Karim ME “Machine learning and AI for causal inference from healthcare data”, 2nd annual Data Science and Health Conference, Vancouver, Nov 9th, 2021
Karim ME Healthcare data analytics in the era of machine learning and artificial intelligence, LifeSciences BC Access to Innovation, Vancouver Convention Centre West, Vancouver, Feb 5th, 2020.
Karim ME (joint work with Tremlett H; Zhu F; Petkau, J; Kingwell, E) Dealing with treatment-confounder feedback and sparse follow-up in longitudinal studies - an application of the marginal structural model in a multiple sclerosis cohort;
Invited session on ‘Novel methods and applications in the estimation of longitudinal effects’, Statistical Society of Canada Annual Meeting 2021, June 7-June11, 2021, Virtual
Invited Session - 7: Biostatistics and data science; 2nd International Conference on Applied Statistics 2019, Dhaka University, Bangladesh; December 27-29, 2019.
Karim, M.E. High-dimensional propensity score adjustment for analyzing electronic healthcare data: recent advances, Statistical issues in administrative data, Banff International Research Station, Banff, Feb 2019.
Karim ME (joint work with Pang, M.; Platt, R.) Comparing approaches for Confounding Adjustment in Secondary Database Analyses: High-Dimensional Propensity Score versus two machine learning algorithms: Random Forest and Elastic Net, invited session on Statistical Methods to Improve Drug and Vaccine Safety Surveillance Using Big Healthcare Data, XXVIIIth International Biometric Conference, Victoria Convention Centre, Victoria, Canada 10 - 15 July, 2016.
Karim ME (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; Zhao, Y.; Kingwell, E.; van der Kop, M.; Oger, J.; UBC MS Clinic Neurologists.; Tremlett, Helen) Causal inference tools for estimating the effect of beta-interferon exposure in delaying disease progression in a relapsing-remitting multiple sclerosis cohort data obtained from observational sources 2013 endMS Conference in December 2013, St. Sauveur, Quebec. [Invited poster presentation]
Karim ME (joint work with Gustafson, P) Adjusting for Exposure Misclassification in Bayesian Hypothesis Testing in Case-Control Studies, The First International Conference on Theory and Applications of Statistics; Dhaka University, Bangladesh; December 26-28, 2010.
— UBC Centre for Health Services and Policy Research (@CHSPR) February 23, 2021
Karim ME (joint work with Tremlett H; Zhu F; Petkau, J; Kingwell, E) “Dealing with treatment-confounder feedback and sparse follow-up in longitudinal studies - an application of the marginal structural model in a multiple sclerosis cohort”, Department of Epidemiology, University of Washington, May 4th, 2021,
URL.
Karim ME Causal inference in analyzing administrative healthcare data: Can we integrate machine learning approaches within this framework?, UBC Centre for Health Services and Policy Research, Feb 23, 2021
Karim ME Causal Inference from Large, Real-world and Complex Healthcare Data in the Era of Data Science, UBC School of Population and Public Health, May 6th, 2020.
Karim, M. E. Best practices of various propensity score methods in comparative effectiveness research, Biogen ALIGN meeting, Montreal, June 12, 2019.
Karim ME (joint work with Pang, M.; Platt, R.) Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?
Department of Community Health Sciences & George and Fay Yee Centre for Healthcare Innovation, Max Rady College of Medicine, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, May 9, 2019.
Biogen Symposium on Statistical Methods in Multiple Sclerosis, Cambridge, Massachusetts. November 2018.
Departmental Seminar Series, Department of Statistics & Actuarial Science, Simon Fraser University, April 6, 2018
Research seminar, Institute of Statistical Research and Training, University of Dhaka, Bangladesh, June 6th, 2018
Karim, M. E. Statistical Learning Approaches and Health Administrative Data, Big Data and Depression Care, St. Paul’s Hospital, Vancouver, 27 March 2018.
Karim, M. E. Comparing approaches for Confounding Adjustment in Secondary Database Analyses: High-Dimensional Propensity Score versus two machine learning algorithms, Drug Safety and Effectiveness Cross-Disciplinary Training / Drug Safety and Effectiveness Network (DSECT/DSEN) Monthly Seminar Series, Online Seminar, Mar 23, 2017. (100 registered nationwide, which is the maximum limit accommodated by the seminar organizers.)
Karim, M.E. Application of Machine Learning Techniques to Improve Causal Inference in Observational Studies., Seminar at School of population and public health, UBC, April 21, 2017.
Karim, M. E. Automated Confounding Control in Comparative Effectiveness Research: Help or Hype? Work in Progress Seminar, Hurlburt Auditorium, St. Pauls Hospital, Vancouver, April 12, 2017.
