Hannes Kühtreiber, Lisa Auer, Michael Mildner, Bernhard Moser, Christine Bekos, Clemens Aigner, Martin Direder, Thomas Mueller, Hendrik Jan Ankersmit","doi":"10.3390/diagnostics15182412","DOIUrl":"10.3390/diagnostics15182412","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Soluble ST2 (sST2) has gained recognition as a clinically relevant biomarker across a spectrum of inflammatory, cardiovascular, and respiratory conditions. However, the lack of assay standardization raises concerns about result comparability across platforms and studies. <b>Methods</b>: This study systematically evaluated serum sST2 concentrations measured with two ELISA systems-DuoSet and Quantikine-produced by the same manufacturer (R&D Systems, Minneapolis, MN, USA). <b>Results</b>: Using archived serum samples from healthy volunteers and marathon runners, we identified marked discrepancies: serum sST2 concentrations using the DuoSet recombinant standard were on average 4.3-fold higher than those using Quantikine (median 308.3 [106.6-608.6] vs. 71.5 [41.8-115.6] ng/mL). On the pre-coated Quantikine plate, using the DuoSet recombinant standard increased calculated concentrations 4.3-fold compared with the native Quantikine standard (median 308.3 [106.6-608.6] vs. 71.5 [41.8-115.6] ng/mL). On the manually coated DuoSet plate, the DuoSet standard yielded higher medians than the Quantikine standard (8.0 [5.6-11.3] vs. 5.0 [3.7-7.4] ng/mL). Furthermore, between-lot variability within the same ELISA platform resulted in concentration shifts from 0.09 [0.07-0.10] ng/mL (2016) to 1.17 [0.81-3.23] ng/mL (2023) using the same sample. Previously published studies also exhibited wide inter-study variability among healthy cohorts. <b>Conclusions</b>: These findings emphasize that current ELISA systems for sST2 are not standardized and that cross-study comparisons should be interpreted with caution. Until universal standardization is implemented, sST2 should primarily be used for within-study comparisons. This variability may limit the reliability of longitudinal sST2 assessment even in clinical settings.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468627/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cumulative Effect of Metabolic Factors on Hepatic Steatosis.","authors":"Anna Egresi, Brigitta Kozma, Márton Karácsony, Aladár Rónaszéki, Klára Werling, Barbara Csongrády, Pál Kaposi Novák, Anikó Folhoffer, Attila Szijártó, Krisztina Hagymási","doi":"10.3390/diagnostics15182406","DOIUrl":"10.3390/diagnostics15182406","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Hepatic steatosis, a hallmark of metabolic dysfunction-associated steatotic liver disease (MASLD), is closely associated with systemic metabolic dysfunction. However, the cumulative impact of metabolic risk factors on liver fat content remains underexplored. To evaluate the association between metabolic risk factors and hepatic steatosis severity using magnetic resonance imaging proton density fat fraction (MR-PDFF) measurement, and to assess the cumulative effect of multiple metabolic abnormalities. <b>Methods</b>: In this cross-sectional study, MASLD patients (<i>n</i> = 132, aged ≥ 18 years, age: 61.3 ± 10.3, male: 54, female: 78) underwent metabolic risk assessment and MR-PDFF liver fat content measurement. The association between certain metabolic risk scores (obesity/overweight, hypertension, hypercholesterolemia, hypertriglyceridemia, impaired fasting glucose or type 2 diabetes mellitus) both continuous and categorized, as well as liver fat content was analyzed using linear regression models. The cumulative effect of increasing metabolic risk was further explored with subgroup comparisons. <b>Results</b>: A significant positive association was observed between continuous metabolic risk scores and MR-PDFF values (β = 0.021, <i>p</i> < 0.001). Participants with higher cumulative metabolic risk (4 and 5 risk factors group) showed significantly higher liver fat content compared to the reference group (<i>p</i> < 0.01) (MetfO0 = 5.7 ± 5.9%; MetfO1 = 11.6 ± 9.5%; MetfO2 = 7.9 ± 5.6%; MetfO3 = 10.2 ± 7.9%; MetfO4 = 16.4 ± 11.0%; MetfO5 = 17.8 ± 9.5%). Intermediate metabolic risk categories showed a trend toward increased steatosis but did not reach statistical significance. <b>Conclusions</b>: Cumulative metabolic risk is strongly associated with increased hepatic fat accumulation. These findings underscore the need for early identification and management of metabolic risk factors to prevent the development and progression of hepatic steatosis.