Bobak Jack Mortazavi, PhD
Assistant Professor AdjunctCards
Appointments
Additional Titles
Associate Professor, Center for Outcomes Research & Evaluation (CORE)
Contact Info
Appointments
Additional Titles
Associate Professor, Center for Outcomes Research & Evaluation (CORE)
Contact Info
Appointments
Additional Titles
Associate Professor, Center for Outcomes Research & Evaluation (CORE)
Contact Info
About
Titles
Assistant Professor Adjunct
Associate Professor, Center for Outcomes Research & Evaluation (CORE)Biography
J. Bobak Mortazavi is an Associate Professor, researching at the Center for Outcomes Research and Evaluation (CORE). Dr. Mortazavi's background is in Electrical Engineering and Computer Science. He graduated with a B.A. in Applied Mathematics and B.S. in Electrical Engineering and Computer Science from University of California Berkeley in 2007. In 2009 he earned his M.S. in Electrical and Computer Engineering from University of California Irvine. He earned his Ph.D. in Computer Science from University of California Los Angeles in 2014, where he researched realistic and real-time activity monitoring of humans with wearable sensors; one demonstration of such a system won him a Best Demonstration Award at the 2012 IEEE Body Sensor Networks Conference. His interests include researching embedded and reconfigurable systems for medical applications, wireless health, and the application of embedded and reconfigurable systems and machine learning of time-series data to clinical applications.
Appointments
Cardiovascular Medicine
Assistant Professor AdjunctPrimary
Other Departments & Organizations
Education & Training
- Postdoctoral Associate
- Yale University (2016)
- PhD
- University of California Los Angeles, Computer Science (2014)
- MS
- University of California Irvine, Electrical and Computer Engineering (2009)
- BA
- University of California Berkeley, Applied Mathematics (Computer Science) (2007)
- BS
- University of California Berkeley, Electrical Engineering and Computer Science (2007)
Research
Overview
My research began in traditional computer science systems. This included architecture development for processing elements as well as Field Programmable Gate Array (FPGA) reconfigurable networks for multimedia and smart home environments. These FPGAs allow for the design and prototype of reconfigurable hardware systems ideal for signal processing. From this I moved into the embedded systems realm, applying my electrical engineering hardware background with my computer science math and algorithms background to develop full working systems. These embedded systems are application oriented, where each end product/goal introduces new challenges to the hardware platforms needed as well as the software algorithms that run on those platforms or the data produced by them.
With the advent of small, wearable sensors, it became possible to apply reserach in sensor networks to the human through the use of Body Sensor Networks (BSN). These BSN allow for the development of human-oriented embedded systems, with a wide range of possible applications, many of which span the realm of health care. My Ph.D. focussed on such a system for physical activity monitoring. By placing multiple inertial measurement units (IMUs - sensors containing accelerometers, gyroscopes, and magnetometers) on various parts of the body, it becomes very simple to collect lots of time-series data on human motion. However, determining more detailed specifics of such motion are often more complicated. Many traditional human activity goals look at either developing a simple pedometer application or identifying common cyclical patterns (such as walking, climbing stairs, etc.). These patterns use common supervised learning techniques to identify a type of motion over a period of time. What if, however, you wanted to know detailed movements, such as those in sports, and as they were happening?
My research in physical activity monitoring aimed at focusing on such a question. In particular, could you monitor sports motinos, where the actions are often singular intense actions with little to no repetition, and apply such a recognition system to be the input to a new video gaming system? If so, you could develop an exercise-based game (called exergaming) that would allow for users to play games with increased energy expenditure. I looked at all the challenges in developing such a system, applied to a soccer gaming environment, from the sensor design for ubiquitous monitoring, to the machine learning algorithm at the core of the work. I analyzed the feature extraction and classificaiton techniques necessary to make the recognition of fine-grain activities possible. Furhter, I investigated the trade-offs necessary in a gaming environment, which include possibly sacrificing accuracy in an attempt to arrive at a classification in a timely fashion.
The application of such algorithms and systems can, however, be extended beyond the exergaming environment. My research goals at Yale include applying such supervised and unsupervised learning techniques to medical data in an attempt to develop better risk models for hospital re-admissions, with an eye toward cardiology and heart failure. Such data analytic techniques may be able to identify patterns for risk models not known through common biostatistic methods.
Machine learning and Systems Development for Medical/Clinical Data and Applications
Research at a Glance
Yale Co-Authors
Publications Timeline
Rohan Khera, MD, MS
Evangelos K. Oikonomou, MD, DPhil
Benjamin Tolchin, MD, MS, FAAN (Neurology), FAES
Erica Spatz, MD, MHS
James V. Freeman, MD, MPH, MS
Jeptha Curtis, MD
Publications
2024
Transforming Hypertension Diagnosis and Management in The Era of Artificial Intelligence: A 2023 National Heart, Lung, and Blood Institute (NHLBI) Workshop Report.
