Analytics Lead, Machine Learning, Cytel
Transparent Machine Learning in Oncology
Tuesday, April 21, 12pm EDT
Machine learning (ML) aims to discover patterns from data that can be used for prediction. The use of “black-box” ML models in healthcare research and decision-making has been limited due to clinical liability and lack of trust from stakeholders. FDA guidelines for ML-based devices mandate transparency to assure continual safety and efficiency as notable recent failures have prompted increasing ML research into bias, fairness and causality. We will present our continuing work in immuno-oncology using Bayesian network models for predicting safety and survival outcomes, extrapolating from limited follow-up data and validating with external real-world data for key subgroups. We will also present ways to incorporate subject-matter expertise and causality, and address ways to enhance transparency and communication for stakeholders.
About the Speaker
Alind Gupta is a Machine learning specialist at Cytel in Toronto, Canada focusing on probabilistic graphical models and Bayesian inference. His current work focuses on the use of Bayesian networks and Markov models for modelling heterogeneity in response to cancer immunotherapy and for long-term survival prediction using clinical trial and real-world data. Alind has a PhD from the University of Toronto studying genetics of rare diseases.
Principal, Strategic Consulting
East Trial Design Software Webinars
Phase 1 dose escalation trials with ESCALATE
Wednesday, April 22, 2020, 11AM EDT
This webinar will enable you to better characterize the maximum tolerated dose to improve your probability of success in later trials.
At the end of the webinar you will be able to:
- Simulate and analyse Phase 1 dose escalation trials for determining maximum tolerated dose (MTD)
- Understand a range of different methodologies that are used in Phase 1 dose escalation trials
- Communicate findings to the clinical team using East’s intuitive graphs and tables
- Simulate a dose escalation design followed by single-arm cohort expansion
Conducting Sample Size Reassessment with Time-to-event Endpoints
Wednesday, May 6, 11AM EDT
This webinar will provide an overview of the SURVIVAL and SURVADAPT modules. Dealing with time-to-event endpoints, this will enable you to increase your sample size when your results look promising but lack the targeted power.
At the end of the webinar you will be able to:
- Use simulation tools to illustrate complex survival data at the design stage
- Explore trade-offs between duration and patient accrual, choice of boundaries, spending functions and hazard functions
- Utilize the promising zone to determine increases in sample size given information acquired during the trial
Refocus Your Enrollment to the Subpopulation of Interest with ENRICH
Wednesday, May 13, 11AM EDT
This webinar will teach you how to simulate an adaptive population enrichment design with a survival endpoint, which enables you to decide whether to continue enrollment in both sub-populations with or without sample size re-estimation, only continue enrollment from the sub-population of interest, or terminate the trial for futility.
At the end of the webinar you will be able to:
- Simulate a population enrichment design with a survival endpoint
- Understand the 5 different zones used in adaptive population enrichment design
- Utilize different zones to make decisions regarding adaptation on sample size and patient population
About the Speaker
Pantelis Vlachos is a Principal, Strategic Consulting for Cytel based in Geneva. He joined the company in January 2013. Before that, he was a Principal Biostatistician at Merck Serono as well as a Professor of Statistics at Carnegie Mellon University for 12 years. His research interests lie in the area of adaptive designs, mainly from a Bayesian perspective, as well as hierarchical model testing and checking although his secret passion is Text Mining. He has served as Managing Editor of the journal “Bayesian Analysis” as well as editorial boards of several other journals and online statistical data and software archives.
Executive Advisor, Strategic Consulting
Oncology and Rare Disease
*Details are pending and will be shared with registrants once available.
About the Speaker
Natasa Rajicic has been a practicing biostatistician for over 20 years. At Cytel, she helps clients explore and apply appropriate study designs and address difficult clinical development problems. Her experiences range from studies employing advanced methods to dose escalation to late-stage regulatory interactions on product development issues. Prior to Cytel, Natasa was a biostatistician at Pfizer in New York where she provided statistical reviews of business opportunities and due diligence evaluations, and oversaw statistical input on regulatory interactions related to submissions, label extensions and negotiations, and product safety inquiries. Earlier in her career, Natasa was a statistician at the Center for Biostatistics in AIDS Research in Boston. Natasa teaches Research Design at the Columbia University’s Applied Analytics graduate program.