Data & Science with Glen Wright Colopy

Philosophy of Data Science Series Session 1: Scientific Reasoning for Practical Data Science Episode 1: Critical Reasoning in Medical Machine Learning Data science in medicine and healthcare requires not only algorithmic and statistical knowledge but also a strong appreciation of the clinical environment in which (i) the data is being collected and (ii) the algorithm will be used. I'll showcase a scenario where a machine learning system failed to perform a "simple" clinical task and how critical reasoning was used to resolve the problem. Guest-host Kristin Morgan (University of Connecticut) joins us to lead the discussion in how this example is applicable to the broader field of biomedical data science. This is... Session 1: Scientific Reasoning for Practical Data Science Episode 1: Critical Reasoning in Medical Machine Learning Watch it on... YouTube: https://youtu.be/o5YmdoCiyug Podbean: Coming up next week: Applying Scientific Reasoning to Statistical Practice with Andrew Gelman (Columbia University) We're always happy to hear your feedback and ideas - just post it in the YouTube comment section to start a conversation. Thank you for your time and support of the series!

The Philosophy of Data Science Series Session 1: Scientific Reasoning for Practical Data Science Episode 0: Welcome to the Philosophy of Data Science Series! This is our very first episode of "The Philosophy of Data Science" series on Pod of Asclepius! We go over our plans for the series plus some thoughts on why data science is such a rich field for discussions on scientific reasoning. Your time is valuable and you deserve a good explanation of why the topics were chosen and how the series is structured to maximize learning. Topic List 0:00 New intro jingle for the series! 0:10 Welcome to the Philosophy of Data Science Series! 1:07 Modes of reasoning 5:33 Session 1 Overview: Scientific Reasoning for Practical Data Science 10:15 Session 2 Overview: Essential Reasoning Skills for Data Science 11:32 Keynotes and Session 4 14:15 Future Sessions Coming up next week: Critical Reasoning in Medical Machine Learning Thank you for your time and support of the series! It only gets better from here! (Seriously, it really does only get better from here. We've got Andrew Gelman coming up, plus Cynthia Rudin, Mihaela van der Schaar...)

Lisa LaVange (Gillings School of Global Public Health at the University of North Carolina at Chapel Hill) was the 2018 American Statistical Association (ASA) president and the director of the Office of Biostatistics in the Center for Drug Evaluation and Research (CDER) at the FDA. She give a high-level overview of issues surrounding Innovative Trial Design and Master Protocols. A great listen for anyone wanting to be introduced to the subject or (for those already familiar) interested in its growing breadth of applications. #datascience #statistics #biopharm #pharma #FDA

Amy Shi (SAS), Emily Griffith (North Carolina State University), and Elizabeth Mannshardt (EPA) discuss the many activities of the North Carolina Chapter of the American Statistical Association, including a lot of online activities that can be enjoyed even if you aren't in NC. The recording was made on the cusp of COVID...so updated information is posted below. NC ASA Activities NC ASA YouTube Channel: https://www.youtube.com/channel/UCPMPV3vCOY2dZka5ELPBWpA NC ASA Website: https://community.amstat.org/northcarolina/home

Molham Aref and Nathan Daly 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. Both Nathan and Molham with be speaking at JuliaCon 2020 at the end of July. It's free and online, so there's no reason not to attend. You can register for JuliaCon 2020 here: https://juliacon.org/2020/ 0:00 Intro 1:25 RelationalAI 3:25 Advantages of Julia as a foundation 4:21 "Full stack" data science 5:38 Advantages of Julia in the tech stack 6:30 Technical requirements of RelationalAI 7:45 Advantages of Julia (cont.) 10:00 Data munging, preprocessing, and transparency 14:30 Advantages of Julia (cont.) 18:35 RelationalAI's Innovation 22:00 Data Analysis and taking computational efficiency for granted 23:38 Who are the users of RelationalAI? 25:45 What are "knowledge graphs"? 28:30 Knowledge graphs for AI and Software 2.0 32:43 Julia as "executable math" 34:10 "Multiple dispatch" in a nutshell 36:20 Julia in the scientific community 38:53 See Nathan and Molham again at JuliaCon 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.

