RWRory B. Weiner

Rory B. Weiner

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Rory B. Weiner has a total of 63 co-authors. Here are the top co-authors by number of shared publications:

  • Michael H. Picard

    Massachusetts General Hospital

    7 shared publications
  • Aaron L. Baggish

    Harvard Medical School, Massachusetts General Hospital

    6 shared publications
  • Adolph M. Hutter

    From the Cardiovascular Performance Program, Massachusetts General Hospital, Boston (R.B.W., J.R.D., J.L., M.M.W., G.D.L., A.M.H., M.H.P., A.L.B.); Harvard University Health Services, Cambridge, MA (R.B.W., F.W., B.B., A.L.B.); and Cardiff School of Sport, Cardiff Metropolitan University, Cardiff, United Kingdom (E.S., R.S.).

    5 shared publications
  • Francis Wang

    From the Cardiovascular Performance Program, Massachusetts General Hospital, Boston (R.B.W., J.R.D., J.L., M.M.W., G.D.L., A.M.H., M.H.P., A.L.B.); Harvard University Health Services, Cambridge, MA (R.B.W., F.W., B.B., A.L.B.); and Cardiff School of Sport, Cardiff Metropolitan University, Cardiff, United Kingdom (E.S., R.S.).

    5 shared publications
  • Aaron L. Baggish

    Swiss Olympic Medical Center, Lausanne University Hospital (CHUV), Lausanne, Switzerland; Institute for Sport Science, University of Lausanne (ISSUL), Lausanne, Switzerland

    4 shared publications
  • Malissa J. Wood

    3 shared publications

Latest Publications

  • Cardiomyopathies: Dilated, Restrictive/Infiltrative, and Hypertrophic Cardiomyopathies

    by Timothy W. Churchill, Aaron L. Baggish, Rory B. Weiner

  • Personalized treatment for coronary artery disease patients: a machine learning approach

    by Dimitris Bertsimas, Agni Orfanoudaki, Rory B. Weiner

    Current clinical practice guidelines for managing Coronary Artery Disease (CAD) account for general cardiovascular risk factors. However, they do not present a framework that considers personalized patient-specific characteristics. Using the electronic health records of 21,460 patients, we created data-driven models for personalized CAD management that significantly improve health outcomes relative to the standard of care. We develop binary classifiers to detect whether a patient will experience an adverse event due to CAD within a 10-year time frame. Combining the patients’ medical history and clinical examination results, we achieve 81.5% AUC. For each treatment, we also create a series of regression models that are based on different supervised machine learning algorithms. We are able to estimate with average R2 = 0.801 the outcome of interest; the time from diagnosis to a potential adverse event (TAE). Leveraging combinations of these models, we present ML4CAD, a novel personalized prescriptive algorithm. Considering the recommendations of multiple predictive models at once, the goal of ML4CAD is to identify for every patient the therapy with the best expected TAE using a voting mechanism. We evaluate its performance by measuring the prescription effectiveness and robustness under alternative ground truths. We show that our methodology improves the expected TAE upon the current baseline by 24.11%, increasing it from 4.56 to 5.66 years. The algorithm performs particularly well for the male (24.3% improvement) and Hispanic (58.41% improvement) subpopulations. Finally, we create an interactive interface, providing physicians with an intuitive, accurate, readily implementable, and effective tool.


  • Open Access

    Detection and Characterization of Thrombosis in Humans using Fibrin-Targeted Positron Emission Tomography and Magnetic Resonance

    by David Izquierdo-Garcia, Pauline Désogère, Anne L. Philip, Choukri Mekkaoui, Rory B. Weiner, Onofrio A. Catalano, Yin-Ching Iris Chen, Doreen DeFaria Yeh, Moussa Mansour, Ciprian Catana, et al.

    The detection of thrombus in the left atrial appendage (LAA) is vital in the prevention of stroke. We present a novel technique to detect and characterize LAA thrombus in humans using positron emission tomography (PET) of a fibrin-binding radiotracer, [ 64 Cu]FBP8. Initial testing in healthy volunteers (n = 8) revealed that [ 64 Cu]FBP8 was stable to metabolism and was rapidly eliminated with a blood half-life of one hour. Patients with atrial fibrillation (AF) and recent transesophageal echocardiograms (TEEs) of the LAA (positive n = 12, negative n = 12) were studied. PET, integrated with magnetic resonance (PET-MR), of the thorax was performed one hour after [ 64 Cu]FBP8 injection. The maximum standardized uptake value (SUV Max ) in the LAA was significantly higher in the TEE positive than negative subjects, median [interquartile range] of 4.0 [3.0–6.0] vs. 2.3 [2.1–2.5]; p < 0.001. A SUV Max threshold of 2.6 correctly identified 12/12 positive TEEs and 10/12 negative ones, yielding an area-under-the-receiver operating characteristic curve of 0.97. The minimum longitudinal magnetic relaxation time (T1 Min ) in the LAA was significantly shorter in the TEE positive than TEE negative group 970 [780–1080] vs. 1380 [1120–1620], p < 0.05, with some overlap between the groups. Logistic regression using SUV Max and T1 Min allowed all TEE positive and negative subjects to be classified with 100% accuracy. A strong correlation was seen between fibrin (SUV Max ) and methemoglobin (T1 Min ) content in the LAA. In conclusion, the detection of LAA thrombus in humans with PET-MR of [ 64 Cu]FBP8 is highly accurate and provides useful information on the biological properties of cardiac thrombus. One Sentence Summary: First-in-human fibrin-targeted PET-MR of thrombus


