PHASE Laboratory
The PHASE (Physiologic High-Resolution Analytics and Signal Exploration) Laboratory is dedicated to advancing cardiovascular care through the study of high-fidelity physiologic data and waveform analytics. We leverage continuous bedside monitoring data to better understand cardiovascular physiology, characterize responses to therapies, develop novel biomarkers, and create clinically meaningful decision-support tools. By combining clinical expertise with engineering, data science, and advanced analytics, our goal is to transform the wealth of physiologic information generated in modern intensive care units into actionable knowledge that improves patient care.
Our research spans pediatric and adult cardiovascular medicine, with a particular emphasis on congenital heart disease and critical care. Current areas of investigation include hemodynamic monitoring, arterial and photoplethysmographic waveform analysis, oxygen delivery physiology, venous hemodynamics, predictive modeling, and artificial intelligence. Through close collaboration with clinicians, engineers, and industry partners, the PHASE Laboratory develops practical, evidence-based technologies that bridge the gap between physiologic discovery and real-world clinical application, ultimately improving outcomes for patients with cardiovascular disease.
Research Topics
Machine learning
High-fidelity physiologic data
Waveform analysis
Cardiology
Contact
Rohit S. Loomba, MD, MS
rloomba@luriechildrens.org
Research Highlights
THE EFFECTS OF VASOACTIVE MEDICATIONS ON MEAN CIRULATORY FILLING PRESSURE, VENOUS RESISTANCE, SYSTEMIC VASCULAR RESISTANCE, CARDIAC INDEX, AND OXYGEN EXTRACTION AFTER PEDIATRIC HEART TRANSPLANT: LEVERAGING HIGH-FIDELITY PHYSIOLOGIC DATA
The physiologic effects of vasoactive medications on the venous circulation remain incompletely understood. Contemporary bedside management often emphasizes the arterial circulation, whereas Guytonian physiology emphasizes the venous circulation and mean circulatory filling pressure in determining steady-state cardiac output. The primary aim of this study was to characterize the effect of vasoactive medications on mean circulatory filling pressure and venous resistance. Methods: Demographic data and vasoactive data were collected from the electronic health record and collated with high-fidelity physiologic monitoring data. Mean circulatory filling pressure and venous resistance were calculated using clinically validated equations and then were modeled using a random forest regression incorporating postoperative time and infusion doses of epinephrine, norepinephrine, milrinone, vasopressin, phenylephrine, calcium, sodium nitroprusside, and nicardipine. Similar models were constructed for indexed systemic vascular resistance, cardiac index, cerebral oxygen extraction, and renal oxygen extraction. Results: Data from a total of 57 unique patients comprising 9,654,239 data points were analyzed. The model explained 57% of the variance in mean circulatory filling pressure and 59% of the variance in venous resistance. Vasopressin and norepinephrine were the most influential for mean circulatory filling pressure and venous resistance. Conclusions: Vasoactive medications appear to modulate venous tone and impact mean circulatory filling pressure and venous resistance. High-fidelity physiologic data allow for characterizing these effects and guide titration of vasoactive medications at the bedside.
ACUTE HEMODYNAMIC EFFECTS OF IVABRADINE IN PEDIATRIC CARDIAC CRITICAL CARE PATIENTS
Background: Utilization of ivabradine in the pediatric population has been centered on the goal of chronotropic control in patients with arrhythmias and heart failure. Tachycardia is known to be detrimental when it impairs hemodynamics by increasing myocardial oxygen demand, increasing ventricular end-diastolic pressures, and decreasing cardiac output in certain patients. The acute hemodynamic effects of ivabradine have not yet been studied in real time.
Study question: This study was performed leveraging the Sickbay platform (Medical Informatics Company, Houston, TX). The primary aim of this study was to characterize the effect of enteral ivabradine on heart rate in patients in a pediatric cardiac intensive care unit within 24 hours of initiation. Secondary aims were to characterize the effects of ivabradine on arterial saturation, respiratory rate, mean arterial blood pressure, central venous pressure, and renal near infrared spectroscopy for the same time frame.