Shimbo D, Shah R, Abdalla M, Agarwal R, Ahmad F, Anaya G, Attia Z, Bull S, Chang A, Commodore-Mensah Y, Ferdinand K, Kawamoto K, Khera R, Leopold J, Luo J, Makhni S, Mortazavi B, Oh Y, Savage L, Spatz E, Stergiou G, Turakhia M, Whelton P, Yancy C, Iturriaga E. Transforming Hypertension Diagnosis and Management in The Era of Artificial Intelligence: A 2023 National Heart, Lung, and Blood Institute (NHLBI) Workshop Report. Hypertension 2024 PMID: 39011653, DOI: 10.1161/hypertensionaha.124.22095.Peer-Reviewed Original ResearchAltmetricConceptsMachine learning toolsManagement of hypertensionNational HeartArtificial intelligenceBlood InstitutePredictive of incident hypertensionHealth care systemImplementation challengesDiverse group of stakeholdersAI toolsPopulation healthMeasurement of blood pressureCare systemHealth careIncident hypertensionHypertension riskEra of artificial intelligenceHypertension diagnosisLearning toolsManaging hypertensionHypertension-related complicationsAntihypertensive medicationsHealthPublic healthGroups of stakeholdersEfficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning
Holste G, Oikonomou E, Mortazavi B, Wang Z, Khera R. Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning. Communications Medicine 2024, 4: 133. PMID: 38971887, PMCID: PMC11227494, DOI: 10.1038/s43856-024-00538-3.Peer-Reviewed Original ResearchAltmetricConceptsSelf-supervised learningTransfer learningTraining dataEchocardiogram videosPortion of labelled dataStandard transfer learning approachContrastive self-supervised learningSelf-supervised learning approachLearning approachImage recognition tasksState-of-the-artContrastive learning approachFine-tuningTransfer learning approachMedical image diagnosisCardiac disease diagnosisContrastive learningVideo framesLabeled datasetLabeled dataExpert labelsClassification performanceMedical imagesRecognition taskVideoMacronutrient Constraints and Priors Improve Carbohydrate Prediction From Continuous Glucose Monitors
Das A, Do E, Glantz N, Bevier W, Santiago R, Kerr D, Mortazavi B, Gutierrez-Osuna R. Macronutrient Constraints and Priors Improve Carbohydrate Prediction From Continuous Glucose Monitors. Current Developments In Nutrition 2024, 8: 102290. DOI: 10.1016/j.cdnut.2024.102290.Peer-Reviewed Original ResearchSOFA score performs worse than age for predicting mortality in patients with COVID-19
Sherak R, Sajjadi H, Khimani N, Tolchin B, Jubanyik K, Taylor R, Schulz W, Mortazavi B, Haimovich A. SOFA score performs worse than age for predicting mortality in patients with COVID-19. PLOS ONE 2024, 19: e0301013. PMID: 38758942, PMCID: PMC11101117, DOI: 10.1371/journal.pone.0301013.Peer-Reviewed Original ResearchMeSH Keywords and ConceptsConceptsCrisis standards of careIn-hospital mortalityIntensive care unitAcademic health systemSequential Organ Failure Assessment scoreCohort of intensive care unitSequential Organ Failure AssessmentStandard of careLogistic regression modelsMortality predictionPredicting in-hospital mortalityHealth systemUnivariate logistic regression modelCrisis standardsDisease morbidityCOVID-19Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications
Huang S, Jafari R, Mortazavi B. Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications. IEEE Open Journal Of Engineering In Medicine And Biology 2024, 5: 330-338. PMID: 38899025, PMCID: PMC11186651, DOI: 10.1109/ojemb.2024.3398444.Peer-Reviewed Original ResearchConceptsData preprocessing frameworkPreprocessing frameworkMachine learningInternet of Medical ThingsMean-absolute-errorHealth monitoring tasksEnd-to-endRoot-mean-square-errorMedical ThingsSensor dataAdaptation frameworkMonitoring tasksSystolic blood pressure estimationMedical tasksWearable recordingsDatasetBlood pressure estimationPulsatile signalsTaskDataMedical applicationsFrameworkInternetWearableThingsPredicting Major Adverse Events in Patients Undergoing Transcatheter Left Atrial Appendage Occlusion
