Season 1
The episodes of Season 1 will be published biweekly starting January 13, 2020.
Season 1 will run from January through December 2020.
S01 Ep01 with Jeroen Bergmann and Daniel Mogefors: Needs-led Innovation at Oxford University
Jan 13, 2020: Originally developed in the Stanford biodesign ecosystem, the “needs-led” approach to healthtech innovation has rapidly become a key philosophy for those wanting to develop a viable healthcare solution. Prof. Jeroen Bergmann and Daniel Mogefors from the Oxford Healthtech Labs break down the key aspects of needs-led innovation and how researchers at Oxford University are using it
S01 Ep04 with Eric Stephens: Hospital Analytics & CSP 2020
Feb 11, 2020: Eric Stephens, Chief Analytics Officer at Nashville General Hospital, talks about building analytics capacities in the hospital setting and how hospitals select their priorities for new analytics projects. Then he discusses the cool events coming up at CSP 2020 and how applied data scientists have more options than ever for career advancement.
S01 Ep06 with Rob Scott: What are a Clinician's Priorities for Data-Driven Medicine?
Feb 19, 2020: Rob Scott, Chief Medical Officer at AbbVie, discusses the importance of a clinician’s perspective for keeping clinical trial development focused on the patients. He then covers the key areas in which new developments in healthcare technology and patient-specific data can help us better understand a patient’s response to therapies and interventions.
S01 Ep07 with Shane Burns: Data Platforms to Monitor Animal Health
Feb 24, 2020: The episode of milk and honey. Shane shows us some of the real-time data analytics platforms that track the health of dairy cows and honey bees. From wearables to stationary sensors, animals’ health is being monitored via rich multivariate time series, which leads to plenty of opportunities for analysis and optimization. Shane highlights how these machine learning applications have a great benefit to the animals health along with a strong business case. It’s a great visual presentation, where Shane shows you the data behind animal health decision making.
S01 Ep08 with Mona Kanaan and Ada Keding: What is a Stepped-Wedge Trial?
March 4, 2020: Clinical trials are at the core of our clinical science. But how to we design a clinical experiment? When do we deviate from the “gold standard” of a randomized control trial? Mona and Ada discuss the stepped-wedge trial design and recent work in the field.
S01 Ep09 with Dana Al Sulaiman: Engineering Sensing Platforms for Biomarker Detection
March 09, 2020: Dana al Sulaimen’s (MIT) work runs the gamut of biomedical engineering areas. She gives a great presentation on the clinical motivation for her work, engineering sensing platforms, and data analysis. Definitely watch the video for this one for some excellent visual material.
S01 Ep10 with David Madigan and Demissie Alemayehu: Risks and Opportunities of AI in Clinical Drug Development
March 23, 2020: There are many places in which ML/AI methods can be of benefit to pharmaceutical research (several have already been covered on the show). David and Demissie explain where AI can fit in to in vivo studies, which carries it’s own benefits, but also with heightened risk to to human test subjects. They go on to cover several other areas of interest including AI for observation studies and real world evidence. It’s a “big tent” conversation as we lead up to the Pfizer/ASA/Columbia University Symposium on Risks and Opportunities of AI in Clinical Drug Development.
Mihaela van der Schaar will be following up in a subsequent episode on this subject.
S01 Ep11 with Dave Hunter: Disease Network Modelling, Mixture Models, and Career Opportunities at SDSS 2020
April 06, 2020: Dave Hunter highlight a variety of cool life science collaborations he has worked on, including the network models used to describe AIDS transmissions and mixture modelling to describe pediatric cognitive tests. We then talk about the upcoming SDSS 2020 conference, and its newest additions to benefit early career researchers.
S01 Episode 12 with Paul Elbers: AmsterdamUMCdb, Europe’s first open ICU database
April 20, 2020: It’s not everyday that medical researchers give the world access to 13+ years of dense, high-quality critical care data. Intensivist Paul Elbers describes the data set along with the clinical priorities in collecting the data. Paul covers a range of topics including protecting the patients’ interests and anonymity, a clinician’s priorities when selecting clinical performance metrics, and the stages of validating predictive algorithms up to the stage of an RTC. The work done to create AmsterdamUMCdb is an incredible feat and a huge boon to the medical science profession.
