Predictive Models to Optimize Resources in Tele Critical Care in Distributed Hospital Networks


  • Rafael Palacios, PhD Universidad Pontificia Comillas
  • Eugenioio Sánchez-Úbeda, PhD Institute for Research in Technology, Universidad Pontificia Comillas, Madrid, Spain
  • Ralph Panos, MD 3Tele-ICU Program, Cincinnati VA Medical Center, Cincinnati, Ohio, USA
  • Peniel Argaw, MS John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts, USA
  • Malika Shahrawat, MEng Blue Apron, New York, New York, USA
  • Daniel D. Zhang, BS Blue Apron, New York, New York, USA
  • Angelina Zhang, BS Senior Year Princess Máxima Center for Pediatric Oncology, Utrecht, Netherlands
  • Adam Seiver, MD, PhD, MBA Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
  • Omar Badawi, PharmD, MPH, FCCM Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
  • Amar Gupta, PhD, MBA, FIEEE Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA



eICU, eICU collaborative research database, electronic ICU, intensive care, length of stay prediction, mortality prediction, resource management, tele-critical care, telemedicine


Background: Telemedicine creates the opportunity – in pandemic conditions and otherwise -- to spread health care to regions where intensivists and health services may not beavailable. It offers the opportunity to provide better patient care, decrease healthcare costs, and overall improve population health.

Introduction: Critical care telemedicine has increased in deployment due to its impact on providing care at all times of the day as well as in reaching remote regions of the world. Tele-critical care (Tele-CC) systems can provide concurrent service to several hospitals andcan manage available resources more efficiently than traditional ICUs.

Materials and Methods: This study utilizes the Philips eICU system and its CollaborativeResearch Database (eICU-CRD) to evaluate intensive care operations in the electronic ICU setting, with the objective of analyzing where and how system engineering techniques can bepotentially applied to enhance the effectiveness of such environments.

Results: Several metrics are evaluated, including patient outcomes, APACHE score, length of stay and type of unit in regard to the age of the patient. Prediction models based on decision and regression trees are presented to estimate mortality and length of stay.

Discussion: Prediction models offer the potential to optimize the Tele-CC environment by helping to estimate the number of patients who will remain in the ICU during the following days.

Conclusion: Prediction models accurately estimate mortality and length of stay in ICU. The estimation of future number of patients can be used to determine the resources needed at each hospital, as well as to provide insight on potential savings when Tele-CC centers provide concurrent services to multiple hospitals.


Download data is not yet available.


Scalvini S, Vitacca M, Paletta L, Giordano A, Balbi B. Telemedicine:

a new frontier for effective healthcare services. Monaldi

Arch Chest Dis. 2004;61(4). doi: 10.4081/monaldi.2004.686

Rheuban KS. The role of telemedicine in fostering health-care

innovations to address problems of access, specialty shortages

and changing patient care needs. J Telemed Telecare.

;12(2_suppl):45–50. doi: 10.1258/135763306778393171

Arneson SL, Tucker SJ, Mercier M, Singh J. Answering the call:

Impact of Tele-ICU nurses during the COVID-19 pandemic.

Crit Care Nurse. 2020;40(4):25–31. doi: 10.4037/ccn2020126

Gamus A, Keren E, Kaufman H, Chodick G. Synchronous

video telemedicine in lower extremities ulcers treatment: A real-

world data study. Int J Med Inform. 2019;124:31–6. doi:


Young K, Gupta A, Palacios R. Impact of telemedicine in pediatric

postoperative care. 2019;25(11):1083–9. doi: 10.1089/


Uscher-Pines L, McCullough C, Dworsky MS, Sousa J, Predmore

Z, Ray K, et al. Use of telehealth across pediatric subspecialties

before and during the COVID-19 pandemic. JAMA Netw Open.

;5(3):e224759. doi: 10.1001/jamanetworkopen.2022.4759

Howie F, Kreofsky BL, Ravi A, Lokken T, Hoff MD, Fang

JL. Rapid rise of pediatric telehealth during COVID-19

in a large multispecialty health system. Telemed e-Health.

