Application of Artificial Intelligence and Iron Metabolism Markers in Predicting ICU Outcomes for Critically Ill Cancer Patients

NCT07408661 | Completed

• 1 other identifier: MIMIC-IRON-CANCER-2025
• Study Type: observational
• Target: 1,137
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study aimed to develop a more accurate way to predict the 30-day survival of cancer patients admitted to the intensive care unit (ICU). The researchers focused on markers of iron metabolism, as imbalances in iron are common in cancer and severe illness. The study analyzed data from 1,137 critically ill cancer patients. Using artificial intelligence (AI), specifically a model called TabPFN, the study combined these iron markers with other routine clinical data (like blood cell counts and lactate levels) to create a new prediction tool.

Conditions

Cancer

Keywords

Critical care; Cancer; Artificial Intelligence; Risk stratification; Ferritin

Outcome Measures

Primary Outcomes (1)

• All-cause Mortality at 30 Days

  The primary outcome is the incidence of death from any cause within 30 days following the date of ICU admission. Mortality status will be determined by a review of the hospital discharge records and associated death records in the MIMIC-IV database.

  30 days from the date of ICU admission.

Study Arms (1)

Critically Ill Cancer Patients

This group comprises adult cancer patients who were admitted to the intensive care unit (ICU). The primary interest is in their 30-day all-cause mortality following ICU admission. The cohort includes 1,137 patients whose clinical data was extracted from the MIMIC-IV database. Key variables of interest include iron metabolism markers (ferritin, serum iron, TIBC), routine blood tests, and vital signs, all assessed at or near ICU admission. This retrospective observational study investigates the prognostic value of these markers and aims to develop a machine learning model for predicting mortality risk.

Eligibility Criteria

• Age: 18 Years - 100 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of adult cancer patients who were critically ill, requiring intensive care unit admission. This retrospective cohort is derived from the MIMIC-IV database, comprising patients with a cancer diagnosis who had their first ICU stay during hospitalization and for whom complete data on the key predictors and outcome are available.

You may qualify if:

• Adult patients (age ≥ 18 years).
• Diagnosis of any type of cancer, as recorded in the hospital database.
• First ICU admission during the hospital stay (only the first ICU stay is considered for patients with multiple admissions).

You may not qualify if:

• Length of ICU stay less than 24 hours.
• Missing or unavailable data for the key study variables, specifically iron metabolism markers (ferritin, serum iron, total iron-binding capacity) or essential clinical parameters needed for analysis.

Sponsors & Collaborators

• Tongji University: lead

MeSH Terms

Conditions

Neoplasms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: February 6, 2026
• First Posted: February 13, 2026
• Study Start: January 1, 2015
• Primary Completion: October 1, 2024
• Study Completion: December 1, 2025
• Last Updated: February 13, 2026

Record last verified: 2026-02

Data Sharing

• IPD Sharing: Will not share