Shreya Jitendra Shah

All Publications

• Physician Perspectives on Ambient AI Scribes. JAMA network open Shah, S. J., Crowell, T., Jeong, Y., Devon-Sand, A., Smith, M., Yang, B., Ma, S. P., Liang, A. S., Delahaie, C., Hsia, C., Shanafelt, T., Pfeffer, M. A., Sharp, C., Lin, S., Garcia, P. 2025; 8 (3): e251904

  Abstract

  Limited qualitative studies exist evaluating ambient artificial intelligence (AI) scribe tools. Such studies can provide deeper insights into ambient AI implementations by capturing lived experiences.To evaluate physician perspectives on ambient AI scribes.A qualitative study using semistructured interviews guided by the Reach, Efficacy, Adoption, Implementation, Maintenance/Practical, Robust Implementation, and Sustainability Model (RE-AIM/PRISM) framework, with thematic analysis using both inductive and deductive approaches. Physicians participating in an AI scribe pilot that included community and faculty practices, across primary care and ambulatory specialties, were invited to participate in interviews. This ambient AI scribe pilot at a health care organization in California was conducted from November 2023 to January 2024.Facilitators and barriers to adoption, practical effectiveness, and suggestions for improvement to enhance sustainability.Twenty-two semistructured interviews were conducted with AI pilot physicians from primary care (13 [59%]) and ambulatory specialties (9 [41%]), including physicians from community practices (12 [55%]) and faculty practices (10 [45%]). Facilitators to adoption included ease of use, ease of editing, and generally positive perspectives of tool quality. Physicians expressed positive sentiments about the impact of the ambient AI scribe tool on cognitive demand (16 of 16 comments [100%]), temporal demand (28 comments [62%]), work-life integration (10 of 11 comments [91%]), and overall workload (8 of 9 comments [89%]). Physician perspectives of the impact of the ambient AI scribe tool on their engagement with patients were mostly positive (38 of 56 comments [68%]). Barriers to adoption included limited functionality with non-English speaking patients and lack of access for physicians without a specific device. Physician perspectives on accuracy and style were largely negative, particularly regarding note length and editing requirements. Several specific suggestions for tool improvement were identified, and physicians were optimistic regarding the potential for long-term use of ambient AI scribes.In this qualitative study, ambient AI scribes were found to positively impact physician workload, work-life integration, and patient engagement. Key facilitators and barriers to adoption were identified, along with specific suggestions for tool improvement. These findings suggest the potential for ambient AI scribes to reduce clinician burden, with user-centered recommendations offering practical guidance on ways to improve future iterations and improve adoption.

  View details for DOI 10.1001/jamanetworkopen.2025.1904

  View details for PubMedID 40126477

• Ambient artificial intelligence scribes: utilization and impact on documentation time. Journal of the American Medical Informatics Association : JAMIA Ma, S. P., Liang, A. S., Shah, S. J., Smith, M., Jeong, Y., Devon-Sand, A., Crowell, T., Delahaie, C., Hsia, C., Lin, S., Shanafelt, T., Pfeffer, M. A., Sharp, C., Garcia, P. 2024

  Abstract

  To quantify utilization and impact on documentation time of a large language model-powered ambient artificial intelligence (AI) scribe.This prospective quality improvement study was conducted at a large academic medical center with 45 physicians from 8 ambulatory disciplines over 3 months. Utilization and documentation times were derived from electronic health record (EHR) use measures.The ambient AI scribe was utilized in 9629 of 17 428 encounters (55.25%) with significant interuser heterogeneity. Compared to baseline, median time per note reduced significantly by 0.57 minutes. Median daily documentation, afterhours, and total EHR time also decreased significantly by 6.89, 5.17, and 19.95 minutes/day, respectively.An early pilot of an ambient AI scribe demonstrated robust utilization and reduced time spent on documentation and in the EHR. There was notable individual-level heterogeneity.Large language model-powered ambient AI scribes may reduce documentation burden. Further studies are needed to identify which users benefit most from current technology and how future iterations can support a broader audience.

