thumbnail image

SG HEALTHCARE AI

DATATHON & EXPO

  • Home
  • …  
    • Home

SG HEALTHCARE AI

DATATHON & EXPO

  • Home
  • …  
    • Home

SG HEALTHCARE AI

DATATHON & EXPO

  • Results for the Datathon

  • Datasets

     

    Reminder: Teams need to apply and obtain access to the datasets they intend to use before the datathon.

     

    1. Electrical Medical Records Datasets

    During the datathon, teams will have access to 3 de-identified EMR datasets. Teams may choose to use one or all of these datasets to answer their clinical questions. In particular, these three datasets are: 1) the Medical Information Mart for Intensive Care (MIMIC)-IV Database from Physionet 2) the Philips eICU Collaborative Research Database (https://eicu-crd.mit.edu/). These three databases share similar data schemas. They contain hourly physiologic readings from bedside monitors, validated by ICU nurses. They also contain records of demographics, labs, nursing progress notes, discharge summaries, IV medications, fluid balance, and other clinical variables.

    MIMIC-IV Dataset

    Introduction & Access Application: https://mimic-iv.mit.edu/

     

    Github repository: https://github.com/MIT-LCP/mimic-iv

     

    Documentation: https://mimic-iv.mit.edu/docs/

     

    When using this resource, please cite:
    Johnson, A., Bulgarelli, L., Pollard, T., Horng, S., Celi, L. A., & Mark, R. (2020). MIMIC-IV (version 0.4). PhysioNet. https://doi.org/10.13026/a3wn-hq05.


    Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

    eICU-CRD Dataset

    Introduction & Documentation: https://eicu-crd.mit.edu/about/eicu/

     

    Github repository: https://github.com/mit-eicu/eicu-code

     

    Example code: https://github.com/mit-eicu/eicu-code/blob/master/concepts/icustay_detail.sql

     

    When using this resource, please cite:
    Pollard, T., Johnson, A., Raffa, J., Celi, L. A., Badawi, O., & Mark, R. (2019). eICU Collaborative Research Database (version 2.0). PhysioNet. https://doi.org/10.13026/C2WM1R.

     

    The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG and Badawi O. Scientific Data (2018). DOI: http://dx.doi.org/10.1038/sdata.2018.178.

     

    Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

  • We had 50 teams with close to 500 physicians and data scientists from more than 10 regions that joined us in our 2020 event!

    broken image
  • And the winner goes to...

    Champion and Crowd's Favourite

    Team 01: An AI method to help intensivists optimize ventilation settings

    Liu Siqi, Lan Xiang, Liu Zhuo, Xu Zhuoyang, Li Yanxuan, Liesel Fong, See Kay Choong

    First Runner-up

    Team 14: Best Antibiotics Empirically

    Dang Trung Kien, Ke Yuhe, Nicholas Brian Shannon, Muhammad Jarir Kanji, E V S Ravishankar, Li Chenyu, Lee Mei Teng, Hairil Abdullah

    Second Runner-up

    Team 29: Domain Shift Problem in Deep Learning based Chest X-ray Diagnosis AI Models

    Shan Lin, Yufei Wang, Siyuan Yang, Ling Li, Rahul Ahuja

    Best Presentation Award

    Team 21: Vital Sign Triage Alert - in-hospital Cardiac Arrest Prediction Score

    Chien-Chang Lee, Chien-Hung Li, Hong-Jie Jhou, Hsin-Ying Lee, Ke-Ying Su, Po-Huang Chen, Cho-Hao Lee, I-Ju Wu, Po-Chih Kuo

    Best Potential Award

    Team 36: To Use Basic Electronic Data to Predict Prolonged Ventilation

    Sing Chee Tan, Vlada Rozova, Shilpa Veerappa, Ryo Ueno, Douglas Pires, Vinodh Nanjayya, Jing Hui Liu, Carl Xing

    Finalist

    Team 07: Does the use of chest X-ray improve the prediction ability of extubation failure using deep neural networks?

    Goto Tadahiro, Dohi Eisuke, Fukuchi Kiyoyasu, Kasugai Daisuke, Miyamoto Yoshihisa, Ohbe Hiroyuki, Osawa Itsuki, Satake Shunya, Tamoto Mitsuhiro, Yamada Naoki, Yoshikawa Keisuke

    Finalist

    Team 47: Early Prediction of MV Requirement by Deep Learning Model

    Young Seok Jeon, Jung Hwa Lee, Seungmin Baik, Seung Won Lee, Seojeong Shin, Doyeop Kim, Chioh Song, Cinyoung Hur, Geun U Park, Haneol Lee

    Finalist

    Team 31:

    Chunhui He, Xin Jin, Tao Bu, Xiaofang Ye, Wenchun Xia, Ting He, Mingyue Liu

    Finalist

    Team 34: AI in Medical Imaging - Development of Defense System in Preventing Adversarial Attack

    Daniel Ting, Wei Yan Ng, Dinesh Gunasekeran, Yong Liu, Xin Xing Xu, Yan Yu Xu, Gilbert Lim, Shihao Zheng, Dinh Linh, Rick Goh

    Finalist

    Team 49: Better Intubation Timing in Sepsis

    Jiang Shengmao, Yang Xiao, Hu Chang, Hao Fangbin, Liu Xiaoli, Li Bowen, Ma Chenbin, Wu Di, Stacy Xu

SINGAPORE HEALTHCARE AI DATATHON AND EXPO 2021

    Cookie Use
    We use cookies to ensure a smooth browsing experience. By continuing we assume you accept the use of cookies.
    Learn More