Diagnostics最新文献

{"title":"Dual Machine Learning Framework for Predicting Long-Term Glycemic Change and Prediabetes Risk in Young Taiwanese Men.","authors":"Chung-Chi Yang, Sheng-Tang Wu, Ta-Wei Chu, Chi-Hao Liu, Yung-Jen Chuang","doi":"10.3390/diagnostics15192507","DOIUrl":"10.3390/diagnostics15192507","url":null,"abstract":"<p><p><b>Background:</b> Early detection of dysglycemia in young adults is important but underexplored. This study aimed to (1) predict long-term changes in fasting plasma glucose (δ-FPG) and (2) classify future prediabetes using complementary machine learning (ML) approaches. <b>Methods:</b> We analyzed 6247 Taiwanese men aged 18-35 years (mean follow-up 5.9 years). For δ-FPG (continuous outcome), random forest, stochastic gradient boosting (SGB), eXtreme gradient boosting (XGBoost), and elastic net were compared with multiple linear regression using Symmetric mean absolute percentage error (SMAPE), Root mean squared error (RMSE), Relative absolute error(RAE), and Root relative squared error (RRSE) Sensitivity analyses excluded baseline FPG (FPG_base). Shapley additive explanations(SHAP) values provided interpretability, and stability was assessed across 10 repeated train-test cycles with confidence intervals. For prediabetes (binary outcome), an XGBoost classifier was trained on top predictors, with class imbalance corrected by SMOTE-Tomek. Calibration and decision-curve analysis (DCA) were also performed. <b>Results:</b> ML models consistently outperformed regression on all error metrics. FPG_base was the dominant predictor in full models (100% importance). Without FPG_base, key predictors included body fat, white blood cell count, age, thyroid-stimulating hormone, triglycerides, and low-density lipoprotein cholesterol. The prediabetes classifier achieved accuracy 0.788, precision 0.791, sensitivity 0.995, ROC-AUC 0.667, and PR-AUC 0.873. At a high-sensitivity threshold (0.2892), sensitivity reached 99.53% (specificity 47.46%); at a balanced threshold (0.5683), sensitivity was 88.69% and specificity was 90.61%. Calibration was acceptable (Brier 0.1754), and DCA indicated clinical utility. <b>Conclusions:</b> FPG_base is the strongest predictor of glycemic change, but adiposity, inflammation, thyroid status, and lipids remain informative. A dual interpretable ML framework offers clinically actionable tools for screening and risk stratification in young men.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12524205/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145298909","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 Establishment of Reference Intervals for Thyroid Hormone Tests in the Korean Population: Using a Direct Selection Technique.","authors":"Jong Do Seo, Eun-Jung Cho, Changhee Ha, Hyung-Doo Park, Shinae Yu, Woochang Lee, Sollip Kim, Yeo-Min Yun","doi":"10.3390/diagnostics15192510","DOIUrl":"10.3390/diagnostics15192510","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Thyroid-stimulating hormone (TSH), free thyroxine (FT4), and total triiodothyronine (TT3) are biomarkers for evaluating thyroid function. Although hormone levels are affected by many biological and environmental factors, most laboratories use manufacturer-provided reference intervals (RIs) without considering these factors. Thus, in this study we assessed RIs for TSH, FT4, and TT3 in a Korean population, using a direct selection technique. <b>Methods</b>: Serum samples from patients without a history of thyroid disease, medication, family history, or antibody-positive test results were collected after a review of medical records. TSH, FT4, and TT3 levels were measured using the Cobas e801 analyzer (Roche Diagnostics GmbH, Mannheim, Germany) with dedicated reagents. RIs were then established using a non-parametric method, using values at the 2.5th and 97.5th percentiles as reference limits, which were then verified in a validation cohort. <b>Results</b>: A total of 618 subjects were enrolled in this study. Because the distribution of reference values for the four subgroups divided by sex and age (65 years) showed insignificant differences, combined RIs were determined, with the established RIs being 0.38-5.46 mIU/L for TSH, 12.28-22.40 pmol/L for FT4, and 0.94-2.32 nmol/L for TT3. When compared to manufacturer-claimed RIs, the Korean RI for TSH showed higher upper limits, while that for TT3 showed lower upper limits. Additionally, when newly established RIs were applied to the validation cohort, the rate of test-positive results decreased significantly. <b>Conclusions</b>: Significant differences in RIs for TSH and TT3 in the Korean population, compared to manufacturer-claimed values, highlight the need for population-specific RIs. Thus, interpreting the results for the Korean population requires caution, and Korean population-based RIs are necessary.