Skip to main content
McMaster University
DeGroote School of Business
McMaster University
Search

DSB Main Website Search

McMaster Menu
DeGroote Menu
  • Home
  • Programs
  • About
    • About DeGroote
    • Our Leadership
    • Dean’s Corner
    • McLean Centre for Collaborative Discovery
    • Our Faculty & Research  
    • Strategic Plan 
    • Annual Report 
  • Events
  • Students
    • Student Resources
    • Student Clubs
    • Submit a Student Bulletin
    • Submit your Event
  • Alumni
    • Alumni Resources
    • Wayne C. Fox Distinguished Alumni Award 
    • DeGroote Alumni Social Impact Award
  • Staff
  • Give
  • Contact
    • Contact Us
    • DeGroote Directory
Search McMaster Menu
  • Home
  • Programs
  • About
    About DeGrooteOur LeadershipDean’s CornerMcLean Centre for Collaborative DiscoveryOur Faculty & Research  Strategic Plan Annual Report 
  • Events
  • Students
    Student ResourcesStudent ClubsSubmit a Student BulletinSubmit your Event
  • Alumni
    Alumni ResourcesWayne C. Fox Distinguished Alumni Award DeGroote Alumni Social Impact Award
  • Staff
  • Give
  • Contact
    Contact UsDeGroote Directory

HEALTH POLICY AND MANAGEMENT   RESEARCH  

Researchers Create AI Algorithm to Improve Timeliness, Accuracy of Sepsis Predictions

November 25, 2021 ·

Contributed by: The Research Institute of St. Joe's Hamilton

Share

Twitter Facebook LinkedIn Mail Copy Link
Manaf Zargoush and Dan Perri, both in jackets and glasses, smiling next to one another.

Each year, sepsis affects more than 30 million people worldwide, causing an estimated six million deaths. Sepsis is the body’s extreme response to an infection and is often life-threatening.

Since every hour of delayed treatment can increase the odds of death by four to eight per cent, timely and accurate predictions of sepsis are crucial to reduce morbidity and mortality. To that end, various health care organizations have deployed predictive analytics to help identify patients with sepsis by using electronic medical record (EMR) data.

An international research team, including data scientists, physicians, and engineers from McMaster University and St. Joseph’s Healthcare Hamilton, have created an Artificial Intelligence (AI) predictive algorithm that greatly improves the timeliness and accuracy of data-driven sepsis predictions.

“Sepsis can be predicted very accurately and very early using AI with clinical data, but the key questions to the clinician and data scientists are how much historical data these algorithms need to make accurate predictions and how far ahead they can predict sepsis accurately,” said Manaf Zargoush, study co-author and assistant professor of health policy and management at McMaster’s DeGroote School of Business.

To predict sepsis in clinical care settings, some systems use EMR data with disease scoring tools to determine sepsis risk scores – essentially acting as digital, automated assessment tools. More advanced systems employ predictive analytics, such as AI algorithms, to go beyond risk assessment and identify sepsis itself.

Using AI predictive analytics, researchers created an algorithm called the Bidirectional Long Short-Term Memory (BiLSTM). It examines several variables across four key domains: administrative variables (e.g., length of the Intensive Care Unit (ICU) stay, hours between hospital and ICU admission, etc.), vital signs (e.g., heart rate and pulse oximetry, etc.), demographics (e.g., age and gender), and laboratory tests (e.g., serum glucose, creatinine, platelet count, etc.). Compared to other algorithms, the BiLSTM is a more complex subset of machine learning – called deep learning – that uses neural networks to increase its predictive power.

The study compared the BiLSTM with six other machine learning algorithms and found it was superior to the others in terms of accuracy. Improving accuracy by reducing false positives is key to a successful algorithm, since these errors not only waste medical resources, but they also erode physicians’ confidence in the algorithm.

Interestingly, the study found that predictive accuracy may be increased through algorithms that focus more heavily on a patient’s recent datapoints, instead of looking back further to include as many datapoints as possible.

Researchers noted that it is understandable that clinicians would be inclined to populate the algorithm with as many data points as possible over a long timeframe. However, their findings suggest that when the purpose of prediction is being accurate and timely regarding sepsis predictions, physicians with long prediction horizons should rely more on the fewer yet more recent clinical data of the patient.

“St. Joe’s will be launching a cognitive computing pilot project in late November that includes understanding how AI can be used to help predict sepsis in real patients and in real time,” said Dan Perri, study co-author, physician, and chief information officer at St. Joseph’s Healthcare Hamilton. He is also an associate professor of medicine at McMaster.

“Understanding the breadth and scope of data that enables sepsis prediction is important for any organization looking at using AI to save lives from severe infections,” Perri added.

“Learnings from sepsis models translate into building better machine learning tools that lead to appropriate early intervention for some of the sickest patients, while also avoiding unnecessary warnings that could lead to health care worker fatigue.”

