Melania Veronica Ardelean

Dr. Melania Veronica Ardelean


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2024 in Medicina
Verified
Journal Article
Open access
PDF file
Roxana BuzasRoxana Buzas
Roxana Buzas
PCPaul Gabriel Ciubotaru
Paul Gabriel Ciubotaru
AFAlexandra Corina Faur
Alexandra Corina Faur
MPMarius Preda
Marius Preda
MAMelania Veronica Ardelean
Melania Veronica Ardelean
MPMihaela-Diana Popa
Mihaela-Diana Popa
Background and Objectives: Heart failure is associated with high morbidity and mortality and linked with several pre-existing health conditions and risk factors. Early detection and prompt management in heart failure improves patient outcomes. Liver involvement is associated with heart failure disease progression, and hence liver biomarkers and liver fibrosis may have a prognostic impact. Several blood test based markers and scoring systems estimate liver fibrosis and hence can be useful prognostic tools. Materials and Methods: We retrospectively analyzed a series of 303 patients with decompensated heart failure in a city in western Romania over a period of 6 months. Several biochemical parameters were measured, the FIB-4 score was estimated and echocardiography was performed. Results for targeted variables are presented using descriptive statistics. Patients were analyzed based on their LVEF categories. Statistical analysis was based on ANOVA one-way tests for continuous variables and Chi-square tests for categorical variables. Pairwise comparisons were performed based on Bonferroni adjusted significance tests. The correlations between FIB-4 score, LVEF and NT-pro BNP in patients with and without diabetes and hypertension were explored using Spearman’s correlation coefficient. Result: Age, gender, NYHA class, death, history of (h/o) type 2 diabetes mellitus (T2DM), h/o coronary artery disease (CAD), h/o arrhythmias, sodium, potassium, creatinine, eGFR, uric acid, NT-pro BNP, left atrial volume, LDL, HDL, and TG were analyzed by LVEF categories using ANOVA one-way tests, Chi-square tests, and Bonferroni correction comparisons. We found a strong statistically significant correlation between each of NT-pro BNP, left atrial volume, LDL, and HDL with the LVEF categories. Discussion: Early detection of cardiac dysfunction leads to better management in patients with cardiovascular risk factors including diabetes and hypertension. High LDL and low HDL levels contribute to a reduction in left ventricular (LV) function. Available literature suggests the FIB-4 score as superior to other non-invasive markers of fibrosis. It utilizes the patient’s age, platelet count, AST, and ALT, which can be available retrospectively, making it an easy and inexpensive tool. FIB-4 score has a few limitations. Conclusions: Our study has shown a statistically significant positive correlation between severity categories of LVEF and FIB-4 score for heart failure patients with and without diabetes, and for heart failure patients with or without hypertension. We propose the implementation of FIB-4 score as a prognostic tool for heart failure.

20 June 2024 in medRxiv
Verified
Preprint
Open access
PDF file
DBDiogen Babuc
Diogen Babuc
TITodor Ivașcu
Todor Ivașcu
MAMelania Veronica Ardelean
Melania Veronica Ardelean
Darian OnchisDarian Onchis
Darian Onchis
The third most prevalent cancer nowadays is colorectal cancer. Colonoscopy is an important procedure in the stage of detection of polyps’ malignancy because it helps in early identification and establishes effective therapy. This paper explores specific deep-learning architectures for the binary classification of colorectal polyps and considers the evaluation of their premalignancy risk. The main scope is to create a custom-based deep learning architecture that classifies adenomatous, hyperplastic, and serrated polyps’ samples into benign and premalignant based on images from the colonoscopic dataset. Each image’s output is modified through masked autoencoders which enhance the classification performance of the proposed model, called Bionnica . From the four evaluated state-of-the-art deep learning models (ZF NET, VGG-16, AlexNet, and ResNet-50), our experiments showed that ResNet-50 and ZF NET are most accurate (above 84%), with ResNet-50 excelling at indicating patients with premalignant colorectal polyps (above 92%). ZF NET is the fastest at handling 700 images. Our proposed deep learning model, Bionnica , is more performant than ZF NET and provides an efficient classification of colorectal polyps given its simple structure. The advantage of our model comes from the custom enhancement interpretability with a rule-based layer that guides the learning process and supports medical personnel in their decisions.