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299162","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":"CIN2 in the Era of Risk-Based Management and HPV Vaccination: Epidemiology, Natural History and Guidelines.","authors":"Maria Teresa Bruno, Alessia Pagana, Carla Lo Giudice, Marco Marzio Panella, Giuseppe Mascellino, Antonio Simone Laganà","doi":"10.3390/diagnostics15192512","DOIUrl":"10.3390/diagnostics15192512","url":null,"abstract":"<p><p><b>Background:</b> Cervical intraepithelial neoplasia grade 2 (CIN2) represents a controversial lesion in cervical cancer prevention. Traditionally included in the aggregate CIN2+ endpoint for reasons of diagnostic stability and statistical power, isolated CIN2 has unique biological characteristics: greater interobserver variability, a high probability of spontaneous regression and a lower risk of progression compared to CIN3. <b>Objectives:</b> To critically describe the epidemiology, natural history and management strategies of CIN2, integrating data from clinical and population-based studies and comparing the recommendations of the main international guidelines. <b>Methods:</b> A narrative review was conducted using a search of PubMed and Scopus (1990-January 2025). Prospective and retrospective studies on isolated CIN2, screening and vaccination trials with CIN2+ endpoints, biomarker research, and consensus documents (ASCCP, ESGO, GISCi, Ministry of Health, WHO) were included. <b>Results:</b> Clinical studies have shown a high probability of CIN2 regression (50-70% within two years, >70% in those <25 years), compared to a 10-15% risk of progression, especially in the presence of persistent HPV16. Screening trials and vaccine evaluations with CIN2+ endpoints have documented the efficacy of the HPV test and a dramatic reduction in lesions in vaccinated cohorts, which was also confirmed for isolated CIN2. The most recent guidelines have progressively adopted a risk-based approach, which allows for active surveillance in young women or those seeking to conceive, while the WHO maintains a screen-and-treat model in resource-limited countries. <b>Conclusions:</b> CIN2 is not a lesion to be treated automatically, but rather a paradigmatic model for personalized management. Integrating epidemiological and clinical data, supported by biomarkers, allows for reducing overtreatment without compromising oncological safety.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12524061/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299153","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":"Predictive Modeling of Central Precocious Puberty Using IGF-1 and IGFBP-3 Standard Deviation Scores.","authors":"Rihwa Choi, Gayoung Chun, Sung-Eun Cho, Sang Gon Lee","doi":"10.3390/diagnostics15192508","DOIUrl":"10.3390/diagnostics15192508","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Central precocious puberty (CPP) is diagnosed via gonadotropin-releasing hormone (GnRH) stimulation testing, which can be burdensome in pediatric settings. This study evaluated the utility of baseline hormonal markers-particularly insulin-like growth fac-tor 1 (IGF-1) and IGF-binding protein 3 (IGFBP-3)-as auxiliary tools for CPP diagnosis in Korean children. <b>Methods</b>: We retrospectively analyzed patients who underwent GnRH stimulation testing. Baseline LH, FSH, IGF-1, and IGFBP-3 levels were assessed, along with standard deviation scores (SDS) calculated using two different reference intervals. Multivariable logistic regression was performed to improve diagnostic accuracy. Performance was evaluated using area under the curve (AUC) values from receiver operating characteristic (ROC) analyses, stratified by sex. <b>Results</b>: Among 2464 Korean children (2025 girls and 439 boys), CPP diagnosis rates were 54.2% in girls and 65.6% in boys. Among baseline markers, FSH showed the highest AUCs using raw values with sex-specific cutoffs (AUC = 0.767 in girls and 0.895 in boys). Although IGF-1 SDS and IGFBP-3 SDS showed AUCs < 0.7 when used alone, predictive models incorporating these SDS values yielded higher performance (AUC = 0.800 in girls and 0.920 in boys. <b>Conclusions</b>: SDS-based IGF-1 and IGFBP-3 enhance CPP diagnosis when used in predictive models, emphasizing the need for sex-specific interpretation and standardized reference intervals in real-world clinical practice.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12524067/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299090","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 Association Between Naples Prognostic Score and Coronary Collateral Circulation in Patients with Chronic Coronary Total Occlusion.","authors":"Abdullah Tunçez, Sevil Bütün, Kadri Murat Gürses, Hüseyin Tezcan, Aslıhan Merve Toprak Su, Burak Erdoğan, Mustafa Kırmızıgül, Muhammed Ulvi Yalçın, Yasin Özen, Kenan Demir, Nazif Aygül, Bülent Behlül Altunkeser","doi":"10.3390/diagnostics15192500","DOIUrl":"10.3390/diagnostics15192500","url":null,"abstract":"<p><p><b>Background:</b> Coronary collateral circulation (CCC) plays a crucial protective role in patients with chronic total occlusion (CTO), mitigating ischemia and improving long-term outcomes. However, the degree of collateral vessel development varies substantially among individuals. Systemic inflammatory and nutritional status may influence this variability. The Naples Prognostic Score (NPS) is a composite index reflecting these parameters, yet its relationship with CCC remains incompletely defined. <b>Methods:</b> We retrospectively analyzed 324 patients with angiographically confirmed CTO at Selçuk University Faculty of Medicine between 2014 and 2025. Coronary collaterals were graded using the Rentrop classification, and patients were categorized as having poor (grades 0-1) or good (grades 2-3) collaterals. The NPS was calculated using serum albumin, cholesterol, neutrophil-to-lymphocyte ratio, and lymphocyte-to-monocyte ratio. Baseline clinical and laboratory data were compared between groups. Univariate and multiple binary logistic regression analyses were performed to identify independent predictors of collateral development. <b>Results:</b> Of the 324 patients, 208 (64.2%) had poor and 116 (35.8%) had good collateral circulation. Patients with good collaterals had higher body mass index, HDL Cholesterol (HDL-C), and triglyceride levels, and significantly lower NPS values compared with those with poor collaterals (<i>p</i> < 0.05 for all). In multiple binary logistic regression analysis, HDL-C (OR 1.035; 95% CI 1.008-1.063; <i>p</i> = 0.011) and NPS (OR 0.226; 95% CI 0.130-0.393; <i>p</i> < 0.001) emerged as independent predictors of well-developed collaterals. <b>Conclusions:</b> Both NPS and HDL-C are independently associated with the degree of coronary collateral circulation in CTO patients. These findings highlight the interplay between systemic inflammation, nutritional status, lipid metabolism, and vascular adaptation. As simple and routinely available measures, NPS and HDL-C may serve as practical tools for risk stratification and identifying patients at risk of inadequate collateral formation. Prospective studies with functional assessments of collateral flow are warranted to confirm these associations and explore potential therapeutic interventions.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523551/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299134","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":"Molecular Characterization of Wilson's Disease in Liver Transplant Patients: A Five-Year Single-Center Experience in Iran.","authors":"Zahra Beyzaei, Melika Majed, Seyed Mohsen Dehghani, Mohammad Hadi Imanieh, Ali Khazaee, Bita Geramizadeh, Ralf Weiskirchen","doi":"10.3390/diagnostics15192504","DOIUrl":"10.3390/diagnostics15192504","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Wilson's disease (WD) is an autosomal recessive disorder characterized by pathological copper accumulation, primarily in the liver and brain. Severe hepatic involvement can be effectively treated with liver transplantation (LT). Geographic variation in <i>ATP7B</i> mutations suggests the presence of regional patterns that