Supreeth Prajwal Shashikumar     Research     Teaching

A major focus of my research has been in the Intensive Care Unit (ICU) and wearable technologies, where I’ve been applying deep learning algorithms that are capable of analyzing large volumes of data (such as vital time series, lab values etc.) for predicting clinical events such as Sepsis, Atrial Fibrillation etc.

Recently, I have also been working with Google Cloud’s ML Engine for developing and deploying deep learning models for predicting Sepsis in the ICU.

My advisors are Prof. Shamim Nemati and Prof. Gari Clifford.

Papers (Published)

  • Supreeth P. Shashikumar, Qiao Li, Gari D Clifford, and Shamim Nemati. Multiscale Network representation of physiological time series for early prediction of sepsis, In Physiological Measurement, 2017 [Link]

  • Supreeth P. Shashikumar, Matthew D. Stanley, Ismail Sadiq, Andre Holder, Gari D Clifford, and Shamim Nemati. Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics, In Journal of Electrocardiology, 2017 [Link]

  • Supreeth P. Shashikumar, Amit J. Shah, Qiao Li, Gari D Clifford, and Shamim Nemati. A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology, In Biomedical & Health Informatics, 2017 IEEE International Conference on [Link]

  • Biswajit D. Sarma, Supreeth P. Shashikumar, and S.R.M. Prasanna. Improved vowel onset and offset points detection using bessel features, In Signal Processing and Communications (SPCOM), 2014 International Conference on [Link]

Papers (In Preparation)

  • Supreeth P. Shashikumar, Gari D Clifford, and Shamim Nemati. Detection of Paroxysmal Atrial Fibrillation using attention based bidirectional Recurrent Neural Networks, In preparation

  • Supreeth P. Shashikumar, Shamim Nemati, et al. A deep learning approach to early prediction of Sepsis in ICU, In preparation

  • Qiao Li, Qichen Li, Supreeth P. Shashikumar, et al., Sleep Staging Classification from Electrocardiogram using a Deep Learning Approach, In preparation

Patents

  • Shamim Nemati, Gari D. Clifford, Supreeth P. Shashikumar, Andre Holder. System for predicting or identifying patient deterioration or improvement, United States provisional patent application #62/534,322, filed July 19, 2017

  • Shamim Nemati, Supreeth P. Shashikumar, et al. Method for detecting abnormal cardiac activity, United States provisional patent application #62/437,457, filed December 21, 2016

Expertise

  • Predictive analytics in Healthcare
  • Applied Deep Learning
  • Google Cloud – ML Engine
  • Signal Processing
  • Multivariate time series
  • Data visualization
  • ECG, PPG and accelerometer data analysis
  • Information & graph theory

Software

Matlab, Python,

Advisors & collaborators