The study was published in the journal Nature Scientific Reports.

Tags:   AI ARTIFICIAL INTELLIGENCE MANAF ZARGOUSH RESEARCH

Related Stories

Empowering professionals to lead with confidence into tomorrow’s AI-driven world
September 23, 2025 · STRATEGIC PLAN | TEACHING AND LEARNING

Empowering professionals to lead with confidence into tomorrow’s AI-driven world

DeGroote welcomes faculty driving innovation across business disciplines 
September 12, 2025 · RESEARCH · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP · HUMAN RESOURCES AND MANAGEMENT · STRATEGIC MANAGEMENT · MARKETING

DeGroote welcomes faculty driving innovation across business disciplines 

From research to impact: DeGroote undergraduate student research day  
August 20, 2025 · RESEARCH · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP · STUDENT

From research to impact: DeGroote undergraduate student research day  

DeGroote School of Business launches innovative AI driven graduate programs
July 28, 2025 · STRATEGIC PLAN | TEACHING AND LEARNING

DeGroote School of Business launches innovative AI driven graduate programs

Breaking financial barriers: New learning hub explores solutions to address financial exclusion
July 25, 2025 · MCCD · SOCIETAL IMPACT · STRATEGIC PLAN | ENGAGING COMMUNITIES

Breaking financial barriers: New learning hub explores solutions to address financial exclusion

Confronting the inherent bias of artificial intelligence
May 1, 2025 · INFORMATION SYSTEMS · SOCIETAL IMPACT · RESEARCH · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP · STRATEGIC PLAN | INCLUSIVE EXCELLENCE

Confronting the inherent bias of artificial intelligence

Customer connections powered by artificial intelligence
February 5, 2025 · MARKETING

Customer connections powered by artificial intelligence

In the news: Government officers told to skip fraud prevention steps when vetting temporary foreign worker applications, Star investigation finds
September 3, 2024 · RESEARCH · HUMAN RESOURCES AND MANAGEMENT · STAFF

In the news: Government officers told to skip fraud prevention steps when vetting temporary foreign worker applications, Star investigation finds

In the news: The Musk problem: Why are businesses leaving X?
September 3, 2024 · RESEARCH · STRATEGIC MANAGEMENT · STAFF

In the news: The Musk problem: Why are businesses leaving X?

Bridging the digital divide
August 9, 2024 · INFORMATION SYSTEMS · RESEARCH · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP

Bridging the digital divide

2023 Annual Report: Impacting our Communities Through Connection
August 9, 2024 · RESEARCH · STRATEGIC PLAN | ENGAGING COMMUNITIES · STUDENT

2023 Annual Report: Impacting our Communities Through Connection

Hidden Gatekeepers: How Hiring Bias Affects Workers in the Food Service Industry
July 31, 2024 · RESEARCH · STAFF · HUMAN RESOURCES AND MANAGEMENT

Hidden Gatekeepers: How Hiring Bias Affects Workers in the Food Service Industry

Four Professors Named 2024 University Scholars
July 23, 2024 · STAFF · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP · RESEARCH · HUMAN RESOURCES AND MANAGEMENT

Four Professors Named 2024 University Scholars

Standing out to fit in: How new Employees can set Themselves up for Success at a new Workplace
July 10, 2024 · HUMAN RESOURCES AND MANAGEMENT · RESEARCH · STAFF

Standing out to fit in: How new Employees can set Themselves up for Success at a new Workplace

MIRA Funds two new Major Programs of Research in Aging, Addressing Frailty and the Digital Divide
June 24, 2024 · STRATEGIC PLAN | RESEARCH AND SCHOLARSHIP · RESEARCH · INFORMATION SYSTEMS · STAFF · SOCIETAL IMPACT

MIRA Funds two new Major Programs of Research in Aging, Addressing Frailty and the Digital Divide

DeGroote School of Business DeGroote School of Business Logo
DeGroote Instagram logo DeGroote Linkedin logo DeGroote Facebook logo DeGroote YouTube Logo DeGroote TikTok Logo
DeGroote Menu

  • Programs
  • About DeGroote
  • Events
  • Student Resources
  • Staff Resources
  • Alumni Resources
  • Give
  • DeGroote Directory
  • Contact Us
  • Faculty & Research  
Hamilton Campus

DeGroote School of Business
McMaster University

1280 Main Street West

Hamilton, Ontario
L8S 4M4
Burlington Campus

DeGroote School of Business
Ron Joyce Centre

4350 South Service Road

Burlington, Ontario
L7L 5R8
AACSB Logo

McMaster University is committed to providing websites that are accessible to the widest possible audience.  

If you require any content on this website in an alternate format, please contact dsbweb@mcmaster.ca and we will respond promptly.

DeGroote Online Privacy Policy

McMaster Brighter World Logo McMaster University - Brighter World Logo
Contact McMaster McMaster Terms & Conditions McMaster Privacy Policy
Secret Link