;28(1):93–101. doi: 10.1089/tmj.2020.0562

Leong JR, Sirio CA, Rotondi AJ. eICU program favorably affects

clinical and economic outcomes. Crit Care. 2005;9(5):E22.

doi: 10.1186/cc3814

Udeh C, Udeh B, Rahman N, Canfield C, Campbell J, Hata

JS. Telemedicine/virtual ICU: Where are we and where are we

going? Methodist Debakey Cardiovasc J. 2018;14(2):126–33.

doi: 10.14797/mdcj-14-2-126

Subramanian S, Pamplin JC, Hravnak M, Hielsberg C,

Riker R, Rincon F, et al. Tele-critical care: An update

from the society of critical care medicine tele-ICU committee.

Crit Care Med. 2020;48(4):553–61. doi: 10.1097/


Young LB, Chan PS, Lu X, Nallamothu BK, Sasson C, Cram

PM. Impact of telemedicine intensive care unit coverage on

patient outcomes. Arch Intern Med. 2011;171(6):498–506. doi:


Sadaka F, Palagiri A, Trottier S, Deibert W, Gudmestad

D, Sommer SE, et al. Telemedicine intervention improves

ICU outcomes. Crit Care Res Pract. 2013;2013:456389. doi:


Shirke MM, Shaikh SA, Harky A. Tele-oncology in the COVID-

era: The way forward? Trends Cancer. 2020;6(7):547–9. doi:


Courtney E, Blackburn D, Reuber M. Neurologists’ perceptions

of utilising tele-neurology to practice remotely during the

COVID-19 pandemic. Patient Educ Couns. 2021. doi: 10.1016/j.


Kapoor A, Guha S, Kanti Das M, Goswami KC, Yadav R. Digital

healthcare: The only solution for better healthcare during

COVID-19 pandemic? Indian Heart J. 2020;72(2):61–4. doi:


AlDossary S, Martin-Khan MG, Bradford NK, Smith AC. A

systematic review of the methodologies used to evaluate telemedicine

service initiatives in hospital facilities. Int J Med Inform.


Hwang S. Reducing ICU length of stay: the effect of Tele-ICU.

On-Line J Nurs Inform. 2014;18(3).

Kohl BA, Fortino-Mullen M, Praestgaard A, Hanson CW,

DiMartino J, Ochroch EA. The effect of ICU telemedicine on

mortality and length of stay. J Telemed Telecare. 2012;18(5):282–

doi: 10.1258/jtt.2012.120208

Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov

PC, Mark RG, et al. PhysioBank, PhysioToolkit, and Physio-

Net. Circulation. 2000;101(23). doi: 10.1161/01.CIR.101.23.


Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi

O. The eICU Collaborative Research Database, a freely

available multi-center database for critical care research. Sci

Data. 2018;5:180178. doi: 10.1038/sdata.2018.178

Berenson RA, Grossman JM, November EA. Does telemonitoring

of patients—The eICU—Improve intensive care? Health

Aff. 2009;28(5):w937–47. doi: 10.1377/hlthaff.28.5.w937

Bauman KA, Hyzy RC. ICU 2020: Five interventions to revolutionize

quality of care in the ICU. J Intensive Care Med.

;29(1):13–21. doi: 10.1177/0885066611434399

The American Telemedicine Association A. Telehealth basics—

ATA [Internet]. Available from: https://www.americantelemed.

org/resource/why-telemedicine/ [cited 7 February 2023].

Lilly CM, Cody S, Zhao H, Landry K, Baker SP, McIlwaine J,

et al. Hospital mortality, length of stay, and preventable complications

among critically ill patients before and after Tele-ICU reengineering

of critical care processes. JAMA. 2011;305(21):2175.

doi: 10.1001/jama.2011.697

Kahn JM, Le TQ, Barnato AE, Hravnak M, Kuza CC, Pike F,

et al. ICU Telemedicine and critical care mortality: a national

effectiveness study. Med Care. 2016;54(3):319–25. doi: 10.1097/


Terblanche M, Adhikari NKJ. The evolution of intensive care

unit performance assessment. J Crit Care. 2006;21(1):19–22. doi:


Zimmerman JE, Kramer AA, McNair DS, Malila FM. Acute

Physiology and Chronic Health Evaluation (APACHE)

IV: Hospital mortality assessment for today’s critically ill

patients*. Crit Care Med. 2006;34(5):1297–310. doi: 10.1097/01.