Faridi K, Ong E, Zimmerman S, Varosy P, Friedman D, Hsu J, Kusumoto F, Mortazavi B, Minges K, Pereira L, Lakkireddy D, Koutras C, Denton B, Mobayed J, Curtis J, Freeman J. Predicting Major Adverse Events in Patients Undergoing Transcatheter Left Atrial Appendage Occlusion. Circulation Arrhythmia And Electrophysiology 2024, 17: e012424. PMID: 38390713, PMCID: PMC11021146, DOI: 10.1161/circep.123.012424.Peer-Reviewed Original ResearchCitationsAltmetricConceptsNational Cardiovascular Data RegistryLeft atrial appendage occlusionIn-hospital major adverse eventsMajor adverse eventsBedside risk scoreRisk scoreData RegistryIncreased fall riskAdverse eventsQuality improvement effortsWatchman FLXAppendage occlusionFall riskLeft atrial appendage occlusion procedureRegistry dataImprovement effortsRisk of in-hospital major adverse eventsPredicting major adverse eventsLogistic regressionAdverse event ratesModerate discriminationClinically relevant variablesFemale sexAtrial fibrillation terminationLAAO proceduresBiometric contrastive learning for data-efficient deep learning from electrocardiographic images
Sangha V, Khunte A, Holste G, Mortazavi B, Wang Z, Oikonomou E, Khera R. Biometric contrastive learning for data-efficient deep learning from electrocardiographic images. Journal Of The American Medical Informatics Association 2024, 31: 855-865. PMID: 38269618, PMCID: PMC10990541, DOI: 10.1093/jamia/ocae002.Peer-Reviewed Original ResearchCitationsConceptsLabeled training dataContrastive learningECG imagesLabeled dataTraining dataDeep learningProportions of labeled dataArtificial intelligenceSelf-supervised contrastive learningTraditional supervised learningConvolutional neural networkHeld-out test setSupervised learningPretraining strategyBiometric signatureImageNet initializationPretraining approachNeural networkImageNetAI modelsImage objectsTest setLearningDetect atrial fibrillationEquivalent performance
2023
Modeling user choice behavior under data corruption: Robust learning of the latent decision threshold model
Lin F, Qian X, Mortazavi B, Wang Z, Huang S, Chen C. Modeling user choice behavior under data corruption: Robust learning of the latent decision threshold model. IISE Transactions 2023, ahead-of-print: 1-14. DOI: 10.1080/24725854.2023.2279080.Peer-Reviewed Original ResearchConceptsData corruptionReal-world user dataUser-centered systemsRobust learning frameworkRobust learning methodNew mobile appUser dataUser behaviorLearning frameworkLearning methodsArt methodsMobile appsRobust learningUsers' choice behaviorPrediction accuracyBad actorsUsersNew applicationsConsiderable research effortFrameworkResearch effortsModel estimationRecent yearsAlgorithmAppsJoint Embedding of Food Photographs and Blood Glucose for Improved Calorie Estimation
Zhang L, Huang S, Das A, Do E, Glantz N, Bevier W, Santiago R, Kerr D, Gutierrez-Osuna R, Mortazavi B. Joint Embedding of Food Photographs and Blood Glucose for Improved Calorie Estimation. 2023, 00: 1-4. DOI: 10.1109/bhi58575.2023.10313421.Peer-Reviewed Original ResearchConceptsImage dataNormalized root mean squared errorCalorie estimationLate fusion approachAttention-based transformersFood image dataVision TransformerImage informationFusion approachJoint embeddingRoot mean squared errorAverage normalized root mean squared errorMean squared errorInterstitial glucose dataPeople's health conditionsDiet monitoringHealth conditionsSquared errorType 2 diabetesCGM dataInformationBlood glucoseMeal intakeFood photographsAccurate estimationArterialNet: Arterial Blood Pressure Reconstruction
Huang S, Jafari R, Mortazavi B. ArterialNet: Arterial Blood Pressure Reconstruction. 2023, 00: 1-4. DOI: 10.1109/bhi58575.2023.10313518.Peer-Reviewed Original ResearchCitations
Academic Achievements and Community Involvement
activity Reviewer
Peer Review Groups and Grant Study SectionsWireless Networks JournalJournal Reviewer for Wireless Networks JournalDetails09/01/2011 - Presentactivity Reviewer
Peer Review Groups and Grant Study SectionsIEEE Journal of Biomedical and Health InformaticsJournal ReviewerDetails09/01/2013 - Presentactivity Reviewer
Peer Review Groups and Grant Study SectionsIEEE Sensors JournalJournal ReviewerDetails01/30/2014 - Presentactivity Member
Professional OrganizationsUbicomp '14 SmartHealth WorkshopP.C. Member for WorkshopDetails06/11/2014 - 09/14/2014activity Reviewer
Peer Review Groups and Grant Study SectionsIEEE Bio-Cas ConferenceConference ReviewerDetails06/01/2014 - 08/01/2014
Links & Media
Media
- Near-Realistic Mobile Exergames with Realistic-Motion Activity Recognition for Exergames
News
Related Links