Resources
Oct 9, 2025 |
54 min
|
521 views
|

Migrating to Open Source & the Future of Biostatistics | Beth Atkinson | Data Science Hangout

ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! We'd love to see you!

We were recently joined by Beth Atkinson, principal biostatistician at Mayo Clinic, to chat about the challenges of migrating from SAS to R, working with diverse and noisy data types (including wearable data and omics projects), foundational tooling like RMarkdown and Quarto, and maintaining statistical fundamentals amidst the hype cycle of new tools like AI.

In this Hangout, we explore the challenges of working with complex, high-volume data, like the data derived from wearable devices and medical charts. A challenge with wearable device data is that it can be super noisy, with issues like computers not syncing up, people forgetting to wear the device, or someone else wearing it. Medical chart data can be inconsistent; some things are recorded, and some are not. She also talks about the R/Medicine conference, the future of modern biostatistics, and the journey of compassionately helping an organization move from proprietary tools like SAS to open source tools like R.

Beth also works on omics projects, including genomics (looking at DNA), metabolomics, exposomics (chemical exposures), and multiomics, which involves looking at all of this information together in a holistic way. We hope you'll come along with us if you're interested in learning about the biomedical world of data!

Resources mentioned in the video and zoom chat:
🔗 R/Medicine Conference website → https://rconsortium.github.io/RMedicine_website/
🔗 arsenal R package (MayoVerse) → https://mayoverse.github.io/arsenal/ (The arsenal package was created to help encourage transition from SAS to R by providing equivalent functionality for summary reporting macros that people relied on.)
🔗 2025 Posit Table and Plotnine Contests → https://posit.co/blog/announcing-the-2025-table-and-plotnine-contests/

If you didn’t join live, one great discussion you missed from the zoom chat was about the general dislike of regular expressions (regex) and the tendency to rely on tools like ChatGPT to write complex regex syntax. Many in the chat agreed that regex is difficult to commit to memory but acknowledged the power of the tool. So... do you use an LLM to help with regex? 👀

â–º Subscribe to Our Channel Here: https://bit.ly/2TzgcOu

Follow Us Here:
Website: https://www.posit.co
Hangout: https://pos.it/dsh
LinkedIn: https://www.linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co

Thanks for hanging out with us! 💛

Timestamps
00:00 Introduction
03:25 "You do a lot of things that end in -omics. What are those things?"
05:02 "What are the types of data that you work with and some of the challenges that you face with those data?"
09:37 "What was your favorite new feature that made your work easier?"
11:42 "What is your favorite data science tool or R package that you find helpful in health research as a biostatistician?"
14:04 "I wanted to see if that's consistent with your experience [that 80% of workflow is data prep]" 17:07 "Does it scare you to hand off data to be cleaned by someone else?"
18:11 "What have you noticed that we still need to adhere to [regarding statistics fundamentals]?"
22:48 "Do you also produce reporting products as part of your role, and is your audience primarily internal and narrow, or do you communicate with a broader external audience as well?"
26:35 "Can you talk about a little bit of your personal SAS experience as well as the bigger organizational change maybe that Mayo is is doing?"
30:05 "What are some of the roadblocks that are faced in a SAS-to-R journey and and how can we find compassion for the people that we are helping to transition?"
33:55 "What is the community aspect internally at Mayo Clinic around R?"
35:43 "How do you store and manage all of that [data]?"
40:41 "What tools and skill sets should we focus on if we want to get into biostats today? Do you think it's important for people to still learn SAS if they're coming in fresh? And how about the future of biostatistics as a role separate from data science?"
45:48 "Is it possible for someone with a nontraditional background to make these transitions [into computational epidemiology]?"
48:10 "What's the source of most of these innovations?"
50:05 "Could you talk a little bit about R/Medicine conference?"

image: thumbnail.jpg

Transcript#

This transcript was generated automatically and may contain errors.

Hey there, welcome to the Paws at Data Science Hangout. I'm Libby Herron, and this is a recording of our weekly community call that happens every Thursday at 12pm US Eastern Time. If you are not joining us live, you miss out on the amazing chat that's going on. So find the link in the description where you can add our call to your calendar and come hang out with the most supportive, friendly, and funny data community you'll ever experience. Can't wait to see you there.

All right, I am so excited to introduce our featured leader today, Beth Atkinson, Principal Biostatistician at Mayo Clinic. Beth, welcome. I'm so glad to have you here. Could you please introduce yourself for us? Tell us a little bit about what you do. And I will also ask you about something you like to do for fun.

