Artificial Intelligence for Sepsis Prediction in ICU

• Conditions: Artificial Intelligence; Septic Shock; Intensive Care Unit Psychosis
• Interventions: Diagnostic Test: Artificial intelligence sepsis prediction model

• Registration Number: NCT04913181
• Lead Sponsor: Second Affiliated Hospital, School of Medicine, Zhejiang University

Brief Summary

The development of sepsis prediction model in line with Chinese population, and extended to clinical, assist clinicians for early identification, early intervention, has a good application prospect. This study is a prospective observational study, mainly to evaluate the accuracy of the previously established sepsis prediction model. The occurrence of sepsis was determined by doctors' daily clinical judgment, and the results of the sepsis prediction model were matched and corrected to improve the clinical accuracy and applicability of the sepsis prediction model.

Detailed Description

The sepsis prediction model adopted in this study has been completed in the preliminary preparation, which was constructed on 7,000 patients since the establishment of comprehensive ICU, and the sepsis 3.0 diagnostic standard was adopted.The sepsis prediction model was built using Python platform and XGBoost algorithm, which was used to predict the incidence of sepsis in ICU patients within 24 hours. The overall accuracy was 82%, and the area under the Auroc curve was 0.854.

Patients who met the inclusion and exclusion criteria were given a daily prediction of sepsis model, and a quantitative checklist was formed based on the test results.There are two kinds of forecast outcomes: low risk and high risk.Quantitative checklists are available to attending physicians to improve diagnostic efficiency.The results were kept confidential to the clinician.

All patients were diagnosed with sepsis by two senior attending physicians at a fixed time. The diagnosis consisted of two types: yes and no.If two attending physicians have different opinions, the third attending physician will be included for correction diagnosis, and the presence of sepsis will be determined in a 2:1 manner.The attending physicians are independent of each other.

When the diagnosis results of the attending physician are input into the system, the prediction results of yesterday's sepsis prediction model are compared and calculated to determine the accuracy of the prediction model

Study Timeline

• Status Verified: 2021-05
• Study First Submitted: 2021-05-31
• Study Start: 2021-06-01
• Study First Submitted QC: 2021-06-02
• Last Update Submitted: 2021-06-02
• Study First Posted: 2021-06-04
• Last Update Posted: 2021-06-04
• Primary Completion: 2022-06-01
• Study Completion: 2023-06-01

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 2000

Inclusion Criteria

All patients with acute critical illness who are eligible for admission to ICU during the study period

Exclusion Criteria

1. Patients under the age of 16;
2. Pregnant and parturient women;
3. Patients who planned to be admitted to the department for surgery and transferred the next day after evaluation;
4. Patients admitted to the department and diagnosed with sepsis;
5. Patients with ICU stay less than 24 hours;

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Daily clinical judgment of doctors	Artificial intelligence sepsis prediction model	This group of people was used for the clinician's decision without sepsis prediction model.
Sepsis prediction model	Artificial intelligence sepsis prediction model	This group of people was used for the clinician's decision, and the sepsis prediction model was used simultaneously for the prediction, but the model was not involved in the decision, and was only used for verification

Primary Outcome Measures

Name	Time	Method
Accuracy of model diagnosis	2 years	Evaluation of the accuracy of prediction model in clinical application