  View details for DOI 10.1093/jamia/ocae304

  View details for PubMedID 39688515

• Ambient artificial intelligence scribes: physician burnout and perspectives on usability and documentation burden. Journal of the American Medical Informatics Association : JAMIA Shah, S. J., Devon-Sand, A., Ma, S. P., Jeong, Y., Crowell, T., Smith, M., Liang, A. S., Delahaie, C., Hsia, C., Shanafelt, T., Pfeffer, M. A., Sharp, C., Lin, S., Garcia, P. 2024

  Abstract

  This study evaluates the pilot implementation of ambient AI scribe technology to assess physician perspectives on usability and the impact on physician burden and burnout.This prospective quality improvement study was conducted at Stanford Health Care with 48 physicians over a 3-month period. Outcome measures included burden, burnout, usability, and perceived time savings.Paired survey analysis (n = 38) revealed large statistically significant reductions in task load (-24.42, p <.001) and burnout (-1.94, p <.001), and moderate statistically significant improvements in usability scores (+10.9, p <.001). Post-survey responses (n = 46) indicated favorable utility with improved perceptions of efficiency, documentation quality, and ease of use.In one of the first pilot implementations of ambient AI scribe technology, improvements in physician task load, burnout, and usability were demonstrated.Ambient AI scribes like DAX Copilot may enhance clinical workflows. Further research is needed to optimize widespread implementation and evaluate long-term impacts.

  View details for DOI 10.1093/jamia/ocae295

  View details for PubMedID 39657021

• Recommendations for Clinicians, Technologists, and Healthcare Organizations on the Use of Generative Artificial Intelligence in Medicine: A Position Statement from the Society of General Internal Medicine. Journal of general internal medicine Crowe, B., Shah, S., Teng, D., Ma, S. P., DeCamp, M., Rosenberg, E. I., Rodriguez, J. A., Collins, B. X., Huber, K., Karches, K., Zucker, S., Kim, E. J., Rotenstein, L., Rodman, A., Jones, D., Richman, I. B., Henry, T. L., Somlo, D., Pitts, S. I., Chen, J. H., Mishuris, R. G. 2024

  Abstract

  Generative artificial intelligence (generative AI) is a new technology with potentially broad applications across important domains of healthcare, but serious questions remain about how to balance the promise of generative AI against unintended consequences from adoption of these tools. In this position statement, we provide recommendations on behalf of the Society of General Internal Medicine on how clinicians, technologists, and healthcare organizations can approach the use of these tools. We focus on three major domains of medical practice where clinicians and technology experts believe generative AI will have substantial immediate and long-term impacts: clinical decision-making, health systems optimization, and the patient-physician relationship. Additionally, we highlight our most important generative AI ethics and equity considerations for these stakeholders. For clinicians, we recommend approaching generative AI similarly to other important biomedical advancements, critically appraising its evidence and utility and incorporating it thoughtfully into practice. For technologists developing generative AI for healthcare applications, we recommend a major frameshift in thinking away from the expectation that clinicians will "supervise" generative AI. Rather, these organizations and individuals should hold themselves and their technologies to the same set of high standards expected of the clinical workforce and strive to design high-performing, well-studied tools that improve care and foster the therapeutic relationship, not simply those that improve efficiency or market share. We further recommend deep and ongoing partnerships with clinicians and patients as necessary collaborators in this work. And for healthcare organizations, we recommend pursuing a combination of both incremental and transformative change with generative AI, directing resources toward both endeavors, and avoiding the urge to rapidly displace the human clinical workforce with generative AI. We affirm that the practice of medicine remains a fundamentally human endeavor which should be enhanced by technology, not displaced by it.

  View details for DOI 10.1007/s11606-024-09102-0

  View details for PubMedID 39531100

  View details for PubMedCentralID 10714249

• Effect of an Electronic Health Record-Based Intervention on Documentation Practices. Applied clinical informatics Shah, S., Bedgood, M., Devon-Sand, A., Dolphin-Dempsey, C., Cherukuri, V., Weng, K., Lin, S., Sharp, C. 2024

  Abstract

  Please see title page and main document for latest version of abstract.

