International Journal of Respiratory and Pulmonary Medicine
Idiopathic pulmonary fibrosis (IPF) is a chronic and fatal interstitial lung disease with no current cure. Progression of IPF is difficult to predict as the clinical course can be highly variable and range from a rapidly deteriorating state to a relatively stable state, or may be characterized by a slow progressive decline. Therefore, the need for an accurate diagnosis and improved tools for monitoring and managing IPF is of paramount importance, all for understanding the mitochondrial structure and the function played in the IPF. Mitochondrial DNA copy number (MtDCN) has been correlated with mortality in IPF patients and is a source of potentially clinically relevant information. We investigated the effects of various expiratory variables on MtDCN via multiple linear regression models. The models and their theoretical framework are presented under a descriptive and then analytic approach to investigate the complex and impact causes of IPF. Generalized linear model (GLM) based boosting is fitted before and after imputing the missing data. The Bayesian Hierarchical logistic models with categorical response variables that were created using carefully chosen cut-off points to classify the patients. This research provides an opportunity for novel patient surveillances.
Original Publication Citation
Alqawba, M., Rodriguez, L., Diawara, N., Beuschel, R., & Kaler, M. (2020). Classification models of idiopathic pulmonary fibrosis patients. International Journal of Respiratory and Pulmonary Medicine, 7(1), 10 pp., Article 131. https://doi.org/10.23937/2378-3516/1410131
Alqawba, Mohammed; Rodriguez, Luis R.; Diawara, Norou; Beuschel, Rebecca T.; Kaler, Maryann; Barochia, Amisha V.; Levine, Stewart J.; Nathan, Steven D.; and Grant, Geraldine, "Classification Models of Idiopathic Pulmonary Fibrosis Patients" (2020). Mathematics & Statistics Faculty Publications. 172.