User Tools

Site Tools



This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
projects:workgroups:wg_meeting_sep_08_2021 [2021/10/05 14:06]
vipina created
projects:workgroups:wg_meeting_sep_08_2021 [2021/11/09 04:48] (current)
vipina [Recording]
Line 6: Line 6:
 ==== Invited talk ==== ==== Invited talk ====
-**Title: ​Leveraging longitudinal ​and multi-modal EHR in Survival Analysis**\\ +**Title: ​Natural Language Processing for Clinical Excellence: The State of Practices, Opportunities, ​and Challenges:** Rapid growth in adoption ​of electronic health records (EHRs) ​has led to an unprecedented expansion ​in the availability of large longitudinal datasets. Large initiatives ​such as the Electronic Medical Records ​and Genomics ​(eMERGE) Networkthe Patient-Centered Outcomes Research Network (PCORNet), and the Observational Health Data Science and Informatics (OHDSIconsortium, have been established and have reported successful applications of secondary use of EHRs in clinical research and practice. In these applicationsnatural language processing (NLP) technologies have played a crucial role as much of detailed patient ​information in EHRs is embedded in narrative clinical documents. Meanwhile, a number of clinical NLP systems, such as MedLEE, MetaMap/​MetaMap Lite, cTAKES, MedTagger, and i2b2 have been developed and utilized to extract ​useful ​information from diverse types of clinical text, such as clinical notes, radiology reports, and pathology reports. This talk will walk through some successful applications of NLP techniques ​in the clinical domain with potential opportunities and challenges.
-**Abstract:** Survival analysis is a fundamental statistical tool that predicts the time of an event. It has multiple healthcare applications ​in areas, ​such as hospitalization ​and patient mortality. Clinicians predict patient outcomes by heterogeneous modalities ​(e.g.text, images, and lab values). Such data poses significant challenges for traditional survival analysis techniques. In this talkwe present our effort to expand the survival analysis using multimodal, longitudinal EHR data. Our results indicate that extracted high-dimensional features from text and image provide complementary ​information in addition to structured EHR, and incorporating longitudinal data is useful in time-to-event prediction.+
-**Presenter:​** Dr. Yifan Peng\\ +**Presenter:​** Dr. Yanshan Wang\\ 
-Dr. Peng is an assistant professor ​at the Department of Population ​Health ​Sciences ​at Weill Cornell Medicine. His main research interests ​include BioNLP ​and medical image analysissuch as named entity recognitioninformation extraction, and eye disease diagnosis ​and prognosisBefore ​joining ​Cornell Medicine, Dr. Peng was a research fellow at the National Center ​for Biotechnology Information ​(NCBI), National Library of Medicine ​(NLM), National Institutes of Health (NIH). He obtained his Ph.Ddegree from the University of DelawareDuring his doctoral training, he investigated applications of machine learning in biomedical relation extraction, with a focus on deep analysis of the linguistic structures of biomedical texts.+Yanshan Wang, PhD, FAMIA is vice chair of Research and assistant professor ​within ​the Department of Health ​Information Management ​at the University of Pittsburgh. His research interests ​focus on artificial intelligence (AI), natural language processing (NLP) and machine/​deep learning methodologies and applications in health care. His research goal is to leverage different dimensions of data and data-driven computational approaches to meet the needs of cliniciansresearcherspatients ​and customersPrior to joining ​Pitt, Dr. Wang was assistant professor in the Department of AI & Informatics at Mayo Clinic. Yanshan has extensive collaborative research experience with physicians, epidemiology researchers,​ statisticians,​ NLP researchers,​ and IT technicians. He has served as investigators ​for multiple extramural NIH-funded projects and intramural operational projects. He has published over 50 peer-reviewed articles in high-impact medical informatics journals ​(e.g., JBI, JAMIA), and conferences ​(e.g., AMIA Annual Symposium, AMIA summit, IEEE BIBM). Dr. Wang is also active in organizing conference workshops and shared tasks in the medical informatics communityincluding the international ​Health ​NLP workshops and the national NLP clinical challenge ​(n2c2). 
 +==== Recording ==== 
 +[[https://​​v:/​r/​sites/​Workgroup-NLPNaturalLanguageProcessing/​Shared%20Documents/​General/​Recordings/​Fwd_%20OHDSI%20NLP%20WG%20Monthly%20Meeting-20210908_130210-Meeting%20Recording.mp4?​csf=1&​web=1&​e=R7rBkZ|Click here to watch the recorded meeting]]
projects/workgroups/wg_meeting_sep_08_2021.1633442814.txt.gz · Last modified: 2021/10/05 14:06 by vipina