Sharif Vakili, MD, MBA, MS, (pronouns: he/him), is an internal medicine physician and educator. He practices at Stanford Los Altos Primary Care.

Dr. Vakili has a background in chronic disease management and health systems delivery, believing strongly in a teamwork approach to patient care that empowers patients to navigate the health system as part of their clinical care.

He is active in the research and business communities. His research has been in peer-reviewed journals including JAMA Network Open, the Annals of Emergency Medicine, Quality Management in Healthcare, and Journal of Clinical Rheumatology.

Dr. Vakili is also the inventor of Remote Patient Intervention (RPI), a model of clinician-supervised AI care delivery first performed at Stanford during a clinical study published in JAMA Network Open.

Clinical Focus

  • Internal Medicine

Academic Appointments

Professional Education

  • Residency: Stanford University Internal Medicine Residency (2022) CA
  • MD, Johns Hopkins University School of Medicine
  • Board Certification: American Board of Internal Medicine, Internal Medicine (2022)
  • MBA, Harvard Business School
  • MS, Yale University
  • BS, Yale University

Clinical Trials

  • Managing Insulin With a Voice AI Not Recruiting

    This study randomizes participants to have their basal insulin titrated either through standard of care or by receiving prompts through interactions with an AI-enabled smart speaker device. The primary objective of this study is to investigate the feasibility of an AI-enabled smart speaker device and whether such a device facilitates insulin titration management, increases insulin adherence and decreases time to optimal insulin dose. The secondary objective of the study is to explore whether the device improves glycemic control as defined by improvements in fasting blood sugar.

    Stanford is currently not accepting patients for this trial. For more information, please contact Study Team, 650-308-8062.

    View full details

All Publications

  • Use of Voice-Based Conversational Artificial Intelligence for Basal Insulin Prescription Management Among Patients With Type 2 Diabetes: A Randomized Clinical Trial. JAMA network open Nayak, A., Vakili, S., Nayak, K., Nikolov, M., Chiu, M., Sosseinheimer, P., Talamantes, S., Testa, S., Palanisamy, S., Giri, V., Schulman, K. 2023; 6 (12): e2340232


    Optimizing insulin therapy for patients with type 2 diabetes can be challenging given the need for frequent dose adjustments. Most patients receive suboptimal doses and do not achieve glycemic control.To examine whether a voice-based conversational artificial intelligence (AI) application can help patients with type 2 diabetes titrate basal insulin at home to achieve rapid glycemic control.In this randomized clinical trial conducted at 4 primary care clinics at an academic medical center from March 1, 2021, to December 31, 2022, 32 adults with type 2 diabetes requiring initiation or adjustment of once-daily basal insulin were followed up for 8 weeks. Statistical analysis was performed from January to February 2023.Participants were randomized in a 1:1 ratio to receive basal insulin management with a voice-based conversational AI application or standard of care.Primary outcomes were time to optimal insulin dose (number of days needed to achieve glycemic control), insulin adherence, and change in composite survey scores measuring diabetes-related emotional distress and attitudes toward health technology and medication adherence. Secondary outcomes were glycemic control and glycemic improvement. Analysis was performed on an intent-to-treat basis.The study population included 32 patients (mean [SD] age, 55.1 [12.7] years; 19 women [59.4%]). Participants in the voice-based conversational AI group more quickly achieved optimal insulin dosing compared with the standard of care group (median, 15 days [IQR, 6-27 days] vs >56 days [IQR, >29.5 to >56 days]; a significant difference in time-to-event curves; P = .006) and had better insulin adherence (mean [SD], 82.9% [20.6%] vs 50.2% [43.0%]; difference, 32.7% [95% CI, 8.0%-57.4%]; P = .01). Participants in the voice-based conversational AI group were also more likely than those in the standard of care group to achieve glycemic control (13 of 16 [81.3%; 95% CI, 53.7%-95.0%] vs 4 of 16 [25.0%; 95% CI, 8.3%-52.6%]; difference, 56.3% [95% CI, 21.4%-91.1%]; P = .005) and glycemic improvement, as measured by change in mean (SD) fasting blood glucose level (-45.9 [45.9] mg/dL [95% CI, -70.4 to -21.5 mg/dL] vs 23.0 [54.7] mg/dL [95% CI, -8.6 to 54.6 mg/dL]; difference, -68.9 mg/dL [95% CI, -107.1 to -30.7 mg/dL]; P = .001). There was a significant difference between the voice-based conversational AI group and the standard of care group in change in composite survey scores measuring diabetes-related emotional distress (-1.9 points vs 1.7 points; difference, -3.6 points [95% CI, -6.8 to -0.4 points]; P = .03).In this randomized clinical trial of a voice-based conversational AI application that provided autonomous basal insulin management for adults with type 2 diabetes, participants in the AI group had significantly improved time to optimal insulin dose, insulin adherence, glycemic control, and diabetes-related emotional distress compared with those in the standard of care group. These findings suggest that voice-based digital health solutions can be useful for medication Identifier: NCT05081011.

