Bio
Alex Weihan Chu, M.D. is a Clinical Assistant Professor at Stanford University School of Medicine and Associate Chief Medical Officer and Vice President for Clinical Affairs, Quality, and Health Equity at Stanford Health Care – Tri-Valley.
Dr. Chu joined Tri-Valley as an academic hospitalist in 2015 after completing his internal medicine residency at Stanford. He served as a Clinical Instructor from 2015 to 2018 and has been a Clinical Assistant Professor since 2018. He is board-certified in Internal Medicine and Clinical Informatics and has served as Tri-Valley’s Medical Informatics Director since 2016.
In his current executive role, which began in 2024, Dr. Chu provides clinical leadership for medical staff quality, patient safety, and performance improvement. He chairs the Joint Quality Council, co-leads Unit-Based Medical Director engagement, and leads strategic work in employee engagement and physician wellness, community partnerships and health equity, and digital innovation. His responsibilities also include clinical affairs, specialty coverage planning, physician agreements, and directorships. In 2026, he became executive sponsor for Support Services II (Telecom, TDS, and BioMed) in the Highly Reliable Patient Centered Care management system launch.
Dr. Chu previously served as Associate Chief Medical Officer for Patient Safety, Infection Control, and Regulatory Compliance (2022–2024) and Vice Chief of Medicine (2021–2023). His work spans accreditation readiness, clinical documentation, transfusion safety, physician engagement, and clinical workflow redesign. He founded the Clinician Builder Program in 2019 and the Health Information Management Services Committee in 2020. His projects include telemedicine services, digital procedure consents, clinical decision support, order set optimization, and support for the Tri-Valley neurosurgery program launch planned for December 2026.
Dr. Chu is a reviewer for Applied Clinical Informatics and received the Division of Hospital Medicine’s Excellence in Interprofessional Practice Award in 2025. His professional development includes the Stanford Leadership Development Program (2024) and the Just Culture Conduct Course for Healthcare Managers & Influencers offered by The Just Culture Company (2026).
Outside of work, Dr. Chu enjoys hiking, scuba diving, photography, and exploring advancements in technology.
Clinical Focus
- Hospital Medicine
- Internal Medicine
- Clinical Informatics
Academic Appointments
-
Clinical Assistant Professor, Medicine
Administrative Appointments
-
Co-Chair, Physician IT Advisory Committee, Stanford Health Care – Tri-Valley (2018 - 2020)
-
Member, Provider OnCall and Advanced Scheduling Executive Steering Committee, Stanford Health Care / Stanford Health Care – Tri-Valley (2025 - Present)
-
Executive Sponsor, HRPCC Support Services II (Telecom, TDS, BioMed), Stanford Health Care – Tri-Valley (2026 - Present)
-
Associate Chief Medical Officer and Vice President for Clinical Affairs, Quality, and Health Equity, Stanford Health Care – Tri-Valley (2024 - Present)
-
Associate Chief Medical Officer for Patient Safety, Infection Control, and AR&L., SHC Tri-Valley Hospital (2022 - 2024)
-
Vice Chief of Medicine, SHC Tri-Valley Hospital (2021 - 2023)
-
Medical Informatics Director for SHC Tri-Valley Hospital, Stanford Health Care (2016 - Present)
-
Co-Chair, Clinical Decision Support Committee, SHC Tri-Valley Hospital (2016 - Present)
-
Founder and Chair, Health Information Management Services (HIMS) Committee, SHC Tri-Valley Hospital (2020 - 2025)
-
Founder and Lead, Clinician Builder Program, Stanford Health Care (2019 - Present)
-
Member, Credentialing Committee, SHC Tri-Valley Hospital (2020 - 2022)
-
Member-at-Large, Medical Executive Committee, SHC Tri-Valley Hospital (2020 - 2022)
