Maria Vaida

Dr. Maria Vaida

orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
9 January 2026 in Frontiers in Artificial Intelligence
Verified
Journal Article
Open access
PDF file
MVMaria Vaida
Maria Vaida
ZHZiyuan Huang
Ziyuan Huang
Graph Neural Networks (GNNs) have transformed multimodal healthcare data integration by capturing complex, non-Euclidean relationships across diverse sources such as electronic health records, medical imaging, genomic profiles, and clinical notes. This review synthesizes GNN applications in healthcare, highlighting their impact on clinical decision-making through multimodal integration, advanced fusion strategies, and attention mechanisms. Key applications include drug interaction and discovery, cancer detection and prognosis, clinical status prediction, infectious disease modeling, genomics, and the diagnosis of mental health and neurological disorders. Various GNN architectures demonstrate consistent applications in modeling both intra- and intermodal relationships. GNN architectures, such as Graph Convolutional Networks and Graph Attention Networks, are integrated with Convolutional Neural Networks (CNNs), transformer-based models, temporal encoders, and optimization algorithms to facilitate robust multimodal integration. Early, intermediate, late, and hybrid fusion strategies, enhanced by attention mechanisms like multi-head attention, enable dynamic prioritization of critical relationships, improving accuracy and interpretability. However, challenges remain, including data heterogeneity, computational demands, and the need for greater interpretability. Addressing these challenges presents opportunities to advance GNN adoption in medicine through scalable, transparent GNN models.

Verified
Journal Article
Open access
PDF file
MVMaria Vaida
Maria Vaida
JWJiawen Wu
Jiawen Wu
EHEyad Akram Himdiat
Eyad Akram Himdiat
JHJean-Francois Haince
Jean-Francois Haince
RBRashid Ahmed Bux
Rashid Ahmed Bux
WFW. Rand Ford
W. Rand Ford
Lung cancer remains the leading cause of cancer-related mortality worldwide, with early detection critical for improving survival rates, yet conventional methods like CT scans often yield high false-positive rates. This study introduces M-GNN, a graph neural network framework leveraging GraphSAGE, to enhance early lung cancer detection through metabolomics. We constructed a heterogeneous graph integrating metabolomics data from 800 plasma samples (586 cases, 214 controls) with demographic features and Human Metabolome Database annotations, employing GraphSAGE and GAT layers for inductive learning on 107 metabolites, pathways, and diseases. M-GNN achieved a test accuracy of 89% and an ROC-AUC of 0.92, with rapid convergence within 400 epochs and robust performance across ten random seeds; key predictors included age, height, choline, Valine, Betaine, and Fumaric Acid, reflecting smoking and metabolic dysregulation. This framework offers a scalable, interpretable tool for precision oncology, surpassing benchmarks by capturing complex biological interactions, though limitations like synthetic data biases and computational demands suggest future validation with real-world cohorts and optimization. M-GNN advances lung cancer screening, promising improved survival through early detection and personalized strategies.

18 August 2025 in IEEE Access
Verified
Journal Article
Open access
ZHZiyuan Huang
Ziyuan Huang
VSVishaldeep Kaur Sekhon
Vishaldeep Kaur Sekhon
RSRoozbeh Sadeghian
Roozbeh Sadeghian
MVMaria Vaida
Maria Vaida
CJCynthia Jo
Cynthia Jo
JHJohn P. Haran
John P. Haran
Alzheimer’s Disease Analysis Model Generation 1 (ADAM-1) is a multi-agent reasoning large language model (LLM) framework designed to integrate and analyze multimodal data, including microbiome profiles, clinical datasets, and external knowledge bases, to enhance the understanding and classification of Alzheimer’s disease (AD). By leveraging the agentic system with LLM, ADAM-1 produces insights from diverse data sources and contextualizes the findings with literature-driven evidence. A comparative evaluation with XGBoost revealed a significantly improved mean F1 score and significantly reduced variance for ADAM-1, highlighting its robustness and consistency, particularly when utilizing human biological data. Although currently tailored for binary classification tasks with two data modalities, future iterations will aim to incorporate additional data types, such as neuroimaging and peripheral biomarkers, and expand them to predict disease progression, thereby broadening ADAM-1’s scalability and applicability in AD research and diagnostic applications.

Verified
Journal Article
Open access
PDF file
MVMaria Vaida
Maria Vaida
KAKamala Arumalla
Kamala Arumalla
PTPavan Kumar Tatikonda
Pavan Kumar Tatikonda
Bharadwaj PopuriBharadwaj Popuri
Bharadwaj Popuri
RBRashid Ahmed Bux
Rashid Ahmed Bux
WFW. Randolph Ford
W. Randolph Ford
Breast cancer remains a major public health concern, and early detection is crucial for improving survival rates. Metabolomics offers the potential to develop non-invasive screening and diagnostic tools based on metabolic biomarkers. However, the inherent complexity of metabolomic datasets and the high dimensionality of biomarkers complicates the identification of diagnostically relevant features, with multiple studies demonstrating limited consensus on the specific metabolites involved. Unlike previous studies that rely on singular feature selection techniques such as Partial Least Square (PLS) or LASSO regression, this research combines supervised and unsupervised machine learning methods with random sampling strategies, offering a more robust and interpretable approach to feature selection. This study aimed to identify a parsimonious and robust set of biomarkers for breast cancer diagnosis using metabolomics data. Plasma samples from 185 breast cancer patients and 53 controls (from the Cooperative Human Tissue Network, USA) were analyzed. This study also overcomes the common issue of dataset imbalance by using propensity score matching (PSM), which ensures reliable comparisons between cancer and control groups. We employed Univariate Naïve Bayes, L2-regularized Support Vector Classifier (SVC), Principal Component Analysis (PCA), and feature engineering techniques to refine and select the most informative features. Our best-performing feature set comprised 11 biomarkers, including 9 metabolites (SM(OH) C22:2, SM C18:0, C0, C3OH, C14:2OH, C16:2OH, LysoPC a C18:1, PC aa C36:0 and Asparagine), a metabolite ratio (Kynurenine-to-Tryptophan), and 1 demographic variable (Age), achieving an area under the ROC curve (AUC) of 98%. These results demonstrate the potential for a robust, cost-effective, and non-invasive breast cancer screening and diagnostic tool, offering significant clinical value for early detection and personalized patient management.

