Researchmatch - first iteration initial projects submissions

Please find below the list of 37 ResearchMatch projects received from the McGill life science and clinical communities. The McGill data science community is now being asked to contact the individual researchers if interested to collaborate in order to submit a full proposal by May 1st 2019.


It should be projects are split into 3 groups:

Clinical Research (19)  Life Science Research (13)  Population Health Research (5)


Clinical Research

Project title: Developing automatic algorithm of voice type identification

A person's voice can tell us a lots, such as emotional stress and health. We have already collected a large volume of voice data sets. We now need to develop an intelligent method to identify what discriminative features are (data mining) and predict a person's voice features (machine learning).

Keywords: data mining, disease surveillance, precision medicine, statistical analyses, quantitative medicine

PI: Nicole Li-Jessen (Assistant Professor)
Department: Communication Sciences and Disorder

email: [at]


Project title: Machine-learning powered clinical decision support for depression treatment selection

Depression is a complex, heterogenous disease and is currently treated with a trial-and-error approach, with most patients needing multiple treatment courses. High quality data from clinical trials and clinical cohorts can be used to produce models of remission prediction and differential treatment response, but many methodological challenges exist.

Keywords: data mining, genomics, imaging, precision medicine, statistical analyses

PI: Gustavo Turecki (Department Chair)

Department: Psychiatry

email: gustavo.turecki [at]


Project title: Personalized medicine for better pediatric pain management

This proposal aims to develop a new clinical tool that will help health care providers treat children with pain conditions with minimal use of painkillers. This new tool will merge skin sensibility, blood test and questionnaires, and will guide and establish rational for an individualization of pain treatment strategies.

Keywords: machine learning, opioids, biomarkers, quantitative sensory testing, electroencephalography, psychological profile, youth

PI: Catherine Ferland (Assistant Professor)

Department: Anesthesia

email: catherine.ferland [at]


Project title: Sample Adequacy Control in Molecular Screening Assays

Sample adequacy controls (SAC) are an important means of ensuring quality in clinical specimens sent for molecular microbiologic assays. Without SAC one cannot trust negative result (case of Ebola and H1N1 pandemic). To the best of our knowledge, we are the only hospital in Canada collecting data of SAC.

Keywords: disease surveillance, infection and immunity, public policy, statistical analyses, quantitative medicine

PI: Ivan BRUKNER (Associate Professor)

Department: Microbiogy

email: ibrukner [at]


Project title: Anonymization of Facial Images in Ophthalmology with Generative Adversarial Networks for Educational Purposes

Protecting patient privacy is inevitable when using clinical photography. However, conventional deidentification method cannot be used for oculomotor paralysis. Generative Adversarial Networks can produce anonymized facial pictures while keeping the representations. This project aims to synthesize realistic clinical images, which are anonymized and can be used for medical education.

Keywords: disease surveillance, societal issues

PI: Akinori Higaki (Postdoctoral Research Fellow)

Department: Lady Davis Institute for Medical Research

email: akinori.higaki [at]


Project title: Estimating individual healthcare worker hand hygiene compliance using a large anonymous database

Using a very large database containing non-nominative information regarding healthcare worker hand hygiene compliance populated through an automated electronic monitoring system, this study will explore the capacity to determine hand hygiene compliance of individual healthcare workers. This could allow personalized feedback, and ultimately improve compliance and prevent nosocomial infections.

Keywords: data mining, infection and immunity, statistical analyses, quantitative medicine

PI: Yves Longtin (Associate professor)

Department: Infectious Diseases

email: yves.longtin [at]


Project title: Computational tools to inform risk of immune-mediated injuries in kidney transplantation

When a donor kidney is transplanted, the recipient’s immune system may recognize it as incompatible and reject it. We seek to promote lifetime kidney transplant survival by applying novel computational tools, which can verify optimal donor-recipient compatibility at the level of human leukocyte antigens.