  View details for DOI 10.1055/a-2367-8564

  View details for PubMedID 39019475

• Artificial Intelligence-Generated Draft Replies to Patient Inbox Messages. JAMA network open Garcia, P., Ma, S. P., Shah, S., Smith, M., Jeong, Y., Devon-Sand, A., Tai-Seale, M., Takazawa, K., Clutter, D., Vogt, K., Lugtu, C., Rojo, M., Lin, S., Shanafelt, T., Pfeffer, M. A., Sharp, C. 2024; 7 (3): e243201

  Abstract

  The emergence and promise of generative artificial intelligence (AI) represent a turning point for health care. Rigorous evaluation of generative AI deployment in clinical practice is needed to inform strategic decision-making.To evaluate the implementation of a large language model used to draft responses to patient messages in the electronic inbox.A 5-week, prospective, single-group quality improvement study was conducted from July 10 through August 13, 2023, at a single academic medical center (Stanford Health Care). All attending physicians, advanced practice practitioners, clinic nurses, and clinical pharmacists from the Divisions of Primary Care and Gastroenterology and Hepatology were enrolled in the pilot.Draft replies to patient portal messages generated by a Health Insurance Portability and Accountability Act-compliant electronic health record-integrated large language model.The primary outcome was AI-generated draft reply utilization as a percentage of total patient message replies. Secondary outcomes included changes in time measures and clinician experience as assessed by survey.A total of 197 clinicians were enrolled in the pilot; 35 clinicians who were prepilot beta users, out of office, or not tied to a specific ambulatory clinic were excluded, leaving 162 clinicians included in the analysis. The survey analysis cohort consisted of 73 participants (45.1%) who completed both the presurvey and postsurvey. In gastroenterology and hepatology, there were 58 physicians and APPs and 10 nurses. In primary care, there were 83 physicians and APPs, 4 nurses, and 8 clinical pharmacists. The mean AI-generated draft response utilization rate across clinicians was 20%. There was no change in reply action time, write time, or read time between the prepilot and pilot periods. There were statistically significant reductions in the 4-item physician task load score derivative (mean [SD], 61.31 [17.23] presurvey vs 47.26 [17.11] postsurvey; paired difference, -13.87; 95% CI, -17.38 to -9.50; P < .001) and work exhaustion scores (mean [SD], 1.95 [0.79] presurvey vs 1.62 [0.68] postsurvey; paired difference, -0.33; 95% CI, -0.50 to -0.17; P < .001).In this quality improvement study of an early implementation of generative AI, there was notable adoption, usability, and improvement in assessments of burden and burnout. There was no improvement in time. Further code-to-bedside testing is needed to guide future development and organizational strategy.

  View details for DOI 10.1001/jamanetworkopen.2024.3201

  View details for PubMedID 38506805

• Building Pandemic-Resilient Primary Care Systems: Lessons Learned From COVID-19. Journal of medical Internet research Jeong, Y., Crowell, T., Devon-Sand, A., Sakata, T., Sattler, A., Shah, S., Tsai, T., Lin, S. 2024; 26: e47667

  Abstract

  On January 30, 2023, the Biden Administration announced its intention to end the existing COVID-19 public health emergency declaration. The transition to a "postpandemic" landscape presents a unique opportunity to sustain and strengthen pandemic-era changes in care delivery. With this in mind, we present 3 critical lessons learned from a primary care perspective during the COVID-19 pandemic. First, clinical workflows must support both in-person and internet-based care delivery. Second, the integration of asynchronous care delivery is critical. Third, planning for the future means planning for everyone, including those with potentially limited access to health care due to barriers in technology and communication. While these lessons are neither unique to primary care settings nor all-encompassing, they establish a grounded foundation on which to construct higher-quality, more resilient, and more equitable health systems.

  View details for DOI 10.2196/47667

  View details for PubMedID 38393776

• MEDALIGN: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records Fleming, S. L., Lozano, A., Haberkorn, W. J., Jindal, J. A., Reis, E., Thapa, R., Blankemeier, L., Genkins, J. Z., Steinberg, E., Nayak, A., Patel, B., Chiang, C., Callahan, A., Huo, Z., Gatidis, S., Adams, S., Fayanju, O., Shah, S. J., Savage, T., Goh, E., Chaudhari, A. S., Aghaeepour, N., Sharp, C., Pfeffer, M. A., Liang, P., Chen, J. H., Morse, K. E., Brunskill, E. P., Fries, J. A., Shah, N. H., Wooldridge, M., Dy, J., Natarajan, S. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2024: 22021-22030

  View details for Web of Science ID 001239985800017

• Perspectives on the Intersection of Electronic Health Records and Health Care Team Communication, Function, and Well-being. JAMA network open Amano, A., Brown-Johnson, C. G., Winget, M., Sinha, A., Shah, S., Sinsky, C. A., Sharp, C., Shanafelt, T., Skeff, K. 2023; 6 (5): e2313178

  Abstract

  Understanding of the interplay between the electronic health record (EHR), health care team relations, and physician well-being is currently lacking. Approaches to cultivate interpersonal interactions may be necessary to complement advancements in health information technology with high-quality team function.To examine ways in which the EHR, health care team functioning, and physician well-being intersect and interact.Secondary qualitative analysis of semistructured interview data from 2 studies used keyword-in-context approaches to identify excerpts related to teams. Thematic analysis was conducted using pattern coding, then organized using the relationship-centered organization model. Two health care organizations in California from March 16 to October 13, 2017, and February 28 to April 21, 2022, participated, with respondents including attending and resident physicians.Across data sets, themes centered around the interactions between the EHR, health care team functioning, and physician well-being. The first study data focused on EHR-related distressing events and their role in attending physician and resident physician emotions and actions. The second study focused on EHR use and daily EHR irritants.The 73 respondents included attending physicians (53 [73%]) and resident physicians (20 [27%]). Demographic data were not collected. Participants worked in ambulatory specialties (33 [45%]), hospital medicine (10 [14%]), and surgery (10 [14%]). The EHR was reported to be the dominant communication modality among all teams. Interviewees indicated that the EHR facilitates task-related communication and is well suited to completing simple, uncomplicated tasks. However, EHR-based communication limited the rich communication and social connection required for building relationships and navigating conflict. The EHR was found to negatively impact team function by promoting disagreement and introducing areas of conflict into team relationships related to medical-legal pressures, role confusion, and undefined norms around EHR-related communication. In addition, interviewees expressed that physician EHR-related distress affects interactions within the team, eroding team well-being.In this study, the EHR supported task-oriented and efficient communication among team members to get work done and care for patients; however, participants felt that the technology shifts attention away from the human needs of the care team that are necessary for developing relationships, building trust, and resolving conflicts. Interventions to cultivate interpersonal interactions and team function are necessary to complement the efficiency benefits of health information technology.

  View details for DOI 10.1001/jamanetworkopen.2023.13178

  View details for PubMedID 37171816

• Predicting Avoidable Health Care Utilization: Practical Considerations for Artificial Intelligence/Machine Learning Models in Population Health. Mayo Clinic proceedings Lin, S., Shah, S., Sattler, A., Smith, M. 2022; 97 (4): 653-657

  View details for DOI 10.1016/j.mayocp.2021.11.039

  View details for PubMedID 35379419

• IT TAKES A VILLAGE: COMPARATIVE ANALYSIS OF STRATEGIES TO IMPROVE PROVIDER ENGAGEMENT FOR WEIGHT MANAGEMENT AT AN ACADEMIC MEDICAL CENTER Shah, S., Lu, C., Tsai, S. A., Reisenberg, A., Calugar, A., Filipowicz, H., Sharp, C., Phadke, A. SPRINGER. 2020: S667–S668

