Eyes high1.jpg

THIS IS ME!

Researching and Teaching to Support Precision Medicine and Enhance Health and Wellness for All

I always find joy in learning and exploring new things. This led me to specialize in Artificial Intelligence -Machine Learning, Deep Learning and Ge0-AI Algorithms and apply these to cancer prevention research. It wasn’t until I arrived at academia that I realized just how much I enjoy learning through teaching in the academic environment.

I work smart balancing many aspects involved in being an effective Researcher and Mentor, and try to make sure I have as much time available for teaching as possible. I have published widely and also spoken at the public media, scientific events and conferences worldwide. Get in touch to find out more about my next generation health research applying AI - ML, DL and Geospatial algorithms.

 

DR SELIM KHAN, MD, PhD, MPH

Health Research Scientist

  • My research spans from clinical, health systems reforms, global public health, epidemiological, program evaluation, Indigenous health, interdisciplinary scholarship to population health interventions applying health equity, social justice and sustainability lenses.

  • I delivered consultancies to the WHO, UNDP, Health Canada, Risk Science International and other 4 international organizations from the UK, USA and Germany.

  • I received Howard Research Excellence Award, Two postdoctoral fellowships- Healthy City's Research Initiative from CIHR-CMHC and Eyes High Awards from the University of Calgary, Admission Scholarship for Doctoral Program from the University of Ottawa among others.

UoO PhD Convocation.jpg
 

WELCOME TO MY WORLD

AI in Health Research

 

Published Research in NATURE'S Scientific Reports:
Application of Deep Learning (LSTM) Time-Series Algorithms to Cancer Risk Prediction Research

Rising Canadian and falling Swedish radon gas exposure as a consequence of 20th to 21st century residential build practices.

Authors: Selim M Khan, Dustin D Pearson, Tryggve Rönnqvist, Markus E Nielsen, Joshua M Taron, Aaron A Goodarzi

Publication date: 2021/9/2

Journal: Scientific Reports

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Abstract

Radioactive radon gas inhalation is a major cause of lung cancer worldwide and is a consequence of the built environment. The average radon level of properties built in a given period (their ‘innate radon risk’) varies over time and by region, although the underlying reasons for these differences are unclear. To investigate this, we analyzed long term radon tests and buildings from 25,489 Canadian to 38,596 Swedish residential properties constructed after 1945. While Canadian and Swedish properties built from 1970 to 1980s are comparable (96–103 Bq/m3), innate radon risks subsequently diverge, rising in Canada and falling in Sweden such that Canadian houses built in the 2010–2020s have 467% greater radon (131 Bq/m3) versus Swedish equivalents (28 Bq/m3). These trends are consistent across distinct building types, and regional subdivisions. The introduction of energy efficiency measures (such as heat recovery ventilation) within each nation’s build codes are independent of radon fluctuations over time. Deep learning-based models forecast that (without intervention) the average Canadian residential radon level will increase to 176 Bq/m3 by 2050. Provisions in the 2010 Canada Build Code have not significantly reduced innate radon risks, highlighting the urgency of novel code interventions to achieve systemic radon reduction and cancer prevention in Canada.

Fig1_HTML.webp
Forecast Radon Canada Sweden.webp

Indoor air quality is strongly influenced by the presence of radioactive radon (222 Rn) gas. Indeed, exposure to high 222 Rn concentrations is unequivocally linked to DNA damage, lung cancer, and is a worsening issue in North American residences, having increased over time within newer housing stocks as a function of as yet unclear variables. Indoor air radon concentration can be influenced by a wide range of environmental, structural, and behavioral factors. As some of these factors are quantitative while others are qualitative, no single statistical model can determine indoor radon level precisely, while simultaneously considering all these variables across a complex and highly diverse dataset. The ability of machine learning to simultaneously analyze multiple quantitative and qualitative features makes it suitable to predict radon with a high degree of precision. Using Canadian long-term indoor air radon …

Machine Learning as a Next-Generation Tool for Indoor Air Radon Exposure Prediction.

Authors: Selim M Khan, Joshua M Taron, Aaron A Goodarzi
 

Publication date: 2020

Publisher: SAGE Publications Ltd

 
ADNN.jpg
Ottawa%20Gatineau_edited.jpg

RESIDENTS’ PERCEPTION OF RADON HEALTH RISKS: A QUALITATIVE STUDY

August 2019

Radon is a high impact environmental pollutant and is the second leading cause of lung cancer in Canada. Building design, extended winter, and geographical location expose residents of Ottawa-Gatineau (the national capital region in Canada) to an increased risk. It is surprising that residents have an inadequate awareness of the risk - despite its gravity - and have taken minimum preventive actions. This study explores perceptions of radon health risk and examines the factors that enable and hinder the adoption of preventive measures among Ottawa-Gatineau residents

Deep Learning ai-article-pic8.jpg

MACHINE LEARNING AS A NEXT-GENERATION TOOL FOR INDOOR AIR RADON EXPOSURE PREDICTION.