    View details for DOI 10.1001/jamanetworkopen.2023.40232

    View details for PubMedID 38039007

  • The Inpatient Discharge Lounge as a Potential Mechanism to Mitigate Emergency Department Boarding and Crowding. Annals of emergency medicine Franklin, B. J., Vakili, S., Huckman, R. S., Hosein, S., Falk, N., Cheng, K., Murray, M., Harris, S., Morris, C. A., Goralnick, E. 2020


    Delayed access to inpatient beds for admitted patients contributes significantly to emergency department (ED) boarding and crowding, which have been associated with deleterious patient safety effects. To expedite inpatient bed availability, some hospitals have implemented discharge lounges, allowing discharged patients to depart their inpatient rooms while awaiting completion of the discharge process or transportation. This conceptual article synthesizes the evidence related to discharge lounge implementation practices and outcomes. Using a conceptual synthesis approach, we reviewed the medical and gray literature related to discharge lounges by querying PubMed, Google Scholar, and Google and undertaking backward reference searching. We screened for articles either providing detailed accounts of discharge lounge implementations or offering conceptual analysis on the subject. Most of the evidence we identified was in the gray literature, with only 3 peer-reviewed articles focusing on discharge lounge implementations. Articles generally encompassed single-site descriptive case studies or expert opinions. Significant heterogeneity exists in discharge lounge objectives, features, and apparent influence on patient flow. Although common barriers to discharge lounge performance have been documented, including underuse and care team objections, limited generalizable solutions are offered. Overall, discharge lounges are widely endorsed as a mechanism to accelerate access to inpatient beds, yet the limited available evidence indicates wide variation in design and performance. Further rigorous investigation is required to identify the circumstances under which discharge lounges should be deployed, and how discharge lounges should be designed to maximize their effect on hospitalwide patient flow, ED boarding and crowding, and other targeted outcomes.

    View details for DOI 10.1016/j.annemergmed.2019.12.002

    View details for PubMedID 31983501

  • Lymphocytic Thrombophilic Arteritis: A Review. Journal of clinical rheumatology : practical reports on rheumatic & musculoskeletal diseases Vakili, S., Zampella, J. G., Kwatra, S. G., Blanck, J., Loss, M. 2019; 25 (3): 147-152


    Macular lymphocytic arteritis or lymphocytic thrombophilic arteritis (LTA) is a recently described cutaneous arteritis that is characterized by asymptomatic macules and patches of the extremities associated with lymphocytic arteritis at the deep dermal/subcuticular junction for which little information exists on demographics, evaluation, and management. There has been recent debate in the literature whether this disease is a new distinct entity, misdiagnosed cutaneous polyarteritis nodosa (cPAN), or a disease on a spectrum with cPAN. We systematically review the literature on demographic information, medical history, histopathology findings, and treatment management to analyze trends and clarify controversies in characterizations of LTA. Forty detailed cases of LTA have been published. We submit that, although literature is limited, a review of the data still suggests that LTA is distinct from cPAN and systemic PAN. In addition, to better reflect the pathophysiologic natural history of this condition and correct for the historical artifact of how the disease was identified, we encourage the disease to be referred to as LTA and discourage ongoing use of macular lymphocytic arteritis.

