top of page

AI Case Study

Johns Hopkins Hospital improves patient monitoring and resource allocation in ER and critical care units in real-time using machine learning

Johns Hopkins Hospital monitors admission rates and critical care patients in real-time from a central command centre which uses alerts about trends and patterns to make quick and informed decisions. Bottlenecks are quickly identified to reduce wait time. Resourcing allocation is also done based on this data.

Industry

Healthcare

Healthcare Providers And Services

Project Overview

"Taking advantage of predictive analytics, John Hopkins established a command centre where a constant influx of information keeps staff on alert and able to assess situations and better serve patients with information about influx of patients coming into the hospital, which hospital units need additional staff members, the status of how many patients are being treated, the need for and availability of beds across the hospital, the highest-priority admissions and discharges, and other information essential for ensuring high-quality patient care."

The system constantly monitors patient flow and generates alerts in real-time to take action.

Reported Results

According to the hospital:

* 60% improvement in the ability to accept patients with complex medical conditions transferred from other hospitals
* Critical care team is now dispatched 63 minutes sooner to pick up patients from outside hospitals
* Patients are seen 30% faster and transferred 26% faster once assigned a bed
* Transfer delays from the operating room reduced by 70%
* 21% more patients are now discharged before noon

Technology

Function

Strategy

Data Science

Background

John Hopkins deploys a series of technology innovations to improve operational efficiency.

Benefits

Cost - Reduce wastage,Cost - Process simplification

Data

"the system generates 500 messages per minute and integrates data from “14 different Johns Hopkins IT systems”

bottom of page