Publications
Featured and Recent
A Machine Learning Trauma Triage Model for Critical Care Transport
Organized by Topic
Our team brings decades of industry leading research in these spaces.
No publications match the selected filters.
HemoRisk: Maternal Hemorrhage Risk Assessment
Between Promise and Practice: Provider Challenges in Adopting AI for Clinical Workflows. Abstract to be presented at the Society for Obstetric Anesthesia and Perinatology (SOAP) Annual Meeting; 2026.
Pending
Beyond Survival: The Hidden Maternal, Infant, and Societal Consequences of Postpartum Hemorrhage.
Improvements and limitations in developing multivariate models of hemorrhage and transfusion risk for the obstetric population.
Widespread adoption of AI risk models for maternal hemorrhage requires mitigation of bias.
Rapter: Emergency medicine
A Machine Learning Trauma Triage Model for Critical Care Transport.
Hemorrhage Detection
Detection of hemorrhage by analyzing shapes of the arterial blood pressure waveforms.
Development of hemorrhage identification model using non-invasive vital signs.
Identification and explanation of severity of bleeding-induced hypovolemia using unsupervised deep learning.
Increasing cardiovascular data sampling frequency and referencing it to baseline improve hemorrhage detection.
Parsimony of hemodynamic monitoring data sufficient for the detection of hemorrhage.
Robustness of machine learning models for hemorrhage detection.
Utility of empirical models of hemorrhage in detecting and quantifying bleeding.
Hypotension
Identification of clinical phenotypes in septic patients presenting with hypotension or elevated lactate.
Machine learning driven prediction of hypotension using real-world multi-granular data.
Predicting cardiorespiratory instability.
Prediction of hypotension events with physiologic vital sign signatures in the intensive care unit.
Sepsis
A research agenda for precision medicine in sepsis and acute respiratory distress syndrome: an official American Thoracic Society research statement.
Feasibility of sepsis phenotyping using electronic health record data during initial emergency department care.
Modeling sepsis-induced organ failure.
Prediction of hypovolemic instability in normal volunteer blood donors using machine learning.
Statistical model selection for predicting sepsis mortality.
Unifying cardiovascular modeling with deep reinforcement learning for uncertainty-aware control of sepsis treatment.
Using biomarkers to enhance 60-day in-hospital mortality prediction for early sepsis patients.
Using clinical features and biomarkers to predict 60-day mortality of sepsis patients.
Atrial Fibrillation
Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings.
Racial differences in commercial monitoring software detection of atrial fibrillation.
Reinforcement learning algorithm to improve intermittent hemodialysis.
Using weakly supervised machine learning to label atrial fibrillation in real-world intensive care unit telemetry data.
Machine Learning Using Electronic Health Records
Deep normed embeddings for patient representation.
Hierarchical adaptive multi-task learning framework for patient diagnoses and diagnostic category classification.
Hierarchical deep multi-task learning for classification of patient diagnoses.
Hierarchical multi-task learning.
Not all samples are equal: class-dependent hierarchical multi-task learning for patient diagnosis classification.
The learning electronic health record.
Machine Learning Using Patient Physiological Signals
Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration.
Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction.
Using supervised machine learning to classify real alerts and artifact in online multi-signal vital sign monitoring data.
Bedside Alerting System
A call to alarms: current state and future directions in the battle against alarm fatigue.
Conditional outlier detection for clinical alerting.
Engaging clinicians early during the development of a graphical user display of an intelligent alerting system at the bedside.
Intelligent clinical decision support.
Outlier-based detection of unusual patient-management actions: an ICU study.
Understanding clinical collaborations through federated classifier selection.
User-engaged design of a graphical user interface for instability decision support in the ICU.
Publications from Real-time Deployment for COVID-19 Clinical Trials
Effect of angiotensin-converting enzyme inhibitor and angiotensin receptor blocker initiation on organ support–free days in patients hospitalized with COVID-19: a randomized clinical trial.
Effect of antiplatelet therapy on survival and organ support–free days in critically ill patients with COVID-19: a randomized clinical trial.
Implementation of the Randomized Embedded Multifactorial Adaptive Platform for COVID-19 (REMAP-COVID) trial in a US health system—lessons learned and recommendations.
Long-term (180-day) outcomes in critically ill patients with COVID-19 in the REMAP-CAP randomized clinical trial.
Lopinavir-ritonavir and hydroxychloroquine for critically ill patients with COVID-19: REMAP-CAP randomized controlled trial.