AI and Internet of Medical Things for Healthcare

Faculty: Chenyang Lu

Postdoc and Doctoral Students: Ruixuan Dai, Dingwen Li, Hanyang Liu, Sunny Lou, Bing Xue, Jingwen Zhang

MS and Undergraduate Students: Danny Aguirre Duran, Jeff Candell, Reshad Hamauon, Jooho Kim, Yuqi Lei, Yanase Nao, Harper Qi, Nisha Sahgal, Sam Saxon, Austin Tolani, Josh Wang, Ben Warner, Huilin (Lynn) Xu, Albert Yang, Ethan Zheng

Clinical Collaborators: Joanna Abraham, Michael Avidan, Thomas Bailey, George Despotis, Victoria Fraser, Chet Hammill, Simon Haroutounian, Tamara Hershey, Thomas Kannampallil, Marin Kollef, Eric Lenze, Patrick Lyons, Michael Montana, Maria Cristina Vazquez Guillamet

Past Collaborators and Doctoral Students Roger Chamberlain, Yixin Chen, Octav Chipara, Rahav Dor, Greg Hackmann, Gruia-Catalin Roman, Susan Stark

Current and Recent Projects

Sample Projects

Predicting Clinical Outcomes Using Wearables

We are developing mobile health software and machine learning models to monitor outpatients using wearables (smart watches and wristbands) and predict clinical deterioration among outpatients. For example, we developed and piloted a Fitbit-based data collection software in a clinical study which involved heart failure patients recently discharged from Barnes-Jewish Hospital. The results demonstrated the feasibility of continuously monitoring outpatients using wristbands. We observed high levels of patient compliance in wearing the wristbands regularly and satisfactory yield, latency and reliability of data collection from wristbands to a cloud-based database. Finally, we explored a set of machine learning models to predict deterioration based on the Fitbit data. Through 5-fold cross validation, K nearest neighbor achieved the highest accuracy of 0.8667 for identifying patients at risk of deterioration using the data collected from the beginning of the monitoring. Machine learning models based on multimodal data (step, sleep and heart rate) significantly outperformed the traditional clinical approach based on LACE index. Moreover, our proposed Weighted Samples One Class SVM model with estimated confidence can reach high accuracy (0.9635) for predicting the deterioration using data collected within a sliding window, which indicates the potential for allowing timely intervention. Our ongoing clinical studies involve wearable-based clinical monitoring for cancer surgical patients, lung-transplant patients, and other surgical patients.

Clinical Warning Systems

Early detection and intervention are essential for preventing clinical deterioration in patients.  We are developing a two-tiered clinical warning system designed to identify the signs of clinical deterioration and provide early warning of serious clinical events at general hospital units.  The first tier of the system automatically identifies patients at risk of clinical deterioration from existing electronic medical record databases.  The second tier performs real-time clinical event detection based on vital sign data collected from on-body wireless sensors attached to those high-risk patients.  Wireless sensor networks play an important role in clinical warning by collecting real-time vital signs for clinical decision support.  We have developed and deployed a large-scale wireless clinical monitoring system that encompasses portable wireless pulse oximeters, a wireless relay network spanning multiple hospital floors, and integration with electronic medical record databases.  Our system has been deployed over a 14-month clinical trial in six hospital wards of Barnes-Jewish Hospital in St. Louis, Missouri.  Our experiences show the feasibility of achieving reliable vital sign collection using a wireless sensor network integrated with hospital IT infrastructure and procedures.  We also identify and overcome technical and non-technical elements that pose challenges in a real-world hospital environment and provide guidelines for successful and efficient deployment of similar systems.  The convergence of wireless sensors, mobile computing, data mining and electronic medical record in clinical warning systems will lead to enhanced quality of care for patients in hospitals as well as outpatients in their everyday lives.

Wireless Clinical Monitoring Systems at Washington University

Fall Studies of Community-Dwelling Older Adults

Despite over a decade of research and development in fall detection systems, accurate and reliable systems in use are few. The existing fall detection approaches leave three major challenges unsolved: (1) insufficient fall data for model training process, (2) unreliable labeling of ground truth, and (3) resorting to artificial falls to model falls. We are addressing these challenges through an inter-disciplinary clinical study with community-dwelling older adults. The data collected from the real world reveal significant differences between artificial falls and actual falls, and also to illuminate the limitations of existing algorithms. We are developing new fall studies and technologies based on the challenges, experience, and lessons we learned from earlier studies.