-
ValleyCare Downtime Governance Committee, SHC Tri-Valley Hospital (2018 - Present)
-
Clinical Applications Steering Committee, SHC Tri-Valley Hospital (2016 - 2018)
-
Member, Medical Staff Quality Committee, SHC Tri-Valley Hospital (2016 - 2018)
Honors & Awards
-
Excellence in Interprofessional Practice Award, Division of Hospital Medicine, Stanford School of Medicine (2025)
Professional Education
-
Board Certification: American Board of Internal Medicine, Internal Medicine (2015)
-
Board Certification: American Board of Preventive Medicine, Clinical Informatics (2021)
-
Certification, Epic Systems, Physician Builder (2017)
-
Residency: Stanford University Internal Medicine Residency (2015) CA
-
Internship: Stanford University Internal Medicine Residency (2013) CA
-
Medical Education: Case Western Reserve School of Medicine (2012) OH
-
BA, Johns Hopkins University, Biophysics (2007)
Community and International Work
-
Baltimore Rescue Mission Homeless Shelter — Patient Educator (2004–2007)
Partnering Organization(s)
Baltimore Rescue Mission Homeless Shelter
Ongoing Project
No
Opportunities for Student Involvement
No
-
Tri-City Homeless Coalition — After-School Program Volunteer (2007–2008)
Partnering Organization(s)
Tri-City Homeless Coalition
Ongoing Project
No
Opportunities for Student Involvement
No
-
Physical Diagnosis Course — Student Preceptor (2011–2012)
Ongoing Project
No
Opportunities for Student Involvement
No
-
Pacific Free Clinic — Medical Student Preceptor (2012–2015)
Partnering Organization(s)
Pacific Free Clinic
Ongoing Project
No
Opportunities for Student Involvement
No
Projects
-
Neurosurgery Program Launch at Tri-Valley — Launch Support, Stanford Health Care – Tri-Valley
Supports the launch of the Tri-Valley neurosurgery program, with program start in fall 2026 and launch planned for December 2026. Supports the Epic order set build, including a new ICU neurosurgery postoperative order set, and assists OR leadership, ICU, pharmacy, and nursing with competency and readiness for intracranial medication administration workflows.
Location
Pleasanton, CA
-
Telemedicine Consult Services, Stanford Health Care – Tri-Valley
2019–Present. Launched telemedicine consult services for transplant, addiction, psychiatry, hepatology, and neurology. Evaluated and implemented the Tri-Valley telepsychiatry service (2020–2021) and led the extension of Addiction Medicine to Tri-Valley via telemedicine (2024). Led a teledermatology feasibility assessment in 2024; launch was deferred pending capacity and a sustainable financial model. Led the ED telepsychiatry request for proposal in 2026, evaluating five vendors, and advanced 24/7 behavioral health coverage and HL7/Epic integration.
Location
Pleasanton, CA
-
Anesthesia Services Transition to Stanford Medicine Partners — Lead, Stanford Health Care – Tri-Valley
2025–2026. Analyzed the existing anesthesia service model and developed the rationale for transition to Stanford Medicine Partners to align with Stanford quality infrastructure, MPOG dashboards, ICDP participation, and enterprise recruitment pathways. Named presenter to the Medical Executive Committee in June 2026 and an ad hoc Board of Directors meeting in September 2026.
Location
Pleasanton, CA
-
Emergency Medicine Contract Review and Transition Planning — Lead, Stanford Health Care – Tri-Valley
2025–2026. Developed the business case for a potential transition of Emergency Medicine services to Stanford Medicine Partners, addressing quality metrics, coverage continuity, and strategic alignment. Led the Medical Executive Committee governance process and co-presented to MEC and the Board of Directors. The outcome was renewal of the existing Emergency Medicine arrangement, with transition planning to reconvene in January 2027.
