Okay, so, can you guys hear me, I guess? So once again, thank you, Ian and SCCM and all the guys who worked with me at Datathon. It was a pleasure to be in New York last August and to actually be here to present to you some of our findings. Just a disclaimer, all, 99% of these slides, all the work here was achieved, like, in less than 24 hours. So please, as soon as you are going to make questions, please be aware that we had, like, 24 hours to do this, and we had, like, a very straight, like, moderator, as Ian, because we really had to be on time. Right. So my name is Thiago, Artie is right there, and we would like to acknowledge all the other members who actually worked tirelessly to actually achieve this work. Okay, so before going into the hypothesis in the work, let me give you, like, some context on why we decided, like, with this topic and theme. So we know that there is some impact of the English proficiency in healthcare, which means that if you are a native or not, probably the outcomes of healthcare will be different. Another thing, I'm not a clinician, I'm an engineer, so once again, don't get out on me if I say something wrong. But we know that, like, English proficiency will have impact. For instance, there are some language barriers. It can actually lead to longer lengths of stay. It can actually increase the odds of more visits to the hospital and the emergency department. And of course, on the other hand, that could be also, like, different survival outcomes for both, like, native speakers or non-native speakers. So this was the main context. Of course, there are lots of studies that you guys can search on, but in five minutes I will not, like, I will not tell you all of them. And we all know, like, as a summary of all of that, we know that language will affect healthcare in diverse ways. Once again, it may lead to misdiagnosis or diagnostic testing or poor quality of care. And on the other hand, we actually want to increase patient engagement and decrease the delays in care, right? So we have to be on time. And language will play a very important role in this. And so the main goal with this project, it's actually to increase the quality of time in the ICU or the comfort and their care. So we know that we have this equation. We have health literacy and language barriers. And in this work, we try to tackle language barriers. Because if we actually solve that problem, probably it can also increase, like, the health literacy of your patients. And so the main hypothesis that we derived in less than 24 hours was among patients who expired during admission, patients with limited English proficiency will probably have increased time to death, secondary to delays in goals of care, these discussions. So this was the hypothesis, okay? I'm not saying that this is true. We try to tackle this in the laptop. So what we did, we used a public database, MIMIC-3 is a very huge database, public one. You can actually access it and work with it. And we did some statistics and data analysis to see if we could answer or not the main question. So these are pretty much the statistics we did. We derived some Cox proportional hazards. We studied the procedure utilization and the end-of-life care discussion by analyzing some of the notes that are present in the ICU at MIMIC. I will show some statistics and graphics that we derived with this project. So we analyzed age. We have more limited English proficiency patients, actually, in older ones. By gender, we didn't find, actually, a significant difference, all right? So it seems that there is no difference between gender or sex in terms of limited English proficiency. In race or ethnicity, we actually found that there is more limited English proficiency in minorities, which is a very interesting finding for us to bear in mind. And of course, all of these also will play a role in the type of insurance you have. And so we end up knowing that we have more LAPs in Medicaid people, in Medicaid-covered people, as opposed to the other ones. Then we did a study on procedure utilization by English-speaking proficiency. As you can see in this graphic, there is no actually relevant difference from what we could find. And in survival probability, if you like plot the probability of survival for both English and LAP, once again, we didn't find no significant differences. So you are already probably seeing that the hypothesis probably will have to change in a further study. Once again, we did a bunch of Cox proportional hazards models based on several variables. We can discuss about these later. So basically, we tried to see what kinds of variables would actually be more important to the main outcomes. And we have these plots. And then we tried to analyze also the end-of-life conversations. And that's where the team of Artie, Beatrice, and Vedant are playing a very important role right now. Once again, we have some interesting findings that we can discuss afterwards. And we also tried to see some kind of gender certification. And here, we could see that the most pronounced difference in end-of-life conversations are found among female patients, which is also a very interesting finding. So for you to get some takeaway messages, we understood that actually limited English proficiency is actually less impactful on time-to-death, oppositely to the initial hypothesis. We know that older patients and Medicaid ones are underrepresented in the data set, which presents a limit of the data. And we also find in these 24 hours that female patients with LAPs actually have more frequent and later conversations compared to other groups, which is something that it's interesting to dig in more in the future. Let me just take you with a motivational, let's say, quote. If you talk to him in a language he understands, then he goes to his head. If you talk to him in his language, probably that goes to his heart, and this will play a role in patients. So if you actually can communicate with your patients, probably the healthcare outcomes will be different. Just me, let me just give you some limitations of the study. Once again, we did one in the head, one 24 hours, one database, MIMIC. It's a very huge database. And if you work with it, you will understand our pains with 24 hours. We didn't, like some of the descriptors actually do not change over time. It was an assumption, and it didn't find out. Of course, we had like others, other vials that we actually have to, would like to know, to study and investigate. So that means we need more databases. And this one is also very limited to Boston, Massachusetts. And of course, these will change across like demographic regions. And that is something that is already being tackled as well. All right. So at the Datathon, we can, in the end of Datathon, these were like the next steps. So increased sample size, advanced modeling techniques, more NLP analysis, try to see bias in sentimentality analysis. And these was the next steps when we finished the Datathon. So we finished Datathon, and we had these challenges. So let me finish the presentation right here. Acknowledge all the team, of course, for all, for the amazing, we can, we have, this is the code if you want to check some of the analysis that we did. We will, I mean, increase the quality of the GitHub as well. And then after this, Artie, Vedant, and Beatrice start working on more stuff. And now they are actually increasing more analysis we make from NLP techniques to LLMs. She can talk about it later. Of course, increasing the data size in the population. So we are also studying the Wake Forest School of Medicine, once again, where Artie works. And we have more hypotheses I want to study. But since I'm getting out of time, I'll just leave this for the Q&A. And once again, thank you all. The corresponding author of this study will be Artie, and we will expect you in Chicago next July to work more on this. Thank you.

Datathon

limited English proficiency

healthcare outcomes

MIMIC-3 database

end-of-life discussions