Keywords: data mining, genetics, infection and immunity, precision medicine

PI: Ruth Sapir-Pichhadze (Assistant professor)

Department: Medicine

email: ruth.sapir-pichhadze [at]


Project title: Data Integration for Development of a Predictive Machine Learning Model of Frequent Exacerbations of COPD

Chronic Obstructive Pulmonary Disease (COPD) is a lung disease affecting 20% of Canadians over the age of 40 years who smoke. To deliver Precision Medicine in COPD, we need to be able to predict patients’ disease trajectories. This project is the necessary first step towards building such predictive computational model.

Keywords: data mining, disease cohorts, genomics, precision medicine, statistical analyses, quantitative medicine, data integration; data harmonization; machine learning; predictive model; international collaboration

PI: Nurlan Dauletbayev (Assistant Professor)

Department: Pediatrics

email: nurlan.dauletbayev [at]


Project title: Trajectories of liver disease in people living with HIV: insight from two large prospective cohorts

Non-alcoholic fatty liver disease (NAFLD) affects over 40% of HIV-infected patients, a prevalence that is double that of the general population. The LIVEHIV and the Modena HIV Metabolic Clinic Cohorts are two prospective screening programs for NAFLD and liver cirrhosis established at McGill University and University of Modena (Italy). In both cohorts, HIV-infected patients undergo innovative non-invasive tests to diagnose NAFLD and liver cirrhosis. At 1,250 and 2,050 patients, respectively, they represent among the largest cohorts in the world. We will employ these cohorts to determine individual trajectories for liver cirrhosis development, based on NAFLD, obesity and viral hepatitis coinfections.

Keywords: disease cohorts, disease surveillance, infection and immunity, statistical analyses, study design

PI: Giada Sebastiani (Assistant Professor)

Department: Medicine

email: giada.sebastiani [at]


Project title: Building a Rare Disease Database for a Natural History Study of 4H Leukodystrophy

4H leukodystrophy is a neurodegenerative disease with poorly understood natural history. A LORIS database will use medical history, MRIs, and genomic data to characterize disease evolution and identify surrogate markers necessary for evaluation of potential therapies. This database will allow for development of a prediction tool based on clinical characteristics.

Keywords: disease surveillance, genomics, imaging, statistical analyses, study design

PI: Genevieve Bernard (Associate Professor)

Department: Neurology and Neurosurgery

email: genevieve.bernard [at]


Project title: Machine Learning for Predicting Brain Injury in Asphyxiated Newborns

This project aims to use machine learning to evaluate incoming clinical data from an ongoing clinical trial to predict the outcome of brain injury in asphyxiated newborns. This project will also assess the efficacy of a new treatment aiming at repairing the brain of these newborns.

Keywords: brain research, disease cohorts, imaging, statistical analyses, quantitative medicine, Clinical Trial, Sildenafil, Asphyxia, Neonatal Neurology, Supervised Learning, Machine Learning, MRI, Imaging, aEEG, NIRS, Echo

PI: Pia Wintermark (Associate Professor)

Department: Pediatrics

email: Pia.Wintermark [at]


Project title: Phase sorting of dynamic magnetic resonance imaging data to extract regional lung ventilation and perfusion information

There is intense interest in quantifying lung ventilation and perfusion to understand and treat lung diseases. Current techniques require harmful ionizing radiation, contrast agents, and sustained breath hold, which are problematic for patients. We seek to implement and optimize a novel magnetic resonance technique that overcomes these limitations.

Keywords: complex systems, imaging, statistical analyses, quantitative medicine

PI: Benjamin Smith (Clinician-scientist; assistant professor)

Department: Medicine

email: benjamin.m.smith [at]


Project title: Development of a website for a living systematic review on the diagnostic accuracy of novel rapid tests for influenza

We aim to develop automated processes to identify and extract new data on the diagnostic accuracy of rapid influenza diagnostic tests as it becomes available with results published regularly on a dedicated website thereby integrating the latest evidence into actionable summaries to inform influenza-related recommendations and guidelines.