    View details for DOI 10.1097/RHU.0000000000000846

    View details for PubMedID 30044260

  • Macular lymphocytic arteritis: Clinical-pathologic correlation of a rare vasculitis. JAAD case reports Zampella, J. G., Vakili, S., Doig, S., Girardi, N., Kwatra, S. G., Seo, P., Patel, M. 2017; 3 (2): 116-120

    View details for DOI 10.1016/j.jdcr.2017.01.014

    View details for PubMedID 28337473

    View details for PubMedCentralID PMC5349452

  • Timing of surgical treatment for idiopathic normal pressure hydrocephalus: association between treatment delay and reduced short-term benefit. Neurosurgical focus Vakili, S., Moran, D., Hung, A., Elder, B. D., Jeon, L., Fialho, H., Sankey, E. W., Jusué-Torres, I., Goodwin, C. R., Lu, J., Robison, J., Rigamonti, D. 2016; 41 (3): E2


    OBJECTIVE A growing body of evidence suggests that longer durations of preoperative symptoms may correlate with worse postoperative outcomes following cerebrospinal fluid (CSF) diversion for treatment of idiopathic normal pressure hydrocephalus (iNPH). The aim of this study is to determine whether the duration of preoperative symptoms alters postoperative outcomes in patients treated for iNPH. METHODS The authors conducted a retrospective review of 393 cases of iNPH involving patients treated with ventriculoperitoneal (VP) shunting. The duration of symptoms prior to the operative intervention was recorded. The following outcome variables were assessed at baseline, 6 months postoperatively, and at last follow-up: gait performance, urinary continence, and cognition. RESULTS The patients' median age at shunt placement was 74 years. Increased symptom duration was significantly associated with worse gait outcomes (relative risk (RR) 1.055 per year of symptoms, p = 0.037), and an overall absence of improvement in any of the classic triad symptomology (RR 1.053 per year of symptoms, p = 0.033) at 6 months postoperatively. Additionally, there were trends toward significance for symptom duration increasing the risk of having no 6-month postoperative improvement in urinary incontinence (RR 1.049 per year of symptoms, p = 0.069) or cognitive symptoms (RR 1.051 per year of symptoms, p = 0.069). However, no statistically significant differences were noted in these outcomes at last follow-up (median 31 months). Age stratification by decade revealed that prolonging symptom duration was significantly associated with lower Mini-Mental Status Examination scores in patients aged 60-70 years, and lack of cognitive improvement in patients aged 70-80 years. CONCLUSIONS Patients with iNPH with longer duration of preoperative symptoms may not receive the same short-term benefits of surgical intervention as patients with shorter duration of preoperative symptoms. However, with longer follow-up, the patients generally reached the same end point. Therefore, when managing patients with iNPH, it may take longer to see the benefits of CSF shunting when patients present with a longer duration of preoperative symptoms.

    View details for DOI 10.3171/2016.6.FOCUS16146

    View details for PubMedID 27581314

  • Comparison of outcomes between patients with idiopathic normal pressure hydrocephalus who received a primary versus a salvage shunt. Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia Moran, D., Hung, A., Vakili, S., Fialho, H., Jeon, L., Sankey, E. W., Jusué-Torres, I., Lu, J., Goodwin, C. R., Elder, B. D., Rigamonti, D. 2016; 29: 117-20


