A5008608843- Advanced MRI Techniques and Applications
- Functional Brain Connectivity Studies
- Mental Health Research Topics
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Machine Learning and Data Classification
- Medical Image Segmentation Techniques
- Hemodynamic Monitoring and Therapy
- Brain Tumor Detection and Classification
- Cell Image Analysis Techniques
- Crime Patterns and Interventions
- Policing Practices and Perceptions
- Statistical and numerical algorithms
- Chronic Kidney Disease and Diabetes
- AI in cancer detection
- Cardiac Arrest and Resuscitation
- Decision-Making and Behavioral Economics
- Artificial Intelligence in Healthcare
- Ultrasound Imaging and Elastography
- Explainable Artificial Intelligence (XAI)
- Traffic and Road Safety
- Imbalanced Data Classification Techniques
- Adversarial Robustness in Machine Learning
- Schizophrenia research and treatment
- Atomic and Subatomic Physics Research
St. Francis Xavier University
2020-2024
University of Toronto
2017
Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and academic research. These technologies predict whether a series measurements belong to one multiple groups examples on which was previously trained. Prior real-world deployment, all implementations need be carefully evaluated with hold-out validation, where algorithm tested different samples than it provided for training, order ensure generalizability reliability AI models....
Although serum lactate levels are widely accepted markers of haemodynamic instability, an alternative method to evaluate stability/instability continuously and non-invasively may assist in improving the standard patient care. We hypothesise that blood paediatric ICU patients can be predicted using machine learning applied arterial waveforms perioperative characteristics.Forty-eight post-operative children, median age 4 months (2.9-11.8 interquartile range), mean baseline heart rate 131 beats...
We have performed a morphological analysis of patients with schizophrenia and compared them healthy controls. Our includes the use publicly available automated extraction tools to assess regional cortical thickness (inclusive within region variability) from structural magnetic resonance imaging (MRI), characterize group-wise abnormalities associated based on dataset. also correlation between automatically extracted biomarkers variety patient clinical variables available. Finally, we present...
Neuroscience studies are very often tasked with identifying measurable differences between two groups of subjects, typically one group a pathological condition and representing control subjects. It is expected that the measurements acquired for comparing also affected by variety additional patient characteristics such as sex, age, comorbidities. Multivariable regression (MVR) statistical analysis technique commonly employed in neuroscience to "control for" or "adjust secondary effects (such...
Traffic stops represent a crucial point of interaction between citizens and law enforcement, with potential implications for bias discrimination. This study performs rigorously validated comparative machine learning model analysis, creating artificial intelligence (AI) technologies to predict the results traffic using dataset sourced from Montgomery County Maryland Data Centre, focusing on variables such as driver demographics, violation types, stop outcomes. We repeated our rigorous...
Applying artificial intelligence (AI) and machine learning for chronic kidney disease (CKD) diagnostics characterization has the potential to improve standard of patient care through accurate early detection, as well providing a more detailed understanding condition. This study employed reproducible validation AI technology with public domain software applied CKD on publicly available dataset acquired from 400 patients. The approach presented includes patient-specific symptomatic variables...
Error consistency is a validation metric for evaluating the sample-based error variability across machine learning models trained as part of in-lab validation. Many (ML) based regression algorithms are likely to be inconsistent with each other when repeatedly on same task standard cross validation, in due sampling, but also, potentially associated inclusion randomness their training paradigms, which common many techniques. In this work, we propose novel approach and evaluation...
PurposeRandom matrix theory (RMT) is an increasingly useful tool for understanding large, complex systems. Prior studies have examined functional magnetic resonance imaging (fMRI) scans using tools from RMT, with some success. However, RMT computations are highly sensitive to a number of analytic choices, and the robustness findings involving remains in question. We systematically investigate usefulness on wide variety fMRI datasets rigorous predictive framework.ApproachWe develop...
Introduction: Despite improvements in management for children after cardiac surgery, a non-negligible proportion of patients suffer from arrest, having poor prognosis. Although serum lactate levels are widely accepted markers hemodynamic instability, measuring requires discrete blood sampling. An alternative method to evaluate stability/instability continuously and non-invasively may assist improving the standard patient care. Hypothesis: We hypothesize that PICU can be predicted using...
Multiple Sclerosis (MS) is a chronic neurological condition characterized by the development of lesions in white matter brain. T2-fluid attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) provides superior visualization and characterization MS lesions, relative to other MRI modalities. Follow-up FLAIR helpful information for clinicians towards monitoring disease progression. In this study, we propose novel modification generative adversarial networks (GANs) predict...
Multiple Sclerosis (MS) is a chronic progressive neurological disease characterized by the development of lesions in white matter brain. T2-fluid-attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) provides superior visualization and characterization MS lesions, relative to other MRI modalities. Longitudinal FLAIR MS, involving repetitively patient over time, helpful information for clinicians towards monitoring progression. Predicting future whole examinations with...