A study to check the accuracy of a machine learning derived model that predicts the risk of a patient developing pulmonary complications ( lung ) after a surgery (Post Operative ) based on the certain characteristics of the patient.
Not Applicable
- Conditions
- Health Condition 1: O- Medical and Surgical
- Registration Number
- CTRI/2024/07/070709
- Lead Sponsor
- Dr. Aumkar Kishore Shah
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Open to Recruitment
- Sex
- Not specified
- Target Recruitment
- 0
Inclusion Criteria
Undergoing major (duration more than 2hours) abdominal surgery
Elective or Emergency
Exclusion Criteria
Pregnancy
Post-partum up to 6 weeks
Moribund patients not expected to survive more than 48 hours
Study & Design
- Study Type
- Observational
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method To externally validate a machine learning model in an independent population for predicting POPC as per Melbourne group scaleTimepoint: 2 years
- Secondary Outcome Measures
Name Time Method To evaluate the calibration of the model in the external validation datasetTimepoint: 2 years;To explore the performance of the model across different subgroups age gender comorbidity status and type of surgery <br/ ><br>Timepoint: 2 years;To validate the model to predict postoperative respiratory failure up to day 7 <br/ ><br>Timepoint: 2 years