Using Machine Learning to Predict Acute Kidney Injury Requiring Renal Replacement Therapy After Cardiac Surgery
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Machine Learning
- Sponsor
- Chinese PLA General Hospital
- Enrollment
- 2108
- Locations
- 1
- Primary Endpoint
- patients required renal replacement therapy
- Status
- Completed
- Last Updated
- 4 years ago
Overview
Brief Summary
Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication which may result in adverse impact on short- and long-term mortality. The researcher here developed several prediction models based on machine learning technique to allow early identification of patients who at the high risk of unfavorable kidney outcomes. The retrospective study comprised 2108 consecutive patients who underwent cardiac surgery from January 2017 to December 2020.
Investigators
Yunlong Fan
Clinical Professor
Chinese PLA General Hospital
Eligibility Criteria
Inclusion Criteria
- •age over 18 years who underwent cardiac surgery
Exclusion Criteria
- •data miss greater than 10%
Outcomes
Primary Outcomes
patients required renal replacement therapy
Time Frame: 14 days
The primary outcome was patients with the requirement for acute dialysis within 14 days after cardiac surgery. Renal replacement therapy is recommended for patients with severe acute kidney injury as well as hemodynamic instability or severe electrolyte disturbances (e.g. blood potassium \> 6) or acid-base balance disturbances (e.g. H value less than or equal to 7.15). Prior to the start of renal replacement therapy, the investigator invited a consultation with the nephrology department to assess the condition