00:00:00: You are listening to the Effective Statician Podcast.

00:00:04: The weekly podcast with Alexander Schacht and Benjamin Piske designed help you reach a potential, lead great science & serve patients while having a great work-life balance!

00:00:22: In addition our premium courses on the Effectives Staticians Academy.

00:00:28: we also have lots of free resources for you across all kind of different topics within that academy.

00:00:38: Head over to theeffectivestatistician.com and find The Academy, And much more For You To Become An Effective Statistician.

00:00:49: I'm producing this podcast in association with PSI A community dedicated to leading and promoting user statistics within the healthcare industry to benefit patients.

00:01:01: Join PSI today to further develop your statistical capabilities with access to the ever-growing video on demand content library, free registration for all PSI webinars and much more.

00:01:13: Head over through the PSI website at psivab.org To learn more about PSI activities.

00:01:20: you can come up here as a member too.

00:01:30: Welcome to another episode of The Effective Statistation!

00:01:34: Today I'm super excited to have two statisticians from France on my podcast, but of course we'll speak English.

00:01:44: My French is really terrible!

00:01:45: I had a couple years in French and that was disaster.

00:01:49: Anais and Marie-Carrelle will talk about early phase things how we can be more innovative within companies.

00:02:00: And so that's a very interesting topic, set we are bringing together.

00:02:05: Anais maybe you could start and introduce yourself?

00:02:08: Thank you Alexander for having us!

00:02:11: It is a real pleasure to be here.

00:02:13: I am Anais-André Yong.

00:02:14: I'm a Senior Statistical Meteorologist at CERIGA.

00:02:18: I joined CERigA more than three years ago right after finishing my PhD in Biostatistics.

00:02:24: I completed my PhD at INSERM, a French research institute and my research focused on dose-finding clinical trials in oncology.

00:02:34: And while doing my PhD i was also working as a methodologist at APHP de Paris University Hospitals for about three years where I helped design an analysed clinical studies.

00:02:49: I started my career in a very academic environment but at the end of my PhD, I faced this dilemma that i would say most PhD students face.

00:03:01: Should I stay in academia or should I move into the pharmaceutical industry?

00:03:06: And when I had these discussions with Gael, CEO of Saryga she told me about her company and it actually matched exactly with what I was looking for because i wanted to continue that methodological research work.

00:03:21: But at the same time,I also want you be involved in innovative clinical trials so CERIGA felt me the right balance.

00:03:30: overall my background is mainly in early phase trials but since joining CERiga ,i had the opportunity to walk across all phases on a wide variety of projects including adaptive triumph designs both by Asian and Frequentists.

00:03:46: Awesome!

00:03:47: Marie-Carrelle, please introduce yourself.

00:03:50: Hi I'm Marie-Carrell Rivière Chief Scientific Officer at Sariga.

00:03:56: For those who don't know, Sariga is a consulting company dedicated to statistical innovation and decision making in healthcare.

00:04:05: Our job is support pharma & biotechs with advanced statistical methodology to optimize drug development and clinical trials.

00:04:14: That has where we have close collaboration with Academia, and republished novel methods.

00:04:19: I'm also recently a fellow at INRIA so the French National Institute for Research in Digital Science & Technology.

00:04:27: In addition my role is in SARIGA.

00:04:30: So my background i hold a PhD in biostatistics And especially designs for early phase dos finding in oncology.

00:04:38: My PhD was a collaboration between industry and academia, Serviette & Inserm which is the French National Institute of Health and Medical Research.

00:04:49: So I had the opportunity to work on my PhD in research projects but also on early phase clinical trials because that was nice experience.

00:04:59: then i chose to do postdoc in pharmacometrics at Bishop Hospital in Paris And during approximately seven years I joined the statistical methodology group at Sanofi.

00:05:13: It was a very nice experience where i was able to support all phases and all therapeutic era, it's been really nice!

00:05:22: Today since twenty-twenty two I've joined SARIGA where I lead the methodology team.

00:05:29: so in fact.

00:05:32: So we are currently seven plus me and Gael, And I'm running the project.

00:05:37: Because i really love methodology, I organize teams so that they can still have time to actively be involved in the science itself.

00:05:48: That is pretty cool!

00:05:49: We will talk about this a little bit further.

00:05:52: You also presented what were talking here from kind of content perspective at PSI conference.

00:05:59: if you want to look into going on slides around what your list about listen-to that will be in the show notes.

00:06:08: So this all has to do with Project Optimus and there's been a previous episode where we had deep dive into project optimus but maybe can have quick kind of overview, What Project Optimous is?

00:06:24: And how your research actually relates.

00:06:27: The project

00:06:30: Optimus is an FDA initiative.

00:06:32: It was launched back in twenty-twenty one by the FDA and they published a guidance on it in twenty, twenty four.

00:06:39: basically its about rethinking how doses are selected in early phase oncology trials.

00:06:45: so this project arose from shared understanding of different experts including clinicians pharmacologists statistician and regulators.

00:06:54: And these shared understandings Doses and schedules of immunotherapies are often inadequately characterized by the time a drug reaches their market.

00:07:05: And that's why traditional dose-finding paradigms should be revised.

00:07:09: So if we can explain it quickly, historically, the paradigm was... The more is better!

00:07:16: It comes from chemotherapy.

00:07:18: That means you push your dose as high as patients can tolerate it.

00:07:22: This is what we call the maximum tolerated dose, the MCD Because there was this assumption for chemotherapy that efficacy on toxicity both increased together, has the dosing crisis.

00:07:34: But this logic breaks down from modern targeted therapies and immunotherapies because efficacy can plateau well before you hit a maximum tolerated dose.

00:07:44: So the highest dose is not necessarily the backbone And we would like to recommend lower doses That provide the same efficiency but much less toxicity.

00:07:54: And in the past, for many approved cancer drugs we pushed for a dose level that turned out to be too high and post-approval they had to go back and modify the dosing regime based on safety and tolerability results which is the worst case of our company.

00:08:11: So... That's the context in which projects or things were born really reformed how we optimised the dose.

00:08:18: but as you said You have this previous episode Alexander with Ayune & Kaji where you cover it deeply.

00:08:23: so Maybe I can continue on what this recommendation means for industry instead of the initiative again.

00:08:32: So in practice, Project Optimus is asking for industries to move beyond simply targeting the highest tolerable dose and find those that provide a trade-off between efficacy and toxicity – so a dose that optimizes balance between benefit entries.

00:08:53: And to achieve this, the LVA recommends we can say that they recommend two main things.

00:08:59: The first thing is that those decisions should be based not only on toxicity binary toxicity endpoints but also on efficacy data tolerability patient reported outcome PKPD data activity data.

00:09:14: so a more comprehensive approach integrating all these multiple endpoints to inform the dose decision.

00:09:23: The second major recommendation from Project Optimus is to explore multiple doses early in clinical development through proper randomization phase, so once you have identified few potential optimal dose.

00:09:37: after those escalation phases they encourage what we call dose optimization phase where you randomize patients across candidate-dose to figure out which one is actually the best.

00:09:50: So it sounds simple in theory, but in practice its a real challenge for industry because it means finding balance between regulatory expectations and what's feasible on ongoing trials.

00:10:02: so this situation really requires reactivity and adaptability of our industry And that's exactly what, in the context we do our research at Cerega because we develop metals and tools to help companies.

00:10:16: In this process of those selection and optimization while still converging towards an optimist-compliant development.

00:10:25: If you talk about efficacy endpoints... ...in oncology.

00:10:30: What would that be?

00:10:31: Because I would assume things like toxicity, or certain side effects you can see pretty fast.

00:10:39: But efficacy probably takes much longer to actually observe.

00:10:43: Yeah a lot of methods for that.

00:10:44: because indeed yeah For efficacy sometimes we observe it not at the first cycle but for example objective response rate Or for sure PFS.