Sure. I work at the Mayo Clinic. I'm a biostatistician there. I've been there for 35 years. I don't know how that got to be 35 years, but it is what it is. I start when I started off, almost everybody worked, used SAS on the mainframe computer. So you wrote a job and you submitted it and you waited for things to run in the queue and took a break together because it was all queue-based. And pretty soon after, we got a Unix system and people started transitioning and we had S Plus and I got involved with S Plus and working with Terry Thurnau on the survival package and our part. And I kept asking him questions of, well, can we do this with our part? And he finally just said, you do it. And that's how I got involved. And so I have been involved with the infrastructure of S Plus and then migrating to R almost from the beginning.

So I work on a variety of different types of projects. I work on clinical trials. I work on genetics, omics projects. I've done things with epidemiology. I try to look at a number of different things. A lot of the projects I work on are related to aging and understanding what is aging and how do you measure it and what are the diseases that change with aging?

Okay. Those were a lot of things I would love to get examples of. So you talked about the survival package. You work on survival analysis and the R part package, which I think is a regression tree package, right? Yeah. So regression classification. Okay. And you also said omics. A lot of things that end in omics. What are those things?

So like genomics is looking at the DNA. So then you've got things looking at the RNA. You've got metabolomics. So there are measures of the metabolome. There are exposomics that they're looking at in the blood and other samples, trying to understand that the chemical exposures that you may have had. Everybody's looking at different aspects of the body, looking at your gut biome and understanding what it is that you've eaten and how that might influence your health. And multi-omics is hot now. So people started off by looking at just the genomics or just the proteomics or just the microbiome. And now people want to see how do we look at all of that information together, which is a huge challenge.

Yeah. Raha also says lipidomics as well. Yes. Lipidomics. Yep. Yeah. Thomas says, when I see omics, the only thing I can think of is comics. And me too. It just looks like the word comics to me. Okay. Could you give us a little bit of an example of the type of data that you work with? So we are from all these different industries and we might work with completely different data than you do. Transactional data, sales data, customer data, click data, who knows? What are the types of data that you work with and some of the challenges that you face with those data?

Working with wearable and medical record data

So right now I'm starting to look at data from wearable devices. So wearable devices, I've got my Fitbit on my watch, got something looking at the aura ring. So you get measurements every day for each person. And sometimes computers don't sync up or people forget to wear their device or somebody else wears it. Or it's very noisy and how do you collapse it into something that's explainable? And that can be a challenge.

That sounds really difficult. You're looking at sleep and you're looking at heart rate and you're looking at things like that. So that is one challenge. So a lot of the data also has is what's available in the medical charts. So it's some things are recorded, some things aren't recorded. So you want to understand BMI. You want to capture the BMI from the medical records and some people have lots of measurements and some people don't come in as often. They don't get it measured when they come in. And you have to estimate or sometimes it's written in the wrong units, especially historically, or people who are pregnant. And so that's not really capturing who they are and what that might do. So you have to pay attention to that.

That sounds extremely challenging because I think I thwart my Apple watch all the time. My Apple watch, if I knit or crochet or sew, it thinks I am running a marathon. It's like, do you want to record an outside run? And I'm like, no, I want to knit. What are you doing? It is so confused by everything that I do. And I think, wow, anybody who's in a study who's doing anything with their hands is probably confusing the heck out of their wearable device, right? Right.

Oh, you guys, I'm on the wrong Slido. Hold on. Let me find the right Slido so that we can make sure that we ask questions. If somebody has asked a question. I may have been slow in updating the short one for it, which is probably why that's happening. But if you refresh, it will be the right one. It's okay. I'm on the back end of Slido. If somebody asks the question in Slido and I can't see it or I'm not asking it, let me know because yeah, I see two of them. All right. I think Dami asked a question, but there's an asterisk there. Oh, dang it. See, I don't see anything. Okay. One second. We're going to go back.

Well, and one of the, I'm in a research study right now where every week you're supposed to record your voice and vowel sounds. And so then they're going to map that to cardiac. It's a cardiac study so that they're wanting to somehow translate that to understanding who's having cardiac issues or something. Oh, wow. That's really interesting because I have a thyroid disease and vocal symptoms are part of my follow-up every time, right? Because your thyroid is in your neck. So if you have things happening on your thyroid, they might be affecting the way that you talk. And I do, right? Like I have things happening on my thyroid that have to be checked long-term. That's so interesting. Wow, wow, wow.

