Dimitrios Galiatsatos

Dr. Dimitrios Galiatsatos

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
22 May 2026 in Information
Verified
Journal Article
Open access
PDF file
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
Panagiota GaliatsatouPanagiota Galiatsatou
Panagiota Galiatsatou
Predictive analytics has become increasingly important in educational decision-making, supporting at-risk identification and adaptive tutoring. The accurate early prediction of school achievement can enable timely intervention. Using the Math Students dataset, which contains data on students from two Portuguese secondary schools, we model three categorical outcomes derived from the students’ final grade, namely the final grade level (low, medium, high), its qualitative evaluation (fail, satisfactory, good, excellent), and the final pass/fail outcome. After preprocessing, three filter methods—Correlation-Based Feature Subset Selection (CFS), Correlation Attribute Evaluation (CorrEval), and Information Gain (InfoGain)—are applied to reduce the dimensionality of the datasets. Nine classifiers (Naive Bayes, Logistic, MLP, SMO, IBk, Bagging, J48, Random Forest, Random Tree) are evaluated using ten-fold cross-validation in the Waikato Environment for Knowledge Analysis (Weka) platform. Random Forest with InfoGain achieves 90.7% accuracy on the three-band task, while Bagging with InfoGain achieves 92.5% on the binary pass/fail outcome, outperforming benchmarks in prior Educational Data Mining (EDM) studies. Results confirm that prior academic performance indicators (first- and second-period grades) and failure history dominate predictive power and contribute substantially to the success of ensemble models, particularly when paired with feature selection methods that reduce noise and highlight relevant attributes.

5 November 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
Panagiota GaliatsatouPanagiota Galiatsatou
Panagiota Galiatsatou
Unsupervised feature selection is difficult when relevance must be inferred without labels, and redundancy, outliers, and sample-localized geometry can distort marginal criteria. This study presents Geometry-Supported Residual Feature Selection (GSR-FS), a fully label-blind algorithm and open-source Python library that represents each feature by its contribution to pairwise sample geometry. Structural relevance is quantified by Bhattacharyya affinity to the aggregate geometry of the remaining features, calibrated against within-feature permutations, and downweighted by an entropy-based Sample-Geometric Coverage term. A non-negative residual reconstruction criterion then penalizes candidates whose geometry is already represented by previously selected features. Automatic selection uses a feature-wise max-null permutation distribution, whereas fixed-cardinality selection follows the same greedy score without using target information. The released library additionally provides balanced pair subsampling, numerically equivalent residual solvers, source-integrity audits, publication guardrails, and diagnostic structural-group outputs. In a source-audited 30-dataset evidence panel, 29 datasets supported complete five-method comparisons. Mean balanced accuracy was 0.6031 for GSR-FS, compared with 0.6019 for SPEC, 0.5970 for MCFS, 0.5892 for MaxVariance, and 0.5810 for Laplacian Score. The Friedman test was not significant (p = 0.488), and no Holm-corrected pairwise comparison was significant. Additional robustness analyses showed that automatic GSR-FS achieved mean balanced accuracy of 0.6216 compared with 0.6069 for fixed-cardinality GSR-FS on the 30-dataset panel, without a significant paired difference (p = 0.1215). Further validation showed high-precision independent-null calibration at α = 0.05, with 25 of 500 datasets producing a non-empty subset (empirical rate of 0.050; exact 95% CI of 0.0326–0.0729). Controlled dependent-feature experiments showed that GSR-FS combined higher latent-group coverage with lower redundancy than Laplacian Score and MCFS in the examined structural-recovery scenarios, while a recent FGMRW-UFS comparator showed limited recovery under this specific criterion. An engineering stress test was completed successfully through 20,000 candidate features under explicitly capped pair and permutation budgets. Controlled nuisance simulations further confirmed that structurally coherent but target-independent variation can be selected, emphasizing that GSR-FS estimates internal structural relevance rather than guaranteed target-specific relevance. These results support GSR-FS as a reproducible, structurally motivated alternative rather than a statistically superior replacement.

25 August 2026 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
AGArgyrios Ginoudis
Argyrios Ginoudis
DPDimitra Pardali
Dimitra Pardali
EVEleni Vagdatli
Eleni Vagdatli
Evgenia LymperakiEvgenia Lymperaki
Evgenia Lymperaki
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
Early identification of individuals with abnormal glucose metabolism is essential for timely intervention and prevention of diabetes-related complications. Routine laboratory testing generates large amounts of clinical data that may support automated glycemic classification through machine learning approaches. This study aimed to develop and evaluate a machine learning framework for the classification of HbA1c-defined glycemic status using routinely available clinical laboratory features. A retrospective dataset of 1434 individuals with available glycemic measurements was analyzed. Participants were categorized into HbA1c-defined normoglycemic, prediabetic-range, or diabetic-range groups. Three concurrent classification tasks were examined: HbA1c-defined dysglycemia classification, diabetic-range HbA1c classification, and multiclass HbA1c-defined glycemic-status classification. Demographic, biochemical, and hematological variables were used as predictors. Data preprocessing included missing-value handling, feature filtering, and outlier treatment. Several supervised learning algorithms were evaluated, including Logistic Regression, Random Forest, Gradient Boosting, Support Vector Machine, and Multinomial Logistic Regression. Model performance was assessed using train–test validation and cross-validation with accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve. For dysglycemia, Gradient Boosting achieved the highest AUC (0.848), while Random Forest achieved the highest accuracy (0.801) and sensitivity (0.908). For diabetic-range HbA1c, Random Forest achieved the highest AUC (0.864), whereas SVM achieved the highest accuracy (0.794). In multiclass classification, Random Forest achieved the highest accuracy (0.610), while Gradient Boosting achieved the highest macro-AUC (0.796) and macro-F1 score (0.603). Pairwise comparisons showed no statistically significant superiority of any classifier after Holm correction. Clinical-baseline and ablation analyses demonstrated that fasting glucose accounted for a substantial proportion of discrimination, with only modest incremental value from additional laboratory variables. These findings support cautious interpretation of routine laboratory-based classification models pending further validation and clinical-utility assessment.