    Placement of a ventriculoperitoneal (VP) shunt is the treatment of choice for communicating hydrocephalus; however, the extent to which VP shunting is able to relieve symptoms in patients who had previously been treated with cerebrospinal fluid diverting therapy at an outside institution remains unclear. A retrospective review of patients with idiopathic normal pressure hydrocephalus treated with VP shunts at a single institution between 1993 and 2013 was conducted. Patients were classified as having received a primary VP shunt if they had not been previously treated with a VP shunt, ventriculoatrial shunt, lumboperitoneal shunt, or endoscopic third ventriculostomy. Patients were classified as having received a salvage VP shunt if they had been previously treated by one of these four modalities at an outside institution prior to their presentation to our institution. There were 357 patients who received a primary shunt and 33 patients who received a salvage shunt. Patients who had a salvage shunt placed had significantly higher odds of requiring a future revision (54% versus 41%; odds ratio=2.85; 95% confidence interval [CI]: 1.24-6.57; p=0.014). Patients who received a salvage shunt had statistically significantly lower rates of gait improvement at 6months in comparison to patients who received a primary shunt (relative risk=0.35; 95% CI: 0.14-0.87; p=0.025). Despite these findings, there was no significant difference at last follow-up in improvement in gait, continence, and cognition, indicating that outcomes for patients requiring a salvage shunt were comparable to patients receiving a primary shunt.

    View details for DOI 10.1016/j.jocn.2015.12.009

    View details for PubMedID 26898583

  • Predictors of Ventriculoperitoneal Shunt Revision in Patients with Idiopathic Normal Pressure Hydrocephalus. World neurosurgery Hung, A. L., Moran, D., Vakili, S., Fialho, H., Sankey, E. W., Jusué-Torres, I., Elder, B. D., Goodwin, C. R., Lu, J., Robison, J., Rigamonti, D. 2016; 90: 76-81


    Few studies have focused on predictive factors of ventriculoperitoneal (VP) shunt revision in patients with idiopathic normal pressure hydrocephalus (iNPH). This study aims to determine whether comorbidities and baseline symptoms are associated with the need for shunt revision.A retrospective review of patients with iNPH treated with VP shunts by the senior author from 1993 to 2013 was conducted. Demographics and baseline symptoms were compared between patients with and without shunt revision. The need for revision, total number of revisions, and time to first revision were examined. Statistical analysis was performed using simple logistic, linear, and Poisson regression, and a multivariate analysis was performed.A total of 347 patients with iNPH who received VP shunts were included. One hundred patients (28.8%) required shunt revision, with an average of 1.38 ± 0.76 revisions per patient. Mean time to revision was 19.2 ± 31.7 months. Gait and cognitive symptoms were associated with fewer revisions (incidence rate ratio, 0.45 and 0.67; P = 0.03 and 0.004, respectively). Headaches and urinary incontinence showed a greater time to revision (32.0 and 12.0 months; P = 0.014 and <0.0005, respectively). Gait instability demonstrated decreased time to revision (P < 0.0005).Preoperative symptoms, such as headaches, gait instability, cognitive decline, and urinary incontinence, were significantly correlated with number of revisions and time to first revision. These factors should be considered during the initial counseling of prognosis for patients with iNPH receiving VP shunts.

    View details for DOI 10.1016/j.wneu.2016.02.061

    View details for PubMedID 26915697

  • The Student Curriculum Review Team: How we catalyze curricular changes through a student-centered approach. Medical teacher Hsih, K. W., Iscoe, M. S., Lupton, J. R., Mains, T. E., Nayar, S. K., Orlando, M. S., Parzuchowski, A. S., Sabbagh, M. F., Schulz, J. C., Shenderov, K., Simkin, D. J., Vakili, S., Vick, J. B., Xu, T., Yin, O., Goldberg, H. R. 2015; 37 (11): 1008-12


    Student feedback is a valuable asset in curriculum evaluation and improvement, but many institutions have faced challenges implementing it in a meaningful way. In this article, we report the rationale, process and impact of the Student Curriculum Review Team (SCRT), a student-led and faculty-supported organization at the Johns Hopkins University School of Medicine. SCRT's evaluation of each pre-clinical course is composed of a comprehensive three-step process: a review of course evaluation data, a Town Hall Meeting and online survey to generate and assess potential solutions, and a thoughtful discussion with course directors. Over the past two years, SCRT has demonstrated the strength of its approach by playing a substantial role in improving medical education, as reported by students and faculty. Furthermore, SCRT's uniquely student-centered, collaborative model has strengthened relationships between students and faculty and is one that could be readily adapted to other medical schools or academic institutions.