Okay. I'm going to Google a little bit about that, but we do have so many questions in Slido. You guys, I'm on it. I'm on the right Slido. We made it. And Dami did have a question. Let's go find it. All right. Dami asks, you have such a long history working with a lot of different stats programs. What was your favorite new feature that made your work easier? Oh, I like this one because things have changed a lot over the past couple of decades.

RMarkdown as a game changer

RMarkdown was a game changer, hands down. It totally changed the way that I do my job because I'm writing a report partly just for my own sanity of recording what it is that I'm doing and I can document kind of here's my thought process. So sometimes I'll just write a version of it for myself and then a smaller version that I'm going to share with the investigative team because I have a lot of projects that I do something and then I don't hear back from them for maybe five years and trying to keep track of what in the world did I do and what was I thinking about five years ago. I'm lucky if I can think last month.

RMarkdown was a game changer, hands down. It totally changed the way that I do my job because I'm writing a report partly just for my own sanity of recording what it is that I'm doing and I can document kind of here's my thought process.

I was going to say maybe like last week I will have already forgotten. Marcus says, where are my SWEVE homies at? And I have a question for everybody in the chat. Do you say SWEVE or do you say SWEVE? Because I say SWEVE. I say SWEVE. I'm always feeling like I am the one saying everything wrong. Dami, I think maybe says SWEVE. I see a SWEVE in the chat. Okay. I love that. That is an amazing answer and I feel like Quarto is equally magical as a transition. It took me a little bit to hop over to Quarto from RMarkdown, but I made that jump and I love it.

I wanted to hop over in Slido to our next question here. And it is an anonymous question. It says, also a biostatistician here, whoever you are, hello, recognizing that there is a lot of overlap between data science and the more traditional statistics field. I was wondering what is your favorite data science tool or R package that you find helpful in health research as a biostatistician? So this could be RMarkdown, maybe some packages.

Yeah, there is definitely a lot of overlap because I do a lot of data mining, using a lot of data mining tools and other types of things. So, yeah, we have discussions about what does it mean to be a data scientist and what does it mean to be a biostatistician? And it is not always clear. We stumped you, Beth. I'm sorry. Yeah, just, you know, some of the tools for working with larger datasets, I think is kind of one of the challenges that I have is, you know, if I've got, I had one project where I looked at all of the medical records, or all of the diagnostic codes for everybody in Olmstead County, you know, over, you know, a 10-year period, which is just lots of records. And so, using more efficient ways to merge data and subset and understand that was important. So, general tools for working with large data, I think, is...

That is an area that I feel like I know the least about, and I always get FOMO when people talk about it. Nick Crane had a talk on, like, big data stuff at the composite conference that I was, like, skimming through. I'm like, wow, I don't know what any of this is. Right. I need to have Nick on to talk about it. Okay. I have a question here in our lovely Slido. Everybody go ask questions in Slido, and don't forget to upvote your favorite question. It is from Nick. Nick Drew, would you like to unmute and ask your question yourself? Let's see if we can find Nick. There he is.

Hi, Libby. I can hear you. Great. Thanks, Libby. Hi, Beth. Welcome. Yeah. I had a statistics professor say one time that in his work as being a biostatistician, 80% of the workflow was around prepping and getting the data ready for analysis. I wanted to see if that's consistent with your experience, and if so, how do you balance that with all the other tasks that are so important, such as, you know, actually doing the analysis, communicating results? So, what's your experience like in that regard?

Cleaning data, organizing data, pulling it together, understanding it definitely

takes up a huge amount of time. Then communicating results sometimes in working with the investigators.

For some of it, I am fortunate that I can delegate to other people and say, can you create a clean version of the data for me? And, you know, some projects I do it, but for others I can get other people involved, and that gives me kind of the bandwidth to think about all the other aspects. Because I think also just the being suspicious of things that are too good, results that are too good, or we face a lot of hype of, oh, this is the answer. You know, when I first started doing genetics, GWAS was going to solve everything. We were going to know all of the answers by doing GWAS, and it was, if you had 100,000 variables, that was great, and then it was 500,000, then it was a million, then it was, oh, exome sequencing, that's going to solve everything, and now it's the artificial intelligence, that's going to be the answer.

I put GWAS in the chat as genome-wide association study. Is that right? Okay, correct. So looking at the DNA of a bunch of people and comparing genetic variations for specific diseases and traits and stuff like that, right? Yes, lots of buzzwords. I wish that I could just be like, hey, some other people in other places do this data cleaning for me, but that gives me a little bit of fear where I'm like, oh, if I'm not the one cleaning the data, maybe I won't understand it as well. Does that scare you? Yes, it's challenging. So for a lot of new data types, I will dig into it. So for some things, I dig into it enough to understand it and then say, have worked with the team member to take it to the next step. So I've played a little, I kind of understand a little bit, and for some tasks, I trust the people on my team more than I trust what I'm going to do. Yep. That makes sense as well. Totally understandable.