Keywords: data mining, infection and immunity, study design

PI: Jesse Papenburg (Pediatric infectious disease physician and medical microbiologist)

Department: Department of Pediatrics and Department of Clinical Laboratory Medicine

email: jesse.papenburg [at]


Project title: Sugar, the microbiome, and health outcomes in early childhood

The current cross-sectional study will examine the relationship between free sugar intake and gut microbiome diversity and cardiometabolic markers (measures of adiposity, blood glucose, C-reactive protein, lipids, sleep duration) in 200 preschool-aged children. We have funding and REB approval to collect the prospective data, which will start within the next 2 months through the TARGet Kids! primary care research network. Our budget for biostatistical support/data analysis was cut short with unforeseen data management fees. Our goal for the MiCM Research Match Program is to collaborate with McGill data sciences researchers to gain their expertise on state-of-the-art analyses and work together on elaborating the current study methods.

Keywords: statistical analyses, pediatrics; microbiome; nutrition; obesity

PI: Patricia Li (Assistant Professor, clinician-scientist)

Department: Pediatrics

email: [at]


Project title: Creating a Model to Predict CBT Outcome in a University Teaching Unit

This study analyses predictors and outcomes from over 1400 patients with heterogenous diagnoses referred for short-term cognitive behavioural therapy in a University Teaching Unit. This project aims to derive a model for outcome prediction, which will aid clinicians in better selecting patients suitable for this treatment modality.

Keywords: data mining, precision medicine, statistical analyses, quantitative medicine

PI: Gail Myhr (Associate professor)

Department: Psychiatry

email: gail.myhr [at]


Project title: Advancing risk prediction and prognostication of early stage lung cancer using computational models

Lung cancer is the leading cause of cancer death in Quebec in both men and women. The prevalence of early stage non-small cell lung cancer (NSCLC) is expected to increase given current trends in population aging and the advent of low dose CT screening. The standard curative intent treatment for primary LC is lobectomy, with 5-year survival rates of 70%. Lung cancer patients have significant competing risks on mortality from smoking, the most important risk factor for lung cancer. These include cardiac disease, emphysema, and frailty syndromes.

A wealth of data is currently available in early stage lung cancer which are not traditionally used pre-operatively for risk assessment and treatment planning or prognostication. These include imaging data (CT chest and abdomen) provides information about 1) tumor morphometry and draining lymph nodes and 2) non-tumor data such as degree of emphysema, coronary calcifications, and muscle thickness among other identifiable by computer aided detection using available open source software. Similarly, health services data from the clinical data warehouse of the MUHC provides data on comorbidities and competing risk which is not currently integrated into clinical decision making. It is not clear how to best integrate these data using suitable computational models.

The main goal of this project is to use these different data sources to guide “perception” (or data acquisition), abstract comprehension or cognition, and ideally facilitate strategic clinical decision making for each individual patient being evaluated for treatment of an early stage lung cancer.

Keywords: cancer, data mining, genomics, imaging, precision medicine, statistical analyses, quantitative medicine, lung cancer

PI: Nicole Ezer (Assistant Professor)

Department: Respirology

email: nicole.ezer [at]


Project title: Quantification of the effect of Smoking on arterial stiffness (Smokeless)

Cigarette smoking increases arterial stiffness, which is an independent predictor for cardiovascular events. Previous studies have assessed the effect of smoking on arterial stiffness only at rest. In our study, we introduced the ‘arterial stress test’, a new approach of evaluating vascular function, whereby arterial stiffness is assessed pre- and at several timepoints post-exercise. Cross-sectional analyses demonstrated that smoking leads to a blunted ability of the arteries to respond to acute physical stress. We now wish to 1) better analyze the ‘arterial stress test’, and 2) address the study’s longitudinal component and evaluate the impact of smoking on arterial stiffness over time.

