Artificial Intelligence Prognostic Model for Sepsis Based on Time Series Analysis

NCT06724120 | Completed

• 1 other identifier: No.126 in 2024
• Study Type: observational
• Target: 3,641
• Locations: 1 country
• Sites: 1

Brief Summary

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. It is one of the leading causes of death and disability worldwide, with an inpatient mortality rate of 10-20%. Sepsis is a severe complication in critically ill patients and can lead to septic shock and multiple organ dysfunction syndrome (MODS), usually triggered by severe trauma, surgery, and infections. Despite the availability of advanced diagnostic, therapeutic, and monitoring technologies, the incidence and mortality of sepsis remain high, posing a significant global challenge to the medical community. Over 49 million people worldwide develop sepsis annually, with approximately 11 million deaths, resulting in a mortality rate of about 15%-25%. This study aims to develop a prognosis prediction model for sepsis patients using a neural network architecture (Transformer algorithm), based on time-series data. The primary outcome observed is the mortality outcome of sepsis patients. The goal of the research is to enhance the early identification of high-risk sepsis patients, thereby optimizing the timing of sepsis treatment and intervention and improving the accuracy of prognosis prediction for sepsis patients.

Conditions

Sepsis; Prognostic Model; Artificial Intelligence; Individuality

Outcome Measures

Primary Outcomes (1)

• Biomarker level

  Including inflammatory markers (such as C-reactive protein (CRP), interleukins (IL-6, IL-10), and procalcitonin (PCT)) and metabolic markers (such as lactate levels and arterial blood gas pH values) for sepsis prognostic analysis.

  5 Years

Secondary Outcomes (3)

• SOFA score

  5 Years

• Length of ICU stay

  5 Years

• APACHE II score

  5 Years

Study Arms (2)

Survival Group

Other: No interventions

Non-survival Group

Other: No interventions

Interventions

No interventions OTHER

No interventions

Non-survival Group; Survival Group

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Retrospective analysis of clinical data of patients diagnosed with sepsis at West China Hospital of Sichuan University from January 2020 to December 2023. Review and summarize the baseline data of patients (including age, gender, comorbidities, history of malignant tumors, lesion location, pathological type, etc.), occurrence of serious complications, total length of hospital stay, survival time, and construct a time-series based mortality risk prognosis prediction model for sepsis patients.

You may qualify if:

• Patients clinically diagnosed with sepsis at West China Hospital of Sichuan University from January 2020 to December 2023

You may not qualify if:

• Under the age of 18;
• Gender unknown;
• Incorrect or invalid discharge diagnosis;
• The hospitalization time is less than 24 hours;
• Data information is missing by more than 30%.

Sponsors & Collaborators

• West China Hospital: lead

Study Sites (1)

Chi Zhang

Chengdu, Sichuan, 610041, China

Location

MeSH Terms

Conditions

Sepsis

Condition Hierarchy (Ancestors)

Infections; Systemic Inflammatory Response Syndrome; Inflammation; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Dr. Chi Zhang

Study Record Dates

• First Submitted: November 30, 2024
• First Posted: December 9, 2024
• Study Start: January 1, 2020
• Primary Completion: December 31, 2023
• Study Completion: December 31, 2023
• Last Updated: December 9, 2024

Record last verified: 2024-12

Locations

CN (1)