Location
Pleasanton, CA
-
Inpatient Oncology Service Development — Co-Lead, Stanford Health Care – Tri-Valley
2025–2026. Co-lead and lead author of the phased implementation framework. Co-designed with David Svec and Kavitha Jennifer Ramchandran a three-phase plan for inpatient oncology consultation and co-management at Tri-Valley, progressing from APP-based coordination to a seven-day inpatient oncology service. Conducted a gap analysis presented in May 2026 and co-led operational design, Epic/QGenda on-call integration planning, and nursing competency requirements.
Location
Pleasanton, CA
-
Just Culture Re-implementation Program — Co-Lead, Stanford Health Care – Tri-Valley
2025–2026. Helped drive Tri-Valley’s re-engagement with the Just Culture Company, aligned with Stanford Medicine Partners and Stanford Health Care, as part of the Highly Reliable Patient Centered Care initiative. Supported identification of champions, charter development, and formation of a cross-functional guiding coalition. The roadmap spans mobilization in 2026 through enterprise scale and sustainment in 2027–2028 and beyond.
Location
Pleasanton, CA
-
New Procedure Process (NPP) — Patient Safety Triage Tool (PSTT) — Co-Developer, Stanford Health Care – Tri-Valley
2025–2026. Co-developed an institutional framework for evaluating new clinical procedures before they reach patients, informed by HFMEA, the IDEAL framework, and WHO/AHRQ patient safety standards. The framework is designed to standardize new-procedure governance across clinical, operational, pharmacy, facilities, risk, and support teams at a community hospital. Manuscript in preparation.
Location
Pleasanton, CA
-
QGenda Physician On-Call Scheduling Platform Launch, Stanford Health Care – Tri-Valley
2025–2026; go-live February 2026. Championed hospital-wide adoption of real-time, Epic-integrated on-call scheduling to replace PDF/intranet schedules. Designed scheduling taxonomy and specialty-specific workflows across more than 20 departments, including faculty and community pools in multi-group specialties. Built reporting to support physician contract compliance. Provided clinical leadership as a key Tri-Valley point of contact with Stanford IT and QGenda. Tri-Valley served as the enterprise pilot site; schedules feed Epic On-Call Finder, with full schedule creation and maintenance in QGenda planned as a subsequent phase.
Location
Pleasanton, CA
-
Massive Transfusion Protocol Safety Redesign — Co-Lead, Stanford Health Care – Tri-Valley
2022–2025; completed November 2025. Co-led a RITE project to address Epic order confusion, role ambiguity, and blood bank communication gaps. Redesigned the MTP order set, reducing incorrect order entries from 25% to 7%. Established the Voalte MTP Response Team, trained OR charge nurses, created one-point lessons, and updated hospital policy through MEC and the Board. Co-led the Blood Transfusion Workgroup, expanding to obstetric hemorrhage protocols, and presented to approximately 50 hospitalists across Tri-Valley and Stanford.
Location
Pleasanton, CA
-
Epic EHR Implementation — Lead Project Physician, Stanford Health Care – Tri-Valley
2016–2018. Led more than 25 specialty physician subject matter experts through workflow design and critical design decisions; built approximately 250 order sets for go-live. Rebuilt the Clinical Decision Support Committee and established cross-institutional EHR governance. Led the paper-to-Epic transition and physician change management through bimonthly newsletters and monthly Medical Executive Committee updates.
Location
Pleasanton, CA
-
Clinician Builder Program — Founder and Lead, Stanford Health Care – Tri-Valley
2019–Present. Founded and leads a physician-led workflow optimization and IT engagement initiative at Stanford Health Care – Tri-Valley.
Location
Pleasanton, CA
-
Telemetry Utilization Optimization, Stanford Health Care – Tri-Valley
Presented “Straight to the Heart: Optimizing Telemetry Utilization with Physician Collaboration” at the Vizient Summit in Las Vegas, Nevada, in September 2025.