S01 Ep13 with Stephanie Hicks: Data Science Education and the upcoming tracks at SDSS 2020
May 04, 2020: A mini-epsidoe with (fellow data science podcaster) Stephanie Hicks. Stephanie highlights the keynote speakers at SDSS 2020 along with the conference themes.
Stephanie will be returning in a few weeks to discuss her own research at the nexus of data science, genomics, and public health.
Bonus Episode with Wendy Martinez: Early Career Services for Statisticians and Data Scientists
May 11, 2020: Wendy Martinez (2020 President of the American Statistical Association) joined us to give an overview of career services that are available to statistician and data scientists. In particular, the ASA is running a resume review service. So if you’re a recent undergraduate: sign up for a free resume review. Not so recent? You can join in as a resume reviewer!
S01 Episode 14 with Mike McArdle: Virtual and Augmented Reality in the Life Sciences
May 18, 2020: Mike McArdle, co-founder and Chief Product Officer at Lucid Dream VR, breaks down the key technological factors that have led to the rapid increase in VR and AR solutions for the life sciences. He then walks us through two products helping companies and hospitals to accelerate training and talent development on their staff.
Watch or listen on: Youtube Podbean
May 25, 2020: Mike is back to walk us through applications of VR that helps clinicians train for rare events and better understand the patient’s experience.
S01 Episode 15 with Rita Hendricusdottir: Oxford Global Guidance to Navigate Medical Device Regulations
May 29, 2020: Rita Hendricusdottir (Department of Engineering Science, University of Oxford) show cases a new tool to help innovators quickly assess the regulatory buden of their medical devices. From answering the simple question of “Is my invention a medical device?” to the complex considerations for “which classification is my device?” the Oxford Global Guidance tool is designed to facilitate this initial evaluation.
Theme: SAMSI Month(s)
Starting in June, we’ll kick off a month of weekly episodes of the precision medicine research being conducted at the Statistical and Applied Mathematical Sciences Institute (SAMSI), which is one of the premier data science research institutions. We will follow this up with with an overview of other data science activities in the Research Triangle.
S01 Episode 16 with John Nardini: Machine Learning and Mathematical Modeling of Wound Healing
June 1, 2020: John discusses his work in the precision medicine program at the Statistical and Applied Mathematical Sciences Institute (SAMSI) to model wound healing. He describes the physiological mechanisms of wound healing and how to select a applications that are appropriate for mathematical modelling.
Watch or listen on: Youtube Podbean
June 8, 2020: John is back to show how machine learning can vastly speed up the selection of mathematical models. His presentation provides great visual intuition on how machine learning methods can help select mathematical models, even as measurement noise increases. It’s a huge improvement over selecting models by hand!
S01 Episode 17 with Xinyi Li: Big Data Squared - Combining Brain Imaging and Genomics for Alzheimer’s Studies
June 15, 2020: Xinyi continues the conversation on precision medicine research at SAMSI. Xinyi describes the challenges of combining genomic data with imaging data for modelling Alzheimer’s with the goal to supplement subjective diagnosis criteria with the more objective biomarkers.
Watch or listen on: Youtube Podbean
June 22, 2020: Working with brain imaging data, Xinyi has a lot of cool figures to show off in her technical presentation. She walks us through the image-on-scalar regression model and how it is used to infer a personalized “baseline” brain image along with the effects of different cognitive diagnoses.
S01 Episode 18 with Jane Herriman: JuliaCon 2020 & High Performance Computing for Data Science
July 9, 2020: Jane Herriman (Lawrence Livermore National Laboratory) talks about the versatility of the Julia programming language, from data science to high-performance computing. Jane is also an Executive Chair of JuliaCon 2020, which can be attended for free online at the end of July. Don’t miss out!
S01 Episode 19 with Lily Wang: Forecasting COVID-19 Infections and Deaths
July 13, 2020: Lily Wang (Iowa State University) summarizes common infection models and differentiates between the strengths and weaknesses of statistical modelling vs mathematical modelling. She then breaks down her own team’s forecasting model and the data outputs (“data products”) that it provides. This is a great, visually-intuitive presentation, particularly for early-career data scientists looking to understand how experts might apply different tools to the same scientific phenomenon (and how the work doesn’t end with fitting the model).
S01 Episode 20 with RelationalAI: Building a Knowledge Graph Database with Julia
July 15, 2020: Molham Aref and Nathan Daly (RelationalAI) describe their experience using Julia to build a next-generation knowledge graph database that combines reasoning and learning to solve problems that have historically been intractable. They explain how Julia's unique features enabled them to build a high-performance database with less time and effort.
