Machine Learning Prediction of Multiple Infections in Elderly Surgical Patients

Elderly Surgical Patients Multi-Infection Prediction: Machine Learning Model Development & Validation With SHAP Analysis

Utilizing machine learning techniques, investigators developed the geriatric infection assessment model, leveraging domestic databases to predict multiple postoperative infections in elderly patients. The model addresses the current gap in predictive tools tailored for elderly surgical patients in China, offering insights into both overall and specific infection risks.

Study Overview

• Status: Completed
• Conditions: Postoperative Infection; Geriatrics; Prediction

Detailed Description

Backgrounds:

Postoperative infections are a leading cause of adverse perioperative outcomes, particularly for elderly patients. Given the varied diagnostic presentations of infection, there is a significant gap in the use of predictive tools to identify those at high risk of developing such complications.

Objective:

Investigators aimed at developing machine learning models to predict various postoperative infection risks in elderly patients, facilitating early detection and intervention.

Methods:

A retrospective analysis was conducted on 42,540 elderly patients who underwent non-cardiac surgery at the First Medical Center of the Chinese PLA General Hospital between January 2012 and August 2018, forming the Training set. From this, a 30% subset was randomly designated as the Test set. The models incorporated 51 variables including key infection-related factors. Three machine learning techniques-Logistic Regression (LR), Random Forest (RF), and Gradient Boosting Machines (GBM)-were utilized to develop predictive models for overall and specific postoperative infections, categorized according to the European Perioperative Clinical Outcome (EPCO) definitions. Model performance was gauged by metrics such as the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), accuracy, and precision. To enhance model interpretability, investigators employed the RF model's Variable Importance (VIMP) and Shapley Additive Explanations (SHAP) algorithm. For a demonstrable prediction of specific infection types, data of randomly selected 5 patients were fed into the model with the resulting probabilities depicted in a radar chart.

• Study Type: Observational
• Enrollment (Actual): 42540

Contacts and Locations

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China, 100853
      • Depatment of Anesthesiology, The First Medical Center Affiliation: Chinese PLA General Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

The Training set included 42,540 elderly patients treated at the First Medical Center of the Chinese PLA General Hospital (PLAGH) from January 2012 to August 2018.

Description

Inclusion Criteria:

1. Age ≥ 65 years;
2. Patients undergoing surgeries not involving local anesthesia.

Exclusion Criteria:

1. Patients undergoing neurosurgery or cardiac surgery;
2. Patients with preoperative infections (including pneumonia, SSIs, UTIs, and bloodstream infections).

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Machine Learning Prediction of Multiple Infections in Elderly Surgery Patients	Utilizing machine learning techniques, investigators developed the geriatric infection assessment model, leveraging domestic databases to predict multiple postoperative infections in elderly patients.	January 2012 - August 2018

Collaborators and Investigators

• Sponsor: Weidong Mi
• Investigators: Study Chair: Weidong Mi, Depatment of Anesthesiology, The First Medical Center Affiliation: Chinese PLA General Hospital

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2022
• Primary Completion (Actual): December 30, 2023
• Study Completion (Actual): March 30, 2024

Study Registration Dates

• First Submitted: August 7, 2024
• First Submitted That Met QC Criteria: August 7, 2024
• First Posted (Actual): August 9, 2024

Study Record Updates

• Last Update Posted (Actual): September 24, 2024
• Last Update Submitted That Met QC Criteria: September 21, 2024
• Last Verified: September 1, 2024

More Information

Terms related to this study

• Keywords: machine learning; risk model; postoperative infection; the elderly
• Additional Relevant MeSH Terms: Pathologic Processes; Disease Attributes; Infections; Communicable Diseases
• Other Study ID Numbers: PLAGH-AOC-L03

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No