AI, statistics fundamentals, and the hype cycle

All right. Thank you for the explanation. Thank you, Nick, for the fantastic question. Let's see what else we have going on in the Slido because there were two questions that I would love to combine. There was an anonymous one asking where Mayo Clinic is on its AI journey, but there is a more specific one that came from Brijesh. Brijesh, if you are available to ask your question live, you could unmute and ask that. That'd be great. Do we have Brijesh? Where are you, Brijesh? There he is. Hey. Hey, can you guys hear me? Yes.

Hey. So my question is, given how AI is changing the landscape of many things we do from a data science machine learning standpoint, the one aspect that it's not really able to touch adequately, I would say, is data engineering, which is kind of still fundamental to what we do. Among all of these things, there are certain fundamentals that we still adhere to, such as understanding the basics of statistics to begin with. What have you noticed that we still need to adhere to, and how do we go about doing that given that LLMs can, quote unquote, do anything and everything these days? So what are your suggestions on that?

I'm seeing a lot of presentations where I was at a conference yesterday and people had 20 versus 30 in a group. They ran all of these models and did all of these fancy things and optimized all their settings and said, oh, our model's great. I'm a little suspicious about how well that's going to do in the practice. So it's using the tools that are available, exploring things, but questioning, thinking back through, are the results too good? Why is it causing that? Being suspicious. I have to be careful. It's a fine line between being the naysayer because everybody wants to use these tools and thinks they're magical and can do everything. So I don't want to be too negative, but at the same time, it's just another tool. You have to think in terms of, you've got a million variables or attributes that you're looking at, but you have very small sample size. Is it really representative? Is it going to really be helpful? I guess that's the balance that I'm struggling with, especially coming from the statistics.

I have to be careful. It's a fine line between being the naysayer because everybody wants to use these tools and thinks they're magical and can do everything. So I don't want to be too negative, but at the same time, it's just another tool.

Thanks. Thank you, Rajesh, for that great question. I think that that's something I've been hearing over and over again, actually, from different people about AI, especially in talks at Posit.com, was the helpfulness question is the main determining factor. It's like, try it out. Is it helpful? If it's not, abandon. Go back to your other thing. Don't try to force it if it's not a helpful thing just because it's AI.

Yeah. I mean, chat GPT, when I have to do regular expressions, is great because I can never remember all the specific syntax for doing a specific task. But there are other things that some of these tools aren't as helpful for, and sometimes just a penalized model, simple penalized model, is more than sufficient.

Right. There's a lot of people in the chat saying yes to regular expressions. Regular expressions are terrible. Same. If I get past a certain level of complexity in RegEx, I am going to go to chat GPT and ask for some help. I have seen some terrible RegEx created by chat GPT, unfortunately, because you can go too far. But yes, it's a fantastic, fantastic use.

All right. Thank you so much for your questions, everybody. Let's hop over to Slido again and take a look at what we've got. Don't forget, you can upload questions. If you see ones that you really like, go ahead and put a little bit. Keep it simple is a good comment there. Yes. I would rather do several rounds of RegEx, actually, layered RegEx, than try to put everything in one RegEx. That can get wild. Let your RegEx be a layer cake, everybody, if you can.

Reporting and tailoring outputs for different audiences

Okay. We had a question that was about reporting that I would love to talk about here. It says, do you also produce reporting products as part of your role, and is your audience primarily internal and narrow, or do you communicate with a broader external audience as well? How do you tailor your reporting to suit different audiences? I'm on a number of different projects. Some of them are big grants, multi-year grants, and some of them are just short-term. They have something, analysis, that they're looking at. Most of the teams I'm working with are internal. Sometimes there are also external team members on the projects. I find it helpful to write a general report using the RMarkdown or Quarto of, here's what was done. It makes sure everybody's on the same page in terms of, here are the results, here's where we started with, here are the methods that were used. I've got some teams where the people know and so then I turn on being able to share the code if that's something that's helpful for them. It really depends on the sophistication of the team members, what it is that they need, but it's not, I'm not doing myself, I'm not doing reports for large audiences.