9 September 2026 in Antioxidants
Verified
Journal Article
Open access
PDF file
AGArgyrios Ginoudis
Argyrios Ginoudis
DPDimitra Pardali
Dimitra Pardali
MMMathios E. Mylonakis
Mathios E. Mylonakis
Serafeim C. ChaintoutisSerafeim C. Chaintoutis
Serafeim C. Chaintoutis
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
Zoe PolizopoulouZoe Polizopoulou
Zoe Polizopoulou
Canine mast cell tumors (MCTs) exhibit heterogeneous biological behavior and provide a clinically relevant setting in which relationships between tumor phenotype and systemic redox homeostasis can be investigated. This exploratory prospective cohort study evaluated complementary circulating redox-related biomarkers representing hydroperoxide-derived oxidant products, antioxidant capacity, lipid peroxidation-related products, and oxidative DNA damage, and examined their associations with clinicopathological features of canine MCTs. Sixty-seven dogs with cytologically and histologically confirmed cutaneous or subcutaneous MCTs were included. Clinical staging was performed using cytological evaluation of lymph nodes, liver and spleen, and excised tumors were classified according to the Patnaik and Kiupel systems. Proliferative activity was assessed using Ki-67, and surgically excised lymph nodes were classified according to the Weishaar HN system. Serum reactive oxygen metabolites (d-ROMs), malondialdehyde (MDA), 8-hydroxy-2′-deoxyguanosine (8-OHdG) and antioxidant capacity using the OXY-adsorbent test were measured before therapeutic intervention. In the unadjusted analysis, serum MDA concentrations were higher in dogs with Ki-67 >23 than in dogs with Ki-67 ≤23 (median 10.8 vs. 7.0 μmol/L; raw p = 0.0254); however, this comparison did not remain statistically significant after Bonferroni correction for the 12 formal inferential biomarker × clinicopathological comparisons (adjusted p = 0.3052). The estimated Hodges–Lehmann location shift was +3.00 μmol/L (unadjusted bootstrap 95% CI, 0.58–6.00). No evaluated biomarker–clinicopathological association remained statistically significant after multiplicity adjustment. The observed MDA–Ki-67 pattern should therefore be regarded as exploratory and hypothesis-generating rather than as evidence of established prognostic or clinical utility. Long-term data on recurrence, progression, and survival were not available; therefore, prognostic utility could not be evaluated. Larger prospective studies incorporating longitudinal outcomes are warranted.

1 January 2013
Verified
Journal Article
Closed access
GAGeorge Anastassopoulos
George Anastassopoulos
Adam V. AdamopoulosAdam V. Adamopoulos
Adam V. Adamopoulos
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
GDGeorgios Drosos
Georgios Drosos

5 July 2026 in Geohazards
Verified
Journal Article
Open access
PDF file
DMDimitrios Malamataris
Dimitrios Malamataris
FGFilippos Ganoulis
Filippos Ganoulis
Panagiota GaliatsatouPanagiota Galiatsatou
Panagiota Galiatsatou
Iraklis NikoletosIraklis Nikoletos
Iraklis Nikoletos
HPHaris Prapas
Haris Prapas
DGDimitrios Galiatsatos
Dimitrios Galiatsatos
Land Use and Land Cover (LULC) change is widely acknowledged as a pivotal driver of environmental change, exerting an escalating influence on surface hydrological processes. The accelerating pace of LULC alterations in response to burgeoning human populations underscores the pressing need for a comprehensive evaluation of their ramifications on surface runoff dynamics. This study investigates the impacts of LULC changes on flood behavior in a Mediterranean watershed in Crete, Greece (Geropotamos watershed). LULC data spanning the years 1990, 2006, and 2018 were procured from the European CORINE Land Cover database at a refined spatial resolution. The HEC-HMS hydrological model is employed to simulate peak discharge and associated hydrograph characteristics under varying recurrence intervals. Subsequently, selected river segments within the studied catchments undergo hydrodynamic flood modelling using the HEC-RAS hydraulic model. Flood depth maps are generated to illustrate the evolution of inundated areas relative to LULC change. The overarching objective of this research is to furnish a comprehensive understanding of how spatiotemporal variations in land use and land cover in-fluence flood characteristics, thereby facilitating informed decision making for sustainable planning.