25 July 2020

The ability of machine learning to simultaneously analyze multiple quantitative and qualitative features makes it suitable to predict radon with a high degree of precision. Using Canadian long-term indoor air radon exposure data, we are using an artificial neural network with random weights and polynomial statistical models in MATLAB to predict radon levels as a function of geospatial and built environmental metrics. Our initial artificial neural network with random weights model run by sigmoid activation tested different combinations of variables and showed the highest prediction accuracy within the reasonable iterations. Here, we present details of these emerging methods and discuss strengths and weaknesses compared to the traditional artificial neural network and statistical methods commonly used to predict indoor air quality in different countries. We propose artificial neural network with random weights as a highly effective method for predicting indoor radon.

Radon 222.jpg

RADON, AN INVISIBLE KILLER IN CANADIAN HOMES: PERCEPTIONS OF OTTAWA-GATINEAU RESIDENTS

November 2018

Canadians have reason to care about indoor air quality as they spend over 90% of the time indoors. Although indoor radon causes more deaths than any other environmental hazard, only 55% of Canadians have heard of it, and of these, 6% have taken action. The gap between residents’ risk awareness and adoption of actual protective behaviour presents a challenge to public health practitioners. Residents’ perception of the risk should inform health communication that targets motivation for action. In Canada, research about the public perception of radon health risk is lacking. The aim of this study was to describe residents’ perceptions of radon health risks and, applying a theoretical lens, evaluate how perceptions correlate with protection behaviours.

Radom mitigation system SSD.jpg

RADON INTERVENTIONS AROUND THE GLOBE: A SYSTEMATIC REVIEW.

May 2019

This paper systematically reviewed both experimental and observational studies (S) with radon interventions (I) used globally in residential houses (P) compared to other residential or model houses (C) to evaluate relative mitigation effectiveness (O) that could guide selecting the best radon reduction strategy for residential buildings.

Health Equity Lens.jpg

DROUGHT IN ETHIOPIA: A POPULATION HEALTH EQUITY APPROACH TO BUILD RESILIENCE FOR THE ARGO-PASTORALIST COMMUNITY

January 2019

This study aims to identify the critical population health outcomes, underlying determinants, and the leverage points for actions that can guide effective policies and interventions for building health resilience for the vulnerable agro-pastoralist population in Ethiopia

SLHDP3.jpg

CRITIQUE OF A COMMUNITY-BASED POPULATION HEALTH INTERVENTION IN A FIRST NATIONS COMMUNITY: PUBLIC HEALTH AND MEDICAL ANTHROPOLOGY PERSPECTIVES

November 2016

Launched as a community-based partnership endeavour, the Sandy Lake Health and Diabetes Project (SLHDP) aimed to prevent diabetes in a First Nations community (FNC) in Northern Ontario. With active engagement of the key stakeholders, SLHDP conducted a series of studies that explored public health needs, priorities, and the contexts. These led to the adoption of a variety of culturally appropriate health interventions, addressing several health determinants such as health education, physical environments, nutrition, personal health practices, health services, and FNC culture. SLHDP built reciprocal capacity for both the community stakeholders and academic partners, thus evolved as a model of population health intervention. The school components are being scaled-up in other parts of FNCs in Canada. This paper presents a critique from public health and medical anthropology perspectives and draws evidence-based recommendations on how such programs can do better.

CARST Radon Team.jpg

AN INTERDISCIPLINARY POPULATION HEALTH APPROACH TO THE RADON HEALTH RISK MANAGEMENT IN CANADA

March 2017

This review applies an Integrated Population Health Framework to look at the relationships and interactions between population health determinants such as biology and genetics, environment and occupation, and social and economic factors, that influence the health risk of radon. The evidence gathered supports policy analysis with the application of ethical and risk management principles that lead to the identification of efficient and affordable broad-based and population-level preventive strategies. The final inferences enhance the framework by adding critical intervention modalities to Health Canada’s National Radon Program.

TEACHING MATERIALS

Teaching Dossier

My teaching philosophy is student focused; I want to make sure my students are learning. As they have different learning style, I have adopted my teaching ideas from different school of thoughts. Firstly, I believe in pragmatic pedagogy1 – most students learn by doing, so, I apply different instructional techniques and adopt of a variety of digital technologies and formats as teaching tools to make sure learning occurs actively. I bring students’ focus on the crucial current issues and guide them to find solutions that are needed NOW.

TEACHING MATERIALS

I have produced and delivered teaching and training materials in multiple formats. These include lecture items in PPT, Audio, and Videos forms; course syllabi, session planning, outline of topics, online quizzes, classroom activities, Pre-Post Tests, general and objective rubrics for assignments, Sample Assignments: Mid-Term and Final Assignment, Poster and Science Talk Rubrics, Course Evaluation Surveys  etc.

RESOURCES

Here you get course-wise recommended text books and other links to resources.

Please reach out with any questions about the products presented here or to learn more about my offerings. I am open to constructive feedback. Your inputs will help me refining the materials and improving my teaching approaches.

School LIbrary
 

GET IN TOUCH

2500 University Dr NW, Calgary, AB T2N 1N4

  • LinkedIn

Thanks for submitting!

Eyes high1.jpg
 
Beautiful Canada.jpg