Location
Pleasanton, CA
-
Digital Procedure Consents (E-Signature), Stanford Health Care – Tri-Valley
Presented in May 2025. Led adoption of electronic signatures for procedure consents, eliminating paper consents and improving workflow efficiency. Presented “No More Hide and Seek: Digitizing Procedure Consents in a Community Hospital” at the Epic Xpert Group Meeting in Verona, Wisconsin, in May 2025.
Location
Pleasanton, CA
-
Network Access Optimization — Tri-Valley Regional Representative, Stanford Health Care – Tri-Valley
2025. Represented Tri-Valley with CMO David Svec in a Stanford systemwide initiative to standardize referral networks, visit types, and patient triage. Advocated for appropriate East Bay triage and accessible informatics referral design, including radiology orders geolocated by patient preference and need.
Location
Pleasanton, CA
-
Sepsis Lactic Acid Ordering, Stanford Health Care – Tri-Valley
Presented in May 2022. Used Beaker CP for lactic acid orders to improve sepsis compliance. Presented “Improving Sepsis Compliance by Leveraging Beaker CP for Lactic Acid Orders” at the Epic Xpert Meeting in Verona, Wisconsin, in May 2022.
Location
Pleasanton, CA
-
CMS Documentation Compliance, Stanford Health Care – Tri-Valley
2020–2025. As founder and chair of the Health Information Management Services Committee, established policies that drove CMS documentation compliance above 90%.
Location
Pleasanton, CA
-
Order Set Optimization, Stanford Health Care – Tri-Valley
Ongoing; presented in May 2019. Maintains and optimizes more than 188 order sets, focusing on safety and specialty transitions. Presented “Data-Driven Order Set Management” at the Epic Xpert Group Meeting in Verona, Wisconsin, in May 2019.
Location
Pleasanton, CA
-
Computer-Assisted Sponge Counting, Stanford Health Care – Tri-Valley
2025. Implemented computer-assisted sponge counting to reduce retained surgical item risk.
Location
Pleasanton, CA
-
Primary Care Network Access Optimization, Stanford University
2019. Developed a proof of concept and scalable framework for a simplified primary care referral system at Stanford.
Location
Stanford, CA
-
Enterprise Contact Center Integration, Stanford Health Care – Tri-Valley
September 2018. Integrated Stanford Health Care – ValleyCare Physical Therapy and Occupational Therapy into the Enterprise Contact Center algorithm.
Location
Pleasanton, CA
-
Joint Commission Remediation, Stanford Health Care – Tri-Valley
2022–2024. Resolved multiple Joint Commission findings by reengineering physician workflows and documentation practices at Stanford Health Care – Tri-Valley. Work included physician documentation requirements and immediate postoperative note compliance.
Location
Pleasanton, CA
All Publications
-
SmartAlert - Implementing Machine Learning-Driven Clinical Decision Support for Inpatient Laboratory Utilization Reduction.
NEJM AI
2026; 3 (7)
Abstract
Repetitive laboratory testing that is unlikely to yield clinically useful information is a common practice that burdens patients and increases health care costs. Education and feedback interventions have limited success, while general test ordering restrictions and electronic alerts impede appropriate clinical care. We introduce and evaluate SmartAlert, a machine learning-driven clinical decision support (CDS) system integrated into the electronic health record that predicts stable laboratory results to reduce unnecessary repeat testing. This Case Study describes the implementation process, challenges, and lessons learned from deploying SmartAlert targeting complete blood count (CBC) utilization in a randomized controlled pilot across 9270 admissions in eight acute care units across two hospitals between August 15, 2024, and March 15, 2025. The results show a significant decrease in the number of CBC results within 52 hours of SmartAlert display (1.54 vs. 1.82; P<0.01) without adverse effect on secondary safety outcomes, representing a 15% relative reduction in repetitive testing. Implementation lessons learned include interpretation of probabilistic model predictions in clinical contexts, stakeholder engagement to define acceptable model behavior, governance processes for deploying a complex model in a clinical environment, user interface design considerations, alignment with clinical operational priorities, and the value of qualitative feedback from end users. In conclusion, a machine learning-driven CDS system backed by a deliberate implementation and governance process can provide precision guidance on inpatient laboratory testing to safely reduce unnecessary repetitive testing. (Funded by the Agency for Science, Technology, and Research and others.).