Keywords: disease cohorts, statistical analyses, quantitative medicine

PI: Stella Styliani Daskalopoulou (Associate Professor in Medicine)

Department: Medicine

email: stella.daskalopoulou [at]



Project title: Quantitative Modeling of the Heart Failure Trajectories in Patients with Congenital Heart Disease

Heart failure is the most common disease amongst patients with all afflictions of the heart. Because of advances in medicine and surgery, patients with complex heart conditions are now surviving over the course of a lifetime. Such patients require careful surveillance with expert care. In this study, we are proposing to use advanced quantitative method to model the dynamic heart failure trajectory among patients with congenital heart disease across the lifespan. Working in collaboration with the data scientists will enable us to assess the dynamic nature of the trajectory in-depth to direct clinical interventions for improving patient care. Through this grant, we will assemble a strong group of experts from multiple disciplines to achieve this.

Keywords: data mining, disease cohorts, precision medicine, statistical analyses, quantitative medicine,

PI: Ariane Marelli (Professor and director)

Department: Cardiology

email: ariane.marelli [at]


Project title: Understanding intra- and inter-individual variation in the course of symptoms and functioning in early psychosis

Psychosis is a serious mental illness whose onset is typically in late adolescence and young adulthood. The first two to five years following onset are considered a critical period during which specialized early intervention services are typically offered for maximizing chances of symptomatic and functional recovery. There is tremendous heterogeneity in the course and outcomes of psychosis which has been the subject of much research. However, most such research suffers from a few important limitations. While data on symptoms, functioning and predictors are typically collected at multiple timepoints over the course of treatment, most research usually has analyzed composite indices, such as percentages or mean scores, without examination of stability of course for individuals. Examining the stability of course for each individual and then analyzing patterns across individuals that also reflects such intra-individual variation over time is important to have a more nuanced picture of how individuals fare following treatment, the extent to which their course is stable versus fluctuating, what predicts the nature of varying types of courses, etc. Such a nuanced picture has significant implications for tailoring and sequencing treatments, and thereby for improving the overall outcomes for young persons with psychosis, which is an urgent need.

Keywords: complex systems, data mining, disease cohorts, precision medicine, statistical analyses, quantitative medicine

PI: Srividya Iyer (Assistant Professor)

Department: Psychiatry

email: srividya.iyer [at]




Life Science Research

Project title: Sequence binding plasticity of dysfunctional epigenetic regulatory proteins

The spread of Breast Cancer (BC) to distal organs accounts for 90% of all BC-related deaths. Here, we aim to define novel genomic changes that facilitate the evolution of cells from normal to highly metastatic. Defining these changes may reveal new therapeutic avenues to combat poor prognosis BC.

Keywords: cancer, genomics

PI: Michael Witcher (Associate Professor of Medicine)

Department: Oncology

email: michael.witcher [at]


Project title: Signaling pathways in human glomerular diseases

Our goal is to achieve a comprehensive understanding of proteostasis in human glomerulonephritis, and open therapeutic opportunities. We propose to compare gene expression in glomeruli from human kidney biopsies with cell lines treated with bioactive small molecules, to evaluate similarities and identify potential drugs able to alter the gene signatures.

Keywords: disease cohorts, disease surveillance, genomics, precision medicine, statistical analyses

PI: Andrey Cybulsky (Professor)

Department: Medicine

email: andrey.cybulsky [at]


Project title: Purine salvage deficiency in human dopmainergic cell differentiation

We have found that purine salvage is a critical component for proper ventral midbrain (VM) dopaminergic cell development. The purpose of this proposal is to understand the role of purine salvage during VM dopaminergic cell development.

Keywords: brain research, complex systems, data mining, disease cohorts, disease surveillance, genomics, high-thoughput biology, precision medicine

PI: Carl Ernst (Associate Professor)

Department: Human Genetics

email: carl.ernst [at]


Project title: Transcriptional function of YAP1 in interferon signaling

The transcription factor YAP1 is hyper-activated in many human cancers. We found that YAP1 cooperates with the transcription factor STAT1 to promote KRAS colon tumor growth. STAT1 and YAP1 may mediate the expression of genes with roles in interferon signaling and biological responses affecting innate and anti-tumor immunity.