00:10:54: We can observe now.

00:10:56: so there is methodes.

00:10:58: take into account that these are in fact time-to-events.

00:11:02: When you decide to include a new patient in the trial, You don't have yet all complete observation of this endpoint.

00:11:10: so there is methods for that.

00:11:11: We will go more deeply on the method later we propose.

00:11:16: But you can do different steps in your clinical trials.

00:11:18: So first step when you include your first patient?

00:11:22: You can base your decision only on toxicity and use the efficacy end point when they are available, so you can do in a step.

00:11:31: So those escalation steps is usually based on toxicity endpoint And dose optimization phase.

00:11:37: is this phase When we used all possible end points but already have included many patients.

00:11:43: You already have data available in your trial.

00:11:48: We used preliminary evidence of efficacies.

00:11:52: if I can give two examples of what we used for some clients.

00:11:56: So as Anais mentioned, it was ORR or Tumor Shrinkage that enabled to drive the decision.

00:12:04: so let's talk through your methods at your proposing

00:12:08: maybe if i may.

00:12:10: all this context has also why there is a new special interest group on early phase That was recently set up within the PSI and I'm a colleague, an analyst is also part of this group.

00:12:23: And the objective is to bring people together and share practice... ...and share some ideas on what we could do etc.

00:12:32: It's open for new members so anyone who is listening to our podcast is very welcome to join!

00:12:38: Yeah i wanted you give us these information.

00:12:41: How can people contact you via LinkedIn or send you an email?

00:12:46: They can send me emails.

00:12:47: There is a web page on the PSI website with our contact.

00:12:52: Okay, awesome very good we'll link to that in the show notes as well and let's mention these kind of things at the end of the podcast as well.

00:13:00: if you're now listening to this I would like to remember all those things will have a couple action items.

00:13:07: so it really gets everything.

00:13:10: New method!

00:13:11: We've got some different steps and there you already highlighted kind of the dose selection, and then those optimization phase.

00:13:19: Can you walk us a little bit more in a more detailed view through these kinds of different steps or methods?

00:13:25: Yeah our method is called UDSP for utility based on dose exposure safety pharmacodynamics efficacy.

00:13:35: so it's in several steps.

00:13:36: The first step is the POP-PK model.

00:13:39: So we link that does regimen does unscheduled, which is interesting.

00:13:45: It links into the exposure because we know that two patients on the same dose can end up with very different exposures and it's maybe very interesting to go through the PK part.

00:13:58: Then once you have this POP-PK model We want to model each endpoint in function of exposure.

00:14:05: So any endpoint that matters for decision Can be included in approach.

00:14:10: It's not fixed, it is very flexible.

00:14:13: So we talk about safety so that can be as usual those limiting toxicities.

00:14:19: It can be grade three four TEAE or TAE leading to those modifications.

00:14:25: We also talked about activity for example we already integrated target engagement and for efficacy As mentioned earlier it could be tumor shrinkage ORR any endpoint that matters in the decision.

00:14:42: So we have this first part, those regiments to exposure then exposure to any end point of interest.

00:14:49: but then we need to go back from the exposure to the regiment because clinicians don't prescribe an exposure they prescribe a regimen.

00:14:59: and so that's why At the end, we have a full distribution of every endpoint for each DOZ regimen.

00:15:11: And so we also have uncertainty around our estimations.

00:15:16: and finally what do is that we have an utility function which brings the endpoint together into one measure to guide the decision.

00:15:28: This utility is constructed with clinicians because they are ranking the endpoints by importance and giving some information to have a trade-off between the endpoint.

00:15:42: For instance, we're asking them is just an example how much extra toxicity would you accept for ten percent more tumor shrinkage?

00:15:51: Okay so it's like a preference survey

00:15:56: Exactly!

00:15:57: And with all these questions and preferences we are eliciting the weight of our utility function.

00:16:05: We have a utility for each DOS regimen and one, when you need to choose... And we made some propositions with HemaEase.. ..and we suggest look at different criteria so that they can have the utility in their credible interval.