Karim ME (2017) Marginal Structural Models in Multiple Sclerosis: Recent Developments and Suitable Alternatives, Biogen Symposium on Statistical Methods in Multiple Sclerosis, Cambridge, Massachusetts. November 2017.
Karim ME (joint work with Gustafson, P.; Petkau, J.; Tremlett, H.; The BeAMS study group) Comparison of Statistical Approaches Dealing with Immortal Time Bias in Drug Effectiveness Studies:
January 19, 2016, Biostatistics seminar, Department of Epidemiology, Biostatistics and Occupational Health, McGill University, Montreal, QC.
February 8, 2016, Causal inference journal club, Faculté de pharmacie, Université de Montréal, Montreal, QC.
March 8, 2016, Epidemiology seminar, Centre for Clinical Epidemiology Jewish General Hospital, Lady Davis Research Institute, Montreal, QC.
June 30, 2016, Department seminar, Landmark Center, Harvard Medical School & Harvard Pilgrim Health Care Institute, Boston, MA.
Karim ME. Application of Propensity Scores in Epidemiology, December 2010, Institute of Statistical Research and Training Seminar, University of Dhaka, Bangladesh.
Karim ME (joint work with Rahman, P.K. and Matsui, N. and Ikemoto, Y.). Livelihoods of Chronically Poor in Rural Bangladesh. International Workshop on Chronic Poor in Bangladesh. 17-19 March 2007, The Institute of Oriental Culture, University of Tokyo, Japan.
Invited Presentations to Specific Research Groups
Karim, M. E. “Valid Causal Effect Estimates with Machine Learning Algorithms”, Causal Inference Journal Club Meeting, UBC Department of Statistics, 16th Feb, 2021.
Karim, M. E. “Deep learning-based propensity scores in large-scale study”, Causal Inference Journal Club Meeting, UBC Department of Statistics, 23rd March, 2021.
Karim, M. E. Mediation analysis using administrative data, BC-CDC, Vancouver, Oct 16, 2019
Karim, M. E. Confounder selection principles: Statistical and epidemiologic considerations,
Special seminar session on Epidemiologic Methodology, Institute of Statistical Research and Training, University of Dhaka, Bangladesh, Dec 26th, 2019
Epidemiology methods group meeting, VGH Eye Care Center, Vancouver, Oct 2nd, 2019
Stats group meeting, St. Pauls Hospital, Vancouver, Oct 7th, 2019
Karim, M. E. Navigating complex survey data analysis for health research, Statistics group seminar, St Paul’s Hospital, Vancouver, 10 March 2019.
Karim, M. E. Propensity score matching in presence of immortal time bias November 2013, Brain Research Centre conference centre, Western Pacific endMS Research & Training Centre, UBC Hospital, Vancouver.
Karim, M. E. How to estimate beta-interferon treatment effectiveness in MS using some fancy modelling, September 2011, Pharmacoepidemiology in MS Research Group (PiMS), Brain Research Centre conference centre, UBC Hospital, Vancouver.
Contributed Conference Presentations:
Karim ME (joint work with Hossain MB) “Implications of choosing different imputation methods while inferring about per-protocol effects of sustained treatment strategies”, ESPACOMP 2021 Conference, Nov 8-19, Virtual event.
Karim ME (joint work with Tremlett H; Zhu F; Petkau, J; Kingwell, E) Dealing with treatment-confounder feedback and sparse follow-up in longitudinal studies - an application of the marginal structural model in a multiple sclerosis cohort
a. Topic-contributed paper session, Novel perspectives on the estimation of longitudinal effects; Joint Statistical meetings, Philadelphia, Pennsylvania; August 1-6, 2020 (online).
b. Society of Epidemiologic research (SER) annual meeting, December 15 – 18, 2020, Boston (Online)
Karim ME (joint work with Pellegrini F, Platt RW, Simoneau G, Rouette J, de Moor K) The Use And Quality Of Reporting Of Propensity Score Methods In Multiple Sclerosis Literature; ICPE All Access (ICPE 2020 Berlin Virtual Event), September 16-17, 2020 (audio uploaded)
Karim ME (joint work with Atiquzzaman M.) Mediating role of pain-medication in the increased risk of cardiovascular diseases among Canadian osteoarthritis patients, International Society for Clinical Biostatistics (ISCB) Annual Conference, July 2019 Leuven, Belgium [poster presentation].
Karim, M. E. (joint work with Pang, M.; Platt, R.) Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?
Section on Statistics in Epidemiology, Joint Statistical Meetings, August 1, 2018.
International Society for Clinical Biostatistics (ISCB) Annual Conference, August 2018 Melbourne, Australia
Annual Meeting of the Statistical Society of Canada, Calgary, May, 2019
Karim, M. E. (joint work with Pang, M.; Platt, R.) Comparing approaches for Confounding Adjustment in Secondary Database Analyses: High-Dimensional Propensity Score versus two machine learning algorithms: Random Forest and Elastic Net, International Society for Clinical Biostatistics (ISCB) Annual Conference, 21-25 Aug 2016 Birmingham, UK.
Karim, M. E. (joint work with Platt, R., Tremlett, H.; The BeAMS study group) Estimating Inverse Probability Weights using Super Learner when Weight-Model Specification is Unknown in a Marginal Structural Cox Model Context: An Application to Multiple Sclerosis,
session on Biostatistics Applications, Annual Meeting of the Statistical Society of Canada, Brock University, St. Catharines, May 29 - June 1, 2016.
XXVIIIth International Biometric Conference, Victoria Convention Centre, Victoria, Canada 10 - 15 July, 2016.
International Society for Clinical Biostatistics (ISCB), Annual Conference, 9-13 July 2017 Vigo, Spain.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Tremlett, H.; The BeAMS study group) Comparison of Statistical Approaches Dealing with Immortal Time Bias in Drug Effectiveness Studies, session on Biostatistics in Action 1, Annual Meeting of the Statistical Society of Canada, Dalhousie University, Halifax, Nova Scotia, June 14-17, 2015.
Karim, M. E. (joint work with Petkau, J.; Gustafson, P.; Tremlett, H.; The BeAMS study group) The Performance of Statistical Learning Approaches to Construct Inverse Probability Weights in Marginal Structural Cox Models: A Simulation-based Comparison, The 3rd annual Statistical Society of Canada Student Conference, Dalhousie University, Halifax, Nova Scotia, June 13, 2015.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; Zhao, Y.; Kingwell, E.; van der Kop, M.; Oger, J.; Tremlett, H.) Estimating the effect of beta-interferon exposure in delaying disease progression in relapsing-remitting multiple sclerosis patients using causal inference tools, Session on Novel Methods for Analysis of Survival and Longitudinal Data, Section on Statistics in Epidemiology, 2014 Joint Statistical Meetings, August 2-7, 2014.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; Zhao, Y.; Kingwell, E.; van der Kop, M.; Oger, J.; Tremlett, H.) Logrank tests with the inverse probability of treatment weighting to assess the impact of beta-interferon treatments in delaying disability progression in multiple sclerosis, Session on Causal Methods and Applications in Variable Selection, Genetics, Mediation and Survival Analysis, Section on Statistics in Epidemiology, 2013 Joint Statistical Meetings, August 3-8, 2013.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; Zhao, Y.; Kingwell, E.; van der Kop, M.; Oger, J.; Tremlett, H.) A simulation study of methods used to reduce variability in the inverse probability of treatment weights for marginal structural Cox models, Annual Meeting of the Statistical Society of Canada, University of Alberta, Edmonton, Alberta, May 26-29, 2013.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; Zhao, Y.; Kingwell, E.; Evans, C.; van der Kop, M.; Oger, J.; Tremlett, H.) Comparing the direct and approximate approaches to implement marginal structural Cox models: An Application to Multiple Sclerosis, Inaugural Statistical Society of Canada Student Conference, University of Alberta, Edmonton, Alberta, May 25, 2013.
Karim, M. E. Reverse-engineering randomization!, Joint UBC/SFU, Department of Statistics, University of British Columbia, March 2013.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Zhao, Y.; Shirani, A.; Evans, C.; Kingwell, E.; van der Kop, M.; Tremlett, H.) A simulation study of the performance of the prescription time-distribution matching method to address immortal time bias, Session on Causal Inference in Epidemiology, Section on Statistics in Epidemiology, 2012 Joint Statistical Meetings, San Diego, July 28-August 2, 2012.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.) Generating survival data for fitting marginal structural Cox models using Stata, Stata Conference, San Diego, July 26–27, 2012.
Karim, M. E. A Path to Causal Inference, Joint UBC/SFU, Department of Statistics and Actuarial Science, Simon Fraser University, September 2011.
Karim, M. E. (joint work with Gustafson, P.; Petkau, J.; Shirani, A.; van der Kop, M.; Kingwell, E.; Zhao, Y.; Evans, C.; Tremlett, H.) Marginal Structural Models for Investigating Long-Term Effectiveness of a Time-Dependent Treatment: An Application to Multiple Sclerosis, Session on Innovative Approaches for Analyzing Repeated Measures Data, Section on Statistics in Epidemiology, 2011 Joint Statistical Meetings, Miami, Florida; July 31st, 2011.