View details for DOI 10.1056/aics2501086
View details for PubMedID 42453199
View details for PubMedCentralID PMC13367503
-
Closing the Gap: Optimizing Hospital Discharge Planning for Improved Outcomes.
Health services research
2026; 61 (2): e70101
View details for DOI 10.1111/1475-6773.70101
View details for PubMedID 41914775
-
MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries.
Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
2026; 31: 388-399
Abstract
Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an "LLM Jury"-a multi-LLM majority vote-assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-quality, factual discharge summaries. To validate our evaluation framework, we established a gold-standard reference using a seven-physician majority vote on clinician-defined key facts from inpatient cases. The MedFactEval LLM Jury achieved almost perfect agreement with this panel (Cohen's κ = 81%), a performance statistically non-inferior to that of a single human expert (κ = 67%, P < 0.001). Our work provides both a robust evaluation framework (MedFactEval) and a high-performing generation workflow (MedAgentBrief), offering a comprehensive approach to advance the responsible deployment of generative AI in clinical workflows.
View details for DOI 10.1142/9789819824755_0027
View details for PubMedID 41758155
-
MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries
edited by Altman, R. B., Hunter, L., Ritchie, M. D., Murray, T., Klein, T. E.
WORLD SCIENTIFIC PUBL CO PTE LTD. 2026: 388-399
Abstract
Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an "LLM Jury"-a multi-LLM majority vote-assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-quality, factual discharge summaries. To validate our evaluation framework, we established a gold-standard reference using a seven-physician majority vote on clinician-defined key facts from inpatient cases. The MedFactEval LLM Jury achieved almost perfect agreement with this panel (Cohen's κ = 81%), a performance statistically non-inferior to that of a single human expert (κ = 67%, P < 0.001). Our work provides both a robust evaluation framework (MedFactEval) and a high-performing generation workflow (MedAgentBrief), offering a comprehensive approach to advance the responsible deployment of generative AI in clinical workflows.
View details for Web of Science ID 001796654100027
View details for PubMedID 41758155
-
Validation of Test Performance and Clinical Time Zero for an Electronic Health Record Embedded Severe Sepsis Alert.
Applied clinical informatics
2016; 7 (2): 560-572
Abstract
Increasing use of EHRs has generated interest in the potential of computerized clinical decision support to improve treatment of sepsis. Electronic sepsis alerts have had mixed results due to poor test characteristics, the inability to detect sepsis in a timely fashion and the use of outside software limiting widespread adoption. We describe the development, evaluation and validation of an accurate and timely severe sepsis alert with the potential to impact sepsis management.To develop, evaluate, and validate an accurate and timely severe sepsis alert embedded in a commercial EHR.The sepsis alert was developed by identifying the most common severe sepsis criteria among a cohort of patients with ICD 9 codes indicating a diagnosis of sepsis. This alert requires criteria in three categories: indicators of a systemic inflammatory response, evidence of suspected infection from physician orders, and markers of organ dysfunction. Chart review was used to evaluate test performance and the ability to detect clinical time zero, the point in time when a patient develops severe sepsis.Two physicians reviewed 100 positive cases and 75 negative cases. Based on this review, sensitivity was 74.5%, specificity was 86.0%, the positive predictive value was 50.3%, and the negative predictive value was 94.7%. The most common source of end-organ dysfunction was MAP less than 70 mm/Hg (59%). The alert was triggered at clinical time zero in 41% of cases and within three hours in 53.6% of cases. 96% of alerts triggered before a manual nurse screen.We are the first to report the time between a sepsis alert and physician chart-review clinical time zero. Incorporating physician orders in the alert criteria improves specificity while maintaining sensitivity, which is important to reduce alert fatigue. By leveraging standard EHR functionality, this alert could be implemented by other healthcare systems.