Keywords: cancer, genomics, infection and immunity, Yes-associated protein 1, signal transducer and activator of transcription 1, interferon, KRAS, colon cancer

PI: Antonis Koromilas (Professor)

Department: Oncology

email: antonis.koromilas [at]


Project title: Large-scale gene-by-environment interaction (GxE) modelling using deep learning to extract genetic and environmental risk scores

Using deep learning, we seek to construct complex Gene by Environment interaction (GxE) models which could identify patients at risk of depression/ADHD and determine which modifiable aspect of the environment should be targeted for maximizing improvement (personalized treatment). We will use DREAM BIG, a consortium of 5 harmonized prenatal cohorts.

Keywords: complex systems, genetics, imaging, statistical analyses, quantitative medicine

PI: Ashley Wazana ( Child psychiatrist researcher )

Department: Psychiatry

email: ashley.wazana [at]


Project title: Age and causes of founder mutations in NLRP7

Women with recessive mutations in NLRP7 are not able to conceive. Yet, there are founder mutations. Hypotheses: mutations have been maintained because of NLRP7 role in inflammation or location close to KIR genes with roles in immune response. The goal is to determine the cause and age of founder mutations.

Keywords: disease cohorts, infection and immunity

PI: Rima Slim ( Associate Professor )

Department: Human Genetics

email: rima.slim [at]


Project title: Non-coding RNA profile during human immunodeficiency virus latency and reactivation

Human Immunodeficiency Virus (HIV) infection cannot be cured because HIV remains silent in reservoir cells. Understanding the factors that maintain inactive HIV would help find a cure. We isolated and sequenced non-coding RNAs from HIV latent lymphocytes. The data will be analyzed by bioinformatics to find markers of latency.

Keywords: complex systems, data mining, high-thoughput biology, infection and immunity, statistical analyses

PI: Anne Gatignol (Professor)

Department: Medicine

email: anne.gatignol [at]


Project title: Genome-wide circadian regulation of gene expression in T cells

Circadian clocks control various aspects of physiology. The circadian control of T cells, which are at the core of immune responses to pathogens, is unclear. We showed a role for circadian clocks in controlling the magnitude of T cell responses. To decipher the mechanisms involved, we study the genes showing 24 h rhythms in T cells, to get insights on the pathways that are regulated by clocks in these cells, and how this regulation occurs. This work will contribute to better understanding the role of circadian clocks in the immune response, and opens a door to new T cell-based therapies.

Keywords: data mining, genomics, infection and immunity, circadian rhythms, gene expression

PI: Nicolas Cermakian (Professor)

Department: Psychiatry

email: nicolas.cermakian [at]


Project title: Regulation of axon-myelin relationships in gene edited mice

Myelin sheaths surround axons with individual sheath thickness and length proportional to axon diameters. To probe how this relationship is controlled we derived multiple mouse models with variably attenuated myelination capacity. In depth characterization of their axon-myelin relationships should illuminate key features of the cellular mechanisms regulating myelin volume.

Keywords: brain research, complex systems, imaging, statistical analyses, quantitative medicine

PI: Alan Peterson (Associate Professor)

Department: Oncology, Human Genetics, Neurology & Neurosurgery

email: alan.peterson [at]


Project title: Accurate identification of transcription factor regulatory targets

Chromatin immunoprecipitation and sequencing (ChIP-seq) has made it possible to identify where in the genome a transcription factor binds. The much harder task is using that information to identify the targets that the transcription factor regulates. We seek to integrate ChIP-seq and RNA-seq data to more accurately identify regulatory targets and thus determine how different transcription factors bring about normal mammalian development.


complex systems, data mining, genomics, high-thoughput biology, statistical analyses

PI: William Pastor (Associate Professor)

Department: Biochemistry

email: william.pastor [at]


