Events Add an event Speakers Talks Collections
 
Duration 03:08
16+
Video

C22 The CLinically Explainable Actionable Risk Model

Ruijun Chen
Assistant Professor in Translational Data Science and Informatics at Geisinger
+ 8 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
C22 The CLinically Explainable Actionable Risk Model
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Add to favorites
66
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 speakers

Ruijun Chen
Assistant Professor in Translational Data Science and Informatics at Geisinger
Victor Rodriguez
MD-PhD Student at Columbia University
Lisa Liu
PhD Candidate at Columbia Department of Biomedical Informatics
Elliot Mitchell
Graduate Research Assistant at Columbia University Irving Medical Center
Amelia Averitt
Manager, Clinical Informatics at Regeneron Pharmaceuticals
Oliver Bear Don't Walk IV
PHD Student at Columbia University Graduate School of Arts and Sciences
Shreyas Bhave
Software Engineering Intern at Counsyl
Tony Sun
PhD Student at Columbia University in the City of New York
Phyllis Thangaraj
Resident Physician at Yale New Haven Hospital

RuiJun Chen (Ray) is a Clinical Assistant Professor of Medicine and Hospitalist at Weill Cornell Medical College, as well as a NLM Postdoctoral Fellow at Columbia University. He obtained his Bachelor’s degree in Computer Science from Duke University and his Doctor of Medicine from the Yale University School of Medicine. He completed his Internal Medicine residency at UCSF before joining DBMI at Columbia and the Department of Medicine at Cornell. While at Yale, he received the James G. Hirsch, MD, Endowed Medical Student Research Fellowship, leading to his work in cardiovascular outcomes research with Dr. Harlan Krumholz at the Center for Outcomes Research and Evaluation (CORE). He continued to pursue outcomes research in residency while looking for ways to reincorporate his previous interest in Computer Science, ultimately leading to his interest in clinical informatics and the OHDSI program.

View the profile

I research tools and technologies to help doctors and patients make better decisions. My work is highly practical, uses state-of-the-art methods, and has led to recent advances in the field. I am also enthusiastic about using visual design to improve how doctors and patients interact with computers. Before pursuing my degree, I founded and directed a for-profit design collaborative, active over 8 years in multiple countries. Specialties: Biomedical Informatics, Health Information Technology, Knowledge Engineering, Natural Language Processing, Machine Learning, Visual Design, User Experience, Front-End Development

View the profile

I'm a PhD Student in Biomedical Informatics at Columbia University, working with Dr. Lena Mamykina. My research is at the intersection of data science, human computer interaction, and decision-making. Before starting my PhD, I worked in technical services at Epic in Madison, WI, and studied Psychology and Cognitive Science at Carleton College in Northfield, MN.

View the profile

I'm a quantitative health researcher with an interest in translating biomedical data into actionable knowledge through machine learning and data science. Alumna of Columbia DBMI & Columbia Mailman School of Public Health. Based in New York City.

View the profile

I am a Biomedical Informatics student with a strong background in Machine Learning. I chose Biomedical Informatics because I believe that people should benefit from giving their information to data scientists, and that we have an obligation to use tools like machine learning to improve people's lives in meaningful ways. For me this means mining Electronic Health Records for relevant information to patient and physician needs. My goal as a PhD student is to drive the application of machine learning in health care, with an emphasis on underrepresented minorities. I hope to show other researchers that unique answers can be found in studying the health of underrepresented populations from a Biomedical Informatics perspective.

View the profile

My name is Shreyas Bhave. I’m currently a PhD student at the Columbia University Department of Biomedical Informatics (DBMI). My research interests are broadly in modeling EHR data for the purposes of developing risk prediction models. In particular, I am interested in developing methods which address the inherent biases in such data. My recent work focuses on approaches to better model multi-scale irregularly sampled time series data and detecting missingness in tabular data. Prior to Columbia, I received my Bachelor’s degree from UC Berkeley in Electrical Engineering and Computer Science. I spent a summer as a SWE intern at Counsyl, now Myriad Women’s Health , where I worked on buidling pipelines for processing large genomic datasets. I’ve also worked at Harvard Medical School and Johns Hopkins.

View the profile

Fun loving individual with an eclectic variety of experiences, ranging from research internships to medical device startups. Completed his BS in biomedical engineering and computational neuroscience at Hopkins, and is slowly working on his PhD in biomedical informatics at Columbia. In his spare time, passionate about potatoes, poetry, and Al Pacino's Michael Corleone from the Godfather.

View the profile

Studies computational modeling of biological systems, personalized medicine, machine learning in bioinformatics. Ph.D. in the lab of Nicholas Tatonetti researching applications of machine learning methods to improve cohort selection from electronic health records and the power of genome-wide association studies. B.S. in Physics with research experience in bioinformatics, theoretical neuroscience, experimental biophysics, computational analysis in oceanography, tissue engineering. Coursework in statistical mechanics, biophysics, systems modeling in biology, computer science, differential equations, neurobiology, molecular biology, biochemistry, econometrics and data analysis, and quantum mechanics and computing. Can program in Python, MySQL, R, Matlab, Mathematica, Fortran, Awk, Java and Scheme, limited C and Perl knowledge. Familiar with Word, Excel, PowerPoint, HTML, Unix and MS Windows.