Results: Heart rate decreased approximately 17% in the first 15 hours after ivabradine administration. Changes were seen in the secondary aims that varied depending on time after first and second doses. Specifically, decreases in central venous pressure and increased renal tissue oxygen saturation (rSO2) were observed by the end of the 24 hours.
Conclusions: Ivabradine seems safe in pediatric patients. It is associated with 3 distinct hemodynamic response phases: the first phase is associated with decreased heart rate and unchanged systemic oxygen delivery, the second phase is associated with increased heart rate and worsened systemic oxygen delivery, and the third phase being associated with decreased heart rate and improved systemic oxygen delivery. These phases coincide with the pharmacokinetic properties of ivabradine.
ASSOCIATION OF MUSIC THERAPY AND PHYSIOLOGIC INDICES IN THE PEDIATRIC CARDIAC INTENSIVE CARE UNIT: INSIGHTS FROM MACHINE LEARNING AND HIGH-FIDELITY PHYSIOLOGIC DATA
Music therapy is increasingly used in critically ill children, yet its real-time physiologic effects remain incompletely characterized. This study used high-fidelity physiology data to characterize the physiologic response to music therapy in pediatric cardiac intensive care unit patients. Physiologic data were extracted from Sickbay. Heart rate, mean arterial blood pressure, central venous pressure, arterial saturation, respiratory rate, end tidal carbon dioxide, and renal near infrared spectroscopy were analyzed from 1 h before through 4 h after the start of therapy. Percent change from baseline was modeled using multivariable regression adjusting for participation level, therapy technique, circulatory physiology, mechanical ventilation, mechanical circulatory support, sedation, and vasoactive inotrope score. Cluster analysis of session-level percent changes was conducted to identify physiologic response phenotypes. A total of 52 music therapy sessions across 33 unique patients were included in the final analyses. Music therapy was independent associated with changes in heart rate (+ 3%, p = 0.03), central venous pressure (+ 10%, p < 0.01), end tidal carbon dioxide (+ 11%, p < 0.01), and renal near infrared spectroscopy (+ 3%, p = 0.02). Cluster analysis revealed two physiologic response clusters: one demonstrating stable hemodynamics and improved adequacy of oxygen delivery and another demonstrating heightened respiratory activity but no improvement in the adequacy of oxygen delivery. Cluster 1, with improvement in the adequacy of oxygen delivery, was associated with active patient participation. Music therapy was independently associated with physiologic changes. In a majority of patients, the adequacy of oxygen delivery improved and was associated with active patient participation.
Principal Investigator
Rohit S. Loomba, MD, MS
Dr. Rohit Loomba is a pediatric cardiac intensivist and Director of Clinical Research in the Heart Center at Ann & Robert H. Lurie Children’s Hospital of Chicago, with expertise in pediatric cardiac critical care, cardiovascular physiology, and congenital heart disease. His clinical and academic work focuses on the application of high-fidelity physiologic data to improve outcomes for critically ill children with heart disease, with a particular interest in hemodynamics, acute kidney injury, transplantation, and postoperative critical care. He has extensive experience in clinical and translational research and has authored numerous peer-reviewed publications spanning pediatric cardiology, cardiac intensive care, and perioperative physiology.
Dr. Rohit’s research program centers on high-frequency physiologic monitoring, waveform analytics, and advanced hemodynamic modeling using streaming bedside data. His work leverages high-fidelity physiologic signals—including arterial pressure, pulse oximetry, near-infrared spectroscopy, and other continuous monitoring streams—to better characterize cardiovascular function and develop novel approaches for hemodynamic assessment and clinical decision support in pediatric cardiac critical care. He has led and collaborated on studies applying waveform analysis, physiologic modeling, and data science methods to better understand patient trajectories and therapeutic responses in the cardiac intensive care environment.