Verified
Journal Article
Open access
PDF file
KAKamala K. Arumalla
Kamala K. Arumalla
JHJean-Francois Haince
Jean-Francois Haince
RBRashid Ahmed Bux
Rashid Ahmed Bux
GHGUOYU HUANG
GUOYU HUANG
PTParamjit S Tappia
Paramjit S Tappia
MVMaria Vaida
Maria Vaida
Breast cancer is a global concern as a leading cause of death for women. Early and precise diagnosis can be vital in handling the disease efficiently. Breast cancer subtyping based on estrogen receptor (ER) status is crucial for determining prognosis and treatment. This study uses metabolomics data from plasma samples to detect metabolite biomarkers that could distinguish ER-positive from ER-negative breast cancers in a non-invasive manner. The dataset includes demographic information, ER status, and metabolite levels from 188 breast cancer patients and 73 healthy controls. Recursive Feature Elimination (RFE) with a Random Forest (RF) classifier identified an optimal subset of 30 features—29 biomarkers and age—that achieved the highest area under the curve (AUC). To address the class imbalance, Gaussian noise-based augmentation and Adaptive Synthetic Oversampling (ADASYN) were applied, ensuring balanced representation during training. Four machine learning (ML) algorithms—Random Forest, Support Vector Classifier (SVC), XGBoost, and Logistic Regression (LR)—were evaluated using grid search. The Random Forest classifier emerged as the top performer, achieving an AUC of 0.95 and an accuracy of 93%. These results suggest that ML has great promise for identifying specific metabolites linked to ER expression, paving the development of a novel analytical tool that can minimize current challenges in identifying ER status, and improve the precision of breast cancer subtyping.

30 April 2025 in Journal of Neurotrauma
Verified
Journal Article
Closed access
JBJames P. Barrett
James P. Barrett
TATaryn G. Aubrecht
Taryn G. Aubrecht
ASAidan Smith
Aidan Smith
MVMaria Vaida
Maria Vaida
RHRebecca J. Henry
Rebecca J. Henry
BSBogdan A. Stoica
Bogdan A. Stoica
Traumatic brain injury (TBI) causes complex, time-dependent molecular and cellular responses, which include adaptive changes that promote repair and recovery, as well as maladaptive processes such as chronic inflammation that contribute to chronic neurodegeneration and neurological dysfunction. Hormesis is a well-established biological phenomenon in which exposure to low-dose toxins or stressors results in protective responses to subsequent higher-level stressors or insults. Hormetic stimuli show a characteristic U-shaped or inverted J-shaped dose–response curve, as well as being time and exposure-frequency dependent, similar to pre-conditioning and post-conditioning actions. Voluntary exercise interventions, before or after injury, appear to follow these general hormetic principles. But the molecular alterations associated with exercise interventions or more general hormetic responses have received only limited attention. In this study, we used a well-characterized mouse TBI model to assess the effects of different post-conditioning exercise-intervention paradigms on diverse molecular pathways, including neuroinflammation regulators, and post-traumatic neurological deficits. We generated high-throughput gene expression data and associated molecular pathway analyses to assess the potential molecular mechanisms associated with time- and duration-dependent voluntary exercise intervention, as well as time after treatment. Importantly, we also used newer analytical methods to more broadly assess the impact of exercise on diverse molecular pathways. TBI caused long-term changes in multiple neuroinflammation markers and chronic cognitive dysfunction. Notably, all delayed, post-conditioning exercise interventions reduced post-traumatic neuroinflammation and/or attenuated the related cognitive changes, albeit with different pathway specificity and effects magnitude. Exercise comprehensively reversed injury-associated effects in the hippocampus across both activated inflammatory and inhibited neuronal pathways, consistent with a return toward the noninjured, homeostatic state. In contrast, the cortex showed a less consistent pattern with more limited attenuation of inflammatory pathway activation and an amplification in the injury-dependent inhibition of select noninflammatory pathways, indicating less effective and potentially detrimental responses to exercise. Exercise intervention beginning 2 weeks after injury and lasting 2 weeks was less effective than exercise continuing for 4 weeks. Exercise initiated at a more delayed timepoint of 6 weeks after injury and continuing for 4 weeks was more effective than that during the acute phase. The delayed paradigm was also more effective than exercise initiated at 10 weeks after injury and continuing for 8 weeks, consistent with hormetic responses in other models and species. Overall, our study delineates regional and interventional parameters, as well as related molecular pathway changes, associated with post-conditioning exercise treatment, which may help inform future translational interventional strategies.