Yeah, so nothing that's like a big public report or anything. There are people in our group who are creating dashboards that lots of people are using. Yeah, it's definitely a report. I had talked to a bunch of people in the past week who were interested in parameterized report building in Shiny apps, actually, which has been on my radar for a while, is a fun thing to do. And Marlene, if Marlene's here, I know she's worked on that before. So if anybody has any information on that, I'm putting a call out. If you know about parameterized report building inside of Shiny apps, using Shiny apps, I'd love to hear it.

Okay, let's move on to- Well, and I will do parameterized or markdown reports. So I've got regular DSMB meetings. So clinical trials, you have to do reports on, here's the recruitment and here's the adverse events that are seen. And so for the big team, you have to do it so that they don't see the randomization. They don't see the differences between the groups because they need to be blinded. But then for the advisory committee that aren't part of the regular team, they need to see that detail. So then I've got a version that's for them and a version that's anonymous.

Nice. There's an opportunity there for Quarto's conditional offenses, right? I love those. Show this, if this, if not, don't do that. But I only know how to use it with the export types, like PDF versus HTML and stuff. I guess you can parameterize it in another way. I'm not sure. Yeah, I do it in markdown. Okay.

SAS to R migration at Mayo Clinic

Well, let's talk a little bit about SAS because we have several questions about it. Rachel had asked about the SAS to R transition, best practices. There's also a question that's anonymous that says, what is Mayo's SAS and R approach or strategy today? It sounds like you've made the switch and are there still legacy SAS users, but you have been in the R pipeline since S. So for a long time, can you talk about a little bit of like your personal SAS experience as well as the bigger organizational change maybe that Mayo is doing?

So Mayo is still using SAS, especially in the clinical trials area. But a lot more people have migrated to R and that because coming out of school, that's what people know. They don't get trained in SAS, but there's all this legacy code. This is how, when you're doing so many studies, you build up a lot of legacy code and that makes it really challenging to migrate. We've got one particular area of data that we need to pull from and that's still only available in SAS. So we have to use SAS for some of those things. So we're trying to kind of use the best tools for the situation.

Always the best idea to use the best tools for the situation. I think it's really interesting to hear that academia is actually sort of moving the needle on this one because we always think of academia as just being behind the curve always, right? Like always behind. But they don't have money. Yeah. Yeah, exactly. I learned SAS in university alongside R and once I got out of my undergrad program, I couldn't afford to keep using SAS. I could use SAS, the academic on demand version or the university version. There was a couple of options back then for using it for free, but there were such limitations on it. You couldn't do much with it. And out license was just so expensive. So yeah, it makes sense. That's a really, really good point. Of course, academia is moving the needle. They don't have any money to just pump into big SAS license pools.

Okay. Let's see. But I think part of the transition is also figuring out what are the tools that people rely on. So we had some in-house macros that these are summary reporting things that people relied on for all of their projects. So can we do the equivalent in R? And so we created the arsenal package because it kind of, here were things that at the time weren't easy to do in R and we needed to do. And so that helped encourage people to transition. So what are the tasks? What are the roadblocks? And can you say, well, this is how you would do it in R and this is maybe the advantages. Again, our markdown was something that was added value.

Yeah, that's a great question. I wanted to ask you sort of the human side of that.

What are some of the challenges that you face when you're talking with people who are staunch SAS users or very, very long-term SAS users and you're saying, okay, well, we're moving in this direction towards R. What are some of the roadblocks that they sort of face and how can we find compassion for the people that we are helping to transition? Because I think for a lot of us, we're like, SAS sucks, boo SAS, just use R. And there's not a lot of compassion behind that.

But if somebody came to you and said, you must stop using R, you must now use something else, that would be difficult for you. So how do you face the human side of that?

Well, and it's hard because we're all busy and we don't have time to learn something new and taking time out of your day to struggle with something when you know how to do it in the other language. I know how to do this in SAS, it's going to take me 10 minutes, but if I have to do it in R, it's going to take a lot more time. And where do I charge my time to do that? Because we have to account for the time that we're spending. So trying to find, here's example documentation to say, okay, if you have a project like this, here's kind of some of the workflow that you might want to have, and here's some code that you can steal. Having places to start with is always helpful as opposed to, here's a blank page and you have to start from scratch.

Yeah, I was going to ask, do you, as a sort of organizational or systematic approach, do you find it more helpful to say, oh, here are foundational stuff in R and here's what the data types are? Or do you just jump right into, here is a workflow, here's how the whole picture works, the whole game presented, because you're already a person who knows how to program and we're going to skip all the basic stuff and you can fill that in later? It's kind of a combination. So it helps to have some of the basics and know some of the lingo and what somebody's talking about the data type and what is a function versus a macro.