Collins TA, Robertson MP, Sicoutris CP, Pisa MA, Holena

DN, Reilly PM, et al. Telemedicine coverage for post-operative

ICU patients. J Telemed Telecare. 2017;23(2):360–4. doi:


Lam KW, Lai KY. Evaluation of outcome and performance of

an intensive care unit in Hong Kong by APACHE IV model:

–2014. J Emerg Crit Care Med. 2017;1(8):16. doi: 10.21037/


Afessa B, Keegan MT, Hubmayr RD, Naessens JM, Gajic O,

Long KH, et al. Evaluating the performance of an institution

using an intensive care unit benchmark. Mayo Clin Proc.

;80(2):174–80. doi: 10.4065/80.2.174

Anushiravani A, Masoompour SM. Assessing the performance

of a medical intensive care unit: A 5-year single-center experience.

Indian J Crit Care Med. 2017;21(3):163–6. doi: 10.4103/


Barbash IJ, Le TQ, Pike F, Barnato AE, Angus DC, Kahn JM.

The effect of intensive care unit admission patterns on mortality-

based critical care performance measures. Ann Am Thorac

Soc. 2016;13(6):877–86. doi: 10.1513/AnnalsATS.201509-645OC

Awad A, Bader-El-Den M, McNicholas J. Patient length of stay

and mortality prediction: A survey. Health Serv Manag Res.

;30(2):105–20. doi: 10.1177/0951484817696212

Garland A. Improving the ICU. Chest. 2005;127(6):2151–64.

doi: 10.1378/chest.127.6.2151

Timmers TK, Verhofstad MH, Moons KG, Leenen LP. Intensive

care performance: How should we monitor performance in

the future? World J Crit Care Med. 2014;3(4):74. doi: 10.5492/


Knaus WA, Draper EA, Wagner DP, Zimmerman JE. APACHE

II: a severity of disease classification system. Crit Care Med.

;13(10):818–29. doi: 10.1097/00003246-198510000-00009

Le Gall JR, Lemeshow S, Saulnier F. A new Simplified Acute

Physiology Score (SAPS II) based on a European/North American

multicenter study. JAMA. 1993;270(24):2957–63. doi:


Lemeshow S, Teres D, Pastides H, Avrunin JS, Steingrub

JS. A method for predicting survival and mortality of ICU

patients using objectively derived weights. Crit Care Med.

;13(7):519–25. doi: 10.1097/00003246-198507000-00001

James G, Witten D, Hastie T, Tibshirani R. An introduction to

statistical learning [Internet]. New York, NY: Springer New

York, 2021; 607 p. (Springer Texts in Statistics). Available from:

Hastie T, Tibshirani R, Friedman J. The elements of statistical

learning. data mining, inference, and prediction [Internet].

New York, NY: Springer New York; 2009. (Springer

Series in Statistics). Available from: http://link.springer.


Breiman L. Classification and regression trees [Internet]. Routledge;

eBook. Available from: https://www.taylorfrancis.


Johnson AEW, Mark RG. Real-time mortality prediction

in the Intensive Care Unit. AMIA—Annu Symp Proceed.

;2017:994–1003. Available from: http://www.ncbi.nlm.nih.


Kaur D, Panos RJ, Badawi O, Bapat SS, Wang L, Gupta A.

Evaluation of clinician interaction with alerts to enhance performance

of the tele-critical care medical environment. Int J Med

Inform. 2020;139:104165. doi: 10.1016/j.ijmedinf.2020.104165

Wollenstein-Betech S, Cassandras CG, Paschalidis IC. Personalized

predictive models for symptomatic COVID-19 patients using

basic preconditions: Hospitalizations, mortality, and the need for

an ICU or ventilator. medRxiv. 2020;2020.05.03.20089813. doi:




How to Cite

Palacios, PhD, R., iSánchez-Úbeda, E., Ralph Panos, P., Argaw, P. ., Shahrawat, M., Zhang, D. D., Zhang, A. ., Seiver, A. ., Badawi, O. ., & Gupta, A. . (2023). Predictive Models to Optimize Resources in Tele Critical Care in Distributed Hospital Networks. Telehealth and Medicine Today, 8(1).



Original Clinical Research

Similar Articles

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)