Dear Device WG members, if you have not joined OHDSI MS Teams, please fill in this form to get onboarded. (best now, donât wait for Jan 28 (next meeting) to do this)
Follow these steps to add yourself to invite for a WG (after you have obtained guest MS Teams login):
Find WG team and find calendar invite in the channel and view meeting details in ⌠menu of it
Click â+ Add to calendarâ and you name will appear in optional list of invited attendees (so any changes to appointment made by WG leader will be communicated to you)
Any WG Meetings you accepted will now show in your MS Teams calendar (not fully ideal but better than nothing)
Sarah is correct. Guests in the tenant dont have calendars and therefore I dont think they can âaddâ to their calendar that way. They have to be sent the link. I will check with our microsoft team to see if there is another work around.
Elisse, no worries. Iâve just successfully landed to the Team through online page. It dosenât show on my desktop App. Can you add me as a member or owner, since I am a co-chair? Is there any policy about being an owner or member in Teams per OHDSI?
Presentation by Dr. Mohammad M. Ghassemi ( DATA scholar at NIH, assistant professor of Computer Science at Michigan State University) (30min talk + 10min Q&A)
An Open Source Tool for the Automated Transcription of Paper Spreadsheet Data.
Dr. Ghassemiâs talk will include two parts: the first part, he will describe a tool that utilizes AI and crowd intelligence to automatically transcribe images of paper-based spreadsheets into electronic form while protecting sensitive personal information. The second part, he will discuss the three major contributions to the problem of coma prognostication after cardiac arrest: (1) the collection of the worldâs largest multi-center : Electroencephalography (EEG) database for patients in coma after cardiac arrest, (2) the development of time-dependent, interpretable, feature-based EEG models that may be used for both risk-scoring and decision support at the bedside, and (3) a careful comparison of the performance and utility of feature-based techniques to that of representation learning models that fully-automate the extraction of time-dependent features for outcome prognostication.
Bio: Dr. Ghassemi is an assistant professor of Computer Science at Michigan State University and National Scholar for Data and Technology Advancement at the NIH. He holds multiple patents and has published over 35 peer-reviewed publications in venues including Science Translational Medicine, and AAAI. He has 10+ years of technical and strategic consulting experience in the AI and âBig Dataâ.
This is a reminder for our call on May 27, 2021 (Thursday) at 10AM EDT.
Agenda:
Team member provides updates (10min)
Danica Marinac-Dabic (FDA) and Art Sedrakyan (Cornell) will give presentation about MDEpiNet and the MDEpiNet Coordinated Registry Network (CRN) CDM status. (30min)
