• Research
• ·
• Datathon
• ·
• Education
• ·
• Collaborators


• Publications
• ·
• Collections
• ·
• Blogs

---

Research

• AI-assisted Emergency Medical Dispatch (EMD) system
• Epidemiological studies on retrospective EHR data
• Predictive modelling on Electrocardiogram (ECG) signals
• Natural Language Processing (NLP) on clinical text
• Experience with datasets: MIMIC, eICU, NUH Datamart

---

Datathon

• Healthcare AI Datathon is an initiative started by Laboratory for Computational Physiology in Massachusetts Institute of Technology in 2015.
• I have been in datathons in Singapore, Beijing, Seoul, Tokyo and Taipei as a organizing committee member, mentor and speaker (see the profile picture).
• Interview during Korean Datathon 2018
• I am happy to share my experience on Datathon if you are interested.

---

Education

• My team and I started the Robotics Innovation Challenge (RIC), extending the AI education to the juniors in Singapore and other Asian countries via robotics.
• RIC is supported by multiple schools and organizations in NUS, MSD, Science Centre Singapore and NVIDIA.
• Every year, we are expecting hundreds of 8-15 years old students coming to Singapore for the grand final.
• For potential collaboration, please feel free to contact me via email.

---

Collaborators

• National University Hospital, Singapore
  • Dr. Ngiam Kee Yuan (Cancer & Surgery)
  • Dr. Manjari Lahiri (Rhematology & Advanced Internal Medicine)
  • Dr. Irwani Ibrahim (Emergency Medicine)
  • Dr. Pipin Kodjodjo (Cardiology)
  • Dr. Benjamin Leong Siew Hon (Emergency Medicine)
  • Dr. Ko Qianwen Stephanie (Internal Medicine)
  • Dr. Hooi Ming-Yew Benjamin (Internal Medicine)
  • Dr. Wesley Yeung Lok Kin (Internal Medicine)
  • Dr. John Soong Tshon Yit (Acute Medicine)
• Singapore General Hospital, Singapore
  • Dr. Marcus Ong Eng Hock (Emergency Medicine)
• Duke-NUS Medical School, Singapore
  • Prof. Liu Nan
• Singapore Civil Defence Force, Singapore
• Dr. Shalini Arulanandam (ex-Chief Medical Officer)
• Dr. Colin Tan (Chief Medical Officer)
• Dr. Ng Qin Xiang (Emergency Medical Services Department)
• Unit for Pre-hospital Emergency Care, Singapore
• MIT Critical Data, US
• Ping An Technology, China
• Dr. Sun Xingzhi (Lead of the clinical decision support division)

---

Publications

Hospital Admission Risk Stratification of Patients with Gout presenting to the Emergency Department (demo)
Han Wang^*, Nur Azizah Allameen, Irwani Ibrahim, Preeti Dhanasekaran, Mengling Feng^# and Manjari Lahiri^#

To facilitate the development and early institution of targeted interventions to reduce the frequency of gout-related admissions, and potentially allow for the improvement of the care of these complex multimorbid patients, we examined the potential factors that predict the gout-related admissions and come up with a risk prediction model with 5 easy predictors.

A Weakly-Supervised Named Entity Recognition Machine Learning Approach for Emergency Medical Services Clinical Audit (paper) (demo)
Han Wang^* and Wesley Yeung^*, Qin Xiang Ng, Angeline Tung, Joey Tay Ai Meng, Davin Ryanputra, Marcus Eng Hock Ong, Mengling Feng^# and Shalini Arulanadam

Our Name Entity Recognition tool for Emergency Medical Service Report (NEREMSR) is an online natural language processing system to identify the potential entities in the paramedics report for auditing purposes.

Classification of Cardiac Abnormalities From ECG Signals Using SE-ResNet (paper)
Zhaowei Zhu^* and Han Wang^*, Tingting Zhao, Yangming Guo, Zhuoyang Xu, Zhuo Liu, Siqi Liu, Xiang Lan, Xingzhi Sun^# and Mengling Feng^#

In PhysioNet/Computing in Cardiology Challenge 2020, we developed an ensembled model based on SE-ResNet to classify cardiac abnormalities from 12-lead electrocar- diogram (ECG) signals.

Serial Heart Rate Variability Measures for Risk Prediction of Septic Patients in the Emergency Department (paper)
Calvin J. Chiew^* and Han Wang^*, Marcus E.H. Ong, Ting Hway Wong, Zhi Xiong Koh, Nan Liu^# and Mengling Feng^#

In this study, we used serial heart rate variability (HRV) measures over 2 hours to improve the prediction of 30-day in-hospital mortality among septic patients in the emergency department (ED). We presented a generalizable methodology for processing and analysing HRV time series (HRVTS) data which may be noisy and incomplete.

Searching for Optimal Blood Pressure Targets in Critically Ill Patients: Analysis of Large Observational Databases (paper)
Siqi Liu^* and Zhemin Wang^*, Vinay Bahadur Panday, Han Wang, Atlanta Chakraborty, Liangyu Chen, Min Han Lee, Wei Chit Tan, Mengling Feng^# and Kay Choong See^#

Mean arterial blood pressure (BP) is currently recommended to be maintained at 65mmHg or higher, though evidence remains weak with regards to mortality and incident acute kidney injury (AKI). In this study, we aim to search for optimal BP targets using real-world data.

Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with sign loss function (paper)
Zhaowei Zhu^*, Xiang Lan^*, Tingting Zhao, Yangming Guo, Pipin Kojodjojo, Zhuoyang Xu, Zhuo Liu, Siqi Liu, Han Wang, Xingzhi Sun^# and Mengling Feng^#

Cardiovascular disease is a major threat to health and one of the primary causes of death globally. The 12-lead ECG is a cheap and commonly accessible tool to identify cardiac abnormalities. Early and accurate diagnosis will allow early treatment and intervention to prevent severe complications of cardiovascular disease. In the PhysioNet/Computing in Cardiology Challenge 2020, our objective is to develop an algorithm that automatically identifies 27 ECG abnormalities from 12-lead ECG recordings.

---

Acknowledgement

The design of this website is hugely influenced by Prof. Matt Might. His personal story really inspires me a lot and I would like to pay my respect to him.