may impact disease presentation and management. This study aims to investigate the genetic basis of WD in patients from a major LT center in Iran. <b>Methods</b>: A retrospective analysis was conducted on clinical, biochemical, and pathological data from patients suspected of WD who underwent evaluation for LT between May 2020 and June 2025 at Shiraz University of Medical Sciences. Genetic testing was carried out on 20 patients at the Shiraz Transplant Research Center (STRC). Direct mutation analysis of <i>ATP7B</i> was performed for all patients, and the results correlated with clinical and demographic information. <b>Results</b>: In total, 20 WD patients who underwent liver transplantation (15 males, 5 females) carried 25 pathogenic or likely pathogenic <i>ATP7B</i> variants, 21 of which were previously unreported. Fifteen patients were homozygous, and five were compound-heterozygous; all heterozygous combinations occurred in the offspring of second-degree consanguineous unions. Recurrent changes included p.L549V, p.V872E, and p.P992S/L, while two nonsense variants (p.E1293X, p.R1319X) predicted truncated proteins. Variants were distributed across copper-binding, transmembrane, phosphorylation, and ATP-binding domains, and in silico AlphaMissense scores indicate damaging effects for most novel substitutions. Post-LT follow-up showed biochemical normalization in the majority of recipients, with five deaths recorded during the study period. <b>Conclusions</b>: This single-center Iranian study reveals a highly heterogeneous <i>ATP7B</i> mutational landscape with a large proportion of novel population-specific variants and underscores the benefit of comprehensive gene sequencing for timely WD diagnosis and family counseling, particularly in regions with prevalent consanguinity.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523244/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299106","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":"Transarterial Embolization for Refractory Non-Cervical-Origin Interscapular Pain Following Ultrasound-Guided Injection: A Retrospective Feasibility Study.","authors":"Yu-Han Huang, Chia-Wei Chang, Jui-Yuan Chen, Chia-Shiang Lin, Chun-Wei Lin, Ping-Sheng Lu, Neng-Yu Chiu, Keng-Wei Liang","doi":"10.3390/diagnostics15192496","DOIUrl":"10.3390/diagnostics15192496","url":null,"abstract":"<p><p><b>Objective</b>: Chronic non-cervical-origin interscapular pain remains challenging to treat when refractory to conservative management and ultrasound-guided injections. This retrospective feasibility study aimed to assess the feasibility, procedural practicality, safety, and preliminary clinical outcomes of transarterial embolization (TAE) as a salvage therapy in this patient population. <b>Methods</b>: This single-center retrospective study included 20 patients with chronic interscapular pain (Numeric Rating Scale [NRS] score ≥5 for >3 months) who initially underwent ultrasound-guided injection therapy. Patients who experienced inadequate pain relief after 3 months (<i>n</i> = 10) proceeded to TAE, while the remaining 10 patients with sufficient relief formed the comparison group. TAE primarily targeted the transverse cervical artery using imipenem/cilastatin sodium as the embolic agent. Pain outcomes were assessed using NRS scores at 1, 3, and 6 months post-procedure. The primary outcome was pain reduction (≥50% decrease in NRS score), with secondary outcomes including technical success, medication use, and safety assessment. <b>Results</b>: The mean baseline NRS score for all patients was 6.5 ± 1.4, which decreased to 3.4 ± 2.0 at 1 month and 3.9 ± 2.5 at 3 months post-injection (<i>p</i> < 0.001). In the TAE group, the NRS score decreased from 7.4 ± 1.4 to 5.1 ± 1.1 at 1 month and 6.0 ± 1.4 at 3 months, indicating inadequate pain relief. In contrast, the injection-only group showed significant improvement, with NRS scores decreasing from 5.6 ± 0.5 to 1.6 ± 0.5 at 1 month and 1.7 ± 0.7 at 3 months (<i>p</i> < 0.001). The reduction in NRS scores was significantly less in the TAE group compared with the injection-only group (-2.2 vs. -4.0 and -28.7% vs. -71.4% at 1 month; -1.4 vs. -3.9 and -18.2% vs. -69.7% at 3 months; all <i>p</i> ≤ 0.001). Following TAE, the mean NRS score further decreased to 2.1 ± 0.7, 2.0 ± 1.1, and 1.9 ± 1.2 at 1, 3, and 