A multidisciplinary approach to the development of digital twin models of critical care delivery in intensive care units

Abstract

To investigate critical care delivery in intensive care units (ICUs), we propose a qualitative and quantitative coupling approach to developing an ICU digital twin model. The Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 model was adapted to conceptualise the current ICU system. A hybrid simulation model was developed to characterise major care delivery processes as discrete-time events, feature patients, clinicians, and other artifacts as autonomous agents, and integrate them in the same simulation environment to capture their interactions under a variety of ICU production conditions. Electronic health record (EHR) data from a medical ICU of Mayo Clinic Rochester, Minnesota, were used to calibrate model parameters. Upon iterative refinement and validation, the model has the potential to be integrated with the hospital information system to simulate real-life events as a full-fledged digital twin of the system. It can be used as an in-silico testbed to investigate the real-time allocation of ICU resources such as medical equipment, flexible staffing, workflow change, and support decisions of patient admission, discharge, and transfer, for healthcare delivery innovation. The interdisciplinary nature of this framework demonstrates and promotes the partnership between healthcare and engineering communities to building a better delivery system.

KEYWORDS:

• Systems engineering
• digital twin
• hybrid simulation
• patient safety
• critical care

Data availability statement

Due to the nature of this research, participants of this study did not agree for their data to be shared publicly, so supporting data is not available.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This project was supported by [grant number R18HS026609] from the Agency for Healthcare Research and Quality.

Notes on contributors

Xiang Zhong

Xiang Zhong received her B.S. from the Department of Automation, Tsinghua University, Beijing, China, in 2011, and her M.S. in Statistics and Ph.D. in Industrial Engineering from the University of Wisconsin –Madison in 2014 and 2016. Currently, she is an Assistant Professor of the Department of Industrial and Systems Engineering at the University of Florida. Her research interests include stochastic modelling and control, and data analytics with the application in healthcare, service and production systems. She is a member of the Institute of Electrical and Electronics Engineers (IEEE), the Institute of Industrial and Systems Engineers (IISE) and the Institute for Operations Research and the Management Sciences (INFORMS).

Farnaz Babaie Sarijaloo

Farnaz Babaie Sarijaloo is a data scientist at Bayer, Crop Science Division. She received her bachelor's degree in 2010 from the Department of Industrial Engineering at Amirkabir University of Technology, Tehran. In 2014, she attended Department of Industrial Engineering at Sharif University of Technology in Tehran, earning her master's degree in 2016. In January 2017, she joined the Ph.D. programme in the Department of Industrial and Systems Engineering at the University of Florida. She received her Doctor of Philosophy degree in the summer of 2021. Her research interests lie in application of machine learning, data analysis and simulation in healthcare.

Aditya Prakash

Aditya Mahadev Prakash received his bachelors’ degree from IIT Kharagpur, India in 2013, Post-Graduate Diploma in Management from IIM Bangalore, India in 2015, and his PhD in Industrial and Systems Engineering from the University of Florida in 2020. His research focuses on stochastic modelling and analysis of healthcare delivery systems. He currently works as a quantitative specialist at Wells Fargo Bank, U.S.A.

Jaeyoung Park

Jaeyoung Park is a PhD candidate of the Department of Industrial and Systems Engineering at the University of Florida and was a research intern at Mayo Clinic in Rochester, MN. He holds BS and MS degrees in Industrial Engineering. His research interest is data analytics with the in Medicine from Sun Yat-Sen University in China and currently works as an anesthesiologist at the First Affiliated Hospital, Sun Yat-primary application in healthcare. Specifically, his interests in methodology include causal inference, transfer learning, and doubly robust semiparametric estimation. He has published several papers addressing pressing healthcare challenges in leading medical journals.

Chanyan Huang

Dr. Chanyan Huang received both the Bachelor's and Master's Degree in Medicine from Sun Yat-Sen University in China and currently works as an anesthesiologist at the First Affiliated Hospital, Sun Yat-Sen University. She also worked as a visiting scientist at Mayo Clinic, Rochester, MN, U.S.A. in 2019 - 2020. Her professional interests focus on perioperative organ function protection and patient safety.

Amelia Barwise

Amelia Barwise, MB BCh BAO, PhD is an Assistant Professor of Medicine and Biomedical Ethics at Mayo Clinic Rochester. Dr. Barwise was born in Dublin and completed medical education at Trinity College Dublin before training as a family medicine physician in the UK. She completed a PhD in Clinical and Translational research in 2019. Her research interests focus on disparities in critical illness communication and outcomes and end of life care among patients who have limited English proficiency.

Vitaly Herasevich

Vitaly Herasevich, MD, PhD, MSc is a Professor of Anesthesiology and Medicine in the Department of Anesthesiology and Perioperative Medicine, Division of Critical Care, Mayo Clinic, Rochester, Minnesota. He has been involved in medical informatics for over 20 years, with a specific concentration on applied clinical informatics in critical care and perioperative environment. Dr. Herasevich codirects the Clinical Informatics in Intensive Care laboratory that works to decrease complications and improve outcomes for critically ill patients through applied clinical informatics and quality improvement. He is interested in studying and developing clinical syndromic surveillance alerting systems (‘sniffers’), clinical data visualisation (novel patient-centred EMR), and health care predictive and prescriptive ambient intelligence. He is co-inventor of number of technologies including AWARE platform. Dr. Herasevich has coauthored over 100 articles and book Health Information Evaluation Handbook (now in second edition). He is Senior Member at IEEE, Fellow of Society of Critical Care Medicine and American Medical Informatics Association active within professional societies and served SCCM Tele-ICU committee as chair.

Ognjen Gajic

Ognjen Gajic, MD MSc FCCM FCCP practices and teaches critical care medicine at Mayo Clinic in Rochester, Minnesota. Dr. Gajic has published more than 350 peer-reviewed articles and book chapters related to critical care medicine. He has served as a chair of the Discovery Research Network of the Society of Critical Care Medicine. He pioneered the concepts of improving critical care and outcomes with intelligent ICU environments. Dr. Gajic and his group designed and implemented one of the largest international quality improvement project in critical care: CERTAIN (Checklist for Early Recognition And Treatment of Acute Illness & iNjury) www.icertain.org

Brian Pickering

Brian Pickering, MD, MSc, FFARCSI is an Associate Professor of Anesthesiology in the Department of Anesthesiology - Division of Critical Care, Mayo Clinic, Rochester. Dr. Pickering was born in Dublin Ireland. He completed his medical education at Trinity College Dublin prior to his residency and fellowship training in Anesthesiology and Critical care at College of Anesthetists, Royal College of Surgeons Ireland. Dr Pickering’s primary research area is focused on application of clinical informatics to the task of improving patient health and outcomes while reducing medical costs. His group have developed bedside informatics tools for the intensive care patient population.

Yue Dong

Dr. Yue Dong is Assistant Professor of Medicine at the Mayo Clinic College of Medicine and Science. He is patient safety and healthcare delivery researcher in the Multidisciplinary Epidemiology and Translational Research in Intensive Care (METRIC) group, Clinical Informatics in Intensive Care lab, Department of Anesthesiology and Perioperative Medicine, Mayo Clinic. Dr. Dong’s research interests are using simulation and modelling technology to analyze healthcare delivery systems, design, test, and implement interventions for patient safety and quality improvement. Dr. Dong is a Fellow of the Society for Simulation in Healthcare Academy (FSSH). He is currently serving as the Board of Director for the Society for Simulation in Healthcare Care (SSH).