00:16:24: A rule could be to take the dose regimen with a highest utility, which is very simple.

00:16:31: But something we also explored because we wanted it to take into account uncertainty... ...is the probability of each dosing regimen have their highest utility.

00:16:44: One is basically if you think from other examples, there could be a network meta-analysis and you get the rank out of it.

00:16:51: But of course we also have probabilities for being the best out of that in such very similar approach

00:16:57: Exactly!

00:16:57: And we recommend to look at all these criteria together... ...to make this decision.

00:17:03: So that's the approach.

00:17:04: The approach can be used at different times during those findings.

00:17:09: So because evolution is quite slow, a few years ago we were still using the three plus three.

00:17:15: First

00:17:16: without applying our approach at the end of those escalation phase for instance with model-based approach.

00:17:23: but then it's to follow optimist recommendation and have a dose optimization phase.

00:17:31: so that would be first on a model-based approach, then use our UDSP approach to have this probability of being the best dose and then run a dose optimization phase.

00:17:46: And there are several possibilities depending what is the constraint.

00:17:51: so we thought randomizing patients with different dosing regimens according their probabilities of being optimaled.

00:17:59: Let's imagine for instance that companies can only select two doses.

00:18:03: We could do with the two best doses identified by the method.

00:18:09: The constraint is that if you want to use the PK part, because it's quite flexible we can imagine not having this PK part and modeling directly those to end point.

00:18:20: but It was really of interest in a project which supported to have it.

00:18:25: If You Want To Have This PK Part Of Course You Need A Few Courts Included And PK Sample Available which may take some time, and so you can apply the method only after a few chords were included.

00:18:39: And the POP-PK model was built by the PK team.

00:18:44: I see that!

00:18:44: And i guess if we have let's say one pretty good regimen... ...and then second and third are very close?

00:18:53: Then there is bigger gap to the fourth than probably would go for three To better understand everything from those selection point of view.

00:19:01: Exactly

00:19:03: If I can add a few things on top of that, maybe.

00:19:07: And it's may be the flexibility in this method as Marie-Caren already mentioned but there are other things to make the method flexible is that the endpoints of interest that drive decisions aren't fixed by methods so you use whatever endpoints makes sense for your study.

00:19:26: So the idea really needs to capitalize all available data.

00:19:30: Sometimes we include PFS or error PD marker, it really depends on the compound of interest for your patient population.

00:19:39: And secondly what makes also the method flexible is that you can use different exposure metrics from each endpoint.

00:19:47: Again, it depends on the pharmacology of the compounds.

00:19:50: For example, peak concentration might be more relevant to explain toxicity but cumulative exposure may better to explain efficacy is an example.

00:19:59: so this has been discussed with the pharmacological teams and that's why also its important work closely with them.

00:20:07: And a third thing I would like to add Is that UDSP method works as Marika said optimising regimen schedules.

00:20:17: So it's not just dosies, because two different regiments can have the exact same dose level but a completely different rhythm of administration.

00:20:27: And we hand up with a different toxicity and efficacy profile.

00:20:31: so With the UDSP design you can compare those directly Because We take into account the exposure in the modeling and not just at this model.

00:20:40: A really last interesting thing if I can add which is related to exposure Is that include covariates in the population-PK model.

00:20:50: So we can see why a given patient hands up over or under exposed, which in fact opens up real paths toward more individualized dosing because for example Marie Carrell presented when he applied this method to clients The exposure was different between male and female Which led us to recommand potentially differents dosing regimen for men and women.

00:21:18: So to conclude more globally on the method, if we step back from the first question you asked about the Optimus project.

00:21:25: so what does Project Optimus ask for?

00:21:29: They first specify that those should be based on the benefit risk not on toxicity alone but built in different sources of evidence safety tolerability efficacy and PKPD and they ask for several doses to be compared early in the development through randomization phase.

00:21:48: And this is exactly what UDP was developed because it's a quantitative tool, transparent tool that helps teams justify their dose.

