YWYingjie Weng

Yingjie Weng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yingjie Weng has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Measured Left Ventricular Mass Ratio for Size-Matching Identifies Graft Failure Risk in Obese Heart Transplantation

    by Christian O’DOnnell, Juka S. Kim, Jonathan Hu, Erik J. Henricksen, Alexander K. Karius, Corbin Goerlich, Shiqi Zhang, Yingjie Weng, Jonathan Zaroff, Louise Y. Sun, et al.

  • Lack of association between donor left ventricular hypertrophy and graft survival in the contemporary era of heart transplantation

    by Jamal H. Mahar, Brian Wayda, Yingjie Weng, Shiqi Zhang, Jonathan G. Zaroff, Kiran K. Khush


  • Prediction of Donor Heart Acceptance for Transplant and Its Clinical Implications: Results From The Donor Heart Study

    by Brian Wayda, Yingjie Weng, Shiqi Zhang, Helen Luikart, Thomas Pearson, Javier Nieto, Bruce Nicely, P.J. Geraghty, John Belcher, John Nguyen, et al.

    BACKGROUND: Despite a shortage of potential donors for heart transplant in the United States, most potential donor hearts are discarded. We evaluated predictors of donor heart acceptance in the United States and applied machine learning methods to improve prediction. METHODS: We included a nationwide (2005–2020) cohort of potential heart donors in the United States (n=73 948) from the Scientific Registry of Transplant Recipients and a more recent (2015–2020) rigorously phenotyped cohort of potential donors from DHS (Donor Heart Study; n=4130). We identified predictors of acceptance for heart transplant in both cohorts using multivariate logistic regression, incorporating time-interaction terms to characterize their varying effects over time. We fit models predicting acceptance for transplant in a 50% training subset of DHS using logistic regression, least absolute shrinkage and selection operator, and random forest algorithms and compared their performance in the remaining 50% (test) of the subset. RESULTS: Predictors of donor heart acceptance were similar in the nationwide and DHS cohorts. Among these, older age ( P value for time interaction, 0.0001) has become increasingly predictive of discard over time while other factors, including those related to drug use, infection, and mild cardiac diagnostic abnormalities, have become less influential ( P value for time interaction, <0.05 for all). A random forest model (area under the curve, 0.908; accuracy, 0.831) outperformed other prediction algorithms in the test subset and was used as the basis of a novel web-based prediction tool. CONCLUSIONS: Predictors of donor heart acceptance for transplantation have changed significantly over the last 2 decades, likely reflecting evolving evidence regarding their impact on posttransplant outcomes. Real-time prediction of donor heart acceptance, using our web-based tool, may improve efficiency during donor management and heart allocation.


  • Open Access

    Education Research: Educational Outcomes Associated With the Introduction of a Neurohospitalist Program

    by Shefali Dujari, Brian J. Scott, Carl A. Gold, Yingjie Weng, Kathryn A. Kvam

    As the prevalence of the neurohospitalist (NH) practice model grows, understanding its effect on trainee education is imperative. We sought to determine the impact of an academic NH program on neurology resident evaluations of faculty teaching. We performed a retrospective study of faculty teaching evaluations before and after the implementation of a full-time NH service. Primary outcomes were neurology resident evaluations of faculty teaching, which were compared in the pre-NH period (August 2010-July 2014) vs the post-NH period (August 2016-July 2018). In a secondary analysis, we used the difference-in-difference approach to analyze the effect of introducing the NH service on resident evaluation of faculty teaching compared with stroke and neurocritical care faculty controls. We performed an additional descriptive analysis of medical student evaluation of faculty teaching and described Residency In-service Training Exam scores and Accreditation Council for Graduate Medical Education (ACGME) resident survey data before and after the intervention. There were 368 resident and 360 medical student evaluations of faculty teaching during the study period. Compared to the pre-NH period, the post-NH period had significantly higher resident evaluations of faculty teaching in 19 of 27 questions of faculty teaching, across 5 of the 6 ACGME core competencies. Within the competencies of patient care, practice-based learning and improvement, and systems-based practice, the NH teaching faculty were rated significantly higher across all questions. In the difference-in-difference model, resident evaluations of faculty teaching following the implementation of the NH service remained significantly improved compared with controls in teaching evidence-based medicine, teaching diagnostic algorithms, and explaining rationale for clinical decisions. Medical student ratings of faculty teaching were unchanged in the pre-NH and the post-NH period. Neurology residents may benefit from the clinical expertise of NHs and their ability to teach evidence-based practice and role model systems-based practice. Given the central role NHs may play in trainee education, additional focus on both the local and national levels should be dedicated to further developing the teaching skills of NHs.


  • Open Access

    Influence of a Large Language Model on Diagnostic Reasoning: A Randomized Clinical Vignette Study

    by Ethan Goh, Robert Gallo, Jason Hom, Eric Strong, Yingjie Weng, Hannah Kerman, Josephine Cool, Zahir Kanjee, Andrew S. Parsons, Neera Ahuja, et al.

    Importance Diagnostic errors are common and cause significant morbidity. Large language models (LLMs) have shown promise in their performance on both multiple-choice and open-ended medical reasoning examinations, but it remains unknown whether the use of such tools improves diagnostic reasoning. Objective To assess the impact of the GPT-4 LLM on physicians’ diagnostic reasoning compared to conventional resources. Design Multi-center, randomized clinical vignette study. Setting The study was conducted using remote video conferencing with physicians across the country and in-person participation across multiple academic medical institutions. Participants Resident and attending physicians with training in family medicine, internal medicine, or emergency medicine. Intervention(s) Participants were randomized to access GPT-4 in addition to conventional diagnostic resources or to just conventional resources. They were allocated 60 minutes to review up to six clinical vignettes adapted from established diagnostic reasoning exams. Main Outcome(s) and Measure(s) The primary outcome was diagnostic performance based on differential diagnosis accuracy, appropriateness of supporting and opposing factors, and next diagnostic evaluation steps. Secondary outcomes included time spent per case and final diagnosis. Results 50 physicians (26 attendings, 24 residents) participated, with an average of 5.2 cases completed per participant. The median diagnostic reasoning score per case was 76.3 percent (IQR 65.8 to 86.8) for the GPT-4 group and 73.7 percent (IQR 63.2 to 84.2) for the conventional resources group, with an adjusted difference of 1.6 percentage points (95% CI -4.4 to 7.6; p=0.60). The median time spent on cases for the GPT-4 group was 519 seconds (IQR 371 to 668 seconds), compared to 565 seconds (IQR 456 to 788 seconds) for the conventional resources group, with a time difference of -82 seconds (95% CI -195 to 31; p=0.20). GPT-4 alone scored 15.5 percentage points (95% CI 1.5 to 29, p=0.03) higher than the conventional resources group. Conclusions and Relevance In a clinical vignette-based study, the availability of GPT-4 to physicians as a diagnostic aid did not significantly improve clinical reasoning compared to conventional resources, although it may improve components of clinical reasoning such as efficiency. GPT-4 alone demonstrated higher performance than both physician groups, suggesting opportunities for further improvement in physician-AI collaboration in clinical practice.


  • Open Access

    Acquisition of Cardiac Point-of-Care Ultrasound Images With Deep Learning

    by Evan Baum, Megha D. Tandel, Casey Ren, Yingjie Weng, Matthew Pascucci, John Kugler, Kathryn Cardoza, Andre Kumar


  • Open Access

    A quality-improvement approach to urgent-care antibiotic stewardship for respiratory tract infections during the COVID-19 pandemic: Lessons learned

    by Sharon K. Ong’uTi, Maja Artandi, Brooke Betts, Yingjie Weng, Manisha Desai, Christopher Lentz, Ian Nelligan, David R. Ha, Marisa K. Holubar

    Objective: We investigated a decrease in antibiotic prescribing for respiratory illnesses in 2 academic urgent-care clinics during the coronavirus disease 2019 (COVID-19) pandemic using semistructured clinician interviews.Methods: We conducted a quality-improvement project from November 2020 to May 2021. We investigated provider antibiotic decision making using a mixed-methods explanatory design including interviews. We analyzed transcripts using a thematic framework approach to identify emergent themes. Our performance measure was antibiotic prescribing rate (APR) for encounters with respiratory diagnosis billing codes. We extracted billing and prescribing data from the electronic medical record and assessed differences using run charts, p charts and generalized linear regression.Results: We observed significant reductions in the APR early during the COVID-19 pandemic (relative risk [RR], 0.20; 95% confidence interval [CI], 0.17–0.25), which was maintained over the study period (P < .001). The average APRs were 14% before the COVID-19 pandemic, 4% during the QI project, and 7% after the project. All providers prescribed less antibiotics for respiratory encounters during COVID-19, but only 25% felt their practice had changed. Themes from provider interviews included changing patient expectations and provider approach to respiratory encounters during COVID-19, the impact of increased telemedicine encounters, and the changing epidemiology of non–COVID-19 respiratory infections.Conclusions: Our findings suggest that the decrease in APR was likely multifactorial. The average APR decreased significantly during the pandemic. Although the APR was slightly higher after the QI project, it did not reach prepandemic levels. Future studies should explore how these factors, including changing patient expectations, can be leveraged to improve urgent-care antibiotic stewardship.


  • A Cross-sectional Study Characterizing Pediatric Temperature Percentiles in Children at Well-Child Visits

    by Rebecca Dang, Alan R. Schroeder, Yingjie Weng, Marie E. Wang, Anisha I. Patel


  • Testing Hypnotizability by Phone: Development and Validation of the Remote Hypnotic Induction Profile (rHIP)

    by Jessie Kittle, Emma Zhao, Katy Stimpson, Yingjie Weng, David Spiegel

    Standard hypnotizability scales require physical contact or direct observation by tester and participant. The authors addressed this limitation by developing and testing the remote Hypnotic Induction Profile (rHIP), a hypnotizability test derived from the Hypnotic Induction Profile that is completed by telephone. To assess the validity of the rHIP, 56 volunteers naïve to hypnotizability testing completed both the HIP and the rHIP, with order of testing randomized. Results indicate a strong correlation between HIP and rHIP scores, r s =.71(0.53–0.84), p <.0001, and good concordance, difference =.03(−0.53, 0.59), p =.91, independent of testing order. The rHIP had few complications. Possible advantages of using the rHIP include improving patient expectancy prior to scheduling a hypnosis session, increasing access to hypnotizability testing for remote interventions, and obviating resource-intensive in-person hypnotizability screening for trials that exclude subjects with certain scores.


  • Remote Hypnotic Induction Profile

    by Jessie Kittle, Emma Zhao, Katy Stimpson, Yingjie Weng, David Spiegel