
William Hiesinger
VerifiedStanford University · Rheumatology
Active 2006–2026
About
William Hiesinger is an Assistant Professor of Cardiothoracic Surgery (Adult Cardiac Surgery) at the Stanford University Medical Center. He is affiliated with the Center for Artificial Intelligence in Medicine & Imaging (AIMI) at Stanford University. His professional focus involves integrating artificial intelligence into the field of medicine and imaging, contributing to research and education in this interdisciplinary area. Further details about his specific research contributions or background are not provided on the page.
Research topics
- Medicine
- Cardiology
- Internal medicine
- Computer Science
- Surgery
- Artificial Intelligence
- Radiology
- Pathology
- Political Science
- Emergency medicine
- Biology
- Intensive care medicine
- Medical education
- Genetics
Selected publications
JACC Case Reports · 2026-04-04
articleOpen accessBACKGROUND: Late coronary anastomotic complications after Cabrol composite graft repair for aortic dissection are rare and pose unique revascularization challenges. CASE SUMMARY: A 72-year-old man with a prior Cabrol composite mechanical aortic graft presented with progressive exertional angina and dyspnea. Stress imaging showed extensive ischemia. Coronary angiography revealed occlusion of the right Cabrol limb and a severely calcified stenosis at the left coronary anastomosis, jeopardizing global coronary supply. After multidisciplinary planning, high-risk percutaneous coronary intervention was undertaken with standby extracorporeal membrane oxygenation support. Conventional balloon techniques failed to sufficiently modify the lesion. Intravascular ultrasound demonstrated dense circumferential calcification at the anastomotic site. Intravascular lithotripsy enabled partial lesion preparation, permitting successful drug-eluting stent deployment. DISCUSSION: This case highlights multiple unique interventional challenges in a single-remaining-vessel situation with limited hemodynamic support options. TAKE-HOME MESSAGE: Intravascular imaging and lithotripsy enabled successful high-risk percutaneous coronary intervention of a heavily calcified Cabrol graft.
A generalizable deep learning system for cardiac MRI
Nature Biomedical Engineering · 2026-03-25 · 3 citations
preprintOpen accessSenior authorCardiac MRI allows for a comprehensive assessment of myocardial structure, function and tissue characteristics. Here we describe a foundational vision system for cardiac MRI, capable of representing the breadth of human cardiovascular disease and health. Our deep-learning model is trained via self-supervised contrastive learning, in which visual concepts in cine-sequence cardiac MRI scans are learned from the raw text of the accompanying radiology reports. We train and evaluate our model on data from four large academic clinical institutions in the United States. We additionally showcase the performance of our models on the UK BioBank and two additional publicly available external datasets. We explore emergent capabilities of our system and demonstrate remarkable performance across a range of tasks, including the problem of left-ventricular ejection fraction regression and the diagnosis of 39 different conditions such as cardiac amyloidosis and hypertrophic cardiomyopathy. We show that our deep-learning system is capable of not only contextualizing the staggering complexity of human cardiovascular disease but can be directed towards clinical problems of interest, yielding impressive, clinical-grade diagnostic accuracy with a fraction of the training data typically required for such tasks.
Almanac Copilot: Towards Autonomous Electronic Health Record Navigation
Research Square · 2025-03-18 · 3 citations
preprintOpen accessSenior authorClinical Transplantation · 2025-06-01 · 2 citations
articleOpen accessABSTRACT Introduction Consensus regarding what defines acceptable heart transplant (HT) donors or recipients is lacking. This survey analyzed how risk factors guide donor and recipient selection, and how practices vary across systems. Methods An online survey was conducted among adult HT centers in the US and Eurotransplant (ET) region. We aimed to represent at least 50% of the total adult HT volumes in both regions. Centers were stratified by their HT volumes. To compensate for non‐responders, a safety margin was included, and centers accounting for at least 75% of the total HT volumes were contacted. Centers were queried on relative thresholds and absolute cutoffs for continuous risk factors. For other factors, their influence on donor heart acceptance or the likelihood of listing recipients was assessed. Results Fifty‐three centers from five countries participated: 39 US (accounting for 51.0% of the US HT volume), and 14 ET centers (65.0%) from four countries. ET centers more liberally considered advanced age donor hearts (threshold 64.5 [60.0–70.0] vs. 50.0 [50.0–55.0] years, p < 0.001), and hearts with abnormal echocardiography or coronary findings. Diabetes, smoking, and hypertension were rated by a quarter to more than half of US and ET centers as moderately or heavily influencing donor heart acceptance. ET centers more liberally listed candidates with chronic kidney disease (GFR 30.0 [21.5–32.5] vs. 35.0 [30.0–40.0] mL/min/1.73m 2 , p < 0.001). US centers, conversely, allowed for higher candidate ages (71.5 [70.0–74.0] vs. 68.0 [65.0–70.0] years, p < 0.001), and more likely (76.9%) listed candidates on ECMO support (42.9% of ET centers to less likely list, p = 0.022). Conclusion Selection practices differed distinctly between the US and ET. Further, practices appear to be driven by caution and are more conservative than current guidelines. Strengthening the evidence base to objectify and optimize donor and candidate selection could help alleviate the unmet need for donor hearts.