00:21:59: so its flexible.

00:22:00: you can apply whenever your are under process whether at end of a dosage condition or full optimization if ready.

00:22:09: It's

00:22:10: pretty impressive.

00:22:11: Thanks so much, very well thought through approach with a couple of nice applications of decision theory especially if I think about the utilization or utility-based approach which there are probably lots ways how you can get these utilities?

00:22:29: It is another research subject actually!

00:22:32: But in the end we need to make some kind of trade-offs anyway And by having that questionnaire approach, at least you make it transparent.

00:22:43: how unique trade-offs.

00:22:45: So I think this is very often the biggest challenge.

00:22:48: The tradeoff happens by way of discussing things in a room and That's very difficult to talk your mind.

00:22:56: Thanks so much for that introduction and all those expansion on our presentation at PSI conference.

00:23:06: corresponding paper also gets out there and published quite soon.

00:23:11: And what I see again, is from you and your colleagues a lot of presentations.

00:23:20: If i just think about the PSI conference There were several presentations and posters as Mike Ferrell mentioned You're not big team a hundred or one-hundred fifty, even more institutions.

00:23:37: You have very small teams with less than ten people!

00:23:41: How can you drive so much methodological research forward while being a CRO?

00:23:49: Well of course we also need to work on clients to basically pay our salaries.

00:23:56: I know that this is my kind of also working in CROs or have been working together with CRO for quite some time.

00:24:02: That's really my biggest question!

00:24:05: That's an interesting question and it has so interesting, you are presenting as a tension between methodology and client work because infact thats exactly why Sariga was built for.

00:24:19: So Gael when she created Sariga approximately four years

00:24:23: ago

00:24:23: It was really, she described it as a company that supports statistical innovation and is doing statistical methodology.

00:24:33: We don't have a methodological identity by accident —it's on purpose—and we are feeding it!

00:24:41: So

00:24:42: first in the team everyone holds their PhDs... ...we all spend some time at academia still continuing to collaborate with academia.

00:24:53: We are encouraged to publish and we're going through several conferences each year.

00:24:58: So, why it's working is because the main part of our work is to do consulting for clients but we are supporting clients on complex issues.

00:25:09: they come towards when there have specific issues that aren't standard And they want us support That.

00:25:16: a very good example Because the Udacity method which just presented Is in fact collaboration with a sweet-salon biotech, baby of farm.

00:25:26: And so that really shows us we can do innovation and create new methods based on client's work.

00:25:34: Usually this clients' works usually relies on complex method which may already exist.

00:25:41: So we are looking in the literature to pick the right method and apply it depending upon needs.

00:25:49: But that's already methodology because the method, maybe it was already published but is not standard.

00:25:56: It can be unusual and not trivial.

00:25:59: We need to implement it And its still innovation!

00:26:03: Sometimes we end up with some questions or problems That don't have an existing method published in literature.

00:26:12: and thats also where We are doing innovation and we create our own approaches to answer the problem that we're dealing with.

00:26:22: That's something, for instance... ...we do with Serviet on biomarkers' methods And as I said this is also what we did in Debiopharm on UDSP.

00:26:33: So every day we work on methodological methods of clients.

00:26:40: It can be simple or more complex And that's the main part of our work.

00:26:44: But it is true, we have also a part-of-our-work which are not built to anyone and we spend this time for research For problem projects.

00:26:54: We think they matter.

00:26:56: That may be of interest at some point In those project.

00:27:01: we can do collaboration with academia or create working groups.

00:27:07: So for example we did a scoping review on early phase designs.

00:27:12: So we review more than seven hundred papers of designs.

00:27:17: And for that, We created a working group with people from academia and industry... ...and it was really pure research not built to anyone but we really think that matters.. ..And also participating in lots of working groups.

00:27:32: Yeah so basically you attract especially work That needs not just the standards implementation But where there's something complex in it there's something that needs a little bit more brain power than the standard study.

