Related Experiment Video
Updated: Mar 2, 2026
07:56
Evaluating Regional Pulmonary Deposition using Patient-Specific 3D Printed Lung Models
Published on: November 11, 2020
4.9K
Predicting Lung Cancer Incidence from Air Pollution Exposures Using Shapelet-based Time Series Analysis
Hong-Jun Yoon1, Songhua Xu2, Georgia Tourassi3
1Oak Ridge National Laboratory, Oak Ridge, TN 37831 USA phone: 865-241-2626; fax: 865-574-6275.
... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics
|May 9, 2017
Summary
Geographical lung cancer incidence can be predicted by analyzing air pollution trends. Prolonged exposure to particulate matter (PM2.5 and PM10) and its temporal variability are linked to increased lung cancer risk.
Area of Science:
- Environmental Health
- Epidemiology
- Data Science
Background:
- Lung cancer incidence exhibits significant geographical variation across the U.S.
- Air pollution, specifically particulate matter (PM), is a suspected environmental risk factor for lung cancer.
Purpose of the Study:
- To investigate the predictive relationship between spatiotemporal trends in particulate matter air pollution and lung cancer incidence.
- To determine if temporal variability in PM exposure, in addition to cumulative levels, influences lung cancer risk.
Main Methods:
- Utilized a novel shapelet-based time series analysis to examine regional air pollution trends.
- Identified U.S. counties with high and low lung cancer incidence (2008-2012).
- Collected decade-long particulate matter (PM2.5 and PM10) exposure data (1998-2007) and employed pattern mining to analyze exposure profiles.
Main Results:
- Confirmed a significant association between prolonged particulate matter exposure and elevated lung cancer risk.
- Shapelet-based analysis identified specific sequential exposure patterns linked to lung cancer incidence.
- A binary classifier successfully predicted high lung cancer incidence based on prior decade's PM exposure.
Conclusions:
- Geographical lung cancer incidence can be predicted by analyzing historical particulate matter air pollution patterns.
- Both cumulative exposure duration and the temporal variability of PM exposure are critical factors influencing lung cancer risk.