View the profile
Share

Hello, my name is Hector Rodriguez and I'm in the new PhD candidate at Columbia University. I'll be sharing with you at work on the clinic or clear our submission to the cmsa challenge. Our model is a deep learning architecture to identify patients, at high risk for unplanned hospital admission. Attention, mechanisms are built into provide insights useful for interpreting model out, but online learning. And using punishing feedback, identifies clinically modifiable risk factors and user interface. Visualizing model output is easy to understand if it still takes rapid effective, clinical

decision-making, Model interfacer develop using evidence-based, deep learning and visualization methods. Finally, the overall framework uses a patient's entire clinical history to make predictions at interview double points in the timeline. Clear uses of a cranial Network combine. The feature in temporal attention mechanisms children, which observations in the patient's historical record are important for projecting, an unfounded Mission Mangal patients. Time Series has a total of four times points, and we are making a prediction at the Third. Groupon for vacations occurring. Closing

time are grouped into Temple Windows features in the temporal. Window are not students representations, using pre-trained know to back in betting, the picture attention layer weights, the importance of features within the temporal window information from previous time, steps ahead and stay as input. Take attention, waited and bedding as input at each time, step in layer with all the ore in and out. That's up to the current time. Step the temporal attention, waited are in and outputs are then used to predict if none Center admission will occur at a picture Eisen. The Clear app

allows users to interface with the models out, put the patient panel provides, a view of the patient roster, including each patient's name demographics discharge status. Nothing made a Brisk selecting the patient reviews. An overview of their risk of unplanned permission as estimated by clear. Throwing down, we can see this patient's risk factors which have contributed to their risk for each is annotated according to its modifiability. Graphs of the temporal evolution of the patient's risk and the importance of each feature. Parallels and users to rank the action

ability of clinical features, this process ensures that clears predictions are transparent and clinically useful. Improving resource allocation and promoting trust with the theaters overtime. Russian. Re-rack, the risk factors to provide feedback on whether they believe this to be a chronically. Modifiable Factor. The interface uses this information to learn the modify ability of each, respect her over. Lighter knowledge. All the members of our cmsa, ihealth alkam challenge team as well as our Advisory board. If you would like more details on our work, please do drop by her poster. Thank

you.

Cackle comments for the website

Buy this talk

Access to the talk “C22 The CLinically Explainable Actionable Risk Model”
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
104
ai, application, bot, chatbot, conversation, data, design, healthcare, ml

Similar talks

Hannah Lonsdale
Clinical Research Associate at The Johns Hopkins University
+ 5 speakers
Ali Jalali
Senior Data Scientist at Biofourmis
+ 5 speakers
Luis Ahumada
ДолжностьDirector Center for Pediatric Data Science and Analytic Methodology at Johns Hopkins All Children's Hospital
+ 5 speakers
Mohamed Rehman
Eric Kobren Professor of Applied Health Informatics at The Johns Hopkins University School of Medicine
+ 5 speakers
Walid Habre
Head Anesthesiological Investigations Unit at Université de Genève
+ 5 speakers
Nicola Disma
Director of Unit for Research & InnovationConsultant paediatric Anaesthetist at IRCCS Ospedale Pediatrico Giannina Gaslini
+ 5 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
Christopher Snyder
Assistant Coach at Austin Saints
+ 2 speakers
Jared Ucherek
Data Scientist at BCG GAMMA
+ 2 speakers
Sriram Vishwanath
President and Co-Founder at GenXComm
+ 2 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
John Morrison
Assistant Professor of Pediatrics at The Johns Hopkins University School of Medicine
+ 6 speakers
Ali Jalali
Senior Data Scientist at Biofourmis
+ 6 speakers
Hannah Lonsdale
Clinical Research Associate at The Johns Hopkins University
+ 6 speakers
Paola Dees
Physician at Johns Hopkins All Children's Hospital
+ 6 speakers
Brittany Casey
Pediatric Hospital Medicine Fellow at Johns Hopkins All Children’s Hospital
+ 6 speakers
Mohamed Rehman
Eric Kobren Professor of Applied Health Informatics at The Johns Hopkins University School of Medicine
+ 6 speakers
Luis Ahumada
ДолжностьDirector Center for Pediatric Data Science and Analytic Methodology at Johns Hopkins All Children's Hospital
+ 6 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 “C22 The CLinically Explainable Actionable Risk Model”
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
Ruijun Chen
Victor Rodriguez
Lisa Liu
Elliot Mitchell
Amelia Averitt
Oliver Bear Don't Walk IV
Shreyas Bhave
Tony Sun
Phyllis Thangaraj