00:27:47: Okay,

00:27:47: exactly and I think what is motivating the team?

00:27:51: My team really enjoys having complex approaches to set up.

00:27:56: usually our clients don't come towards for standard analysis.

00:28:00: they go to discuss with standard CROs.

00:28:03: And we're here really to support complex issues.

00:28:07: How do you select your people that join your company?

00:28:11: So we have a process with several rounds of interview.

00:28:16: First,

00:28:17: normally the first thing as I said is to hold a PhD and then there are several round where we're evaluating technical skills for people, adaptability etc... It's a global decision in different steps.

00:28:34: Do you look specifically at people early or can anyone?

00:28:40: join?

00:28:40: that is also I don't know, twenty years in the industry.

00:28:44: Oh yes it's quite large depending on what people already have in their team.

00:28:50: so Anais for instance she joined just after her PhD.

00:28:54: now three year that she is with us but i was right after a PhD.

00:28:58: But we are another person who works at EMA before joining us and has lots of experience.

00:29:06: So were open to all kinds of profiles.

00:29:10: Anais, what made you join Sariga?

00:29:12: I think it was the balance between methodology and clinical trials applied to industry because after my PhD i really wanted to continue on that research work but i wasn't sure if we would have a full academia career.

00:29:29: And yeah, Gael told me about Sariga.

00:29:31: she explained for me.

00:29:36: The company was new and I just finished my PhD, so it motivated me to join a small company.

00:29:46: What do you suggest other employees who also want to drive innovation forward in their companies?

00:29:53: They may not have the benefit of working like... and your setup was small, focused on these more complex projects.

00:30:02: What can you do so that... You can drive things forward even up to publication?

00:30:07: Yeah!

00:30:08: That's a good question.

00:30:09: indeed it is not straightforward.

00:30:11: I think It has to be first personal initiative.

00:30:14: We have to be curious we have to proactive.

00:30:17: but the main skill isn't knowing directly how to write paper.

00:30:22: It's knowing how to spot things, and what I mean by that is being able to notice when there are room for innovation.

00:30:31: So as Marie-Claire mentioned this is a standard method doesn't create work or has real limitations And you could go further than just applying the basic approach.

00:30:42: so The first step really about learning to recognize where potential methodology problems and where the real opportunities are.

00:30:53: And after that, next step is to read literature on this subject because when you're designing a trial You have to take time reading what has already been published in the topic.

00:31:06: Just doing it well is really good contribution itself.

00:31:10: So start by proposing a published method that answers your question.

00:31:14: That's already valuable with credibility And from there, with experience you start proposing your own ideas and naturally you start developing more innovative things.

00:31:26: But in practice there is a few steps before publication.

00:31:30: We said the conference abstract or a poster was already good first step because it will give that push to work publication Co-authoring with academic groups or co supervising master of PhD students The most realistic past when you are coming from industry.

00:31:49: Working group has the PSI six, for instance also a good way.

00:31:54: so honestly don't have to start with first author in biometrics.

00:31:59: there plenty of steps before that.

00:32:02: and last thing I would like to add is what i understood from discussion I had with colleagues at conferences not just about personal motivation.

00:32:13: If you are fully loaded with operational work, You will have a very little time for innovation and even less for writing and publishing.

00:32:22: So if your part of the working group doesn't have enough time It's really hard to make room.

00:32:28: on top of everything else The company has really to support it Not just allow but make it possible.

00:32:35: Otherwise people end up having to use their own personal time To do.

00:32:41: this is not sustainable And I know people from who are literally in methodology teams, but that just don't have a publication objective.

00:32:52: That's very common industry.

00:32:54: Publishing on your own personal time is not realistic.

00:32:58: so it really has to be an objective by the company itself and we had this chance at SORIGA that its exactly the case because publishing is part of our personal objectives.

00:33:11: Loves what you're saying for a couple of reasons.

00:33:14: If you don't have time to do it in your work, over time just burns out.

00:33:20: Yeah that's as you say is not feasible.