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasonographic Median Nerve Cross-Sectional Area and Clinical, Electrodiagnostic, and Laboratory Biomarkers in Electrodiagnostically Confirmed Carpal Tunnel Syndrome: A Single-Center Correlational Study.","authors":"Hasan Kara, Hüseyin Kaplan, Fatma Nur Aba, Servin Karaca, İsa Cüce","doi":"10.3390/diagnostics15182407","DOIUrl":"10.3390/diagnostics15182407","url":null,"abstract":"<p><p><b>Objectives:</b> This study aimed to evaluate the relationship between the median nerve cross-sectional area (CSA, mm²) and clinical findings, blood test results, and electrodiagnostic (EDX) measurements in patients with carpal tunnel syndrome (CTS). <b>Methods:</b> This cross-sectional study included 62 patients (111 hands). The median nerve CSA was assessed using ultrasound (US). The clinical assessment included symptom duration, symptom severity, the Boston Carpal Tunnel Questionnaire (BCTQ), and physical examination. Patient-level analyses used the CSA of the most symptomatic hand for clinical and laboratory variables (<i>n</i> = 62 patients). Hand-level EDX analyses accounted for within-patient clustering by reporting right and left hands separately. Associations were summarized with Spearman's ρ and 95% confidence intervals (CIs); multiplicity was addressed using Benjamini-Hochberg false discovery rate (FDR). EDX units: latency ms, amplitude mV/µV, and velocity m/s. <b>Results:</b> CSA was not associated with global symptom burden (Visual Analog Scale; BCTQ). No laboratory marker remained significant after FDR across the full panel. By contrast, CSA correlated with EDX impairment at the hand level with low-to-moderate effect sizes; for example, distal motor latency was positively associated with CSA on the right (ρ = 0.557, 95% CI 0.334-0.733) and left (ρ = 0.318, 95% CI 0.022-0.578). CSA also correlated positively with CTS EDX severity (right: ρ = 0.449, 95% CI 0.223-0.646; left: ρ = 0.354, 95% CI 0.071-0.609). <b>Conclusions:</b> Ultrasonographic CSA was associated with electrophysiologic impairment and was not associated with overall symptom burden; laboratory signals did not survive FDR control. Accordingly, CSA may serve as a complementary morphologic adjunct to clinical assessment and EDX, with limited utility as a stand-alone severity metric.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468091/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of ⁶⁸Ga-PSMA PET/MRI on the Accuracy of MRI-Derived Grading Systems for Predicting Extraprostatic Extension in Prostate Cancer.","authors":"Lebriz Uslu-Beşli, Selahattin Durmaz, Aslıhan Onay, Barış Bakır, İclal Gürses, Sevda Özel-Yıldız, Çetin Demirdağ, Haluk Burçak Sayman","doi":"10.3390/diagnostics15182405","DOIUrl":"10.3390/diagnostics15182405","url":null,"abstract":"<p><p><b>Objectives</b>: Accurate preoperative staging and prediction of extraprostatic extension (EPE) are critical for optimal surgical planning in prostate cancer (PCa). This study evaluated the diagnostic accuracy of ⁶⁸Ga-PSMA PET for EPE assessment, compared it with the standardized multiparametric MRI (mpMRI)-derived EPE-grading system, and examined whether integrating semi-quantitative PSMA PET parameters improves diagnostic performance using hybrid PET/MRI. <b>Methods</b>: This retrospective, single-center study included treatment-naïve, biopsy-proven PCa patients who underwent ⁶⁸Ga-PSMA-11 PET/MRI followed by radical prostatectomy. Diagnostic accuracy was assessed for clinical variables (PSA, ISUP grade), mpMRI features, mpMRI-derived EPE-grading system, visual PET findings, and semi-quantitative PET parameters (SUVmax, SUVmean, PSMA-tumor volume [PSMA-TV]). Optimal cut-offs were determined using the Youden index. Multivariate logistic regression and receiver operating characteristic (ROC) analyses were performed to compare the predictive value of clinical, mpMRI, or PET-derived variables, with histopathology as the reference standard. <b>Results</b>: Forty-five patients were included; EPE was histologically confirmed in 19 (42.2%). Predictors of EPE included capsular irregularity, neurovascular bundle asymmetry, curvilinear contact length ≥ 1.5 cm, seminal vesicle invasion, tumor size ≥ 14.25 mm, EPE grade ≥ 2, ISUP grade ≥ 3, overt EPE on PET, SUVmax ≥ 13.84, SUVmean ≥ 7.20, and PSMA-TV ≥ 1.40 cm³. The highest ROC performance (AUC = 0.890) was achieved by combining overt EPE on PET, SUVmax, and PSMA-TV. Incorporating PET parameters or tumor size into the EPE-grading system improved predictive accuracy. <b>Conclusions</b>: PSMA uptake in the primary tumor is an independent predictor of EPE. Integrating PSMA PET with mpMRI may provide additional information for preoperative EPE assessment.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468641/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Review of Optic Disc Drusen in the Modern Imaging Era: Structure-Function Correlates, Diagnostic Performance, and NAION Co-Occurrence.","authors":"Alina Dumitriu, Bogdan Dumitriu, Flavius George Socol, Ioana Denisa Socol, Ionela Iasmina Yasar, Camelia Fizedean, Adelina Mavrea, Andrei-Cristian Bondar, Mihnea Munteanu","doi":"10.3390/diagnostics15182414","DOIUrl":"10.3390/diagnostics15182414","url":null,"abstract":"<p><p><b>Background and Objectives:</b> Optic disc drusen (ODD) can mimic papilledema and are linked to structural crowding, microvascular change, and visual-field loss. We synthesized structural/microvascular differences, functional status and change, diagnostic performance, and ODD-NAION co-occurrence. <b>Methods:</b> This study used PRISMA-aligned searches of PubMed, Embase, and Web of Science (inception-15 July 2025). Eligible designs included cross-sectional, cohort, and diagnostic accuracy studies with numeric outcomes (OCT/OCTA, visual fields, test accuracy, NAION prevalence). Two reviewers independently screened, extracted, and appraised bias. Heterogeneity precluded meta-analysis; narrative synthesis was used. Bias risk was moderate. <b>Results:</b> From 359 records, 6 studies met the criteria. ODD eyes showed thicker RNFL than controls (117.54 ± 18.75 vs. 105.81 ± 14.45 µm; 101 ± 12 vs. 97 ± 10 µm) and worse baseline mean deviation (-1.78 ± 3.87 dB). OCTA demonstrated sectoral peripapillary vessel-area density reduction (inferior 0.30 vs. 0.34; temporal 0.44 vs. 0.48; superonasal 0.44 vs. 0.49). Visual-field phenotypes were normal (44-52%), enlarged blind spot (19-29%), and other localized defects (24-29%); the longitudinal decline averaged -0.23 ± 0.26 dB/year with 88% slow progressors. In pseudopapilledema, single-test yields were ultrasound at 87.2%, OCT at 80.2%, and FAF at 62.8%; OCT alone distinguished buried ODD from mild papilledema with 50-64% accuracy (κ ≈ 0.35). Among young NAION, ODD affected 56.7% of patients and 53.3% of eyes; bilaterality was 95.2%, and only 35.9% were ophthalmoscopically visible. <b>Conclusions:</b> Multimodal imaging shows structural thickening, microvascular rarefaction, and modest functional loss in ODD, with slow average progression. In suspected papilledema, protocolized multimodal workflows outperform OCT alone. ODD are common in young NAION, supporting risk stratification and longitudinal monitoring.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cytokine Profiles as Predictive Biomarkers of Disease Severity and Progression in Engineered Stone Silicosis: A Machine Learning Approach.","authors":"Daniel Sanchez-Morillo, Ana Martín-Carrillo, Blanca Priego-Torres, Iris Sopo-Lambea, Gema Jiménez-Gómez, Antonio León-Jiménez, Antonio Campos-Caro","doi":"10.3390/diagnostics15182413","DOIUrl":"10.3390/diagnostics15182413","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Silicosis caused by dust from engineered stone (ES) exposure is an emerging occupational lung disease that severely impacts respiratory health. This study aimed to analyze the association between cytokine profiles and disease severity and progression in patients with engineered stone silicosis (ESS) to assess their potential as biomarkers of progression and their usefulness to stratify risk. <b>Methods</b>: A longitudinal study was conducted with a seven-year follow-up (2017-2024) on 72 workers with simple silicosis (SS) or progressive