Machine Learning Prediction of Mortality After Prone Positioning in ARDS

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

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.

Study Overview

• Status: Completed
• Conditions: ARDS; Machine Learning; Acute Respiratory Distress Syndrome (ARDS); ICU; Prone Position Ventilation
• Intervention / Treatment: Other: Prone Position Ventilation

• Study Type: Observational
• Enrollment (Actual): 358

Contacts and Locations

Study Locations

• China
  • Shanghai Municipality
    • Shanghai, Shanghai Municipality, China, 200032
      • Zhongshan hospital, Fudan University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Adult patients diagnosed with acute respiratory distress syndrome (ARDS) who received prone position ventilation in the intensive care unit at Zhongshan Hospital, Fudan University, between October 2019 and August 2025. Clinical data were retrospectively obtained from electronic medical records.

Description

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.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
ARDS Patients Receiving 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.	Other: Prone Position Ventilation; 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
ICU Mortality	Death from any cause during the intensive care unit (ICU) stay among patients with acute respiratory distress syndrome receiving prone position ventilation.	Up to 90 days.

Other Outcome Measures

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

Collaborators and Investigators

• Sponsor: Shanghai Zhongshan Hospital

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2026
• Primary Completion (Actual): April 1, 2026
• Study Completion (Actual): May 1, 2026

Study Registration Dates

• First Submitted: February 24, 2026
• First Submitted That Met QC Criteria: March 1, 2026
• First Posted (Actual): March 3, 2026

Study Record Updates

• Last Update Posted (Actual): August 14, 2026
• Last Update Submitted That Met QC Criteria: August 12, 2026
• Last Verified: August 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Respiratory Tract Diseases; Lung Diseases; Respiration Disorders; Respiratory Distress Syndrome
• Other Study ID Numbers: B2026-019

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: De-identified individual participant data underlying the results reported in the article will be available from the corresponding author upon reasonable request.
• IPD Sharing Time Frame: Data will be available beginning after publication and for 5 years following publication.
• IPD Sharing Access Criteria: Researchers who submit a scientifically sound proposal may request access from the corresponding author. Requests will be reviewed by the study investigators and will be subject to applicable institutional and ethical requirements. A data use agreement may be required.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ANALYTIC_CODE

Drug and device information, study documents

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