Machine Learning Prediction of Mortality After Prone Positioning in ARDS

NCT07445061 — Completed, 358 participants, Shanghai Zhongshan Hospital

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

A Machine Learning Model to Predict Mortality in Patients With Acute Respiratory Distress Syndrome After Prone Positioning

Registry	NCT07445061
Status	Completed
Study type	Observational
Enrollment	358 (Actual)
Sponsor	Shanghai Zhongshan Hospital (Other)
Conditions	Acute Respiratory Distress Syndrome (ARDS), Prone Position Ventilation, Machine Learning, ICU, ARDS
Interventions	Prone Position Ventilation (Other)
Dates	start 2026-03-01, primary completion 2026-04-01, completion 2026-05-01, first posted 2026-03-03, last updated 2026-08-14
Locations	1 site in China

-Summary

Acute respiratory distress syndrome (ARDS) is a life-threatening condition with high mortality. Prone position ventilation (PPV) is an evidence-based therapy that improves oxygenation and survival in patients with moderate to severe ARDS; however, outcomes remain heterogeneous. Early identification of patients at high risk of mortality after PPV may improve clinical decision-making and individualized management.

This retrospective observational study developed and validated a machine learning model to predict intensive care unit (ICU) mortality in patients with ARDS receiving prone position ventilation. Clinical, laboratory, and treatment variables obtained from ICU electronic medical records were used to construct prediction models using multiple machine learning algorithms. The performance of these models was evaluated and compared to identify the optimal model for mortality prediction.

Expand all sections · Collapse all

+Arms and interventions

Arm	Type	Interventions	Description
ARDS Patients Receiving Prone Position Ventilation		Other: Prone Position Ventilation	Adult patients diagnosed with acute respiratory distress syndrome (ARDS) who received prone position ventilation during intensive care unit (ICU) admission. Clinical data were retrospectively obtained from electronic medical records for the development and validation of machine learning models to predict ICU mortality.

Prone Position Ventilation (Other): Prone position ventilation applied as part of routine clinical care for patients with acute respiratory distress syndrome. No experimental intervention was assigned in this observational study.

+Outcome measures

Primary outcomes

ICU Mortality [Up to 90 days.]: Death from any cause during the intensive care unit (ICU) stay among patients with acute respiratory distress syndrome receiving prone position ventilation.

Other outcomes

ARDS subphenotype classification based on machine learning model. [Baseline (at initiation of prone position ventilation).]: Number of patients classified into different ARDS subphenotypes using a machine learning model based on clinical and physiological variables collected at baseline.

+Eligibility

Sex: All, ages: 18 Years to any

Inclusion Criteria:

* Diagnosis of ARDS according to the Berlin definition;
* Receipt of at least one session of prone position ventilation (PPV) during hospitalization;
* Requirement for mechanical ventilation.

Exclusion Criteria:

* Age <18 years;
* PPV duration <6 hours;
* ICU length of stay <2 days;
* Pregnancy;
* Receipt of awake prone positioning.
* Missing key clinical data.

+Locations (1)

Facility	City	Country	Status
Zhongshan Hospital, Fudan University	Shanghai, Shanghai Municipality	China