massive fibrosis (PMF), all with a history of cutting, polishing, and finishing ES countertops. Data on lung function and levels of 27 cytokines were collected at four control points. Machine learning (ML) models were built to classify the disease stage and predict its progression. <b>Results</b>: 39% of patients with SS progressed to PMF. Significant differences in the expression of some cytokines were observed between ESS stages, suggesting a role in the evolution of the inflammatory process. Specifically, higher levels of IL-1RA, IL-8, IL-9, and IFN-γ were found at checkpoint 1 in patients with PMF compared to SS. The longitudinal analysis revealed a significant relationship between IL-1RA and MCP-1α and disease duration with MCP-1α also being associated with time and disease grade. Machine learning (ML) models were built using the cytokines selected through a sequential backward feature selection. The Support Vector Machine model achieved an accuracy of 83% in classifying disease stage (SS, PMF), and of 77% in predicting the disease progression. <b>Conclusions</b>: The findings suggest that cytokines can be used as dynamic biomarkers to reflect underlying inflammatory processes and monitor disease evolution. The performance of ML algorithms to predict diagnostic status based on cytokine profiles highlights their clinical value in supporting early diagnosis, monitoring disease progression, and guiding clinical decisions.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468016/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Collision Tumor of Angioimmunoblastic T-Cell Lymphoma and Kaposi Sarcoma in an HIV-Negative Elderly Woman: The First Reported Case in Asia.","authors":"Myung-Won Lee, Jin-Man Kim","doi":"10.3390/diagnostics15182411","DOIUrl":"10.3390/diagnostics15182411","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Angioimmunoblastic T-cell lymphoma (AITL) is a rare peripheral T-cell lymphoma of follicular helper T-cell (TFH) origin, often associated with immune dysregulation and EBV-positive B-cell proliferation. Kaposi sarcoma (KS) is a vascular neoplasm caused by human herpesvirus 8 (HHV-8), typically arising in immunocompromised individuals. The synchronous occurrence of AITL and KS in HIV-negative patients is exceptionally rare, with only three cases previously reported worldwide. <b>Case Presentation:</b> We describe an 81-year-old HIV-negative Korean woman presenting with progressive generalized edema and dyspnea. Imaging revealed multifocal lymphadenopathy. Excisional biopsy of the inguinal lymph node showed two distinct but adjacent neoplastic processes. The AITL component demonstrated a polymorphous infiltrate of atypical TFH cells expressing CD3, CD4, CD10, PD-1, and Bcl-6, with monoclonal TCR-γ rearrangement and TET2 and RHOA mutations. The KS component comprised spindle cells with slit-like vascular spaces, red blood cell extravasation, and immunoreactivity for HHV-8, CD31, CD34, and ERG. The findings were consistent with a collision tumor. Despite supportive care, the patient's condition deteriorated, and she was discharged with palliative care. <b>Discussion:</b> The coexistence of AITL and KS in an HIV-negative setting raises important pathogenetic considerations. AITL is characterized by profound immune dysregulation, with depletion of normal T-cell subsets, abnormal B-cell activation, and cytokine milieu changes that may favor latent viral reactivation. This immunologic environment may permit HHV-8 reactivation, thereby facilitating the development of KS even in the absence of overt immunodeficiency due to HIV infection. Our findings support the hypothesis that AITL-related immune dysfunction may create a permissive niche for HHV-8-driven neoplasia. <b>Conclusions:</b> This is the first reported case in Asia and the fourth worldwide of a collision tumor comprising AITL and KS in an HIV-negative patI dient. The case suggests that AITL-associated immune dysregulation may facilitate HHV-8 reactivation and KS development even in the absence of HIV infection. Awareness of this association is critical for accurate diagnosis and optimal patient management.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468100/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}