6 months, respectively (<i>p</i> < 0.001), with clinical success rates of 90%, 100%, and 90% at these respective time points. At the final follow-up, the percentage of NRS score reduction was comparable between the TAE and injection-only groups (-74.8% vs. -69.7%, <i>p</i> = 0.397). No severe or life-threatening adverse events were observed; only self-limited adverse events were reported. <b>Conclusions</b>: In this retrospective feasibility study, TAE appeared safe and effective as a salvage therapy for patients with refractory non-cervical-origin interscapular pain unresponsive to injection therapy. Further prospective, randomized studies are needed to validate these findings, refine patient selection criteria, and optimize treatment outcomes.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523267/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299112","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":"Deep Learning-Based Mpox Skin Lesion Detection and Real-Time Monitoring in a Smart Healthcare System.","authors":"Huda Alghoraibi, Nuha Alqurashi, Sarah Alotaibi, Renad Alkhudaydi, Bdoor Aldajani, Joud Batawil, Lubna Alqurashi, Azza Althagafi, Maha A Thafar","doi":"10.3390/diagnostics15192505","DOIUrl":"10.3390/diagnostics15192505","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Mpox, a viral disease marked by distinctive skin lesions, has emerged as a global health concern, underscoring the need for scalable, accessible, and accurate diagnostic tools to strengthen public health responses. This study introduces ITMA'INN, an AI-driven healthcare system designed to detect Mpox from skin lesion images using advanced deep learning. <b>Methods:</b> The system integrates three key components: an AI model pipeline, a cross-platform mobile application, and a real-time public health dashboard. We leveraged transfer learning on publicly available datasets to evaluate pretrained deep learning models. <b>Results</b>: For binary classification (Mpox vs. non-Mpox), Vision Transformer, MobileViT, Transformer-in-Transformer, and VGG16 achieved peak performance, each with 97.8% accuracy and F1-score. For multiclass classification (Mpox, chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy skin), ResNetViT and ViT Hybrid models attained 92% accuracy (F1-scores: 92.24% and 92.19%, respectively). The lightweight MobileViT was deployed in a mobile app that enables users to analyze skin lesions, track symptoms, and locate nearby healthcare centers via GPS. Complementing this, the dashboard equips health authorities with real-time case monitoring, symptom trend analysis, and intervention guidance. <b>Conclusions</b>: By bridging AI diagnostics with mobile technology and real-time analytics, ITMA'INN advances responsive healthcare infrastructure in smart cities, contributing to the future of proactive public health management.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523520/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299100","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":"Demographic, Morphological, and Histopathological Characteristics of Melanoma and Nevi: Insights from Statistical Analysis and Machine Learning Models.","authors":"Blagjica Lazarova, Gordana Petrushevska, Zdenka Stojanovska, Stephen C Mullins","doi":"10.3390/diagnostics15192499","DOIUrl":"10.3390/diagnostics15192499","url":null,"abstract":"<p><p><b>Background:</b> Early and accurate differentiation between melanomas and benign nevi is essential for making proper clinical decisions. This study aimed to identify clinical, morphological, and histopathological variables most strongly associated with melanoma, using both statistical and machine learning approaches. <b>Methods</b>: This study evaluated 184 melanocytic lesions using clinical, morphological, and histopathological parameters. Univariable analyses were performed in XLStat statistical software, version 2014.5.03, while multivariable machine learning models were developed in Jamovi (version 2.4). Five supervised algorithms (random forest, partial least squares, elastic net regression, conditional inference trees, and k-nearest neighbors) were compared using repeated cross-validation, with performance evaluated by accuracy, Kappa, sensitivity, specificity, F1 score, and calibration. <b>Results</b>: Univariable analysis identified