Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Identification of leading causes and paths of death in alcoholic ARDS patients through clinical dataset-wide computations

Award Number: R21AA033945
ORGANIZATION: NATIONAL INSTITUTE ON ALCOHOL ABUSE AND ALCOHOLISM
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 08/17/2026
PERIOD OF PERFORMANCE END DATE: 07/31/2028

Group Awards By:

View Award Description

Identification of leading causes and paths of death in alcoholic ARDS patients through clinical dataset-wide computations - SUMMARY. Acute respiratory distress syndrome (ARDS) is a prevalent condition among ICU patients, with an overall mortality rate of 44%, as reported in a recent systematic review and meta-analysis. Traditional mathematical and statistical studies suggest that chronic alcohol misuse not only increases the risk of developing ARDS but also elevates overall mortality rates in critically ill patients. Alcohol misuse has been shown to exacerbate multiple organ dysfunction in individuals suffering from ARDS by few traditional reports. However, the leading causes of death and the associated causal pathways in alcoholic ARDS patients have not yet been systematically investigated phenome-wide of all eight NIH-funded clinical trials. We have conducted a pilot study phenome-wide in 1,149 patients enrolled in three ARDSNet clinical trials, combining machine learning (ML) and causal modeling. Based on these novel findings, we hypothesize that alcohol misuse alters the leading causes of death and related causal pathways in ARDS patients. To test this hypothesis, we aim to validate our results in a new cohort comprising five separate clinical trials (n = 5,568 patients). All these trials were NIH-funded, multicenter, randomized, and double-blinded. We will apply advanced computational approaches to prioritize the leading clinical variables associated with mortality and compare differences between drinkers and nondrinkers. The causal pathways in alcoholic patients will be identified by analyzing 1,204 clinical variables using the reliable causal inference approaches. There are two specific Aims for this retrospective cohort study. Aim 1: To rank the leading predictors of death in alcoholic and nonalcoholic ARDS patients by combining random forest and SHAP algorithms. Aim 2: To identify causal pathways specific to alcohol misuse with integrating machine-learning-based causal approaches. Causal discovery, mediation inference, causal inference will be applied to identify causal paths to death. The identified causal paths will be confirmed by developing predictive models and testing for faithfulness, robustness, and statistical significance. We herein introduce a first-in-class clinical phenome-based framework that systematically interrogates all clinical variables using advanced ML, causal discovery, and causal inference. Unlike traditional statistic approaches, this comprehensive, unbiased, and mechanistically informative analysis of all NIH clinical trials phenome-wide will, for the first time, provide real-world evidence to inform targeted interventions, guide research directions, assist resource allocation, and shape public health policies aimed at reducing mortality and improving the health of both alcoholic and nonalcoholic populations.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $115,500 )
2026	2026	LOYOLA UNIVERSITY OF CHICAGO	2160 S 1ST AVE	MAYWOOD	IL	60153	COOK	USA	Alcohol Research Programs	000	1	8/19/2026	NEW	$115,500
														Subtotal = $115,500

Grand Total All Awards = $115,500

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Identification of leading causes and paths of death in alcoholic ARDS patients through clinical dataset-wide computations

Award Number: R21AA033945

ORGANIZATION: NATIONAL INSTITUTE ON ALCOHOL ABUSE AND ALCOHOLISM

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 08/17/2026

PERIOD OF PERFORMANCE END DATE: 07/31/2028

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer