How UMass Memorial Health Reduced LWBS Rates From 20% to 6% Using Nurse-First AI

Hospital achieved a 70% reduction in patients leaving without being seen, while stabilizing nurse turnover.

Download Case Study
UMass Memorial Health Case Study
Ken Shanahan

We knew we had to do something different. We were seeing high left without being seen rates, long wait times in the waiting room, and concerns about triage accuracy.

Ken Shanahan
Senior Director of Emergency Medicine, UMass Memorial Health

UMass Memorial Health At A Glance

138,200
Annual ED Visits
781
Licensed Beds
Epic
EHR System
Level 1
Academic Medical Center & Trauma Center
The Challenge

A Compounding Cycle of Patient Leakage and Staff Instability

UMass Memorial Health wanted to improve patient access and operational strain across two campuses (University and Memorial) by addressing their increased Left Without Being Seen (LWBS) rate of 20%. The root cause was a compounding cycle of long wait times and critical staffing instability, with nurse turnover rates peaking between 20–25%. This volatility created triage bottlenecks that forced patients to leave before receiving care, creating operational and financial challenges for the medical center.

20%
LWBS Rate
Before Implementation
20–25%
Nurse Turnover Rate
Peak Levels
Triage
Bottlenecks Forcing
Patients to Leave
The Solution

KATE AI: Real-Time Clinical Insights to Stop Patient Leakage

To stabilize operations and stop patient leakage, leadership implemented KATE AI to support the frontline workforce with real-time, objective clinical insights. KATE identifies anomalies at ED triage to ensure critically ill patients are prioritized correctly, acting as a “second set of eyes” for the nursing team. This capability allowed the ED to streamline triage decision-making, reducing the cognitive load on staff and ensure that resources were allocated efficiently to reduce wait times without additional headcount

  • Real-time anomaly identification at triage
  • Objective clinical prioritization of critical patients
  • Reduced cognitive load on nursing staff
  • Efficient resource allocation without added headcount
  • Streamlined triage decision-making

Measurable Results

Significant improvements across patient retention, workforce stability, and operational efficiency.

Reduction in LWBS Rate
70%
LWBS rate dropped from 20% to 6%, recapturing significant patient volume
Nurse Turnover Reduction
92%
Nurse turnover decreased from 20–25% to less than 2%
Implementation Date
Feb 2023
KATE AI deployed across University and Memorial campuses

A Stabilized Workforce and Recovered Patient Volume

After implementing KATE AI in February 2023, and in addition to making other targeted interventions in the ED, the medical center successfully drove its LWBS rate down from 20% to 6%, achieving a 70% reduction in patients leaving without care.

Operationally, this intervention not only recaptured volume but also helped to stabilize the workforce. By empowering nurses with real-time AI support, the facility saw nurse turnover decrease from 20–25% to less than 2%.

We knew we had to do something different. We were seeing high left without being seen rates, long wait times in the waiting room, and concerns about triage accuracy.

Ken Shanahan
Senior Director of Emergency Medicine, UMass Memorial Health

More Customer Stories

UMass Memorial Health

AI Assistant Online

Select your role (optional)

This helps us provide more relevant information

Ask anything about Mednition's KATE platform, clinical validation, safety controls, or EMR integration. Questions about KATE? Get product, clinical, and integration answers, or request a demo.

Want to speak with a Mednition expert? Just say the word.

This assistant provides product and clinical information. It does not provide medical advice.

AI Assistant Online

How can I help you today?

AI can make mistakes. Check important info.

l,..