  View details for Web of Science ID 000567143602165

• "MAKING A LIST AND CHECKING IT TWICE": A HIGH BLOOD PRESSURE ADVISORY IN PRIMARY CARE Phadke, A., Sattler, A., Shah, S., Mahoney, M., Sharp, C., Ng, S., Kim, M., Weng, Y. I., Safaeinili, N., Brown-Johnson, C., Desai, M. SPRINGER. 2020: S702

  View details for Web of Science ID 000567143602227

• A Practical Approach to Low-Dose Aspirin for Primary Prevention. JAMA Chiang, K. F., Shah, S. J., Stafford, R. S. 2019

  View details for DOI 10.1001/jama.2019.8388

  View details for PubMedID 31251325

• UTILIZATION OF ELECTRONIC HEALTH RECORD PREFERENCE LISTS TO IMPROVE EFFICIENCY, CONSISTENCY AND SATISFACTION AMONG PROVIDERS IN THE AMBULATORY CARE SETTING Shah, S., Angelo, P., Teuteberg, W. G., Singh, B. SPRINGER. 2018: S837–S838

  View details for Web of Science ID 000442641404248

• Patterns of Systolic Blood Pressure Control in the United States, 2016. Journal of general internal medicine Shah, S. J., Stafford, R. S. 2018

  View details for PubMedID 29679225

• Current Trends of Hypertension Treatment in the United States. American journal of hypertension Shah, S. J., Stafford, R. S. 2017

  Abstract

  To examine current patterns of hypertension (HTN) treatment in the United States, including blood pressure (BP) control, prevalence of different antihypertensive agents, and variations in treatment associated with patient and physician characteristics.We used data from the National Disease and Therapeutic Index (NDTI), a nationally representative physician survey produced by QuintilesIMS. We selected patients with a diagnosis of HTN and identified those prescribed antihypertensive therapies. We analyzed the type of antihypertensive agents prescribed. Extent of BP control, and associated patient and physician characteristics. We calculated 95% confidence intervals that accounted for the multistage NDTI sampling design.Among those treated for HTN in 2014, BP control varied: systolic BP (SBP) ≥160 (15%) vs. SBP 150-159 (9%) vs. SBP 140-149 (19%) vs. SBP 130-139 (26%) vs. SBP <130 (32%). Of those treated for HTN, 29% used of angiotensin-converting enzyme inhibitors (ACEIs); 24%, thiazide-like diuretics; 22%, angiotensin receptor blockers (ARBs), 21%, calcium-channel blockers (CCBs); and 19% beta-blockers. Newer drugs had very limited uptake; no drugs approved after 2002 were used in more than 5% of patients. Selection of agents varied only modestly by patient and physician characteristics.The treatment of HTN in 2014 predominantly involved older medications in 5 major classes of drugs: ACEIs, thiazide diuretics, ARBs, CCBs, and beta-blockers. Selection of antihypertensive agents showed limited variation by age, gender, race, and insurance type. Although 58% of treated patients had SBP <140, 24% had poorly controlled HTN with SBP ≥150, indicating the need for improved treatment.

  View details for DOI 10.1093/ajh/hpx085

  View details for PubMedID 28531239

• Community health center patients' response to and beliefs about outreach promoting clinical preventive services. Preventive medicine reports Brown, T., Lee, J. Y., Long, T., Shah, S., Sanchez, T., Persell, S. D. 2017; 5: 71-74

  Abstract

  We sought community health center (CHC) patients' feedback regarding an outreach intervention promoting primary prevention of cardiovascular disease to patients at increased risk. We performed a telephone survey that assessed whether patients recalled receiving the intervention, what actions occurred in response to the intervention, and patient attitudes regarding receipt of preventive service messages from their CHC. Participants (n = 80) were 89% male, and 59% were black. Among the 88% of respondents who reported a healthcare visit, 84% reported a discussion about cholesterol or heart disease risk with their provider, of these 44% reported a statin was recommended and 89% reported currently taking it. Participants reported high acceptability of receiving preventive service messages, but were less likely to agree that they wanted to receive preventive service messages via text or email compared to other modes of contact. Our results show that outreach programs to promote indicated preventive services were viewed positively by this patient group. We also identified areas where the CVD prevention program may have lost effectiveness.

