COVID-19 Pandemic Highlights Demand for Healthcare Services Outpacing Supply

Strategic Insights -

The COVID-19 pandemic has placed significant strain on healthcare systems worldwide, with demand for services consistently outstripping available supply. According to research by the Johns Hopkins University School of Medicine, emergency departments are facing challenges in distinguishing patients who require hospital resources from those who can be safely discharged to the community. To address this issue, the researchers developed an electronic health record (EHR) embedded clinical decision support (CDS) system that leverages machine learning (ML) to estimate short-term risk for clinical deterioration in patients with or under investigation for COVID-19.

Key Takeaways:

  • The COVID-19 pandemic has led to a significant increase in demand for healthcare services, resulting in a shortage of hospital resources.
  • The researchers developed an EHR embedded CDS system that utilizes ML to estimate short-term risk for clinical deterioration in patients with or under investigation for COVID-19.
  • The ML model was derived from a retrospective cohort of 21,452 ED patients and was prospectively validated in 15,670 ED visits before and after CDS implementation.
  • The model demonstrated excellent performance, with an Area Under the Curve (AUC) ranging from 0.85 to 0.91 for the prediction of critical care needs and 0.80-0.90 for inpatient care needs.
  • The implementation of the CDS system led to a reduction in total mortality among high-risk patients.
  • The researchers highlighted the importance of developing and implementing effective decision support systems to optimize hospital admission decisions during the COVID-19 pandemic.

Statistics:

  • 10.7% of patients required critical care needs within 24 hours.
  • 22.5% of patients required inpatient care needs within 72 hours.
  • The AUC for the ML model ranged from 0.85 to 0.91 for prediction of critical care needs and from 0.80 to 0.90 for inpatient care needs.
  • Total mortality was reduced among high-risk patients after CDS implementation, from 10.2% to 8.5%.

Sources:

  • Multisite implementation of a workflow-integrated machine learning system to optimize COVID-19 hospital admission decisions. npj Digital Medicine, 2022, 5(1): 1-10. (npj Digital Medicine - http://www.nature.com/npjdigitalmed/. The publisher for npj Digital Medicine is Nature Portfolio. A free version of this journal article is available at https://doi-org.sdpl.idm.oclc.org/10.1038/s41746-022-00646-1.)
  • Johns Hopkins University School of Medicine
  • U.S. Department of Health & Human Services | Centers For Disease Control And Prevention
  • U.S. Department of Health & Human Services | Agency For Healthcare Research And Quality