Project title: Analysis to Identify Populations of Cell Adhesions in Breast Cancer Cell Migration

Poor breast cancer prognosis is highly dependent on the ability of breast cancer cells to metastasize from the primary tumor to distant sites. Two key cellular processes are required for efficient metastasis, which include migration and invasion. For cells to migrate, they must form adhesions at the front of the cell that act as traction points used to pull the cell forward. Simultaneously, adhesions at the rear of the cell must disassemble to permit forward movement. There is a need for tight regulation of adhesions across the cell to regulate cell migration. Modern microscopes collect tremendous amounts of data but the tools are not readily accessible for analyzing this data. The basis of this project will be to analyze data on adhesion properties in normal and breast cancer cells to determine key factors that regulate breast cancer.

Keywords: cancer, data mining, imaging, cell migration, quantitative light microscopy

PI: Claire Brown (Assistant Professor)

Department: Physiology

email: claire.brown [at]


Project title: Artificial Intelligence-informed molecular profiling of chronic lung diseases

The traditional pipeline for drug development uses a linear approach that stratifies patients into subgroups based on a pre-conceived understanding of disease biology. However, this stratification approach ignores the complex molecular interactions that underlie disease heterogeneity, thus limiting our ability to precisely target the mechanisms driving disease pathogenesis. To address this gap, we propose to test an alternative framework that uses a cyclical artificial intelligence (AI)-informed approach to stratify patients into unbiased clusters based on their inflammatory profiles that are validated and refined through a reiterative procedure. The objective of this proposal is to pilot the clustering analysis using biospecimens from the Quebec Respiratory Health Network biobank.

Keywords: data mining, disease cohorts, infection and immunity, precision medicine, statistical analyses

PI: Simon Rousseau (Assistant Professor)

Department: Medicine

email: simon.rousseau [at]


Project title: AI-based tools for the quantitative analysis of real-time cell cycle imagery.

Imaging cancer cells as they divide using real-time microscopy captures an enormous amount of information describing the properties of such cells. Currently, the rate-limiting step in extracting data from real-time imaging data is the laborious, and lengthy analysis by an experienced user. Recent advances in artificial intelligence and machine learning provide a unique opportunity to rapidly advance and automate analysis of real-time microscopy. This proposal aims to bring together a cancer biology lab that curates an extensive collection of real-time cell cycle movies with data scientists that can collaborate to extract and analyze data from the imagery. If such data can be mined rapidly and in an automated manner, such tools could lead to novel automated screening methods for anti-cancer drugs. cancer.

Keywords: cancer, data mining, high-thoughput biology, imaging, quantitative medicine

PI: Jose Teodro (Associate Professor)

Department: Biochemistry/Goodman Cancer Research Centre

email: jose.teodoro [at]




Population Health Research

Project title: Is there equity in cardiovascular healthcare accessibility?

In principle, Quebecois have universal access to healthcare, including resource intensive cardiovascular procedures such as coronary revascularization. Using Quebec administrative databases, it is proposed to see if standard statistical modeling and machine learning techniques can identify features associated with access to cardiovascular care.

Keywords: data mining, disease cohorts, public policy, societal issues, statistical analyses

PI: James (Jay) Brophy (Professor)

Department: Medicine

email: james.brophy [at]


Project title: Genetic Determinants of Temporomandibular Disorders

Temporomandibular disorders (TMD) are the major source of chronic orofacial. We propose to combine individual level data from several high-quality phenotyped cohorts into a larger one to conduct GWAS. We seek to meta-analyze data from these cohorts to overcome heterogeneity between studies and enable identification of genetic determinants of TMD.

Keywords: complex systems, genetics, statistical analyses, Polygenic Risk Scores, Meta-Analysis

PI: Luda Diatchenko (Professor)

Department: Anesthesia

email: luda.diatchenko [at]


Project title: Personalized COPD risk prediction by machine learning approach integrating clinical and genomic data

Chronic Obstructive Pulmonary Disease (COPD) is a lung disease caused by both endogenous (e.g., genetic predisposition) and exogenous (e.g., smoking, respiratory infection) factors. COPD patients often suffer from recurrent exacerbations. We propose an interdisciplinary approach using machine learning and clinical expertise for early detection of frequent exacerbation.