    View details for DOI 10.3109/0142159X.2014.990877

    View details for PubMedID 25532595

  • A comparison of commercial and custom-made electronic tracking systems to measure patient flow through an ambulatory clinic. International journal of health geographics Vakili, S., Pandit, R., Singman, E. L., Appelbaum, J., Boland, M. V. 2015; 14: 32


    Understanding how patients move through outpatient clinics is important for optimizing clinic processes. This study compares the costs, benefits, and challenges of two clinically important methods for measuring patient flow: (1) a commercial system using infrared (IR) technology that passively tracks patient movements and (2) a custom-built, low cost, networked radio frequency identification (RFID) system that requires active swiping by patients at proximity card readers.Readers for both the IR and RFID systems were installed in the General Eye Service of the Wilmer Eye Institute. Participants were given both IR and RFID tags to measure the time they spent in various clinic stations. Simultaneously, investigators recorded the times at which patients moved between rooms. These measurements were considered the standard against which the other methods were compared.One hundred twelve patients generated a total of 252 events over the course of 6 days. The proportion of events successfully recorded by the RFID system (83.7%) was significantly greater than that obtained with the IR system (75.4%, p < 0.001). The cause of the missing events using the IR method was found to be a signal interruption between the patient tags and the check-in desk receiver. Excluding those data, the IR system successfully recorded 94.4% of events (p = 0.002; OR = 3.83 compared to the RFID system). There was no statistical difference between the IR, RFID, and manual time measurements (p > 0.05 for all comparisons).Both RFID and IR methods are effective at providing patient flow information. The custom-made RFID system was as accurate as IR and was installed at about 10% the cost. Given its significantly lower costs, the RFID option may be an appealing option for smaller clinics with more limited budgets.

    View details for DOI 10.1186/s12942-015-0023-7

    View details for PubMedID 26511722

    View details for PubMedCentralID PMC4625437

  • Electronic Tracking of Patients in an Outpatient Ophthalmology Clinic to Improve Efficient Flow: A Feasibility Analysis and Benchmarking Study. Quality management in health care Singman, E. L., Haberman, C. V., Appelbaum, J., Tian, J., Shafer, K., Toerper, M., Katz, S., Kelsay, M., Boland, M. V., Greenbaum, M., Adelman, R., Thomas, R. C., Vakili, S. 2015; 24 (4): 190-9


    Real-time location systems (RTLS) and Lean management approaches have been employed to improve patient flow in clinical settings. This study explored the feasibility of using these methodologies in an outpatient resident ophthalmology clinic.Patients, providers, and staff in Wilmer Eye Institute General Eye Services Clinic were provided RTLS tags to track their movement throughout the clinic after observational studies modeling flow were conducted. Tracking data guided changes for clinic processes based on Lean management approaches, including reorganization of the reception desk, consolidation of forms, creation of task sheets to improve communication, installation of door flags on examination rooms, and training the staff in service excellence. Tracking was repeated after changes were implemented. A patient satisfaction survey was also conducted prior to and after the changes.After intervention, significant increases were measured in the average time patients spent in the clinic (99.3 minutes vs 112.8 minutes). Significant decreases were seen in the times patients spent with the optometrists (15.4 minutes vs 12.1 minutes), testing (24.7 minutes vs 23.0 minutes), and together with both the attending and the resident (8.3 minutes vs 5.8 minutes). The patient satisfaction survey indicated improvements in patients' perception of the helpfulness/friendliness of the staff, the length of time patients perceived they waited, and overall clinic experience.Both RTLS and Lean management approaches may be feasible ways to track and improve patient flow and satisfaction if certain limitations can be overcome. This is the first published report describing these approaches applied to an academic ophthalmology clinic in the United States.

    View details for DOI 10.1097/QMH.0000000000000075

    View details for PubMedID 26426320