Identification of Patients Admitted With COPD Exacerbations and Predicting Readmission Risk Using Machine Learning

NCT04192175 | Completed

• 1 other identifier: 19-5124
• Study Type: observational
• Target: 65,000
• Locations: 1 country
• Sites: 1

Brief Summary

Patients with Chronic Obstructive Pulmonary Disease (COPD) who are admitted to hospital are at high risk of readmission. While therapies have improved and there are evidence-based guidelines to reduce readmissions, there are significant challenges to implementation including 1) identifying all patients with COPD early in admission to ensure evidence-based, high value care is provided and 2) identifying those who are at high risk of readmission in order to effectively target resources. Using machine learning and natural language processing, we want to develop models to 1) identify all patients with COPD exacerbations admitted to hospital and 2) stratify them to distinguish those who are at high risk of readmission b) How will you undertake your work? From Toronto hospitals, we will develop a very large dataset of patient admissions for all medical conditions including exacerbations of COPD from the electronic health record. This data will include both structured data such as age, gender, medications, laboratory values, co-morbidities as well as unstructured data such as discharge summaries and physician notes. Using the dataset, we will train a model through natural language processing and machine learning to be able to identify people admitted with COPD exacerbation and identify those patients who will be at high risk of readmission within 30 days. We will test the ability of these models to determine our predictive accuracies. We will then test these models at other institutions.

Conditions

Copd Exacerbation Acute; Readmission; Machine Learning; Natural Language Processing

Outcome Measures

Primary Outcomes (2)

• Identification of COPD exacerbation

  To identify COPD exacerbations, we will use the most responsible diagnosis code for that visit.

  Within admission

• Readmission risk

  To identify readmissions, we will include all cause readmissions within 30 days after an index admission for a COPD exacerbation, similar to previous studies.(3)

  30 days

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Using retrospective data from the University Health Network (UHN), we will create a data set of admissions to General Internal Medicine for the past 7 years.

You may qualify if:

• All admissions to General Internal Medicine between 2012-2018

Sponsors & Collaborators

• University Health Network, Toronto: lead
• Canadian Lung Association: collaborator
• Canadian Institutes of Health Research (CIHR): collaborator

Study Sites (1)

University Health Network

Toronto, Ontario, M5G 2C4, Canada

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: December 6, 2019
• First Posted: December 10, 2019
• Study Start: June 1, 2019
• Primary Completion: August 31, 2021
• Study Completion: December 31, 2023
• Last Updated: January 27, 2025

Record last verified: 2025-01

Locations

CA (1)