View details for DOI 10.4338/ACI-2015-11-RA-0159
View details for PubMedID 27437061
View details for PubMedCentralID PMC4941860
-
Preoperative Angiotensin-converting Enzyme Inhibitor Use is Not Associated With Increased Postoperative Pain and Opioid Use
CLINICAL JOURNAL OF PAIN
2013; 29 (12): 1050-1056
Abstract
Angiotensin-converting enzyme inhibitors (ACEIs) increase potent proinflammatory and pain mediators in local tissues. Consistent with these observations, animal and human studies demonstrate that ACEIs have hyperalgesic and proinflammatory properties. However, there is no information in literature whether or not the use of ACEIs is associated with increased postoperative pain. Specifically, we tested the primary hypothesis that use of ACEIs is independently associated with increased opioid requirements and pain scores during the initial 72 hours after surgery.Data from 9993 patients undergoing colorectal resection, hysterectomy, nephrectomy, or open prostatectomy were obtained from the Cleveland Clinic Perioperative Health Documentation System. A propensity-matching procedure was used to pair ACEI users to similar nonusers. Corresponding estimates and Bonferroni-adjusted 95% confidence intervals for the effect of ACEIs on each outcome were also estimated. The exact matching procedure, based on type of surgery and propensity score, identified 1038 matched pairs. The final analyzed subsample size was 212.The adjusted difference in mean 72-hour postoperative using a time-weighted average pain score was estimated at +0.17 [-0.40, +0.74] units on the verbal response scale. This was not statistically significant (P=0.50). Opioid use was estimated by the percent difference in mean 72-hour total postoperative intravenous morphine equivalent dose at -8.1% [-46%, +56%], which was not statistically significant (P=0.72). In conclusion, after controlling for all available factors, we found no significant difference that postoperative pain-as defined by either pain scores or opioid requirements-differed between patients taking ACEIs and patients not taking ACEIs.
View details for DOI 10.1097/AJP.0b013e318287a258
View details for Web of Science ID 000329937400011
View details for PubMedID 24189772
-
Consequences of Succinylcholine Administration to Patients Using Statins
ANESTHESIOLOGY
2011; 115 (1): 28-35
Abstract
Statins cause structural changes in myocytes and provoke myotoxicity, myopathy, and myalgias. Thus, patients taking statins may be especially susceptible to succinylcholine-induced muscle injury. The authors tested the hypothesis that succinylcholine increases plasma concentrations of myoglobin, potassium, and creatine kinase more in patients who take statins than in those who do not and that succinylcholine-induced postoperative muscle pain is aggravated in statin users.Patients who took statins for at least 3 months and those who had never used statins were enrolled. General anesthesia was induced and included 1.5 mg/kg succinylcholine for intubation. The incidence and degree of fasciculation after succinylcholine administration were recorded. Blood samples were obtained before induction and 5 and 20 min and 24 h after succinylcholine administration. Patients were interviewed 2 and 24 h after surgery to determine the degree of myalgia.The authors enrolled 38 patients who used statins and 32 who did not. At 20 min, myoglobin was higher in statin users versus nonusers (ratio of medians 1.34 [95% CI: 1.1, 1.7], P = 0.018). Fasciculations in statin users were more intense than in nonusers (P = 0.047). However, plasma potassium and creatine kinase concentrations were similar in statin users and nonusers, as was muscle pain.The plasma myoglobin concentration at 20 min was significantly greater in statin users than nonusers, although the difference seems unlikely to be clinically important. The study results suggest that the effect of succinylcholine given to patients taking statins is likely to be small and probably of limited clinical consequence.
View details for DOI 10.1097/ALN.0b013e31822079fa
View details for Web of Science ID 000291925400008
View details for PubMedID 21606827