  • Open Access

    Personalized Treatment for Coronary Artery Disease Patients: A Machine Learning Approach

    by Dimitris Bertsimas, Agni Orfanoudaki, Rory B. Weiner

    Current clinical practice guidelines for managing Coronary Artery Disease (CAD) account for general cardiovascular risk factors. However, they do not present a framework that considers personalized patient-specific characteristics. Using the electronic health records of 21,460 patients, we created data-driven models for personalized CAD management that significantly improve health outcomes relative to the standard of care. We develop binary classifiers to detect whether a patient will experience an adverse event due to CAD within a 10-year time frame. Combining the patients' medical history and clinical examination results, we achieve 81.5% AUC. For each treatment, we also create a series of regression models that are based on different supervised machine learning algorithms. We are able to estimate with average R squared = 0.801 the time from diagnosis to a potential adverse event (TAE) and gain accurate approximations of the counterfactual treatment effects. Leveraging combinations of these models, we present ML4CAD, a novel personalized prescriptive algorithm. Considering the recommendations of multiple predictive models at once, ML4CAD identifies for every patient the therapy with the best expected outcome using a voting mechanism. We evaluate its performance by measuring the prescription effectiveness and robustness under alternative ground truths. We show that our methodology improves the expected TAE upon the current baseline by 24.11%, increasing it from 4.56 to 5.66 years. The algorithm performs particularly well for the male (24.3% improvement) and Hispanic (58.41% improvement) subpopulations. Finally, we create an interactive interface, providing physicians with an intuitive, accurate, readily implementable, and effective tool.

  • Trials of Quality Improvement in Imaging

    by Kavitha M. Chinnaiyan, Rory B. Weiner


  • Exercise-Induced Left Ventricular Remodeling Among Competitive Athletes

    by Rory B. Weiner, James R. DeLuca, Francis Wang, Jeffrey Lin, Meagan M. Wasfy, Brant Berkstresser, Eric Stöhr, Rob Shave, Gregory D. Lewis, Adolph M. Hutter, et al.

    Background—: Contemporary understanding of exercise-induced cardiac remodeling is based on cross-sectional data and relatively short duration longitudinal studies. Temporal progression of exercise-induced cardiac remodeling remains incompletely understood. Methods and Results—: A longitudinal repeated-measures study design using 2-dimensional and speckle-tracking echocardiography was used to examine acute augmentation phase (AAP; 90 days) and more extended chronic maintenance phase (39 months) left ventricular (LV) structural and functional adaptations to endurance exercise training among competitive male rowers (n=12; age 18.6±0.5 years). LV mass was within normal limits at baseline (93±9 g/m 2 ), increased after AAP (105±7 g/m 2 ; P =0.001), and further increased after chronic maintenance phase (113±10 g/m 2 ; P 2 ; P =0.004) with stable LV wall thickness (ΔLV wall thickness, 0.3±0.1 mm; P =0.63). In contrast, chronic maintenance phase LV hypertrophy was attributable to LV wall thickening (Δ LV wall thickness, 1.1±0.4 mm; P =0.004) with stable LV chamber volumes (ΔLV end-diastolic volume, 1±1 mL/m 2 ; P =0.48). Early diastolic peak tissue velocity increased during AAP (−11.7±1.9 versus −13.6±1.3 cm/s; P <0.001) and remained similarly increased after chronic maintenance phase. Conclusions—: In a small sample of competitive endurance athletes, exercise-induced cardiac remodeling follows a phasic response with increases in LV chamber size, early diastolic function, and systolic twist in an acute augmentation phase of exercise training. This is followed by a chronic phase of adaptation characterized by increasing wall thickness and regression in LV twist. Training duration is a determinant of exercise-induced cardiac remodeling and has implications for the assessment of myocardial structure and function in athletes.


  • Acute versus chronic exercise-induced left-ventricular remodeling

    by Rory B Weiner, Aaron L Baggish

    Exercise-induced cardiac remodeling (EICR) is the process by which the heart adapts to the physiologic stress of exercise. Non-invasive cardiovascular imaging has led to advances in the understanding of EICR, with sport-specific changes in left-ventricular (LV) structure and function being described; however, the majority of data stem from cross-sectional and short-duration longitudinal studies. Due to the paucity of long-term longitudinal EICR studies, the time course of this process and any distinct differentiation between acute and chronic adaptations remain largely unexplored. In order to clarify the natural history of EICR, longer duration longitudinal study is required. Such work will determine whether exercise-induced changes in myocardial structure and function occur in discrete stages. Examination of prolonged exposures to exercise training will also be necessary to determine normative values across the age and training spectrums of athletic patients. This information will help to distinguish the boundary between physiology and pathology in athletic patients.


  • Educational Intervention to Reduce Outpatient Inappropriate Echocardiograms

    by R. Sacha Bhatia, David M. Dudzinski, Rajeev Malhotra, Creagh E. Milford, Danita M. Yoerger Sanborn, Michael H. Picard, Rory B. Weiner