Keywords:data mining, disease cohorts, genetics, genomics, high-thoughput biology, infection and immunity, precision medicine, statistical analyses, quantitative medicine

PI: Yue Li (Assistant Professor)

Department: School of Computer Science

email: [at]


Project title: Intersection between sex and gender-related factors in the prediction of clinical outcomes in chronic noncommunicable diseases

Background: Psycho-cultural-social factors, which are associated with the gender of individuals, are rarely collected as determinants of health outcomes, despite their powerful contribution to overall well-being. Gender-related factors including gender identity, gender role, gender relations and institutionalized gender are assumed to differ between sexes.

Objective: The aim of the project is to develop an algorithm to predict health related outcomes based on clinical and gender-related factors know to be associated with patient sex.

Methods: The analysis will be performed on data subsets from three prospective, longitudinal cohorts of adults with ischemic heart disease, aged more than 18 years old, enrolled in Canada and Italy (from 2008 to 2019): the GENESIS-PRAXY (GENdEr and Sex DetermInantS of Cardiovascular Disease: From Bench to Beyond Premature Acute Coronary Syndrome, n=1210); the Alberta Provincial Project for Outcome Assessment in Coronary Heart Disease (APPROACH, n=27034); and the Endocrine Vascular disease Approach (EVA, n=430). Sex, gender-related factors (i.e. personality traits, stress level, social support, level of education, personal income, household primary earner status, caregiver status, employment status) and co-morbidities (e.g. diabetes, hypertension, obesity, smoking, depression) will be analyzed. Health related outcomes will include death, readmission and length of in-hospital stay.

Interest in collaborative transdisciplinary project and potential value: The collaboration between life scientists with expertise in gender measurement and outcome research, with computer scientist will help to generate innovative and feasible solution to integrate and more importantly begin to understand the relationship of sex and gender to clinical outcomes. Specifically, this project will serve to develop an artificial-intelligence methodology that we will use to generate algorithms of outcome prediction in a more comprehensive multinational cohort of data. This includes 32 health related cohorts totaling 30 million individuals affected by cardiovascular disease, chronic kidney disease, neurological diseases and metabolic syndrome, gathered through a network of five countries—Austria, Canada, Cyprus, Spain and Sweden. GOING-FWD (Gender Outcomes International Group: to Further Well-being Development), is a personalized medicine project recently funded by the Canadian Institutes of Health and Research and GENDER-NET+, and is part of the European EU H2020 initiative.

Keywords: disease cohorts, precision medicine, statistical analyses, non-communicable chronic disease, ischemic heart disease

PI: Louise Pilote (Professor of medicine)

Department: Division of Clinical Epidemiology and General Internal Medicine McGill University Health Centre Research Institute

email: louise.pilote [at]


Project title: How does daily smartphone use impact our wellbeing

Smartphones have transformed our lives. Despite the many advantages of such devices, a growing literature has found that problematic smartphone use brings substantial adverse effects. However, there has been limited research that thoroughly explores how daily smartphone use impacts our wellbeing, and what roles of psychological factors --such as daily mood -- play in this relationship. This proposed study aims to explore how daily smartphone use impacts wellbeing by collecting the relevant information over a 2-month period from a community-based population cohort. This project provides a unique opportunity to bring together interdisciplinary researchers to analyze how daily smartphone use behaviour and its changes influence one’s wellbeing, and examine roles of other factors also being involved in this relationship.

Keywords: data mining, statistical analyses, tele-health, quantitative medicine, Smartphone use; Wellbeing

PI: XIANGFEI MENG (Assistant Professor)

Department: PSYCHIATRY

email: xiangfei.meng [at]





Back to top