Jinan Fiaidhi, Lakehead University, Department of Computer Science,, Canada
Sabah Mohammed, Lakehead University, Department of Computer Science,, Canada
Sami Mohammed, University of Victoria, Department of Computer Science, Canada
The covid-19 virus is humanity’s newest enemy, with the potential to prematurely end millions of lives. COVID-19 is out of our control right now and we’re going to have to get innovative if we want to catch up with it. To control this new coronavirus, we need to understand it first. To date, the most reliable information on the clinical syndrome resulting from COVID-19 comes from recently published data out of Wuhan, China that was published in the Journal of the American Medical Association (JAMA) on February 7, 2020. The most common symptoms attributed to COVID-19 infection requiring hospitalization were fever, fatigue, and a dry cough. A majority of those cases also had low white blood cell counts and abnormal blood clotting. The patients hospitalized only 26% were sick enough to be treated in an intensive care unit (ICU) – of these, approximately 60% developed respiratory failure and 31% developed septic shock. According to the Global Sepsis Alliance COVID-19 does indeed cause sepsis . Sepsis is “a life-threatening organ dysfunction caused by a dysregulated host response to infection.” As there are no proven therapies effective against the virus itself, it is apparent that the best COVID-19 care includes good sepsis care. Early clinical recognition of sepsis can help in reducing the effects of having sever COVID-19 cases. This paper attempt to address the issue of building a bedside infrastructure where the healthcare worker can use it to select existing workflows or creating new workflows for predicting the outcome of new cases and whether these cases will likely to have a sepsis shock. In our next stage we will address the issue of developing effective predictors for sepsis in its early stages and whether it these cases will likely to develop a sepsis shock. The first stage uses the notion of Node-Red microservices to build a bedside Such Node-Red environment is considered as a new visual tool that caregivers can use machine learning from the bedside.
Microservices, Clinical Workflow Interoperability, SEPSIS, Bedside Visual Tools, Node-Red
[1] Fleischmann, Carolin, André Scherag, Neill KJ Adhikari, Christiane S. Hartog, Thomas Tsaganos, Peter Schlattmann, Derek C. Angus, and Konrad Reinhart. “Assessment of global incidence and mortality of hospital-treated sepsis. Current estimates and limitations.” American journal of respiratory and critical care medicine, vol. 193, no. 3, (2016), pp. 259-272.
[2] Liu, Luchen, Haoxian Wu, Zichang Wang, Zequn Liu, and Ming Zhang. “Early Prediction of Sepsis From Clinical Datavia Heterogeneous Event Aggregation.” arXiv preprint arXiv:1910.06792 (2019).
[3] Nemati, Shamim, Andre Holder, Fereshteh Razmi, Matthew D. Stanley, Gari D. Clifford, and Timothy G. Buchman. “An interpretable machine learning model for accurate prediction of sepsis in the ICU.” Critical care medicine, vol. 46, no. 4, (2018), pp. 547-553.
[4] Giannini, Heather M., Jennifer C. Ginestra, Corey Chivers, Michael Draugelis, Asaf Hanish, William D. Schweickert, Barry D. Fuchs et al. “A Machine Learning Algorithm to Predict Severe Sepsis and Septic Shock: Development, Implementation, and Impact on Clinical Practice.” Critical care medicine, vol. 47, no. 11, (2019), pp. 1485-1492.
[5] Desautels, Thomas, Jana Hoffman, Christopher Barton, Qingqing Mao, Melissa Jay, Jacob Calvert, and Ritankar Das. “Pediatric severe sepsis prediction using machine learning.” bioRxiv, (2017), pp. 223-289.
[6] Ibrahim, Zina M., Honghan Wu, Ahmed Hamoud, Lukas Stappen, Richard JB Dobson, and Andrea Agarossi. “On classifying sepsis heterogeneity in the ICU: insight using machine learning.” Journal of the American Medical Informatics Association, vol. 27, no. 3, (2020), pp. 437-443.
[7] Fleuren, Lucas M., Thomas LT Klausch, Charlotte L. Zwager, Linda J. Schoonmade, Tingjie Guo, Luca F. Roggeveen, Eleonora L. Swart et al. “Machine Learning for the Prediction of Sepsis, a Systematic Review and Meta-Analysis of Diagnostic Test Accuracy.” (2019).
