Intelligent Learning based Critical Care (ICCare):

Real-time Analytic and Intellitent Learning Platform for Diagnostic Test and Patient Management in Critical Care



Hospital Intensive Care Units (ICUs) has been known as a data-rich, information-poor environment. Multitude of sensors and monitors are often present to monitor the patients' conditions, but the data collected are either not stored and analyzed continuously, or exist in isolated clusters that are not well-integrated. In addition, electronic medical record (EMR) systems often contain unstructured, subjective data from patient histories (e.g., clinician notes, X-ray reports) with limited automation, timeliness, and reproducibility. A real-time analytic platform is essential to integrate these heterogeneous sources of data in a meaningful way that can be fed into intelligent learning algorithms to derive predictive models that can be useful for automating diagnostic tests, detection of patients' states, or aid in making clinical decisions.

In the pilot project, we focus on developing an AI-driven diagnostic and prognosis tests for Acute-Respiratory Distress Syndrome (ARDS) Patients requiring mechanical ventilator machines in Critical Care. While mechanical ventilation (MV) machine is a life-saving therapy for patients in intensive care units (ICUs), it has been conclusively demonstrated in clinical studies that inappropriate delivery of MV can directly injure the lungs, leading to a condition called Acute-Respiratory Distress Syndrome (ARDS) and higher mortality. Attempts to automate ARDS diagnosis using rule-based computer algorithms have seen only limited success, requiring complex informatics infrastructures unavailable in current electronic medical record systems. We propose to employ advanced statistical and machine learning techniques to build an AI model that will operate on objective, readily available, high-dimensionality data including continuous ventilator waveform signals, electronic medical records (EMR), and wearable sensor data, to improve early recognition of ARDS. Early identification of ARDS patients, when they are most likely to benefit from ARDS-specific treatments, will lead to better overall outcomes that can be quantified (e.g., shorter hospital stay, lower mortality rate, mobility index). We expect that the research will lead to the refinement and validation of a functional automated ARDS diagnostic test ready for prospective evaluation in a large, multicenter cohort study aimed at improving the accuracy of ARDS diagnosis.



Graduate Students

  • Gregory Rehm, CS (PhD)
  • Rahul Krishnamurthy, ECE (MS)


  • Yue Xia, ECE (MS, June 2018)
  • Zachary Harris, ECE (MS, Sep 2019)
  • Kavish Doshi, CS (MS, 2020)
  • Bhargav Sundararajan, CS (MS, 2020)


  • G. B. Rehm, I. Cortes-Puch, B. Kuhn, J. Nguyen, S. A. Fazio, M. A. Johnson, N. R. Anderson, C-N. Chuah, and J. Y. Adams, "Use of Machine Learning to Screen for Early Acute Respiratory Distress Syndrome using Raw Ventilator Waveform Data", Critical Care Explorations (CCX), vol. 3, no. 1, p e0313, January doi: 10.1097/CCE.0000000000000313.
  • G. B. Rehm, W. H. Woo, X. L. Chen, B. T. Kuhn, I. Cortes-Puch, N. R. Anderson, J. Y. Adams, C-N. Chuah, “Leveraging IoTs and Machine Learning for Patient Diagnosis and Ventilation Management in the Intensive Care Unit, IEEE Pervasive Computing Magazine, vol. 19, no. 3, pp. 68-78, July-September 2020.
  • G. B. Relm, B. T. Kuhn, J. Nguyen, N. R. Anderson, C-N. Chuah, J. Y. Adams, “Improving Mechanical Ventilator Clinical Decision Support Systems with A Machine Learning Classifier for Determining Ventilator Mode,” MedInfo, August 2019.
  • G. Relm, J. Han. B. T. Kuhn, J-P. Delplanque, N. R. Anderson, C-N. Chuah, and J. Y. Adams, “Creation of a Robust and Generalizable Machine Learning Classifier for Patient Ventilator Asynchrony,” Methods of Information in Medicine, vol. 57, no. 4, pp. 208-219, September 2018.


  • G. Rehm, I. Cortes Puch, J. Nguyen, J. Y. Adams, N. Anderson, and C-N. Chuah, “A Machine Learning Classifier for Early Detection of ARDS using Raw Ventilator Waveform,” UC Davis Lung Day, June 2019. (2018 Philip Thai Memorial Award for the Best Clinical Abstract)

  • Bhargav Sundarajan, "Investigating Pre-training Techniques for Deep-Learning Based ARDS Detection," M.S. Plan-II Project Report, June 2020.
  • Kavish Doshi, "Data Analytic Pipeline for Disease Screening for Detection," M.S. Plan-II Project Report, June 2020.
  • Zachary Harris, "A Deep Learning Model for Predicting Patient Outcomes in the ICU," M.S. Plan-I Thesis, September 2019.
  • Yue Xia, "Anomaly Detection of Mechanical Ventilator Waveform Data Based on Dynamic Time Warping," M.S. Plan-II Project Report, June 2018.


This project is supported by UCD CTSC Highly Innovative Awards 2016-17, UCD Health Collaborative for Diagnostic Innovation 2018-19, and DoD AFRL grant 2019-22.
PhD student Greg Rehm was awarded NIH F31 Fellowship in 2018.