  View details for PubMedID 27957409

  View details for PubMedCentralID PMC5148778

• Individualized Risk Communication and Outreach for Primary Cardiovascular Disease Prevention in Community Health Centers Randomized Trial CIRCULATION-CARDIOVASCULAR QUALITY AND OUTCOMES Persell, S. D., Brown, T., Lee, J. Y., Shah, S., Henley, E., Long, T., Luther, S., Lloyd-Jones, D. M., Jean-Jacques, M., Kandula, N. R., Sanchez, T., Baker, D. W. 2015; 8 (6): 560-566

  Abstract

  Many eligible primary cardiovascular disease prevention candidates are not treated with statins. Electronic health record data can identify patients with increased cardiovascular disease risk.We performed a pragmatic randomized controlled trial at community health centers in 2 states. Participants were men aged ≥35 years and women ≥45 years, without cardiovascular disease or diabetes mellitus, and with a 10-year risk of coronary heart disease of at least 10%. The intervention group received telephone and mailed outreach, individualized based on patients' cardiovascular disease risk and uncontrolled risk factors, provided by lay health workers. Main outcomes included: documented discussion of medication treatment for cholesterol with a primary care clinician, receipt of statin prescription within 6 months, and low-density lipoprotein (LDL)-cholesterol repeated and at least 30 mg/dL lower than baseline within 1 year. Six hundred forty-six participants (328 and 318 in the intervention and control groups, respectively) were included. At 6 months, 26.8% of intervention and 11.6% of control patients had discussed cholesterol treatment with a primary care clinician (odds ratio, 2.79; [95% confidence interval, 2.25-3.46]). Statin prescribing occurred for 10.1% in the intervention group and 6.0% in the control group (odds ratio, 1.76; [95% confidence interval, 0.90-3.45]). The cholesterol outcome did not differ, and the majority of patients did not repeat lipid levels during follow-up.Risk communication and lay outreach increased cholesterol treatment discussions with primary care clinicians. However, most discussions did not result in statin prescribing. For outreach to be successful, it should be combined with interventions to encourage clinicians to follow contemporary risk-based cholesterol treatment guidelines.URL: http://www.clincialtrials.gov. Unique identifier: NCT01610609.

  View details for DOI 10.1161/CIRCOUTCOMES.115.001723

  View details for Web of Science ID 000364791200006

  View details for PubMedID 26555123

• Parenteral Nutrition Use and Associated Outcomes in a Select Cohort of Low Birth Weight Neonates AMERICAN JOURNAL OF PERINATOLOGY Robinson, D. T., Shah, S., Murthy, K. 2014; 31 (11): 933-938

  Abstract

  The aim of this study is to assess the influence of parenteral nutrition (PN) on the time to regain birth weight in premature neonates born between 1,500 and 2,499 g.A retrospective analysis stratified premature neonates born between 1,500 and 2,499 g by receipt of PN or intravenous dextrose at ≤ 72 hours of age. The primary outcome was the time to regain birth weight. Secondary measures included preterm-associated morbidities, time to achieve predefined enteral nutrition milestones, and length of stay. Multivariable regression estimated associations between PN and time to achieve nutrition milestones.Among 260 eligible neonates, those receiving PN (53%) were less mature, weighed less at birth, had a higher index of illness severity, and higher prevalence of preterm-associated morbidities (p < 0.01). The time to regain birth weight (PN, 9.4 ± 3.5 d; no PN, 9.5 ± 3.4 d) was similar between groups. Regression analysis adjusting for gestational age, illness severity, and sepsis demonstrated that PN exposure was associated with a greater time to achieve nutrition milestones and length of stay (p < 0.05).Although its impact on growth remains uncertain among premature neonates born between 1,500 and 2,499 g, PN was independently associated with a greater time to achieve nutrition milestones.

  View details for DOI 10.1055/s-0033-1363770

  View details for Web of Science ID 000343344800002

  View details for PubMedID 24515618