[8] Nemati, Shamim, Andre Holder, Fereshteh Razmi, Matthew D. Stanley, Gari D. Clifford, and Timothy G. Buchman. “An interpretable machine learning model for accurate prediction of sepsis in the ICU.” Critical care medicine, vol. 46, no. 4, (2018), pp. 547-553.
[9] Seneviratne, Martin G., Nigam H. Shah, and Larry Chu. “Bridging the implementation gap of machine learning in healthcare.” BMJ Innovations, vol. 6, no. 2 (2020).
[10] Mohammed, Sabah, Jinan Fiaidhi, and Sami Mohammed. “Pragmatic Interoperability for Extreme Automation and Healthcare Interoperability & Continuity.” IEEE LISS 2020 Conference Preprint, TechRxIv (2020). https://www.techrxiv.org/articles/Pragmatic_Interoperability_for_Extreme_ Automation_and_Healthcare_Interoperability_Continuity/11728956.
[11] Weber, Jens H., and Craig Kuziemsky. “Pragmatic interoperability for ehealth systems: the fallback workflow patterns.” In 2019 IEEE/ACM 1st International Workshop on Software Engineering for Healthcare (SEH), IEEE., (2019), pp. 29-36.
[12] Dunnion, Mary E., and Miriam Griffin. "Care planning in the emergency department." International emergency nursing 18, no. 2 (2010): 67-75.
[13] Liggins, Martin E.; Hall, David L.; Llinas, James (2008). Multisensor Data Fusion, Second Edition: Theory and Practice (Multisensor Data Fusion). CRC. ISBN 978-1-4200-5308-1.
[14] Mark Meloon, What is an example of data fusion? How does it help in big data? Is it data analysis technique?, Sep 19, 2014, Available Online: https://www.quora.com/What-is-an-example-of-data-fusion-How-does-it-help-in-big-data-Is-it-data-analysis-technique
[15] Erik Blasch, One decade of the Data Fusion Information Group (DFIG) model, Proceedings Volume 9499, Next-Generation Analyst III; 94990L (2015) https://doi.org/10.1117/12.2176934
[16] Event: SPIE Sensing Technology + Applications, 2015, Baltimore, Maryland, United States
[17] Brillman, Judith C., Tom Burr, David Forslund, Edward Joyce, Rick Picard, and Edith Umland. "Modeling emergency department visit patterns for infectious disease complaints: results and application to disease surveillance." BMC medical informatics and decision-making 5, no. 1 (2005): 4.
[18] Helland, Pat. "Life beyond Distributed Transactions: an Apostate's Opinion." In CIDR, vol. 2007, pp. 132-141. 2007.
[19] Sun, Long, Yan Li, and Raheel Ahmed Memon. "An open IoT framework based on microservices architecture." China Communications 14, no. 2 (2017): 154-162.
APA:
Fiaidhi, J., Mohammed, S., & Mohammed, S. (2020). Node-Red Microservice Bedside System for Outcome Prediction of Patients with Suspected Sepsis: Useful Study for the Coronavirus Outbreak and Beyond (Stage 1 of the Work). Journal of Community Healthcare and Development (JCHD), ISSN: 2652-6026, NADIA, 1(1), 25-34. doi: 10.33832/jchd.2020.1.1.05.
MLA:
Fiaidhi, Jinan, et al. “Node-Red Microservice Bedside System for Outcome Prediction of Patients with Suspected Sepsis: Useful Study for the Coronavirus Outbreak and Beyond (Stage 1 of the Work).” Journal of Community Healthcare and Development, ISSN: 2652-6025, NADIA, vol. 1, no. 1, 2020, pp. 25-34. JCHD, http://article.nadiapub.com/JCHD/vol1_no1/5.html.
IEEE:
[1] J. Fiaidhi, S. Mohammed, and S. Mohammed, "Node-Red Microservice Bedside System for Outcome Prediction of Patients with Suspected Sepsis: Useful Study for the Coronavirus Outbreak and Beyond (Stage 1 of the Work)." Journal of Community Healthcare and Development (JCHD), ISSN: 2652-6025, NADIA, vol. 1, no. 1, pp. 25-34, Apr 2020.
JCHD aims to facilitate and support research related to community healthcare and development. Our Journal provides a chance for academic and industry professionals to discuss recent progress in the areas of community healthcare and development.
