Our Publications

Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability

Accurate risk stratification is essential for guiding treatment decisions and preventing over treatment of prostate cancer, which remains one of the most prevalent cancers among adult men. While the Gleason score, obtained from prostate biopsies, is routinely used to assess tumor aggressiveness, the biopsy procedure carries risks such as pain, infection, and, in some cases, serious complications such as sepsis. In this study, we proposed an artificial intelligence-based framework that integrates mRNA expression profiles with functional interaction networks to classify prostate cancer patients into low-, medium-, and high-risk groups defined by Gleason scores. The pipeline comprised five steps: (1) data collection from The Cancer Genome Atlas (TCGA), (2) preprocessing of gene expression data, (3) two-stage feature selection to identify informative biomarkers, (4) risk classification using a dual-branch graph neural network (GNN) that combines gene-gene interaction graphs with sample-level expression features, and (5) model interpretation using SHAP to quantify feature contributions. Differentially expressed genes were identified in the High (ASPN, GMNN, PEBP4, C2, KNCK17), Medium (C2, IGSF1, ASPN, CDKN3, AMH), and Low (TNMD, VWA5B2, ST6GALNAC5, CYP3A5, PHGR1) risk groups, underscoring the molecular heterogeneity of disease progression. On an indep…

Artificial Intelligence in Autism Spectrum Disorder Diagnosis: A Scoping Review of Face, Voice, and Text Analysis Methods

Background

Autism is a complex neurodevelopmental condition affecting social interaction and behavior. Traditional diagnostic methods, relying on observational techniques and interviews conducted by trained professionals, remain the gold standard for ASD diagnosis. However, these methods can be time-consuming and may be influenced by subjective factors. Recent advancements in artificial intelligence (AI) offer promising approaches to augment existing methods, potentially enhancing efficiency and providing additional objective data through facial, vocal, and textual analysis.

Objective

The objective of this study was to conduct a comprehensive review of artificial intelligence applications in autism spectrum disorder (ASD) diagnosis, specifically focusing on facial, vocal, and textual analysis methods.

Methods

A comprehensive search was conducted in PubMed, Web of Science, Scopus, and Google Scholar. The findings were reported in accordance with the PRISMA checklist. Data were collated and summarized, and results were reported qualitatively, adopting a narrative synthesis approach.

Results

In facial image analysis, deep learning algorithms demonstrated high accuracy in identifying autism-related …

X-ray Coronary Angiogram images and SYNTAX score to develop Machine-Learning algorithms for CHD Diagnosis

Coronary Heart Disease (CHD) is becoming a leading cause of death worldwide. To assess coronary artery narrowing or stenosis, doctors use coronary angiography, which is considered the gold-standard method. Interventional cardiologists rely on angiography to decide on the best course of treatment for CHD, such as revascularization with bypass surgery, coronary stents, or medication. However, angiography has some issues, including operator bias, inter-observer variability, and poor reproducibility. The automated interpretation of coronary angiography is yet to be developed, and these tasks can only be performed by highly specialized physicians. Developing automated angiogram interpretation and coronary artery stenosis estimation using Artificial Intelligence (AI) approaches requires a large dataset of X-ray angiography images that include clinical information. We have collected 231 X-ray images of heart vessels, along with the necessary angiographic variables, including the SYNTAX score, to support the advancement of research on CHD-related machine learning and data mining algorithms. We hope that this dataset will ultimately contribute to advances in clinical diagnosis of CHD.

A robust model based on root morphological and anatomical features to distinguish high and low methane emission rice varieties through machine learning approaches

Rice fields are a major producer of methane, a strong greenhouse gas. However, identifying genetic variation in methane emissions among rice varieties remains challenging. This study applied association rule mining to detect key rice root morphological and anatomical traits influencing methane emissions, validated using a support vector machine. We report models which accurately classified high and low methane-emitting varieties with 98% (morphological) and 94% (anatomical) accuracy. These models effectively distinguished methane emission categories based on intrinsic trait patterns. Machine learning analysis highlighted the top 10 morphological and anatomical traits associated with methane emission levels. High methane-emitting varieties were characterized by lower middle root porosity, base root porosity, average root porosity, root diameter (RDia), and higher S-type lateral root length. Conversely, low methane-emitting varieties exhibited lower root number, tiller number, root dry weight, leaf number, and higher RDia. Anatomically, high methane-emitting varieties showed reduced lacunae number, total stele area, mean metaxylem size, metaxylem number, and metaxylem vessel area. Low methane-emitting varieties, in contrast, had higher percent aerenchyma, total stele area, ratio of total cortical area to root cross-section area, ratio of stele to root cross-section area, and aerenchyma area. The results suggest that the rhizosphere oxygenation …

Introducing effective genes in lymph node metastasis of breast cancer patients using SHAP values based on the mRNA expression data

Objective

Breast cancer, a global concern predominantly impacting women, poses a significant threat when not identified early. While survival rates for breast cancer patients are typically favorable, the emergence of regional metastases markedly diminishes survival prospects. Detecting metastases and comprehending their molecular underpinnings are crucial for tailoring effective treatments and improving patient survival outcomes.

Methods

Various artificial intelligence methods and techniques were employed in this study to achieve accurate outcomes. Initially, the data was organized and underwent hold-out cross-validation, data cleaning, and normalization. Subsequently, feature selection was conducted using ANOVA and binary Particle Swarm Optimization (PSO). During the analysis phase, the discriminative power of the selected features was evaluated using machine learning classification algorithms. Finally, the selected features were considered, and the SHAP algorithm was utilized to identify the most significant features for enhancing the decoding of dominant molecular mechanisms in lymph node metastases.

Results

In this study, five main steps were followed for the analysis of mRNA expression data: reading, preprocessing, feature selection, classification, and SHAP al…