That's a good point. I was pointing out the differences and how they sort of translate. Like, okay, you really like macros in SAS. Here's how you can get that functionality in R and still feel satisfied. Or like, oh, you really like this output in SAS, this specific, you know, you really like proc freak, or you really, really like, you know, just some specific outputs. Here's how you can kind of get all of those same things in the same way. But then also having examples of here's, you know, here's a mock project and here's how you could kind of work through that. And here's some ideas that would be helpful. And, you know, chat GPT and tools like that are also helpful now in that you can at least stick something in saying, here's my SAS code. Can I come up with something? You know, what would, what do you do in R? And it may not be the best R code. That usually is kind of weird sometimes, but it gets you started.

And at least you can have a conversation with somebody around what needs to change for it to work. Yeah. I mean, the other thing is that when I'm working with team members, I will give them, here is some example code of how I would do this in R. You can use either SAS or R, but I'll give it, give you a start in R.

Building an internal R community

I like that. I was just going to say, what is the community aspect internally around R? Is there a concerted effort to build a community of practice around R and make sure that people have support? Are there like little training teams that get together or is it more of a one-on-one transition type of conversation? We've got R stewards. So I'm one of the R stewards, Jason Sinwell's on here. He's another one of the R stewards. So we try and, um, so we've got a small team and we try and organize training, regular seminars. We're now trying to kind of break into small groups and say, what are, you know, areas where we need documentation that's specific to Mayo or where people are struggling and can we improve on that? You know, we had a group that was looking at REDCap. So REDCap is a tool for capturing data, for entering data, that's used a lot in medical institutions. And so getting that to work well with, with R and at Mayo was something to, we created some documentation around that. So we're trying to, to add value because when you just Google, it's can be overwhelming because there's so much out there and what do I trust and what, whatnot.

And I'm sure there, things need to be verified on the inside as well. Well, this sort of covers the question that has risen to the top of the heap here from Dan Veltri, I think that says, it sounds like you have sources of data coming from many different devices all at once. How do you store and manage all of that? Is it like a data lake house type of deal? Is REDCap the place that things are actually stored?

We have three different systems for studies to enter their data. And so those get stored in different locations. We've got the electronic health record and we can use, it's now in the cloud so we can use SQL code to pull from that. And we get things from surveys, we get wearable devices, we get genomic data from different data types. So part of what I and others do is putting that all together for a particular research project. And then we store that in our Linux system and, or in the Google cloud environment. And then we have an archival system. So we, you know, every project has a number, a tracking number, and we can find it in metadata surrounding those numbers. Okay. So complicated.

Working with new and unfamiliar data types

We had so many questions around the data types and the wearable data as well. So from this question from Dan, Dan, thank you so much for that question. I should have asked you to unmute and ask it yourself, but it was such a good follow on. But there was another one about, let me see if I can find it here. I think it was from Rohan. Rohan, if you're available, you could unmute and ask that live if you would like. Oh, I found it. I'm going to highlight it. Okay. Can you guys hear me? Yeah. Hey.

Great. Hey. So Beth, biostatistics has a bunch of different domains and data types, whether it be streaming, microbiome, omics. Say that you're entering a new domain for the first time. You've never seen the data structure before. What do you have a typical script or process when you're trying to learn that data? I'm Googling a lot to see what's out there. Lately I've been asking, with the aura ring, I was asking chat GPT, can you show me some example data and how I might look at it and publications that people have used? Because that's kind of my latest data type that I'm trying to look with. Or if there are other people in our area that know something about it, you know, trying to learn from them. Because, yeah, you're right. Every data has its own challenge and you can't be an expert in everything.

No, absolutely not. And I remember I did, I had a project in undergrad, one of my first R projects, which used wearable data. It was confusing because it was just stuff I'd never seen before. I'm like X and Y and Z axis, and then variables like yaw, where I was like, what the heck is yaw? I had to Google what these things were and understand the geometry of wearable devices and accelerometer data in order to make any sense of it. And I can imagine that being a huge challenge every single time with new stuff.

Well, when I first started getting into the genomics data and I was having to use SED and awk and all these basic, you know, bash scripting and things that I had no clue what it was that I was doing. I have no idea what I'm doing in bash either, or ZSH as it is now in Mac. I feel like I Google every single thing I do, even if it's something I've done 50 times. Also, I try and kind of have a central place where I keep tips on this is what I had to do in order to figure this out. Because I figured this out for one project that's stored somewhere, and I can't remember where I stored that project. That's often my challenge. I think that's everyone's challenge.

