Machine Learning Predictive Models for Sepsis Risk in ICU Patients With Intracerebral Hemorrhage

Development and Validation of Predictive Models for Sepsis Risk in Patients With Intracerebral Hemorrhage in Intensive Care Units Based on Machine Learning: A Retrospective Cohort Study

Patients with intracerebral hemorrhage (ICH) in the intensive care unit (ICU) are at heightened risk of developing sepsis, significantly increasing mortality and healthcare burden. Currently, there is a lack of effective tools for the early prediction of sepsis in ICH patients within the ICU. This study aims to develop a reliable predictive model using machine learning techniques to assist clinicians in the early identification of patients at high risk and to facilitate timely intervention.

The Medical Information Mart for Intensive Care (MIMIC) IV database (version 2.2) is an international online repository for critical care expertise. This database contains patient-related information collected from the ICUs of Beth Israel Deaconess Medical Center between 2008 and 2019. It includes a vast dataset of 299,712 hospital admissions and 73,181 intensive care unit patients.

The eICU Collaborative Research Database (eICU-CRD) comprises data from over 200,000 ICU admissions for 139,367 unique patients across 208 US hospitals between 2014 and 2015, providing a valuable resource for critical care research.

This study aims to establish and validate multiple machine learning models to predict the onset of sepsis in ICU patients with ICH and to identify the model with the optimal predictive performance.

Study Overview

• Status: Not yet recruiting
• Conditions: Sepsis; Intracerebral Hemorrhage
• Intervention / Treatment: Other: no intervention

Detailed Description

• Data Collection: This study utilized two public databases. The model leveraged clinical data obtained from the Medical Information Mart for Intensive Care (MIMIC) IV database (version 2.2) and selected corresponding patients for external validation from the eICU Collaborative Research Database (eICU-CRD). Data on ICH patients were extracted from the MIMIC IV public database, including baseline characteristics, clinical parameters, therapeutic interventions, and outcomes. The data were randomly divided into two groups, with 70% serving as the training set and 30% as the validation set.
• Model Development: Feature selection was performed using Lasso regression to construct various machine learning models (such as Random Forest, Logistic Regression, and Neural Networks).
• Model Validation: In addition to the internal validation set, external validation was also conducted on the eICU database to test the model's generalizability.
• Statistical Analysis: The predictive performance of the model was evaluated using metrics including the area under the ROC curve (AUC), sensitivity, and specificity.
• Clinical Applicability Assessment: The clinical utility of the model was assessed using Decision Curve Analysis (DCA).

• Study Type: Observational
• Enrollment (Estimated): 1800

Contacts and Locations

• Study Contact: Name: Le Zhang, Doctor; Phone Number: 13973187150; Email: zlzdzlzd@csu.edu.cn
• Study Contact Backup: Name: Ye Li, Doctor; Phone Number: 19967131289; Email: 17670516318@163.com

Study Locations

• China
  • Hunan
    • Changsha, Hunan, China, 410008
      • Le Zhang
      • Contact: Le Zhang; Phone Number: 13973187150; Email: zlzdzlzd@csu.edu.cn
      • Contact: Ye Li; Phone Number: 19967131289; Email: 17670516318@163.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

All diagnoses in the MIMIC-IV and the eICU-CRD databases were identified based on the International Classification of Diseases, Ninth Revision (ICD-9), and ICD-10 codes. For the analysis, patients diagnosed with ICH were included. Sepsis was defined according to the Third International Consensus Definition of Sepsis and Septic Shock (Sepsis-3), which considers patients with suspected infection and a Sequential Organ Failure Assessment (SOFA) score ≥2 as septic.

Description

Inclusion Criteria:

• 1. Diagnosed with primary intracerebral hemorrhage by ICD-9/10 coding.
• 2. Aged 19-89 years old.

Exclusion Criteria:

• 1. Patients admitted to the hospital but not to the ICU.
• 2. Patients with missing follow-up data or incomplete variables.
• 3. Patients with a hospital stay exceeding one month.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
intracerebral hemorrhage	Other: no intervention; no intervention

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Occurrence of sepsis	Occurrence of sepsis	within 30 days of admission

Collaborators and Investigators

• Sponsor: Xiangya Hospital of Central South University

Study record dates

Study Major Dates

• Study Start (Estimated): March 30, 2024
• Primary Completion (Estimated): May 1, 2024
• Study Completion (Estimated): May 30, 2024

Study Registration Dates

• First Submitted: March 16, 2024
• First Submitted That Met QC Criteria: March 16, 2024
• First Posted (Actual): March 22, 2024

Study Record Updates

• Last Update Posted (Actual): March 25, 2024
• Last Update Submitted That Met QC Criteria: March 21, 2024
• Last Verified: March 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Cardiovascular Diseases; Vascular Diseases; Cerebrovascular Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Infections; Systemic Inflammatory Response Syndrome; Inflammation; Intracranial Hemorrhages; Sepsis; Toxemia; Hemorrhage; Cerebral Hemorrhage
• Other Study ID Numbers: 53244021

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: In the paper

Drug and device information, study documents

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