The increasing amount of health-related data pose unprecedented opportunities for mining previously unknown knowledge with semantics-powered data mining and analytical methods. However, due to the heterogeneity of different data sources ranging from electronic health records (EHRs) to environmental exposures, from social determinants of health to social media, it is challenging to exploit and integrate multiple sources to solve real-world problems. Biomedical ontologies and semantics-powered analytical methods are promising solutions. The goal of the 7th International Workshop on Semantics-Powered Data Mining and Analytics (SEPDA 2023) is to bring people in the fields of ontologies, knowledge management, data mining, and data analytics to discuss a wide range of innovative methods and applications that address problems in healthcare, biomedicine, public health, and clinical research with biomedical, clinical, behavioral, and social web data.
We are inviting original research submissions as well as work-in-progress to the 7th International Workshop on Semantics-Powered Health Data Analytics (SEPDA 2023).
Topics of interest include but not limited to:
Papers should be submitted to the SEPDA 2023 Easy Chair Website (https://easychair.org/conferences/?conf=sepda2023).
The conference features regular papers in two categories (please note if you submit a paper as a student):
Papers should be formatted according to Springer's LNCS format and one of the categories must be selected during submission (Full research paper, Short paper, Demo paper). Authors should consult Springer’s authors’ guidelines and use their proceedings templates, either for LaTeX or for Word, for the preparation of their papers. Springer’s proceedings LaTeX templates are also available in Overleaf. Springer encourages authors to include their ORCIDs in their papers.
SEPDA 2023 proceedings will be published in CEUR Workshop Proceedings (http://ceur-ws.org/). Authors of the accepted presentations will be invited to publish an extended paper in a peer-reviewed journal in biomedical and health informatics or semantic web.
|9:00 am – 9:10 am
|Session 1: Machine Learning & AI
|9:10 am – 9:30 am
|Using AI in Healthcare Data to Approach Ground Truth
|Stuart Nelson, Qing Zeng-Treitler and Mark Tuttle
|9:30 am – 9:50 am
|Exploring rare diseases with automatic text classification and interactive data visualisation on published science and news
|Joao Pita Costa and Tanja Zdolšek Draksler
|9:50 am – 10:10 am
|Effect of Eligibility Criteria on Patient Outcome in Colorectal Cancer Clinical Trials
|Chang Wang, Aokun Chen, Zhaoyi Chen, Thomas George, Yi Guo and Jiang Bian
|10:10 am – 10:30 am
|Using Game Performance Data to Predict Adherence to Gamified Cognitive Training
|Yuanying Pang, Ankita Singh, Shayok Chakraborty, Neil Charness, Walter R. Boot and Zhe He
|Coffee Break (30 minutes)
|Session 2: Ontology, Knowledgebase, NLP
|11:00 am – 11:20 am
|F-BERTMed: A new Sentence Embedding Framework for the French Medical domain
|Abdelhamid Gaddari, Guillaume Lefebvre, Haytham Elghazel, Rakia Jaziri, Pierre-Henri Comble and Matthieu Sonnati
|11:20 am – 11:40 am
|A Smart Ontology-Based Annotator for Extracting Cancer Phenotypes from Oncologists' Notes
|Haniya Akhtar Anjum and Muddassar Farooq
|11:20 am – 12:00 pm
|Semantics-Powered Data Mining and Analytics of EHR Data to Predict the Outcome of Opioid Treatment Program
|Wanting Cui, Fatemeh Shah-Mohammadi and Joseph Finkelstein
|12:00 pm – 12:20 pm
|Exploratory Ontology-based Approach For Interlinking Open Government Data of Hospital Services in Developing Nations: An Indonesian Use Case
|Irhamni Ali and Muhammad Amith
|12:20 pm – 12:40 pm
|Benchmarking Transformer-Based Models for Identifying Social Determinants of Health in Clinical Notes
|Xiaoyu Wang, Dipankar Gupta, Michael Killian and Zhe He
|Adjourn - Lunch