significant differences between melanomas and nevi in age, horizontal diameter, gender, lesion location, and selected histopathological features (cytological and extracellular matrix changes, epidermal interactions). However, several associations weakened in multivariable analysis due to collinearity and overlapping effects. Using glmnet, the most influential independent predictors were cytological changes, horizontal diameter, epidermal interactions, and extracellular matrix features, alongside age, gender, and lesion location. The model achieved high discrimination (AUC = 0.97, 95% CI: 0.93-0.99) and accuracy (training: 95.3%; test: 92.6%), confirming robustness. <b>Conclusions</b>: Structured demographic, morphological, and histopathological data-particularly age, lesion size, cytological and extracellular matrix changes, and epidermal interactions-can effectively support classification of melanocytic lesions. Machine learning approaches (the glmnet model in our study) provide a reliable framework to evaluate such predictors and offer practical diagnostic support in dermatopathology.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12524229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299136","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":"From Heart to Abdominal Aorta: Integrating Multi-Modal Cardiac Imaging Derived Haemodynamic Biomarkers for Abdominal Aortic Aneurysm Risk Stratification, Surveillance, Pre-Operative Assessment and Therapeutic Decision-Making.","authors":"Rafic Ramses, Obiekezie Agu","doi":"10.3390/diagnostics15192497","DOIUrl":"10.3390/diagnostics15192497","url":null,"abstract":"<p><p>Recent advances in cardiovascular imaging have revolutionized the assessment and management of abdominal aortic aneurysm (AAA) through the integration of sophisticated haemodynamic biomarkers. This comprehensive review evaluates the clinical utility and mechanistic significance of multiple biomarkers in AAA pathogenesis, progression, and treatment outcomes. Advanced cardiac imaging modalities, including four-dimensional magnetic resonance imaging (4D MRI), computational fluid dynamics (CFD), and specialized echocardiography, enable precise quantification of critical haemodynamic parameters. Wall shear stress (WSS) emerges as a fundamental biomarker, with values below 0.4 Pa indicating pathological conditions and increased risk for aneurysm progression. Time-averaged wall shear stress (TAWSS), typically maintaining values above 1.5 Pa in healthy arterial segments, provides crucial information about sustained haemodynamic forces affecting the vessel wall. The oscillatory shear index (OSI), ranging from 0 (unidirectional flow) to 0.5 (purely oscillatory flow), quantifies directional changes in WSS during cardiac cycles. In AAA, elevated OSI values between 0.3 and 0.4 correlate with disturbed flow patterns and accelerated disease progression. The relative residence time (RRT), combining TAWSS and OSI, identifies regions prone to thrombosis, with values exceeding 2-3 Pa^-1 indicating increased risk. The endothelial cell activation potential (ECAP), calculated as OSI/TAWSS, serves as an integrated metric for endothelial dysfunction risk, with values above 0.2-0.3 Pa^-1 suggesting increased inflammatory activity. Additional biomarkers include the volumetric perivascular characterization index (VPCI), which assesses vessel wall inflammation through perivascular tissue analysis, and pulse wave velocity (PWV), measuring arterial stiffness. Central aortic systolic pressure and the aortic augmentation index provide essential information about cardiovascular load and arterial compliance. Novel parameters such as particle residence time, flow stagnation, and recirculation zones offer detailed insights into local haemodynamics and potential complications. Implementation challenges include the need for specialized equipment, standardized protocols, and expertise in data interpretation. However, the potential for improved patient outcomes through more precise risk stratification and personalized treatment planning justifies continued development and validation of these advanced assessment tools.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12523306/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145299076","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}