1 February 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
CFCatalin Vladut Ionut Feier
Catalin Vladut Ionut Feier
MAMelania Veronica Ardelean
Melania Veronica Ardelean
VGVasile Gaborean
Vasile Gaborean
Muntean CalinMuntean Calin
Muntean Calin
AFAlaviana Monique Faur
Alaviana Monique Faur
MMMarius-Sorin Murariu
Marius-Sorin Murariu
Background/Objectives: Acute calculous cholecystitis remains one of the most frequent surgical emergencies, ranging from mild inflammation to gangrenous forms associated with necrosis and sepsis. Early differentiation between these stages is essential for timely surgical management. This study aimed to evaluate the diagnostic and prognostic value of hematological inflammatory indices—the Aggregate Index of Systemic Inflammation (AISI), the Systemic Immune-Inflammation Index (SII), and the Systemic Inflammation Response Index (SIRI)—in predicting the gangrenous evolution of acute calculous cholecystitis. Methods: A retrospective study was conducted on 435 patients who underwent cholecystectomy between 2016 and 2024 at a tertiary care center. Patients were divided into gangrenous (n = 145) and chronic (n = 290) cholecystitis groups. Preoperative hematological parameters were used to calculate AISI, SII, and SIRI. After histopathological confirmation, patients with GC (gangrenous calculous cholecystitis) were identified, and for each case, two age- and sex-matched controls with chronic CC (calculous cholecystitis) were selected, maintaining a GC:CC ratio of 1:2. Preoperative hematological parameters were used to calculate AISI, SII, and SIRI. Results: All three indices were significantly higher in the gangrenous group (p < 0.001). Logistic regression identified SIRI as the strongest independent predictor of gangrenous cholecystitis (OR = 1.976, p < 0.001). ROC analysis demonstrated excellent discriminative capacity for all markers (AUC > 0.8), with SII achieving the highest diagnostic accuracy (AUC = 0.889, sensitivity 79.5%, specificity 86.3%). Conclusions: AISI, SII, and SIRI represent reliable, easily obtainable, and noninvasive biomarkers for assessing inflammatory severity and predicting gangrenous transformation in acute calculous cholecystitis. Their integration into preoperative evaluation could improve early risk stratification, surgical planning, and patient outcomes.

30 March 2026 in Life
Verified
Journal Article
Open access
PDF file
CFCatalin Vladut Ionut Feier
Catalin Vladut Ionut Feier
MAMelania Veronica Ardelean
Melania Veronica Ardelean
Muntean CalinMuntean Calin
Muntean Calin
AFAlaviana Monique Faur
Alaviana Monique Faur
VGVasile Gaborean
Vasile Gaborean
MMMarius-Sorin Murariu
Marius-Sorin Murariu
Background: Acute cholecystitis, a leading cause of urgent surgical intervention, poses challenges in predicting severity and operative complexity. This study characterized the immuno-inflammatory profile distinguishing acute from chronic cholecystitis and assessed whether blood-derived ratios—neutrophil-to-lymphocyte (NLR), monocyte-to-lymphocyte (MLR), and platelet-to-lymphocyte (PLR)—correlate with histologic severity and surgical difficulty. Methods: The study retrospectively analyzed 759 patients undergoing cholecystectomy from 2016 to 2024. Inflammatory indices from preoperative bloodwork were compared across histopathologic subtypes (catarrhal, phlegmonous, gangrenous), clinical features, and surgical outcomes, including conversion to open procedure. Logistic regression and ROC analyses identified predictors of acute inflammation and conversion. Results: Acute cholecystitis patients showed elevated NLR (7.0 vs. 3.1), MLR (0.44 vs. 0.26), and PLR (194 vs. 142; all p < 0.001). NLR was the only independent predictor of acute disease (OR = 1.29, 95% CI 1.203–1.390, p < 0.001), with superior discrimination (AUC = 0.806, cut-off = 3.56; sensitivity 73.1%, specificity 80.4%). NLR and PLR rose progressively from catarrhal to phlegmonous and gangrenous subtypes (p < 0.05), mirroring conversion rates (0% catarrhal, 3.2% phlegmonous, 10.5% gangrenous; p = 0.001). Conclusions: Routine hematologic ratios capture systemic immune activation in acute cholecystitis, reflecting histologic severity and operative risk. NLR, integrating innate and adaptive immune dynamics, offers a practical biomarker for preoperative risk stratification in acute care surgery.

