Derivation and Validation of Hemodynamic Phenotypes of Cardiac Surgery

NCT07085208 | Completed

• 1 other identifier: KY20250224-KS-04
• Study Type: observational
• Target: 10,847
• Locations: 0 countries
• Sites: N/A

Brief Summary

Background \& Objective: Cardiac surgery patients differ significantly in their health conditions and how they react during operations. Standard risk assessments before surgery often miss the real-time changes happening inside a patient's body during the procedure, which can affect their recovery. Therefore, researchers conducted this study to find different groups (phenotypes) of patients who face varying risks for poor outcomes. They did this by using advanced computer learning techniques to analyze a lot of detailed health information collected both before and during surgery. Methods: This was a study that looked back at patient records from several hospitals. Researchers gathered a large amount of patient information from before surgery, including their basic health details and lab results. They also collected very detailed measurements of patients' vital signs taken during surgery, noting how these changed over time. Then, a computer program that can find patterns without being told what to look for (unsupervised hierarchical clustering) was used to sort patients into distinct groups based on this combined data. Clinical Relevance: This study expects to show that using data to identify patient groups can reveal differences that traditional methods miss. These new patient groups, which are based on how their blood flow and vital signs behave, offer a new way to understand risks in real-time. This could help doctors to predict problems more accurately and create personalized care plans for each patient around the time of surgery, which has great potential for practical use in hospitals.

Conditions

Phenotyping; Machine Learning; Cardiac Surgery; Hemodynamic Parameters

Outcome Measures

Primary Outcomes (1)

• Acute organ dysfunction

  including postoparative acute liver failure and acute kidney injury (up to 7 days postoperative), and acute kidney disease(up to 90 days postoperative)

  Within 7 days post-surgery for acute liver failure and acute kidney inkury, and 90 days for postoperative acute kidney disease

Secondary Outcomes (2)

• Total LOS and ICU-LOS

  up to 90 days post-surgery

• In-hospital mortality

  up to 90 days postoperative, from the end of surgery until patient discharge

Interventions

Unsupervised Machine Learning for Clinical Phenotyping PROCEDURE

This is a data-driven study that uses an unsupervised machine learning algorithm to perform clustering on patient multimodal features. These features include: preoperative demographics, comorbidities, and laboratory data; surgical information; and high-resolution intraoperative data, most notably continuous vital sign trajectories.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

All patients aged 18 years or older who underwent cardiac surgery with CPB were identified from each database.

You may qualify if:

• Patients aged 18 years or older
• Patients who underwent cardiac surgery with cardiopulmonary bypass

You may not qualify if:

• Incomplete information on surgical procedures,
• With History of prior cardiac surgery or underwent second surgery during the same hospitalization
• Insufficient valid perioperative vital sign monitoring data

Sponsors & Collaborators

• Nanjing First Hospital, Nanjing Medical University: lead

MeSH Terms

Interventions

Unsupervised Machine Learning

Intervention Hierarchy (Ancestors)

Machine Learning; Artificial Intelligence; Algorithms; Mathematical Concepts

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 15, 2025
• First Posted: July 25, 2025
• Study Start: April 1, 2016
• Primary Completion: August 31, 2024
• Study Completion: December 31, 2024
• Last Updated: July 25, 2025

Record last verified: 2025-02