B. Xue, D. Li, C. Lu, C.R. King, T. Wildes, M.S. Avidan, T. Kannampallil, and J. Abraham, Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications, JAMA Network Open, 4(3):e212240, 2021.

H. Cos, D. Li, G. Williams, J. Chininis, R. Dai, J. Zhang, R. Srivastava, L. Raper, D. Sanford, W. Hawkins, C. Lu, and C.W. Hammill, Predicting Outcomes in Patients Undergoing Pancreatectomy Using Wearable Technology and Machine Learning: Prospective Cohort Study, Journal of Medical Internet Research, 23(3):e23595, 2021.

R. Dai, C. Lu, M. Avidan, and T. Kannampallil, RespWatch: Robust Measurement of Respiratory Rate on Smartwatches with Photoplethysmography, ACM/IEEE International Conference on Internet of Things Design and Implementation (IoTDI'21), May 2021.

D. Li, J. Vaidya, M. Wang, B. Bush, C. Lu, M. Kollef, and T. Bailey, Feasibility Study of Monitoring Deterioration of Outpatients Using Multi-modal Data Collected by Wearables, ACM Transactions on Computing for Healthcare, 1(1), Article 5, March 2020. Inaugural Issue

D. Li, P. Lyons, C. Lu and M. Kollef, DeepAlerts: Deep Learning Based Multi-horizon Alerts for Clinical Deterioration on Oncology Hospital Wards, AAAI Conference on Artificial Intelligence (AAAI-20), February 2020.

J.P. Burnham, C. Lu, L.H. Yaeger, T.C. Bailey and M.H. Kollef, Using Wearable Technology to Predict Health Outcomes: a Literature Review, Journal of the American Medical Informatics Association, 25(9): 12211227, September 2018. Editor's Choice

X. Hu, R. Dor, S.Bosch, A. Khoong, J. Li, S. Stark, and C. Lu, Challenges in Studying Falls of Community-dwelling Older Adults in the Real World, IEEE International Conference on Smart Computing (SMARTCOMP'17), May 2017. (Invited Paper)

D. Picker, M. Dans, K. Heard, T. Bailey, Y. Chen, C. Lu, and M.H Kollef, A Randomized Trial of Palliative Care Discussions Linked to an Automated Early Warning System Alert, Critical Care Medicine, 45(2): 234-240, February 2017.

M.H. Kollef, K. Heard, Y. Chen, C. Lu, N. Martin and T. Bailey, Mortality and Length of Stay Trends Following Implementation of a Rapid Response System and Real-Time Automated Clinical Deterioration Alerts, American Journal of Medical Quality, 32(1): 12-18, January/February 2017.

S.T. Micek, M. Samant, T. Bailey, Y. Chen, C. Lu, K. Heard and M.H. Kollef, Real-Time Automated Clinical Deterioration Alerts Predict Thirty-Day Hospital Readmission, Journal of Hospital Medicine, 11(11): 768772, November 2016.

Y. Wang, W. Chen, K. Heard, M. Kollef, T. Bailey, Z. Cui, Y. He, C. Lu, and Y. Chen, Mortality Prediction in ICUs Using a Novel Time-Slicing Cox Regression Method, American Medical Informatics Association Annual Symposium (AMIA), November 2015. Distinguished Paper Award

M.H. Kollef, Y. Chen, K. Heard, G.N. LaRossa, C. Lu, N.R. Martin, N. Martin, S.T. Micek, and T. Bailey, A Randomized Trial of Real-Time Automated Clinical Deterioration Alerts Sent to a Rapid Response Team, Journal of Hospital Medicine, 9(7):424429, July 2014.

T. Bailey, Y. Chen, Y. Mao, C. Lu, G. Hackmann, S.T. Micek, K. Heard, K. Faulkner, and M.H. Kollef, A Trial of a Real-Time Alert for Clinical Deterioration in Patients Hospitalized on General Medical Wards, Journal of Hospital Medicine, 8(5): 236242, May 2013.

