Clinical Trials

Symptomatic Management of Metastatic Cancer

PI: Ron Li, MD

Description: This exploratory Phase 1 mixed-methods study with Gilead investigates how digital tools can enhance MD-pharmacist collaboration in managing symptoms and supportive medications for patients with metastatic cancer, laying the groundwork for a potential Phase 2 implementation trial.

Alathea Study - HIT Therapy

PIs: Will Collins, MD; Robert Diep,MD

Sub-PIs: Neera Ahuja, Koorush Kabiri, Margaret Shyu

Description: ALATHEA is a multi-site, randomized, double-blind Phase 2 pilot testing VLX-1005 vs placebo on top of standard care in suspected heparin-induced thrombocytopenia, targeting reduced platelet activation and faster platelet recovery; participants receive 7–14 days of therapy with the primary endpoint of daily rate of change in platelet count.

AI Tools in Bedside Ultrasound

PIs: Andre Kumar, MD; Evan Mullen, MD

Description: This is an investigator-initiated study validating an FDA-approved AI tool for point-of-care ultrasound. We are comparing its accuracy to formal echo. We are currently collecting data.

Opportunistic Imaging for Hepatic Steatosis

Radiology Leads: Akshay Chaudhari, Robert Boutin and David Larson

Hospital Medicine Leads: Laura Derry, David Svec and Jason Hom

Hospital Medicine Co-Investigators: Andre Kumar, Jeff Ketchersid, Kathleen Jia, Thomas Lew, Lisa Shieh, Neera Ahuja

Description: This RSNA-funded research uses opportunistic imaging on routine abdominal CT scans to automatically detect hepatic steatosis, which is currently underdiagnosed based on our prior retrospective studies.

AI and Cardiovascular Care

PI: David Ouyang, MD

Stanford Site PI: Alex Sandhu, MD

Stanford Co-Investigators: Jason Hom, MD; Laura Derry, MD; Paul Heidenreich, MD; Paul Cheng, MD; Warren Sands, MD

A multi-center study is testing whether artificial intelligence can analyze standard heart ultrasound images to detect early signs of liver and kidney disease, with the goal of improving integrated cardiovascular care and earlier diagnosis using opportunistic imaging.

Improving the patient experience: LLMs for radiology results interpretation and discharge paperwork

PIs: Roxana Daneshjou, MD and Akshay Chaudhari, MD

Hospital Medicine Co-Investigator: Jason Hom, MD

Hospital Medicine Collaborators: Poonam Hosamani, MD; Kevin Keet, MD; Minjoung Go, MD; Evelyn Ling, MD; Nidhi Rohatgi, MD

Description: ARPA-Funded Study on Chatbots (including peri-discharge chatbots) to improve communication and efficiency.

Hypnosis for severe GI symptoms in hospitalized patients

Team Members: Jessie Markovits, MD; Meredith Craven-Clancy, PhD, MPH; Irene Sonu, MD

Enrollment: 26 patients randomized to hypnosis or education control

Funding: American College of Gastroenterology

Food Insecurity Reduction Strategy Team (FIRST)

Team Members: Neera Ahuja; Christine Santiago; Carol Yoon; Keith Salvado; Deedra Geniesse; Johnathan Clevinger; Neha Aidasani; Elidia Tafoya; Andre Kumar; Will Collins; Jason Hom; Keejeong Ryu; Yingjie Weng; Sumana Shashidhar; Latanya Dean; Grissel Hernandez; Priscilla Lopez; Diana Rodd; Alexandria Blacker

Description: Utilizing SDOH screening protocols to identify diabetic patients with food insecurity, we then consent patients to receive diabetic-tailored meals for 3 months and assess qualitative outcomes.

Enrollment: ~160 patients

Funding: Investigator-initiated trial

NIH RECOVER: A Multi-site Observational Study of Post-Acute Sequelae of SARS-CoV-2 Infection in Adults

Team Members: Andre Kumar, MD; Alfredo Urdanetta, MD; PJ Utz, MD

Description: This is a longitudinal cohort study looking at the risk factors, markers, and prognosis of long COVID.

Enrollment: Planning to enroll 295 participants

Funding: NIH

Gastric Ultrasound for Pre-Operative Assessment

Hospitalist faculty: Andre Kumar, MD; Evan Baum, MD; Caitlin Parmer-Chow, MD; Vishnu Nair, MD

Description: This is a sponsored study through GE Healthcare that looks at point-of-care ultrasound (pocus) to predict the risk of aspiration with general anesthesia.

Enrollment: 150 patients have been enrolled

Funding: GE Healthcare

TEACH-AI: Comparative Effectiveness of AI Curricula in Residency Training, a Randomized Controlled Trial

Hospitalist faculty: Kevin Keet, MD; Jonathan H. Chen, MD, PhD; Jason Hom, MD

Team members: Ethan Goh, MD; Ariadne Nichol, MD; Anastasia Perez Ternent

Site leads: Jacob Koshy, MD; Priyank Jain, MD; Raj Mehta, MD

Description: Previous studies from our group found that giving physicians an AI tool does not reliably improve their performance on clinical reasoning tasks, and that the physician-AI team often performs no better than the AI alone. We wondered whether teaching physicians about AI could improve their performance. TEACH-AI is a multi-site randomized trial testing whether a 45-minute workshop on using large language models improves how residents reason through clinical cases with an AI assistant. Residents work through three simulated patient cases in a purpose-built electronic health record with an AI assistant available, and are randomized to complete the cases before or after the workshop. Responses are scored by blinded physician graders. The study is conducted through the ARiSE network.

Enrollment: Planned enrollment is about 150 internal medicine and family medicine residents across four sites, including about 70 at Stanford. Enrollment opened in September 2026 and sessions run through November 2026.

Recruitment: Participation is by invitation through each residency program. Stanford internal medicine residents will receive an invitation from the study team ahead of their late October session.

Funding: Josiah Macy Jr. Foundation. Stanford IRB protocol 85976.