Healthcare Operations and Black Swan Event for COVID-19 Pandemic: A Predictive Analytics

Jinil Persis Devarajan, Arunmozhi Manimuthu, V Raja Sreedharan

Research output: Contribution to journalArticlepeer-review


COVID-19 pandemic has questioned the way healthcare operations take place globally as the healthcare professionals face an unprecedented task of controlling and treating the COVID-19 infected patients with a highly straining and draining facility due to the erratic admissions of infected patients. However, COVID-19 is considered as a white swan event. Yet, the impact of the COVID-19 pandemic on healthcare operations is highly uncertain and disruptive making it as a black swan event. Therefore, the study explores the impact of the COVID-19 outbreak on healthcare operations and develops machine learning-based forecasting models using time series data to foresee the progression of COVID-19 and further using predictive analytics to better manage healthcare operations. The prediction error of the proposed model is found to be 0.039 for new cases and 0.006 for active COVID-19 cases with respect to mean absolute percentage error. The proposed simulated model further could generate predictive analytics and yielded future recovery rate, resource management ratios, and average cycle time of a patient tested COVID-19 positive. Further, the study will help healthcare professionals to devise better resilience and decision-making for managing uncertainty and disruption in healthcare operations.
Original languageEnglish
Article number9445568
Pages (from-to)3229-3243
Number of pages15
JournalIEEE Transactions on Engineering Management
Issue number9
Early online date2 Jun 2021
Publication statusPublished - 1 Sept 2023


  • COVID-19 (novel corona)
  • data analytics
  • deep learning
  • extreme learning machine (ELM)
  • long short-term memory (LSTM)
  • multilayer perceptron
  • prediction
  • time series


Dive into the research topics of 'Healthcare Operations and Black Swan Event for COVID-19 Pandemic: A Predictive Analytics'. Together they form a unique fingerprint.

Cite this