Jump to the main content block
TITLE

[2021-May-19] Modelling and Decision Support System for Children Respiratory Tract Infections: A Machine Learning Approach

Institute of Information Systems and Applications

Speaker:

Prof. Chia-Ching Chou 周佳靚教授

National Taiwan University Institute of Applied Mechanics 台灣大學應用力學研究所

Topic:

Modelling and Decision Support System for Children Respiratory Tract Infections: A Machine Learning Approach

Date:

13:30-15:00 Wednesday 19-May-2021

Locate:

Delta R105

QR code:

 

Link:

https://meet.google.com/oxa-smvh-dmk

Hosted by:

Prof. Po-Chih Kuo

Abstract

Timely decision making regarding intensive care unit (ICU) admission for children with pneumonia is crucial for a better prognosis. Despite attempts to establish a guideline or triage system for evaluating ICU care needs, no clinically applicable paradigm is available. In this study, we focus on developing machine learning algorithms to predict ICU care needs for pediatric pneumonia patients within 24 hours of admission, evaluate their performance, and identify clinical indices for making decisions for pediatric pneumonia patients. We selected clinically relevant features concerning ICU admission decisions, including demographic data, underlying diseases, pathogens, lab exam results and vital signs. The outcome of interest was the ICU admission prediction within 24 hours after of hospitalization. We compared clinically relevant features between early ICU transfer patients and patients without ICU care. ML algorithms were developed to predict ICU admission. The results showed that the machine learning model achieved area under the receiver operating characteristic curve of .982 and average precision 0.943 on predicting ICU admission. Relative feature importance of the model displayed was interpretable by clinicians. The ML approach could provide a clinically applicable triage algorithm and identify important clinical indices, such as age, underlying diseases, and abnormal vital signs, and laboratory data for evaluating the need for intensive care in children with pneumonia.

All faculty and students are welcome to join.

Click Num: