Clinical Domains

Research Application Domains

Lab's Interests

In the Kamaleswaran Lab, our research takes a pioneering approach by harnessing the power of multi-modal data to comprehensively investigate the complex dynamics of critical illness. We integrate transcriptomic, metabolomic, lipidomic, and microbiome data to unravel the molecular intricacies underlying acute injury and its ramifications on multi-organ dysfunction and major complications in critically ill patients. Within, the area of precision transplantation, we study how patients who receive organ transplants respond at the cellular level to predict potential risks of downstream complications.

Combining these diverse datasets, our aim is to build a holistic understanding of the interplay between molecular, organ-level, and physiological responses to acute injury and critical illness. Transcriptomic analyses provide insights into gene expression patterns, shedding light on the intricate molecular signaling cascades triggered by acute injury. Simultaneously, metabolomic and lipidomic data offer a nuanced perspective on the metabolic shifts that accompany critical illness, capturing alterations in key metabolites and lipid molecules.

Importantly, our research extends beyond molecular analyses to integrate physiological waveform-derived markers, focusing on the autonomic nervous system and its intricate relationship with the systemic inflammatory response. Physiomarkers, such as heart rate variability and pulse transit time, serve as surrogate indicators of autonomic function and offer valuable insights into the physiological aspects of critical illness.

By harmonizing multi-modal molecular data with physiological waveform-derived markers, our lab strives to bridge the gap between molecular understanding and clinical manifestations in critical care. Advanced computational techniques, including machine learning and data integration, play a pivotal role in uncovering intricate relationships across these diverse datasets. Ultimately, our goal is to provide a comprehensive framework for characterizing critical illness, enabling a more personalized and targeted approach to patient care in intensive care settings.

Critical care research areas



Sikora A, Rafiei A, Rad MG, Keats K, Smith SE, Devlin JW, Murphy DJ, Murray B, Kamaleswaran R, MRC-ICU Investigator Team. Pharmacophenotype identification of intensive care unit medications using unsupervised cluster analysis of the ICURx common data model. Critical Care. 2023 May 2;27(1):167  PDF File 

Rafiei A, Rad MG, Sikora A, Kamaleswaran R. Improving mixed-integer temporal modeling by generating synthetic data using conditional generative adversarial networks: A case study of fluid overload prediction in the intensive care unit. Computers in Biology and Medicine. 2023 Nov 22:107749. PDF File

Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi



Tabaie A, Orenstein EW, Nemati S, Basu RK, Kandaswamy S, Clifford GD, Kamaleswaran R. Predicting presumed serious infection among hospitalized children on central venous lines with machine learning. Computers in biology and medicine. 2021 May 1;132:104289. PDF File

Sepsis and multi-organ dysfunction

Atreya MR, Banerjee S, Lautz AJ, Alder MN, Varisco BM, Wong HR, Muszynski JA, Hall MW, Sanchez-Pinto LN, Kamaleswaran R; Genomics of Pediatric Septic Shock Investigators. Machine learning-driven identification of the gene-expression signature associated with a persistent multiple organ dysfunction trajectory in critical illness. EBioMedicine. 2023 Dec 23;99:104938. doi: 10.1016/j.ebiom.2023.104938. Epub ahead of print. PMID: 38142638.



Huang M, Atreya MR, Holder A, Kamaleswaran R. A MACHINE LEARNING MODEL DERIVED FROM ANALYSIS OF TIME-COURSE GENE-EXPRESSION DATASETS REVEALS TEMPORALLY STABLE GENE MARKERS PREDICTIVE OF SEPSIS MORTALITY. Shock. 2023 Nov 1;60(5):671-7. PDF File


Kobara S, Rad MG, Grunwell JR, Coopersmith CM, Kamaleswaran R. Bioenergetic Crisis in ICU-Acquired Weakness Gene Signatures Was Associated With Sepsis-Related Mortality: A Brief Report. Critical Care Explorations. 2022 Dec;4(12).  PDF File

Differential gene expression analysis among pediatric septic shock patients


Clinical translation of real-time machine learning models to the ICU patient bedside


Acute Lung Injury/Acute Respiratory Distress Syndrome (ARDS) research areas



Krishnan P, Rad MG, Agarwal P, Marshall C, Yang P, Bhavani SV, Holder AL, Esper A, Kamaleswaran R. HIRA: Heart Rate Interval based Rapid Alert score to characterize autonomic dysfunction among patients with sepsis-related acute respiratory failure (ARF). Physiological Measurement. 2023 Oct 13;44(10):105006.  PDF File 

Chanci D, Grunwell JR, Rafiei A, Moore R, Bishop NR, Rajapreyar P, Lima LM, Mai M, Kamaleswaran R. Development and Validation of a Model for Endotracheal Intubation and Mechanical Ventilation Prediction in PICU Patients. Pediatric Critical Care Medicine. 2023 Nov 13:10-97. PDF File

ARDS diagnosis using uncertainty-aware convolutional neural network for identifying bilateral opacities on chest X-rays

Singhal L, Garg Y, Yang P, Tabaie A, Wong AI, Mohammed A, Chinthala L, Kadaria D, Sodhi A, Holder AL, Esper A. eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19. PloS one. 2021 Sep 24;16(9):e0257056. PDF File

Cluster analysis and profiling of airway fluid metabolites in pediatric acute hypoxemic respiratory failure

Precision Cardiology



Shi H, Book W, Raskind‐Hood C, Downing KF, Farr SL, Bell MN, Sameni R, Rodriguez III FH, Kamaleswaran R. A machine learning model for predicting congenital heart defects from administrative data. Birth Defects Research. 2023 Sep 8. PDF File

Machine learning methods to classify abnormal cardiac rhythm using varying length single lead electrocardiogram

Symbolic Pattern Recognition  and hybrid feature extraction method to detect Atrial Fibrillation from single lead ECG recording

Precision Transplant

Kamaleswaran R, Sataphaty SK, Mas VR, Eason JD and Maluf DG (2021) Artificial Intelligence May Predict Early Sepsis After Liver Transplantation. Front. Physiol. 12:692667. doi: 10.3389/fphys.2021.692667 PDF File