A5069570780- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Pregnancy and preeclampsia studies
- Assisted Reproductive Technology and Twin Pregnancy
- COVID-19 diagnosis using AI
- Prenatal Screening and Diagnostics
- Ectopic Pregnancy Diagnosis and Management
- Medical Imaging Techniques and Applications
- Traffic and Road Safety
- Dementia and Cognitive Impairment Research
- Ovarian function and disorders
- Birth, Development, and Health
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Nutritional Studies and Diet
- Systemic Lupus Erythematosus Research
- Long-Term Effects of COVID-19
- Liver Disease Diagnosis and Treatment
- Ocular Diseases and Behçet’s Syndrome
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- COVID-19 Clinical Research Studies
- Blood Pressure and Hypertension Studies
- Erythrocyte Function and Pathophysiology
- Genetic Syndromes and Imprinting
- Lipoproteins and Cardiovascular Health
- Dermatologic Treatments and Research
Karolinska Institutet
2021-2025
Kermanshah University of Medical Sciences
2018-2023
Imam Khomeini Hospital
2023
Texas Children's Hospital
2023
Baylor College of Medicine
2023
Icahn School of Medicine at Mount Sinai
2023
Tehran University of Medical Sciences
2017-2022
Baqiyatallah University of Medical Sciences
2022
Jahrom University of Medical Sciences
2018
Alborz University of Medical Sciences
2018
The aim of this study was to identify the most important features and assess their discriminative power in classification subtypes NSCLC.This involved 354 pathologically proven NSCLC patients including 134 squamous cell carcinoma (SCC), 110 large (LCC), 62 not other specified (NOS), 48 adenocarcinoma (ADC). In total, 1433 radiomics were extracted from 3D volumes interest drawn on malignant lesion identified CT images. Wrapper algorithm multivariate adaptive regression splines implemented...
We aimed to analyze the prognostic power of CT-based radiomics models using data 14,339 COVID-19 patients.
The aim of this work is to investigate the applicability radiomic features alone and in combination with clinical information for prediction renal cell carcinoma (RCC) patients' overall survival after partial or radical nephrectomy. Clinical studies 210 RCC patients from Cancer Imaging Archive (TCIA) who underwent either nephrectomy were included study. Regions interest (ROIs) manually defined on CT images. A total 225 extracted analyzed along 59 features. An elastic net penalized Cox...
Abstract Background Disturbances in brain cholesterol homeostasis may be involved the pathogenesis of Alzheimer’s disease (AD). Lipid-lowering medications could interfere with neurodegenerative processes AD through metabolism or other mechanisms. Objective To explore association between use lipid-lowering and cognitive decline over time a cohort patients mixed dementia indication for treatment. Methods A longitudinal study using Swedish Registry Cognitive/Dementia Disorders, linked national...
Background Medications for comorbid conditions may affect cognition in Alzheimer's disease (AD). Objective To explore the association between common medications and cognition, measured with Mini-Mental State Examination. Methods Cohort study including persons AD from Swedish Registry Cognitive/Dementia Disorders (SveDem). were included if they used by ≥5% of patients (26 individual drugs). Each follow-up was analyzed independently performing 100 Monte-Carlo simulations two steps each 1)...
The use of anthropometric indices is one the new and low-cost diagnostic methods metabolic syndrome (MetS). present study aimed to determine optimal cutoff points for visceral adiposity index (VAI), body roundness (BRI), a shape (ABSI) in prediction MetS.This cross-sectional was performed on 10,000 individuals aged from 35 65 years, recruited Ravansar Non-Communicable Diseases (RaNCD) cohort study, west region Iran, 2019. MetS defined according International Diabetes Federation (IDF)...
We aimed to construct a prediction model based on computed tomography (CT) radiomics features classify COVID-19 patients into severe-, moderate-, mild-, and non-pneumonic. A total of 1110 were studied from publicly available dataset with 4-class severity scoring performed by radiologist (based CT images clinical features). The entire lungs segmented followed resizing, bin discretization radiomic extraction. utilized two feature selection algorithms, namely bagging random forest (BRF)...
Background: The control of auto-reactive cells is defective in rheumatoid arthritis (RA). Regulatory T (Treg) which play a key role the modulation immune responses have an impaired function RA. Foxp3 master regulator Treg its expression under tight epigenetic mechanisms. In current study, we analyzed Treg-specific demethylated region (TSDR) and Helios gene to determine alteration RA patients.Methods: We recruited 20 newly diagnosed patients with 41 healthy controls our study. measurement was...
The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 who had visible scars on short-axis LGE-CMR were candidates for CABG surgery selected enrolled this study. imaging performed preoperatively a 1.5-T MRI scanner. All segmented by two expert radiologists (in consensus). Prior extraction features, all resampled an...
Image artefacts continue to pose challenges in clinical molecular imaging, resulting misdiagnoses, additional radiation doses patients and financial costs. Mismatch halo occur frequently gallium-68 (
Somatic syndrome is one of the remarkably prevalent issues in primary health care and subspecialty settings. We aimed to elucidate multidimensional associations between somatic symptoms with major mental problems personality traits framework quantile regression model a Bayesian approach. A total 4763 employees at Isfahan University Medical Sciences Health Services province, Iran, filled out four validated questionnaires including Hospital Anxiety Depression Scale (HADS), NEO Questionnaire,...
