H2O.ai > Case Studies > Machine Learning to Save Lives

Machine Learning to Save Lives

Customer Company Size

Large Corporate

Region

America

Country

United States

Product

Advanced Alert Monitoring System

Tech Stack

Machine Learning
Data Analytics
H2O

Implementation Scale

Enterprise-wide Deployment

Impact Metrics

Customer Satisfaction
Productivity Improvements

Technology Category

Analytics & Modeling - Machine Learning
Analytics & Modeling - Predictive Analytics

Applicable Industries

Healthcare & Hospitals

Applicable Functions

Quality Assurance

Use Cases

Predictive Maintenance
Remote Patient Monitoring

Services

Data Science Services

About The Customer

Kaiser Permanente is an integrated healthcare system, where patients receive a variety of services and treatments under one roof. With 10 million members, Kaiser Permanente has vast amounts of data, and is using innovative approaches to make this data work for the benefit of its patients and clinicians. Kaiser has always been on the forefront of using technology – as early as 1970s, the company began keeping electronic medical records. Today, Kaiser members have a variety of methods available to them to interact with their doctors and nurses – using the web, e-mail and mobile apps to get the answers they need faster. All this data is captured and can be used to solve specific problems.

The Challenge

Kaiser Permanente, an integrated healthcare system, was facing a challenge with patients who undergo an unplanned transfer to the Intensive Care Unit (ICU). These patients experienced significantly worse outcomes than those directly admitted to the ICU. They represented about a fourth of all Kaiser ICU admissions, a fifth of all deaths in the hospital, and about an eighth of all of the hospital days. The patients who experienced an unplanned transfer to the ICU experienced two to five times the mortality of patients who are directly admitted to the ICU, and they would stay in the hospital an average of 8 to 12 days more than patients who are directly admitted to the ICU. The challenge was to identify these patients ahead of time who are likely to crash and be rushed to the ICU, and intervene before the deterioration.

The Solution

Kaiser decided to use available data about a patient and build a mechanism that could identify when deterioration might occur. They developed the Advanced Alert Monitoring (AAM) System, which helps identify patients who are likely to crash, and they recognize them 12 hours before they experience the deterioration. The AAM has four components: risk analysis and the creation of the score, monitoring and warning, dissemination and communication of the scope, and finally – the intervention. They used bed history data, chemistry, vital signs, comorbidities, and demographic information to estimate either the probability of a late transferring to the ICU that is a sudden crash or mortality in the hospital. Once the data is collected and cleaned, the team worked on feature engineering and then applied a variety of training and testing datasets. The team explored each parameter and its linkage, got the clinicians involved to look at every case, and then performed a characteristics review and threshold analysis to make sure that a threshold made sense.

Operational Impact

Clinicians receive an alert if a threshold is exceeded to evaluate the patient and determine further course of action
Intervention prior to deterioration creates better outcomes for the patient
The results are currently available every six hours, but AAM can be configured to calculate the likelihood of critical deterioration on an hourly basis

Quantitative Benefit

Patients who experience an unplanned transfer to the ICU experience two to five times the mortality of patients who are directly admitted to the ICU
Patients who experience an unplanned transfer to the ICU would stay in the hospital an average of 8 to 12 days more than patients who are directly admitted to the ICU