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.

John is back to show the 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!

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.

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.

Mike McArdle, co-founder and Chief Product Officer at Lucid Dream VR, is back to walk us through applications of VR that helps clinicians train for rare events and better understand the patient’s experience.

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.

Hear about new episodes as they come out by joining our mail list: https://www.podofasclepius.com/mail-list You can find the Virtual Undergraduate Career Fair here: https://ww2.amstat.org/virtualcareerservice/

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.

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.

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.

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.

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.

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.

Rob Scott, Chief Medical Officer at AbbVie, discusses the importance of a clinician’s perspective for keeping clinical trial development focussed on the patients. Rob talks about how the role of a Chief Medical Officer changes between a large pharma company and small biotechs. He then covers the key areas in which new developments in healthcare technology can help us better understand a patient’s response to therapies and interventions.

Gajanan Bhat and Xinping Cui discuss the major themes of data science in clinical drug and device development.

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.

Neurosurgeon and entrepreneur Nick de Pennington talks about the importance of automating clinical tasks to help doctors focus on the most challenging cases.

Niven Narain, CEO of Berg Health, discusses creating value through data platforms and AI in the pharmaceutical industry.

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

We’ve got a great lineup of speakers on deck. A quick explanation of who is coming on and why Glen has organized the episodes this way.

This is Part 2 of a two-part episode in which Allison treats the audience to a technical deep-dive into optimizing bespoke clinical models. In Part 1 of the episode Allison talked about her background, research interests and the research that earned her a win in the ASA Student Paper Competition in 2017.

S00 Ep04 Pt01 with Allison Meisner: Predictive Models in Kidney Injury This is Part 1 of a two-part episode in which Allison talks about her background, research interests and the research that earned her a win in the ASA Student Paper Competition in 2017. In Part 2 she will treat the audience to a technical deep-dive into optimizing bespoke clinical models.

Part 3 of a three part episode with Martin Ho and Greg Maislin, talking about the ASA Section on Medical Devices and Diagnostics (MDD). This part discusses the MDD Idea Exchange and Bayesian p-values. The other two parts of this episodes cover: Part 1: MDD Section Activities Part 2: Bayesian Methods and Digital Health Initiatives

Part 2 of a three part episode with Martin Ho and Greg Maislin, talking about the ASA Section on Medical Devices and Diagnostics (MDD). This part discusses Bayesian Methods and Digital Health Initiatives. The other two parts of this episodes cover: Part 1: MDD Section Activities Part 3: The MDD Idea Exchange and Bayesian p-values

Part 1 of a three part episode with Martin Ho and Greg Maislin, talking about the ASA Section on Medical Devices and Diagnostics (MDD). This part discusses the MDD Section Activities. The other two parts of this episodes will cover: Part 2: Bayesian Methods and Digital Health Initiatives Part 3: The MDD Idea Exchange and Bayesian p-values

Emma Hughes discusses how to find and cultivate technical entrepreneurial talent. She then talks about the critical challenge of making technical solutions sufficiently robust for clinical implementation.

This episode is Part 2 of a two part episode with yours truly, discussing personalized probabilistic patient monitoring. In this part, Glen describes a nifty statistical approach to vital-sign artefact detection. In the first part of this 2 part episode, Glen talks about using Gaussian Processes for identifying the deteriorating patient.

Part 1 of a two part episode with yours truly, discussing personalized probabilistic patient monitoring. In this part Glen talks about Gaussian Processes for Identifying the Deteriorating Patient. The second part of this 2 part episode will describe a nifty statistical approach to vital-sign artefact detection.

Welcome and hello! Glen introduces the podcast, himself, and what’s going on!