Kaiser

Spark NLP in Action: Improving Patient Flow Forecasting at Kaiser Permanente

Read the full case study

INDUSTRY: Healthcare

Introduction: “Kaiser Permanente is one of the USA’s largest health plans, serving 12.3 million members via 39 hospitals and over 217,000 employees.”

Challenge: “Hospitals like Kaiser Permanente face numerous challenges that are straining their existing bed and service
capacity and driving the need for improved patient flow management. The challenges include: • increased demand for services, clinical staff shortages, lack of tools and technology to adequately measure and manage patient flow, the risk of patient deterioration due to prolonged hospital stays and sometimes fewer available beds.
With the continued aging of the U.S. population and accelerated clinical technology advances, demand for inpatient bed capacity is projected to rise by nearly 4-5% per year”

Solution: “The company leveraged John Snow Labs’ AI Platform (for model training, deployment, and monitoring) and Spark NLP (for extracting key features from EMR notes) to optimize hospital patient flow models.”

Benefit (subtitle): “John Snow Labs enabled real-time decision-making and strategic planning, by predicting:

  • Bed demand
  • Safe staffing levels
  • Hospital gridlock”
80xfaster training on 2.6MB
1.6xfaster prediction on 75MB

“Kaiser Permanente uses Spark NLP to integrate domain-specific NLP as part of a scalable, performant, measurable, and reproducible ML pipeline and improve the accuracy of forecasting the demand for hospital beds.”

Executive Director, Analytics Foundation at Kaiser Permanente