JACC: Cardiovascular Interventions · 2025-10-01 · 1 citations
articleArteriosclerosis Thrombosis and Vascular Biology · 2025-03-20 · 4 citations
articleOpen accessBACKGROUND: Loeys-Dietz syndrome (LDS), caused by mutations in the TGF-β (transforming growth factor-β) signaling cascade, leads to aggressive thoracic aneurysms. While vascular smooth muscle cell (SMC) phenotype modulation has been implicated in thoracic aneurysm formation, we sought to characterize the role of cell state transitions in LDS aneurysm pathogenesis. METHODS: We performed single-cell transcriptomic characterization of aortic root/ascending aorta from a murine LDS model ( Tgfbr2 G357W/+ versus littermate WT [wild-type] control) at 8 weeks, 24 weeks, and aortic root/ascending aortic samples from human LDS surgical specimens (n=5 LDS [ TGFBR1/2 ] and n=2 donor control) to understand cell state transitions and transcriptomic alterations in LDS. Select cell markers were spatially localized with RNA in situ hybridization, immunofluorescence, and immunohistochemistry. Single-cell RNA sequencing of murine and human LDS samples (>30 000 cells) revealed unique SMC, fibroblast, and macrophage transcriptomic profiles in LDS. RESULTS: Instead of SMC phenotypic modulation seen in Marfan syndrome, transcriptomic alterations observed in LDS are most prominent in the adventitial fibroblast in the Tgfbr2 G357W/+ mouse model. While a distinct modulated SMC cluster does not appear in Tgfbr2 G357W/+ , SMCs transcriptomically differ from WT counterparts. Adventitial fibroblasts were activated into a proinflammatory state associated with increased macrophage recruitment ( Ccl2 , Il6 , Ccl7 , and Cxcl2 ) and fibrotic response genes ( Col1a1 , Col1a2 , and Col3a1 ), with a 6-fold increase in aortic wall macrophage content in Tgfbr2 G357W/+ compared with WT. Similar findings were also observed in human LDS aortic samples with increased proinflammatory adventitial fibroblast transcriptomic program in parallel with heightened macrophage recruitment. CONCLUSIONS: Despite phenotypic similarities in aneurysm formation, the dominant cellular and molecular mechanism of Marfan syndrome and LDS aneurysms are distinct. LDS mouse and human adventitial fibroblasts transcriptomically modulate into a proinflammatory state. Adventitial fibroblasts, in addition to SMCs, are another important pathological cell population during LDS aneurysm formation to consider for targeted therapy to potentially impede LDS aneurysm formation.
The Journal of Heart and Lung Transplantation · 2025-04-01
articleOpen accessThe Journal of Heart and Lung Transplantation · 2025-04-01
articleOpen accessClinical Transplantation · 2025-07-28
articleABSTRACT As the prevalence of heart failure continues to rise, left ventricular assist devices (LVADs) have become an increasingly common treatment option for patients, demonstrating significant improvements in patient survival. LVAD therapy is also known to induce reverse remodeling, and its underlying mechanisms have garnered attention. This study examines the experience of end‐stage heart failure patients who underwent HeartWare LVAD (HVAD, Medtronic Inc, Minneapolis, MN, USA) implantation. The patients were categorized into responder and non‐responder groups to investigate the impact of LVAD therapy on hemodynamics, ventricular geometry, and transcriptomics in the heart before and after HVAD therapy. In the responder group, significant reductions in left ventricular size and improvements in left ventricular ejection fraction were observed. Furthermore, subtle enhancements in calcium cycling and unique gene expression changes were observed, which were notably different from the patterns observed in the non‐responder group.
The Role of Genetic Variants in Patients Undergoing Left Ventricular Assist Device Placement
The Journal of Heart and Lung Transplantation · 2025-04-01
article
Frequent coauthors
- 91 shared
Y. Joseph Woo
Stanford University
- 56 shared
Yasuhiro Shudo
Stanford University
- 53 shared
John W. MacArthur
- 44 shared
Rohan Shad
- 42 shared
Pavan Atluri
University of Pennsylvania
- 40 shared
Jeffrey J. Teuteberg
- 31 shared
Jack H. Boyd
- 27 shared
Robyn Fong
Stanford Medicine
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with William Hiesinger
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup