Evan Baum, MD
Clinical Assistant Professor, Medicine
Bio
Dr. Evan Baum is a Clinical Assistant Professor in the Division of Hospital Medicine at Stanford University. He is an academic hospitalist whose work centers on medical education, point-of-care ultrasound, and the integration of innovative technologies into bedside care. He earned his MD from the Warren Alpert Medical School of Brown University and completed his residency at Stanford University.
Dr. Baum is deeply committed to advancing point-of-care ultrasound education and scholarship. He serves as Co-Director of the Longitudinal POCUS Curriculum for internal medicine residents and as Co-Director of Education for the Stanford Hospital Medicine POCUS group, where he leads faculty development initiatives. He has taught at national POCUS CME courses, including at UCSF and UT San Antonio.
His research focuses on clinical and educational applications of POCUS, particularly the use of artificial intelligence to enhance image acquisition, diagnostic accuracy, and trainee learning. He has co-led randomized trials evaluating AI-assisted cardiac ultrasound acquisition and educational outcomes.
Dr. Baum is an active educator across the continuum of training, teaching clinical reasoning, physical diagnosis, and bedside ultrasound to medical students, physician assistant students, and residents. He is a Rathmann Family Foundation Fellow in Medical Education, where he is developing and evaluating a patient-centered communication framework to improve code status discussions.
Through his clinical work, scholarship, and leadership, Dr. Baum seeks to strengthen bedside medicine by combining rigorous education, thoughtful mentorship, and emerging technologies that improve diagnostic precision and patient-centered care.
Clinical Focus
- Internal Medicine
- Hospital Medicine
Academic Appointments
-
Clinical Assistant Professor, Medicine
Professional Education
-
Board Certification: American Board of Internal Medicine, Internal Medicine (2023)
-
Residency: Stanford University Internal Medicine Residency (2023) CA
-
Medical Education: Brown University Alpert Medical School (2020) RI
All Publications
-
Limited echocardiogram acquisition by novice clinicians aided with deep learning: A randomized controlled trial.
Biology methods & protocols
2025; 10 (1): bpaf083
Abstract
The global shortage of sonographers has created significant barriers to timely ultrasound diagnostics across medical specialties. Deep learning (DL) algorithms have potential to enhance image acquisition by clinicians without formal sonography training, potentially expanding access to crucial diagnostic imaging in resource-limited settings. This study evaluates whether DL-enabled devices improve acquisition of multi-view limited echocardiograms by healthcare providers without previous cardiac ultrasound training. In this single-center randomized controlled trial (2023-2024), internal medicine residents (N = 38) without prior sonography training received a portable ultrasound device with (N = 19) or without (N = 19) DL capability for a two-week clinical integration period during regular patient care on hospital wards. The DL software provided real-time guidance for probe positioning and image quality assessment across five standard echocardiographic views. The primary outcome was total acquisition time for a comprehensive five-view limited echocardiogram (parasternal long axis, parasternal short axis, apical 4-chamber, subcostal, and inferior vena cava views). Assessments occurred at randomization and after two weeks using a standardized patient. Secondary outcomes included image quality using a validated assessment tool and participant attitudes toward the technology. Baseline scan times and image quality scores were comparable between groups. At two-week follow-up, participants using DL-equipped devices demonstrated significantly faster total scan times (152 s [IQR 115-195] versus 266 s [IQR 206-324]; P < 0.001; Cohen's D = 1.7) and superior image quality with higher modified RACE scores (15 [IQR 10-18] versus 11 [IQR 7-13.5]; P = 0.034; Cohen's D = 0.84). Performance improvements were most pronounced in technically challenging views. Both groups reported similar levels of trust in DL-functionality. Ultrasound devices incorporating deep learning algorithms significantly improve both acquisition speed and image quality of comprehensive echocardiographic examinations by novice users. These findings suggest DL-enhanced ultrasound may help address critical gaps in diagnostic imaging capacity by enabling non-specialists to acquire clinically useful cardiac images.
View details for DOI 10.1093/biomethods/bpaf083
View details for PubMedID 41268207
View details for PubMedCentralID PMC12627401
-
Acquisition of Cardiac Point-of-Care Ultrasound Images With Deep Learning: A Randomized Trial for Educational Outcomes With Novices
CHEST Pulmonary
2023; 1 (3)
View details for DOI 10.1016/j.chpulm.2023.100023
-
Positron Emission Tomography Imaging Evaluation of a Novel 18F-Labeled Sigma-1 Receptor Radioligand in Cynomolgus Monkeys.
ACS chemical neuroscience
2020; 11 (11): 1673-1681
Abstract
We report a convenient radiosynthesis and the first positron emission tomography (PET) imaging evaluation of [18F]FBFP as a potent sigma-1 (σ1) receptor radioligand with advantageous characteristics. [18F]FBFP was synthesized in one step from an iodonium ylide precursor. In cynomolgus monkeys, [18F]FBFP displayed high brain uptake and suitable tissue kinetics for quantitative analysis. It exhibited heterogeneous distribution with higher regional volume of distribution (VT) values in the amygdala, hippocampus, insula, and frontal cortex. Pretreatment with the σ1 receptor agonist SA4503 (0.5 mg/kg) significantly reduced radioligand uptake in the monkey brain (>95%), indicating high binding specificity of [18F]FBFP in vivo. Compared with (S)-[18F]fluspidine, [18F]FBFP possessed higher regional nondisplaceable binding potential (BPND) values across the brain regions. These findings demonstrate that [18F]FBFP is a highly promising PET radioligand for imaging and quantification of σ1 receptors in humans.
View details for DOI 10.1021/acschemneuro.0c00171
View details for PubMedID 32356969
-
Synthesis and Preclinical Evaluation of an 18F-Labeled Synaptic Vesicle Glycoprotein 2A PET Imaging Probe: [18F]SynVesT-2.
ACS chemical neuroscience
2020; 11 (4): 592-603
Abstract
Synaptic vesicle glycoprotein 2A (SV2A) is a 12-pass transmembrane glycoprotein ubiquitously expressed in presynaptic vesicles. In vivo imaging of SV2A using PET has potential applications in the diagnosis and prognosis of a variety of neuropsychiatric diseases, e.g., Alzheimer's disease, Parkinson's disease, schizophrenia, multiple sclerosis, autism, epilepsy, stroke, traumatic brain injury, post-traumatic stress disorder, depression, etc. Herein, we report the synthesis and evaluation of a new 18F-labeled SV2A PET imaging probe, [18F]SynVesT-2, which possesses fast in vivo binding kinetics and high specific binding signals in non-human primate brain.
View details for DOI 10.1021/acschemneuro.9b00618
View details for PubMedID 31961649
-
A Novel 18F-Labeled Radioligand for Positron Emission Tomography Imaging of 11β-Hydroxysteroid Dehydrogenase (11β-HSD1): Synthesis and Preliminary Evaluation in Nonhuman Primates.
ACS chemical neuroscience
2019; 10 (5): 2450-2458
Abstract
11β-Hydroxysteroid dehydrogenase type 1 (11β-HSD1) catalyzes the conversion of cortisone to cortisol and controls a key pathway in the regulation of stress. Studies have implicated 11β-HSD1 in metabolic diseases including type 2 diabetes and obesity, as well as stress-related disorders and neurodegenerative diseases, such as depression and Alzheimer's disease (AD). We have previously developed [11C]AS2471907 as a PET radiotracer to image 11β-HSD1 in the brain of nonhuman primates and humans. However, the radiosynthesis of [11C]AS2471907 was unreliable and low-yielding. Here, we report the development of the 18F-labeled version [18F]AS2471907, including the synthesis of two iodonium ylide precursors and the optimization of 18F-radiosynthesis. Preliminary PET experiments, composed of a baseline scan of [18F]AS2471907 and a blocking scan with the reversible 11β-HSD1 inhibitor ASP3662 (0.3 mg/kg), was also conducted in a rhesus monkey to verify the pharmacokinetics of [18F]AS2471907 and its specific binding in the brain. The iodonium ylide precursors were prepared in a seven-step synthetic route with an optimized overall yield of ∼2%. [18F]AS2471907 was synthesized in good radiochemical purity, with the ortho regioisomer of iodonium ylide providing greater radiochemical yield as compared with the para regioisomer. In monkey brain, [18F]AS2471907 displayed high uptake and heterogeneous distribution, while administration of the 11β-HSD1 inhibitor ASP3662 significantly reduced radiotracer uptake, thus demonstrating the binding specificity of [18F]AS2471907. Given the longer half-life of F-18 and feasibility for central production and distribution, [18F]AS2471907 holds great promise to be a valuable PET radiotracer to image 11β-HSD1 in the brain.
View details for DOI 10.1021/acschemneuro.8b00715
View details for PubMedID 30689943
-
PET Imaging Evaluation of Four σ1 Radiotracers in Nonhuman Primates.
Journal of nuclear medicine : official publication, Society of Nuclear Medicine
2017; 58 (6): 982-988
Abstract
The σ1 receptors (S1Rs) are implicated in a variety of diseases including Alzheimer disease and cancer. Previous PET S1R radiotracers are characterized by slow kinetics or off-target binding that impedes their use in humans. Here, we report the first PET imaging evaluation in rhesus monkeys of 4 18F-labeled spirocyclic piperidine-based PET radiotracers (18F-1 to 18F-4). Methods: Baseline scans for the 4 radiotracers were obtained on an adult male rhesus monkey. Blocking scans were obtained with the S1R-selective agonist SA4503 to assess binding specificity of 18F-2 and 18F-4 Arterial input functions were measured, and binding parameters were determined with kinetic modeling analysis. Results: In the rhesus brain, all 4 radiotracers showed high and fast uptake. Tissue activity washout was rapid for 18F-2 and 18F-4, and much slower for 18F-1 and 18F-3, in line with their respective in vitro S1R-binding affinities. Both the 1-tissue-compartment and multilinear analysis-1 kinetic models provided good fits of time-activity curves and reliable estimates of distribution volume. Regional distribution volume values were highest in the cingulate cortex and lowest in the thalamus for all radiotracers. 18F-4 showed greater differential uptake across brain regions and 3-fold-higher binding potential than 18F-2 SA4503 at the dose of 0.5 mg/kg blocked approximately 85% (18F-2) and 95% (18F-4) of radiotracer binding. Conclusion: Tracers 18F-2 and 18F-4 displayed high brain uptake and fast tissue kinetics, with 18F-4 having higher specific binding signals than 18F-2 in the same monkey. Taken together, these data indicate that both 18F-2 and 18F-4 possess the requisite kinetic and imaging properties as viable PET tracers for imaging S1R in the human brain.
View details for DOI 10.2967/jnumed.116.188052
View details for PubMedID 28232607
-
Imaging synaptic density in the living human brain.
Science translational medicine
2016; 8 (348): 348ra96
Abstract
Chemical synapses are the predominant neuron-to-neuron contact in the central nervous system. Presynaptic boutons of neurons contain hundreds of vesicles filled with neurotransmitters, the diffusible signaling chemicals. Changes in the number of synapses are associated with numerous brain disorders, including Alzheimer's disease and epilepsy. However, all current approaches for measuring synaptic density in humans require brain tissue from autopsy or surgical resection. We report the use of the synaptic vesicle glycoprotein 2A (SV2A) radioligand [(11)C]UCB-J combined with positron emission tomography (PET) to quantify synaptic density in the living human brain. Validation studies in a baboon confirmed that SV2A is an alternative synaptic density marker to synaptophysin. First-in-human PET studies demonstrated that [(11)C]UCB-J had excellent imaging properties. Finally, we confirmed that PET imaging of SV2A was sensitive to synaptic loss in patients with temporal lobe epilepsy. Thus, [(11)C]UCB-J PET imaging is a promising approach for in vivo quantification of synaptic density with several potential applications in diagnosis and therapeutic monitoring of neurological and psychiatric disorders.
View details for DOI 10.1126/scitranslmed.aaf6667
View details for PubMedID 27440727
-
Highly tin-selective stille coupling: synthesis of a polymer containing a stannole in the main chain.
Angewandte Chemie (International ed. in English)
2014; 53 (47): 12916-20
Abstract
The incorporation of heavier Group 14 element heteroles into semiconducting polymers leads to unusual optoelectronic properties. However, polymers containing stannoles have not been accessible to date. We report a synthetic route to a well-defined, stannole-containing polymer, the first example of this class of π-conjugated polymers. This route was made possible by developing difunctionalized stannole monomers and highly tin-selective Stille coupling reactions that leave the tin in the stannole untouched. Compared to poly(3-n-hexylthiophene), the resulting polymer displays a remarkable bathochromic shift in its absorption.
View details for DOI 10.1002/anie.201407377
View details for PubMedID 25258154
https://orcid.org/0000-0002-0998-1293