Watch or listen on: Youtube Podbean
S01 Episode 21 with Richard Yetter Chappell: Are Challenge Trials Ethical for COVID-19?
July 20, 2020: Ethicist Richard Yetter Chappell (University of Miami) discusses his recent publications surrounding the ethical considerations of a challenge trial for COVID-19 vaccinations.
Watch or listen on: Youtube Podbean
S01 Episode 22 with Amy Shi, Emily Griffith, and Elizabeth Mannshardt: The North Carolina Chapter of the American Statistical Association
August 3, 2020: The NC Chapter of the ASA is a sponsor of the show, but it has plenty of other things going on. Amy Shi (SAS), Emily Griffith (NCSU) and Elizabeth Mannshardt (EPA) discuss how the NC Chapter of the ASA fits in with the national organization along with the many opportunities available for statisticians and data scientists in industry, academia, and government.
A key point (that deserves it’s own paragraph!) the NC Chapter of the ASA hosts many activities that are available to people outside of North Carolina or even the US. For example, we have a successful webinar series on data science and analytics that can be enjoyed anywhere in the world!
Theme: Data Science Frontiers in Pharma
S01 Episode 22 with Wenting Cheng and Weidong Zhang: Advances in Biotech/Biopharma and the Boston Chapter of the ASA
August 17, 2020: Wenting and Weidong discuss how the statistical challenges in the biopharm industry have proliferated with the unique demands of biotech and related life sicence industries. (Full description coming soon!)
S01 Episode 19 with Lisa LaVange: Innovative Trial Design and Master Trials
August 31, 2020: Lisa gives a great overview of the scientific concerns behind several different approaches to trial design, along with some great insights from her time as director of the Office of Biostatistics in the FDA’s Center for Drug Evaluation and Research (CDER). Lisa gives a comprehensive introduction to the available guidance on innovative trial design and master trials, while also covering issues like the scientific challenges of Bayesian trial designs. A really fun interview for anyone interested in clinical or pharmaceutical science.
S01 Episode 20 with Rachael DiStantostefano: An Introduction to Real World Evidence
Publication TBA: Whats the difference between “real world data” and “real world evidence”? What are some concrete examples of RWE changing the course of regulatory decisions? How many ways can you define the “replicability” of a study? Rachael at J&J comes in with a great presentation illustrating the key concepts to help get us up to speed on key aspects on the field. Her presentation is a must-watch for those not yet familiar with RWE and RWD.
S01 Episode 21 with Rita Hendricusdottir, Mark Birse, Rob Turpin, and Adrian Price: Regulatory Challenges in AI (Lessons from the AI@Oxford Conference)
Publication TBA: Last September, Rita, Mark, Rob, Adrian, and Glen were panelists discussing regulatory challenges in AI. We recorded a follow-up conversation to cover the main points of the panel and go into a bit more detail.
(Full description coming soon!)
Theme: Imaging and Activity Analysis
S01 Episode 23 with Kristin Morgan: Visualization of Gait Analysis Data
TBA, 2020: Prof. Kristin Morgan at UConn strikes the balances the needs and challenges of (i) clinical interpretability, (ii) automated data analysis, and (iii) physiological knowledge through a suit of interpretable graphs. Clinicians and physiotherapists are then free to feedback and make us their own mind.
S01 Episode 24 with Wes Thompson: Analytic Issues in Biological Psychiatry, Psychiatric Genetics
TBA, 2020: Wes leads us through an overview of the data analysis in psychiatric genetics. We then discuss a large longitudinal study in neuro-development. (Full description coming soon!)
S01 Episode 25 with Julien Oster: Cardiac Imaging and Function
TBA, 2020: Julien shows off one of the the most promising areas of cardiovascular science, in which heart imaging is combined with ECG and other clinical data. Great visual displays on engineering techniques.
S01 Episode 26 with Hubin Zhao: Engineering and Data Science for Infant fNIRS
TBA, 2020: Hubin wraps up our theme on “Imaging and Activity Analysis” with a presentation on how engineering and data science come together to meet a clinical need. Infant fNIRS data is current challenged on many fronts, including the availability of infant-appropriate devices. Hubin and his team engineered an fNIRS device that better fits the contours of an infant’s head, thereby improving the quality of data. He then turns around and uses the data to improve the quality of the device and clinical inference!