R. Dor, G. Hackmann, Z. Yang, C. Lu, Y. Chen, M. Kollef and T.C. Bailey, Experiences with an End-To-End Wireless Clinical Monitoring System, Conference on Wireless Health (WH'12), October 2012.

Y. Mao, W. Chen, Y. Chen, C. Lu, M. Kollef and T.C. Bailey, An Integrated Data Mining Approach to Real-time Clinical Monitoring and Deterioration Warning, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'12), August 2012.

Y. Mao, Y. Chen, G. Hackmann, M. Chen, C. Lu, M. Kollef, and T.C. Bailey, Early Deterioration Warning for Hospitalized Patients by Mining Clinical Data, International Journal of Knowledge Discovery in Bioinformatics, 2(3):1-20, 2012. (Extended version of the BioDM'11 paper.)

Y. Mao, Y. Chen, G. Hackmann, M. Chen, C. Lu, M. Kollef and T.C. Bailey, Medical Data Mining for Early Deterioration Warning in General Hospital Wards, ICDM Workshop on Biological Data Mining and its Applications in Healthcare (BioDM'11), December 2011.

G. Hackmann, M. Chen, O. Chipara, C. Lu, Y. Chen, M. Kollef, and T.C. Bailey, Toward a Two-Tier Clinical Warning System for Hospitalized Patients, American Medical Informatics Association Annual Symposium (AMIA), October 2011.

O. Chipara, C. Lu, T.C. Bailey and G.-C. Roman, Reliable Clinical Monitoring using Wireless Sensor Networks: Experience in a Step-down Hospital Unit, ACM Conference on Embedded Networked Sensor Systems (SenSys'10), November 2010.

J. Ko, C. Lu, M.B. Srivastava, J.A. Stankovic, A. Terzis, and M. Welsh, Wireless Sensor Networks for Healthcare, Proceedings of IEEE, 98(11):1947-1960, November 2010.

O. Chipara, G.Hackmann, C. Lu, W. Smart, and G.-C. Roman, Practical Modeling and Prediction of Radio Coverage in Indoor Sensor Networks, ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN'10), April 2010.

O. Chipara, C. Brooks, S. Bhattacharya, C. Lu, R.D. Chamberlain, G.-C. Roman, and T.C. Bailey, Reliable Real-time Clinical Monitoring Using Sensor Network Technology, American Medical Informatics Association Annual Symposium (AMIA), November 2009.


Internet of Medical Things: Predicting Clinical Outcomes and Digital Phenotyping with Wearables and Machine Learning, Washington University School of Medicine, 2019.

Predicting Clinical Outcomes with Wearables: Machine Learning from Small Data, mHealth Research Core, 2019.

Machine Learning for Healthcare: From Wearables to Electronic Health Record, AI in Health, Washington University, 2019.

Wireless Clinical Monitoring at Scale, Distinguished Lecture, DGIST Global Innovation Festival (DGIF), November 2013.

Wireless Clinical Monitoring at Scale, Samsung Advanced Institute of Technology, November 2013.

Toward Wireless Clinical Warning in Hospitals and Beyond, Illinois Institute of Technology, September 2013.

Toward a Two-Tier Clinical Warning System for Hospitalized Patients, American Medical Informatics Association Annual Symposium (AMIA'11), October 2011.

Reliable Clinical Monitoring using Wireless Sensor Networks: Experience in a Step-down Hospital Unit, ACM Conference on Embedded Networked Sensor Systems (SenSys'10), November 2010.

Toward Wireless Clinical Monitoring in General Hospital Units, PRECISE Seminar, University of Pennsylvania, October 2010.

News Coverage

Wireless Sensors Relay Medical Insight to Patients and CaregiversIEEE Signal Processing Magazine, 29(3): 8-12, May 2012.

Washington University Researchers Seek to Bring Mobility to ICU Patients, RFID Journal, August 2011.

Mesh Network Monitors Patients in Virtual ICU, British Journal of Healthcare Computing, August 2011.

Hospital Tests Wireless Patient Monitoring, UPI, August 2011.

Clinical Warning System Could Change Healthcare,, August 2011.

St. Louis Hospital Tests Wireless System That Monitors Vital Signs,
iHealthBeat, Augist 2011.

Wireless Network in Hospital Monitors Vital Signs, Washington University News Release, August 2011.