Skip to main content
CLIF Logo

Research & Projects

Discover our research, conference presentations, and ongoing collaborative projects advancing critical care through CLIF

Publications

Federation, Not Centralization: A New Paradigm for EHR-Based Critical Care Research

Prone Positioning in a North American Cohort of Hypoxemic Patients on Mechanical Ventilation

The Epidemiology of ICU Readmissions Across Ten Health Systems

Correspondence on "A common longitudinal intensive care unit data format (CLIF) for critical illness research" - Author's reply

A common longitudinal intensive care unit data format (CLIF) for critical illness research

Conference Presentations

CLIF Consortium members at the ATS 2026 International Conference

American Thoracic Society (ATS)

2026

CLIF Consortium investigators gathered at the ATS 2026 International Conference, presenting a broad slate of multicenter critical-care studies built on the Common Longitudinal ICU data Format.

Research Presentations:

Comparing Cross-Site Validation, Transfer Learning, and Independent Training for ICU Mortality Prediction: A U.S. Multicenter Study
Personalized Respiratory Support for Acute Respiratory Failure Using Deep Reinforcement Learning
Patient Preferred Language and Continuous Neuromuscular Blockade During Invasive Mechanical Ventilation: A Multicenter Retrospective Cohort Study
Differential Severity Classification and Prognostic Performance of PaO2/FIO2 Versus SpO2/FIO2 Ratios in Adults With Acute Hypoxemic Respiratory Failure
Redefining White Blood Cell and Temperature Thresholds for Sepsis Detection: A Multicenter, Data-Driven Analysis
Cumulative Air Pollution Exposure Increases the Severity of Acute Respiratory Failure: A U.S. Multicenter Study
Diurnal and Institutional Variation in Sedation and Extubation in Mechanical Ventilation: A Multicenter Study of Six Hospital Systems
The Epidemiology of Hospital Code Status Designations Across Six US Health Systems
A Location Agnostic EHR Definition of Critical Illness Using the Common Longitudinal ICU Data Format (CLIF)
Clinical Effects of a Nationwide IV Fluid Shortage on Patients With Sepsis in an Academic Health System
Intermediate Versus Intensive Care for Patients With Moderate-Severe Acute Respiratory Failure
Characteristics and Outcomes of ED Patients Requiring Non-invasive Respiratory Support Admitted to Different Levels of Care
Heterogeneous Longitudinal Trajectories of Antibiotic Spectrum Coverage in Critically Ill Adults: A Multicenter Study of 9 U.S. Healthcare Systems
Trends in Multidrug-resistant Pseudomonas Aeruginosa in ICU Patients Across U.S. Healthcare Systems, 2018-2024
CLIF research presented at the SCCM 2026 Critical Care Congress CLIF overview presented at the SCCM 2026 Critical Care Congress

Society of Critical Care Medicine (SCCM)

2026 Critical Care Congress

CLIF investigators presented at the SCCM 2026 Critical Care Congress — sharing work on EHR-based phenotyping of spontaneous awakening and breathing trials and introducing the Common Longitudinal ICU data Format to the critical-care community.

Research Presentations:

Multicenter Study on Continuous Renal Replacement Therapy Timing and Intensity in ICU Patients
Phenotyping Spontaneous Awakening and Breathing Trials in the Electronic Health Record
Duration and Predictors of Prolonged Respiratory Failure in 19,444 Mechanically Ventilated Patients
CLIF Meets RL workshop presenters at AMIA Amplify 2026

American Medical Informatics Association (AMIA)

2026 Amplify Informatics Conference

CLIF Consortium members led a hands-on workshop at the AMIA Amplify 2026 Informatics Conference, teaching attendees how to train reinforcement learning models on CLIF-formatted ICU data.

CLIF Meets RL: A Hands-On Workshop on Training Reinforcement Learning Models with Common Longitudinal ICU Format (CLIF) Data

Hands-on workshop — Kaveri Chhikara, Saki Amagai, and Yikuan Li.

CLIF federated ICU clinical decision support poster at SAIL 2026

Symposium on Artificial Intelligence for Learning Health Systems (SAIL)

2026

CLIF investigators presented a federated, privacy-preserving evaluation of ICU clinical decision support spanning eight U.S. health systems at SAIL 2026.

Privacy-Preserving Multicenter Evaluation of ICU Clinical Decision Support: A Federated Framework Across Eight U.S. Health Systems

Poster — Juan Rojas and Vaishvik Chaudhari.

ATS 2025 Conference

American Thoracic Society (ATS)

2025 Multiple CLIF studies presented

Research Presentations:

Electronic health record signatures of spontaneous awakening trials

Multi-center analysis of sedation cessation patterns in mechanically ventilated patients

View Abstract →
Multi-center evaluation of prone positioning practices

For moderate and severe hypoxemic respiratory failure

View Abstract →
Association of sex and height with low-tidal volume ventilation

Multi-center cohort of critically ill adults

View Abstract →
CLIF respiratory support waterfall methodology

Novel method for analyzing ventilator mode patterns in critical care

View Abstract →
ATS 2024 Conference

American Thoracic Society (ATS)

2024 Various CLIF studies presented

Research Presentations:

Advancing multi-center clinical research in critically ill patients

Through the development of a common longitudinal ICU format (CLIF)

View Abstract →
Early mobilization opportunity windows

Multi-center comparative analysis of clinical trial and consensus guideline eligibility criteria

View Abstract →
Variation in setting low tidal volume ventilation on day 1

Analysis of mechanical ventilation practices by hospital

View Abstract →
AMIA 2024 CLIF Presentation

American Medical Informatics Association (AMIA)

2024 Informatics Summit

Kaveri Chhikara presents the CLIF at the AMIA Summit, touching on the standardized data format created to address challenges in using ICU electronic health record data for research.

Ongoing Projects

The CLIF consortium is a network of NIH funded investigators.

Principal Investigators (PIs) in the consortium are supported by a wide range of NIH grants that use big data and advanced ML techniques to answer open scientific questions related to critical illness. Each of these projects would be better with CLIF rather than done in silos.

Improving the efficiency and equity of critical care allocation during a crisis with place-based disadvantage indices

CLIF Project: Creating a life support allocation triage score for crisis standards of care
PI: William Parker, University of Chicago

Identifying Areas to Improve ICU Outcomes through Provider Variation

CLIF Project: Studying hospital variation in low-tidal volume ventilation across hospital systems
PI: Nicholas Ingraham, University of Minnesota

Identification of Precision Sepsis Subphenotypes Using Vital Sign Trajectories

CLIF Project: Validating the association of temperature trajectories and ICU mortality across hospital systems
PI: Sivasubramanium Bhavani, Emory University

Sustainable Implementation of Prone Positioning for the Acute Respiratory Distress Syndrome

CLIF Project: Studying the association between proning practice patterns and ARDS survival
PI: Chad Hochberg, John Hopkins University

Early Mobilization: Operationalizing Big Data & Implementation Science to Lead Expansion to ICUs (E-MOBILE-ICU)

CLIF Project: Identifying critically ill patients who are eligible for mobilization using the electronic healthcare record
PI: Bhakti Patel, University of Chicago

Machine learning to predict cure in severe pneumonia episodes

CLIF Project: Prediction of severe pneumonia using machine learning
PI: Catherine Gao, Northwestern University

SPOT-IT: Sepsis Prediction in Oncology Through Implementation Science and Technology

CLIF Project: Develop an oncology-specific sepsis prediction model using EHR data and human-centered design
PI: Patrick Lyons, Oregon Health and Science University