Career skills and the future of biostatistics

I would love to ask about some career stuff, because we have lots of career questions coming in. And I think maybe we can wrap some of them together. Okay. So, one of them is about tools and skill sets. So, it's sort of like, what do you consider are the more relevant tools and skill sets to be mastered for a present day biostatistician compared to maybe previous years? Like, maybe previously you really needed to be versed in SAS, and maybe now it's really important that you are more familiar with open source tools. I don't know. And then there's also a question from Edward that was like, do you think that biostatistics as a role is going to continue as distinct from data science in the future? Those kind of go together. Can you talk about what tools and skill sets we should focus on if we want to get into biostats today? And then maybe the future of biostats as a role.

I guess I've had to do, I've been successful in part because I've been flexible in learning new tools. So, whatever I learned in school was a good starting point. But being open to learning new tools in general is important. R is great for some things, but I've got a couple of projects where I need to use Python now. So, I'm teaching myself some Python. And that it's constantly been that. When the GWAS world, there were all sorts of separate packages and I had to learn how to use those. So, it's never going to be just one tool, but I think knowing R is a great starting point to get the basics and the structure and how you do things. And then you change the syntax, you change the programming language, but some of the concepts are still the same.

I think knowing R is a great starting point to get the basics and the structure and how you do things. And then you change the syntax, you change the programming language, but some of the concepts are still the same.

Do you think it's important for people to still learn SAS if they're coming in fresh? If you're taking over a project where it's all in SAS, then it would be. But for most areas, it's probably not going to be as important.

Okay. Very, very good feedback. And how about the future of biostatistics as a role separate from data science? Do you see biostatisticians having a role change where they're like, we're just going to call them all data scientists now? For example, as a parallel to this in insurance, which is a world that I come from, a lot of people who are in various actuarial departments are now data scientists. They don't have the actuary title anymore. So, I'm wondering if that's happening in biostats. Maybe Edward's question might have leaned that way too. Well, and it also comes into pay, and data scientists tend to have higher salaries that are offered, at least for right now. That's true.

I still think of data scientists as working with really big data and databases and focusing more on does this algorithm work versus how do I interpret the individual variables and what are the implications of that. So, it still seems like there's a difference, but yeah, the labels are going to be what they are at different institutions. I think that's very true. Different individual companies are going to go different ways for different reasons, and it's hard to say how that's going to pan out kind of industry-wide probably. But if you're doing a clinical trial and you've got certain regulations and you've got these structures, that doesn't feel like it's the same thing as data science. I don't know.

Yeah, I mean, there's a blurry line. I think maybe Zach or Nathan in the chat had said the definition of a data scientist as a role is just such a blurry thing now, kind of a nonsensical word, because who knows what that could mean at different institutions. Well, I wanted to, since we have like eight minutes left,

I wanted to hop in and do a sort of career-focused section here, and Dadakshan had a question. If you are available to ask it live, you could unmute and ask this one. I'm going to highlight it in Slido so it goes to the top, because it was asking about a non-traditional background, and I love this question. I don't know if I see her unmuting anywhere. I did that unmute, but I think maybe, oh, I think. Hi. Hi, everybody. Hey, hey, hey. Hello.

Hello. Hi. So my question is about the epidemiological data, like you collaborated with that or you directly work with the epi data, or like many people, like I am interested in computational epi, but I don't have a traditional epi background. So was the transition easy, like you yourself is from the stag background, right? So I just want to kind of understand this pivot transition or this kind of thing. Yeah, and is it possible for someone with a non-traditional background to make these transitions inside of your space?

And we've got people that start off, we've got, you know, different roles. So we have some people that are statistical programmers, so they have a bachelor's degree in some kind of quantitative field and, you know, demonstrated, you know, programming skills. And then we've got people that are, you know, my level that are more master's degree level, and then we have people at the PhD level, and it's not perfect division, but depending on what it is you're doing, you know, you may or may not need the traditional degree and things like that. For epidemiology, we've got a lot of people in epidemiology, so I've worked, you know, I got trained by them in terms of the terminology and the things that are important there, because every domain kind of has its own lingo. A lot of times, it's part of the challenge is just understanding that lingo and what it is they mean.

Yeah, talk to people is always my best advice to everybody. Thank you so much for your question, and we are creeping closer to the end of our hour here. Let's see if we can rapid fire get in a couple more questions. Joey, you had a question, Joey Marshall, that I also want to know about, if you're available to ask that real quick.