00:33:23: I think its actually dangerous to use at all longer period of time.

00:33:27: It also needs be so important and relevant That the company really supports.

00:33:34: if The method is important or any other kind of business situation, then must be published.

00:33:43: Because if it's not published you can't cite it reference it especially when it comes for also for regulatory work.

00:33:51: You need to have that published and I know the first paper is always a hardest because It gets better over time If you have submitted a couple of papers And then let's get easier.

00:34:01: Oh yeah its an exercise!

00:34:03: You learn how do it!

00:34:05: Marie-Carrelle anything That you would like To add at this point?

00:34:08: I completely agree because i was part of it.

00:34:11: After my postdoc, I joined the statistical methodology group at Sanofi and so in this group had an opportunity to work on different methodological problems.

00:34:23: It's a great experience where I learned a lot And did very interesting works on various complex methods.

00:34:31: But clearly publishing wasn't objective.

00:34:35: So I completely agreed with Anaïs.

00:34:37: We really need support from the company to publish it.

00:34:41: And at some point, I tried to say okay... ...I will write a paper when i have time and so on.. ..and in the end I think that never managed to finish my work.

00:34:53: Some parts of papers started but took too much time!

00:34:58: When you had personal life and became a mum during this period at Sanofi I didn't have time.

00:35:04: I wanted to spend some time with my kids and it was too

00:35:07: much.".

00:35:08: So yes, we need support from the company.

00:35:11: if you want do that?

00:35:13: Yeah!

00:35:13: I think the environment is really important And obviously Dell sets an overall company objective in such a way that there's time... ...and also within-brand because whenever you publish something that helps your brand You become more visible, you can be more trustworthy.

00:35:35: That makes it easier to attract new clients and especially attracts the projects that we want have

00:35:42: Exactly!

00:35:43: And thats why its working perfectly because... We are encouraged to publish for this reason.

00:35:47: It's not useless Because is also a reward of company.

00:35:51: So yes I agree.

00:35:53: Yeah Of course Its great for co-authors from industry companies.

00:35:59: They also get a publication and who doesn't like an additional citation on their CV.

00:36:04: It's really nice!

00:36:07: So I think that makes it couple of important suggestions for the listener, yeah?

00:36:12: Make sure what you work is relevant not just to your company but create or choose area where publication is also important.

00:36:24: make sure there are objectives as well and said, you have really time for this.

00:36:31: And don't underestimate it!

00:36:33: It always takes longer... ...and the first submission to a journal is NOT THE END OF THE JOURNEY.

00:36:40: There's lots of more to come.

00:36:43: If there are a couple people who can do that together with us….

00:36:46: …it will be very important.

00:36:47: but in the end have an mindset which goes through various steps.

00:36:52: like Anais mentioned the first step is usually something internal, then there's something presented at a conference post or presentation and then it is later a paper.

00:37:04: And you can still come on my podcast to speak about that.

00:37:07: so even more things are possible.

00:37:09: but the podcast episode was super easy just one hour of work!

00:37:13: Thanks so much Anais for that.

00:37:16: We talked about lots of topics, we want to highlight Project Optimus again and the link to that in the show note.

00:37:24: Also wanna highlights PSIFs by Working Group is what we talk about.

00:37:28: so have a look into.

00:37:29: this will also put linked to the slides to do some method set with this cast end off course.

00:37:36: we'll put links to Sariga and these wonderful guests I have today on the podcast.

00:37:42: make sure If you're working in this area and if need an additional zero, especially one that does the most heavy liftings or difficult stuff with some people who love doing these.

00:37:55: Thank-you very much!

00:37:56: It was a nice moment to

00:37:58: be here.

00:37:58: Thank You so much Alexander!

00:38:00: Thanks a lot!

00:38:05: This show was created in association with QCycle.

00:38:09: Thanks to Rain for helping us show on the background and thank you for listening.

00:38:13: Reach your potential, lead bright silence and serve patience.

00:38:17: Just

00:38:17: be an effective statistician!