Rishi Kamaleswaran

 Cardiac Arrhythmias constitute a large variety of ailments resulting from irregular heartbeat. While some arrhythmias may not have visible symptoms, they can predispose individuals to a heightened risk of stroke or cardiac arrest. In our lab, we apply state of the art machine learning and deep learning to classify and predict the onset of one such Cardiac Arrhythmias, namely, Atrial Fibrrilations (AF).  We are working towards applying our AF detection and prediction models to identify post-stroke patients at risk for AF. Our recent work in this area are as follows:

1. Kamaleswaran, R., Mahajan, R. and Akbilgic, O. (2018) ‘A robust deep convolutional neural network for the classification of abnormal cardiac rhythm using single lead electrocardiograms of variable length’, Physiological Measurement, 39(3), p. 35006. doi: 10.1088/1361-6579/aaaa9d.
2. Mahajan, R., Kamaleswaran, R., Howe, A. and Akbilgic, O., 2017. Cardiac Rhythm classification from a short single lead ECG recording via random forests. Comput. Cardiol, 44, pp.1-4.
3. Mahajan, R., Kamaleswaran, R. and Akbilgic, O., 2017, September. Effects of varying sampling frequency on the analysis of continuous ECG data streams. In VLDB Workshop on Data Management and Analytics for Medicine and Healthcare (pp. 73-87). Springer, Cham.
4. R Mahajan, R Kamaleswaran, O Akbilgic. A hybrid feature extraction method to detect Atrial Fibrillation from single lead ECG recording. IEEE BHI 2018 (In Press), 2018.

Sepsis is a life-threatening condition that results from a dysfunction in the body''s response to infection, resulting in single or multiple organ failure. In our lab, we focus on early prediction of sepsis in both children and adults.

Children (0-18 years of age):

1. Kamaleswaran, R. et al. (2018) ‘Applying Artificial Intelligence to Identify Physiomarkers Predicting Severe Sepsis in the Pediatric Intensive Care Unit’, Pediatric Critical Care Medicine. (In Revision) 
2. Kamaleswaran, R., Akbilgic, O., Hallman, M., West, A., Davis, R. and Shah, S., 2018. 1524: Physiomarker Variability For Early Prediction Of Severe Sepsis In The Pediatric Intensive Care Unit. Critical Care Medicine, 46(1), p.745.
3. Kamaleswaran, R. et al.(2016) ‘CoRAD: Visual Analytics for Cohort Analysis’, in IEEE International Conference on Healthcare Informatics 2016 (ICHI 2016). Chicago, pp. 517–526. doi: 10.1109/ICHI.2016.93.
4. Kamaleswaran, R. et al.(2016) ‘PhysioEx: Visual Analysis of Physiological Event Streams’, Computer Graphics Forum, 35(3), pp. 331–340. doi: 10.1111/cgf.12909.

Adults (18+):

1. van Wyk, F., Khojandi, A., Williams, B., MacMillan D., Davis, R.L., Jacobson, D., Kamaleswaran, R. (2018) "A Cost-Benefit Analysis of Automated Physiological Data Acquisition Systems Using Data-Driven Modeling “ Journal of Health Informatics Research. (In Revision)
2. van Wyk, F., Khojandi, A., Kamaleswaran, R., Akbilgic, O., Nemati, S. and Davis, R.L., 2017, November. How much data should we collect? A case study in sepsis detection using deep learning. In Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE (pp. 109-112). IEEE.