Sources of innovation in medical research

Yeah, I'd love to. Hey, Beth, thanks for hanging out with us. Kind of at the top, you mentioned all these, like, really cool innovations, like predicting cardiac health outcomes from voice data. That was just one. I'm wondering, what's the source of most of these innovations? Does a lot of the innovation in your field come from academia? Is it from nonprofits or national labs or industry? Where do you think some of the coolest ideas are coming from right now?

And, you know, for me, a lot of it is, you know, the doctors that are working with the patients, and they're making observations, and then they're, you know, seeing sometimes they're collaborating with industry to say, you know, gee, I really noticed that these people, you know, were having voice issues before they develop Parkinson's officially. And, you know, can we capture that somehow? And partnering with somebody in industry saying, oh, we can measure this or these wearable devices or whatever. So it's that collaboration between different groups or, you know, the, you know, let's measure these things in stool instead of, you know, this is a barrier for people to come and get the colonoscopy. Can we do, find a solution to get more people to get tested? And so then, you know, let's, you know, work with developing that. So it's, it's, we're really trying to do patient driven, you know, what, what are the needs of the patients and how do we improve that?

So it's, it's, we're really trying to do patient driven, you know, what, what are the needs of the patients and how do we improve that?

Sounds like it's a lot of talking to each other again and being in community with each other. Well, I would love to talk about community real quick as our last little two minutes of combo.

R/Medicine conference and community

Beth, you are on the planning committee for our medicine conference. I put a link to that in the chat. Could you talk a little bit about our medicine just so that the people who don't know about it can get on board with it and attend it with me? Cause I love attending it. Yeah. So our medicine, we started off as an in-person conference for a few years in focusing on aspects of how, how R is being used with within the medical field. But we've really wanted to bring in the doctors that are using R and, you know, R that's being used in labs and get everybody to talk to each other and think again, that it's not just a, here's a bunch of data scientists talking about R in isolation. It's, it's really looking at the, the issues with R and, you know, how it's helping within the general medical area. And now it's a virtual conference and we're really wanting to make sure that things are accessible to people around the world. You know, so people who can't attend regular conferences, how can they get the support that they need? You know, what, what are people doing to, to teach R to people who don't have access to somebody with training, official training?

And. It's wonderful. Even if you are not in medicine, I highly encourage you to check out the R medicine conference. It is inclusive. It is fun. Everybody is just wonderful personality wise and welcoming in the community.

And speaking of the community, we just had the Posit conference that ended. The discord server for PositConf every year has closed afterwards, but it did not this year. It's staying open as a discord server for all of us in the data community to get together and chat. So if you attended PositConf, whether in person or virtual, you had access to join, and I would like to stick in the chat for everybody here at the data science hangout. Rachel has just put a link to join that link is going to be active for the next like five hours or so, and then it's going to close. So don't wait on that, click it. And then when you get in there, please do me a favor and change your screen name in discord, your display name to your real name, because I know you in zoom as your real name. So if you pop up in discord as something else, I can't find you. You need to make your way. Here's your side quest. Get on the discord server and make your way to the data science hangout channel. Okay. And then once you're in there, be like, hello, I'm here. Hey Libby, say hi, so that I can give you a role in discord. That'll make your name yellow. It'll make you part of the data science hangout crew. You get a little badge, a little DSH badge, but I won't know who you are if you don't come find me in that channel. Okay.

All right, everybody. This has been a fantastic get together. Beth, thank you so much for joining us and sharing all of your wisdom with us. That's great. Thanks for inviting me. Oh, absolutely. This was really fun. I always love the SAS to our conversations as well. Everybody, if you missed the link and you're worried about it, just find me on LinkedIn and we'll help get you sorted out. Everyone is saying, thank you, Beth. Thank you, Beth. We are having a fantastic time. Yay. Okay. If you enjoyed the chat today, you can save the chat. The little three dots in the top right hand corner of the chat will save a TXT file for you because it's full of resources. And eventually, we may move our chat maybe to discord. If everybody can hop on discord, then we will never lose our chat. It will always be there and it will be lots of fun. If you have any thoughts on that, do you like discord? Do we want to move over to discord? Put that in the survey at the end so we can know how you feel about it. Okay. Arsenis says, all thumbs up. Yay. All right, everybody. I will see you on Thursday next week. Cannot wait to see you on Blue Sky and LinkedIn and discord between then. Everybody have a fantastic week and weekend. Bye, everybody.

Bye.