Events Add an event Speakers Talks Collections
 
Duration 02:57
16+
Video

C26 Unsupervised identification of atypical medication orders: A GANomaly-based approach

Maxime Thibault
Pharmacien at CHU Sainte-Justine
+ 2 speakers
  • Video
  • Table of contents
  • Video
Machine Learning for Healthcare
August 8, 2020, Online, Los Angeles, CA, USA
Machine Learning for Healthcare
Request Q&A
Machine Learning for Healthcare
From the conference
Machine Learning for Healthcare
Request Q&A
Video
C26 Unsupervised identification of atypical medication orders: A GANomaly-based approach
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Add to favorites
185
I like 0
I dislike 0
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
  • Description
  • Transcript
  • Discussion

About the talk

00:00 Pharmacists

01:00 Methods

01:30 Results

02:28 Conclusions

About speakers

Maxime Thibault
Pharmacien at CHU Sainte-Justine
Pierre Snell
Machine Learning Researcher at Botpress
Audrey Durand
Assistant Professor at Université Laval

Maxime est pharmacien au CHU Sainte-Justine depuis plus de 10 ans, avec une expérience de pratique en soins intensifs de néonatologie, chirurgie et traumatologie pédiatrique, et nutrition parentérale. Depuis 2015, Maxime travaille en informatique de la pharmacie et a mené plusieurs projets incluant un changement de logiciel de préparations magistrales, le déploiement de la prescription électronique, et l'alimentation de données de dispensation de médicaments au DSQ. Maxime a dirigé et participé à plusieurs projets de recherche sur l'usage des médicaments et la pratique de la pharmacie.

View the profile

I have two M.Sc in computer science / Electronics / AI : one from ENSEA (France) and one from Laval University (Quebec) I’m currently working on NLP problems applied on chatbot technologies at Botpress .

View the profile

Dr. Audrey Durand is an Assistant Professor in the Department of Computer Science and Software Engineering and the Department of Electrical and Computer Engineering at Université Laval. She holds a Canada CIFAR AI Chair and is affiliated with Mila — Quebec AI Institute. She specializes in algorithms that learn through interaction with their environment using reinforcement learning and is particularly interested in leveraging these approaches in health-related applications.

View the profile
Share

Hello. I am acceptable. I am a pharmacist working and clinical informatics at the shoes in Montreal. This work was done in collaboration with gas smell and from ingesting and me, American Hospital, Pharmacy, caring for us, adults patients, review of the list of active medication, what we call a pharmacological profile for the patients under their care to identify potential problems and found interventions. However, in practice problems are rare. The time spent reviewing orders without problems as been described as wasteful and as a

potential safety issue, there is an opportunity to devise a triage system that would be able to separate profiles without issues from pharmacist review. So that pharmacists to focus their attention on patients, more likely to benefit from their expertise. To explore the feasibility of creating such a system. We use the data sets composer. How medication orders from 2005 to 2017 with the year. 2018 as a test set, we represented pharmacological profiles as multi-hop vectors orders or

profiles. And for this reason that we select an unsupervised, We modified the mother structure and losses to accommodate our data and to civilize training, which resulted in this model. Previous work suggests an important effect of the route. I'm on this type of data, we have done this by Carissa's, the increasing, the training. Volume up to 10 years with tri fold cross-validation. I'm the test that we have served at Asian population with more predictable order patterns such as neonatal intensive, care, patients and OBGYN, show lower and go their losses and that populations with more complex

profile, such as absurd, that profiles of it, lower orders, less likely to benefit from extensive pharmacist review. In conclusion, this model shows the potential or the acacian of a typical pharmacological profiles. However we only perform unsupervised training and evaluation at this point, we are currently evaluating this in a prospective study with the evaluation of profiles made by pharmacist in clinical practice. Thank you for your, for your attention. Do not hesitate to contact me. If you have any questions or would like to discuss our

Cackle comments for the website

Buy this talk

Access to the talk “C26 Unsupervised identification of atypical medication orders: A GANomaly-based approach”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Ticket

Get access to all videos “Machine Learning for Healthcare”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Ticket

Interested in topic “Artificial Intelligence and Machine Learning”?

You might be interested in videos from this event

February 4 - 5, 2021
Online
26
106
ai, application, bot, chatbot, conversation, data, design, healthcare, ml

Similar talks

Emma Brunskill
Assistant professor of computer science at Stanford University
+ 1 speaker
Finale Doshi-Velez
Gordon McKay Professor in Computer Science at Harvard University
+ 1 speaker
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Stephanie Skove
Bachelor of Science at Duke University
+ 12 speakers
Harvey Shi
Associate in Research at Duke Institute for Health Innovation (DIHI)
+ 12 speakers
Ziyuan Shen
Software Engineer at ZipRecruiter
+ 12 speakers
Michael Gao
Data Science Lead at Duke Institute for Health Innovation
+ 12 speakers
Mengxuan Cui
Statistical Modeling Engineer at Yidu Tech Inc.
+ 12 speakers
Marshall Nichols
Senior IT & Analytics Manager at Duke Institute for Health Innovation
+ 12 speakers
Suresh Balu
Program Director at Duke School of Medicine
+ 12 speakers
Cara O’Brien
Assistant Professor at Medicine at Duke University
+ 12 speakers
Armando Bedoya
Associate Chief Medical Informatics Officer, Duke University Health System at Duke Health Technology Solutions
+ 12 speakers
Dustin Tart
Duke University at Program Manager, Patient Response
+ 12 speakers
Benjamin Goldstein
Associate Professor at Duke University
+ 12 speakers
Mark Sendak
Population Health & Data Science Lead at Duke Institute for Health Innovation
+ 12 speakers
William Ratliff
Innovation Program Manager at Duke University Health System
+ 12 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Do June Min
Doctor of Philosophy at University of Michigan
+ 4 speakers
Veronica Perez-Rosas
Research Scientist at University of Michigan
+ 4 speakers
Derek Kuo
Strategic Initiatives Intern at LivCor
+ 4 speakers
William Herman
Professor at University of Michigan
+ 4 speakers
Rada Mihalcea
Professor at University of Michigan
+ 4 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Buy this video

Video
Access to the talk “C26 Unsupervised identification of atypical medication orders: A GANomaly-based approach”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Conference Cast

With ConferenceCast.tv, you get access to our library of the world's best conference talks.

Conference Cast
949 conferences
37757 speakers
14408 hours of content
Maxime Thibault
Pierre Snell
Audrey Durand