Background: Marijuana use is increasing among adolescents and young adults. Long-term marijuana magnifies the risk of a wide variety behavioral, cognitive-emotional, neurological problems, can be gateway to other drugs. In present study, we investigated cognitive-emotional behavioral predictors use. To this end, Iranian adults answered questions based on an extended Theory Planned Behavior (TPB) related it We hypothesized that factors would predict intention marijuana, this, in turn, actual...
Rationale: The Toll-like receptor 3 Leu412Phe (TLR3 L412F) polymorphism attenuates cellular antiviral responses and is associated with accelerated disease progression in idiopathic pulmonary fibrosis (IPF). role of TLR3 L412F bacterial infection IPF or acute exacerbations (AE) has not been reported. Objectives: To characterize the association between AE-related death IPF. determine effect on lung microbiome antibacterial TLR primary fibroblasts from patients Methods: TLR-mediated were...
Abstract The aim of this project was to identify candidate novel therapeutic targets facilitate the treatment COPD using machine-based learning (ML) algorithms and penalized regression models. In study, 59 healthy smokers, 53 non-smokers 21 smokers (9 GOLD stage I 12 II) were included (n = 133). 20,097 probes generated from a small airway epithelium (SAE) microarray dataset obtained these subjects previously. Subsequently, association between gene expression levels smoking COPD,...
Abstract Purpose To derive and validate an effective radiomics-based model for differentiation of COVID-19 pneumonia from other lung diseases using a very large cohort patients. Methods We collected 19 private 5 public datasets, accumulating to 26,307 individual patient images (15,148 COVID-19; 9,657 with e.g. non-COVID-19 pneumonia, cancer, pulmonary embolism; 1502 normal cases). Images were automatically segmented validated deep learning (DL) the results carefully reviewed. first cropped...
Machine learning (ML) could have advantages over traditional statistical models in identifying risk factors. Using ML algorithms, our objective was to identify the most important variables associated with mortality after dementia diagnosis Swedish Registry for Cognitive/Dementia Disorders (SveDem). From SveDem, a longitudinal cohort of 28,023 dementia-diagnosed patients selected this study. Sixty were considered as potential predictors risk, such age at diagnosis, type, sex, body mass index...
Little is known about the specific timing and sequence of incident psychiatric comorbidities at different stages dementia diagnosis.To examine temporal risk patterns disorders, including depression, anxiety, stress-related substance use sleep somatoform/conversion psychotic among patients with before, time of, after receipt a diagnosis.This population-based, nationwide cohort study analyzed data from 796 505 participants obtained 6 registers between January 1, 2000, December 31, 2017,...
Diabetes mellitus type 2 (T2D) is associated with accelerated biological aging and the increased risk of onset other age-related diseases. Epigenetic changes in DNA methylation levels have been found to serve as reliable biomarkers for aging. This study explores relationship between various epigenetic diabetes using longitudinal data. Data from Swedish Adoption/Twin Study Aging (SATSA) was collected 1984 2014 included 536 individuals at least one measurement. The following were employed:...
This study aimed to evaluate the primary symptoms, comorbidities, and outcomes of inpatients with confirmed reverse transcription-PCR (RT-PCR) for SARS-CoV-2 infection among 2077 suspected/diagnosed cases COVID-19. Based on results Least Absolute Shrinkage Selection Operator (LASSO) logistic regression, age, suggestive chest X-ray (CXR) findings infection, cardiovascular diseases, diabetes mellitus, chronic lung intensive care units admission had significant associations positive RT-PCR...
This study aims to estimate and compare the parameters of some univariate bivariate count models identify factors affecting number mortality injured in road accidents.
Missing data is a pervasive problem in longitudinal analysis. Several single-imputation (SI) and multiple-imputation (MI) approaches have been proposed to address this issue. In study, for the first time, function of regression tree algorithm as non-parametric method after imputing missing using SI MI was investigated simulated real data.Using different simulation scenarios derived from set, we compared performance cross, trajectory mean, interpolation, copy-mean, methods (27 approaches)...
The linear mixed-effects model (LME) is a conventional parametric method mainly used for analyzing longitudinal and clustered data in genetic studies. Previous studies have shown that this can be sensitive to assumptions provides less predictive performance than non-parametric methods such as random effects-expectation maximization (RE-EM) unbiased RE-EM regression tree algorithms. These trees utilize classification (CART) conditional inference (Ctree) estimate the fixed-effects components...
Abstract Background Glomerular filtration rate (GFR) is a valid indicator of kidney function. Different factors can affect GFR. The purpose this study to assess the direct and indirect effects GFR-related using structural equation modeling. Patients methods We analyzed data from baseline phase Ravansar Non-Communicable Disease cohort study. Data on socio-behavioral, nutritional, cardiovascular, metabolic risk were conceptual model in order test related GFR, separately male female, Results Of...