Asthma exacerbations leads to an irreversible reduction in lung function, especially in the growing phase of life. A major focus of clinical management of pediatric asthma is therefore upon minimizing the exacerbations. Here in this work we are predicting impending childhood asthma exacerbation using a data science approach on a longitudinal cohort of 256 asthmatic children, followed-up quarterly for five years. Our models achieved R-squared of 93 % on exacerbation score prediction and mean AUC of 72% on exacerbation event prediction models.
Describe the new knowledge and additional skills the participant will gain after attending your presentation.: Participants will be able to make use of integrative data-science approach for clinical decision making. Our approach enables clinical decisions for complex scenarios such as early prediction of exacerbation in childhood asthma. Participants will learn about our data science pipeline which helps in building parsimonious and robust predictive models using lean open-source resources.
Aditya Nagori (Presenter)
CSIR- Institute of Genomics and Integrative Biology
Tavpritesh Sethi, All India Institute of Medical Sciences
Sushil Kabra, All India Institute of Medical Sciences
Rakesh Lodha, All India Institute of Medical Sciences
Anurag Agrawal, CSIR- Institute of Genomics and Integrative Biology