22 September 2024 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
MAMelania Veronica Ardelean
Melania Veronica Ardelean
Roxana BuzasRoxana Buzas
Roxana Buzas
OAOvidiu Ardelean
Ovidiu Ardelean
MPMarius Preda
Marius Preda
SMStelian Morariu
Stelian Morariu
Nilima Rajpal KundnaniNilima Rajpal Kundnani
Nilima Rajpal Kundnani
Introduction: Upper gastrointestinal bleeding (UGIB) is among the most common causes of morbidity and mortality worldwide, accounting for major resource allocation and increasing incidence. This study aimed to evaluate the severity of non-variceal bleeding in patients at risk of bleeding through the use of NSAIDs, oral anticoagulants, and antiplatelet therapy. Material and Method: The study included 296 patients admitted in the Gastroenterology Department of the Municipal County Emergency University Hospital, Timisoara, between 01.01.2018 and 01.04.2020, and diagnosed via gastroscopy with non-variceal gastrointestinal bleeding. The patients were divided among four groups based on their use of different drugs known to induce UGIB, i.e., aspirin and clopidogrel, NOACs, NSAIDs, and anti-vitamin K drugs, respectively. Statistical analyses were performed based on ANOVA one-way tests for continuous variables and Chi-square tests for categorical variables with pairwise comparisons based on Bonferroni adjusted significance tests. Results: The results showed several parameters having statistical significance among the different groups of patients. Patients on NOACs had statistically significant lower hemoglobin levels, lower hematocrit values, lower erythrocytes, lower RDW and higher fibrinogen levels compared to patients on VKA. Discussion: Surprisingly, the results from our study suggest that the use of NOACs was associated with a higher risk of bleeding when compared to VKA, which differs from the existing literature. Conclusions: One of the important factors causing upper non-variceal bleeding can be iatrogenic, either due to antiplatelet drugs or anticoagulants, to which NSAID treatment is additionally associated for various reasons. In our study, the use of NOACs seemed to have a more severe bleeding spectrum with higher morbidity compared to VKA.

29 July 2025 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
DBDiogen Babuc
Diogen Babuc
TITodor Ivașcu
Todor Ivașcu
MAMelania Veronica Ardelean
Melania Veronica Ardelean
Darian OnchisDarian Onchis
Darian Onchis
The third most prevalent cancer nowadays is colorectal cancer. Colonoscopy is an important procedure in the stage of detection of polyps’ malignancy because it helps in early identification and establishes effective therapy. This paper explores specific deep-learning architectures for the binary classification of colorectal polyps and considers the evaluation of their premalignancy risk. The main scope is to create a custom-based deep learning architecture that classifies adenomatous, hyperplastic, and serrated polyps’ samples into benign and premalignant based on images from the colonoscopic dataset. Each image’s output is modified through masked autoencoders which enhance the classification performance of the proposed model, called Bionnica . From the four evaluated state-of-the-art deep learning models (ZF NET, VGG-16, AlexNet, and ResNet-50), our experiments showed that ResNet-50 and ZF NET are most accurate (above 84%), with ResNet-50 excelling at indicating patients with premalignant colorectal polyps (above 92%). ZF NET is the fastest at handling 700 images. Our proposed deep learning model, Bionnica , is more performant than ZF NET and provides an efficient classification of colorectal polyps given its simple structure. The advantage of our model comes from the custom enhancement interpretability with a rule-based layer that guides the learning process and supports medical personnel in their decisions.