NRNicholas W. Rizer

Nicholas W. Rizer

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Nicholas W. Rizer has a total of 25 co-authors. Here are the top co-authors by number of shared publications:

  • Alexander H. Chang

    1 shared publication
  • Alexandra T. Strauss

    Division of Gastroenterology & Hepatology, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD. USA; Malone Center of Engineering in Healthcare, Johns Hopkins Whiting School of Engineering, Baltimore, MD. USA

    1 shared publication
  • Daniel S. Herman

    Leonard Davis Institute, University of Pennsylvania, Philadelphia, PA, USA; Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA, USA

    1 shared publication
  • Debbie L Cohen

    Division of Renal, Electrolyte, and Hypertension, Department of Medicine, The Perelman School of Medicine, University of Pennsylvania

    1 shared publication
  • Edbert B. Hsu

    1 shared publication
  • Eili Klein

    Department of Emergency Medicine, Johns Hopkins University School of Medicine, Baltimore, MD

    1 shared publication

Latest Publications

  • Top Cited Papers
    Open Access

    Early Clinical Deterioration Among Emergency Department Boarders: A Retrospective Analysis

    by Nicholas W. Rizer, Eili Klein, Martin S. Copenhaver, Xihan Zhao, Gabor D. Kelen, Jeremiah S. Hinson


  • Hospital-based shootings in the United States, 2000-2019

    by Nicholas Rizer, Gregory Jasani, Alexander H. Chang, Yu-Hsiang Hsieh, Edbert B. Hsu

    Introduction: Violence in healthcare settings, particularly directed toward healthcare workers, has received increasing attention in the United States (US). However, there is limited evidence on trends in hospital-based gun violence. We aimed to better understand the characteristics of US hospital-based shootings over two decades. Methods: A search of Nexis Uni was conducted for newspaper articles, newswires, web news articles, or magazines mentioning hospital-based shootings during the period from 2000 to 2019. Articles were screened for relevance, and data were subsequently extracted and categorized by two independent reviewers. Results: From 2000 to 2019, we identified 148 hospital-based shootings with 241 victims. Mean number of shootings increased from 3.4/year during 2000-2004 to 8.4/year during 2005-2009 (rate ratio [RR]: 2.5, 95 percent confidence interval [CI]: 1.4, 4.3), to 11.2/year during 2010-2014 (RR: 1.3, 95 percent CI: 0.9, 2.0) but decreased to 6.6/year during 2015-2019 (RR: 0.6, 95 percent CI: 0.4, 0.9). An overwhelming majority (91 percent) of shooters were male with a median age of 46. The most frequent motive was the spillover of social violence (22 percent). The majority (59 percent) of events involved a single victim, although 14 percent had three or more victims. Discussion: Hospital-based shootings remain a persistent threat, with the 2010-2014 period representing increased risk. While motives were varied, spillover of social violence was the most frequent. These findings can potentially inform prevention and mitigation strategies for hospital-based gun violence.


    • 19 February 2025
      • Vol. 9  (3)
    Open Access

    Automated identification of incidental hepatic steatosis on Emergency Department imaging using large language models

    by Tyrus Vong, Nicholas Rizer, Vedant Jain, Valerie L. Thompson, Mark Dredze, Eili Y. Klein, Jeremiah S. Hinson, Tanjala Purnell, Stephen Kwak, Tinsay Woreta, et al.

    Hepatic steatosis is a precursor to more severe liver disease, increasing morbidity and mortality risks. In the Emergency Department, routine abdominal imaging often reveals incidental hepatic steatosis that goes undiagnosed due to the acute nature of encounters. Imaging reports in the electronic health record contain valuable information not easily accessible as discrete data elements. We hypothesized that large language models could reliably detect hepatic steatosis from reports without extensive natural language processing training. We identified 200 adults who had CT abdominal imaging in the Emergency Department between August 1, 2016, and December 31, 2023. Using text from imaging reports and structured prompts, 3 Azure OpenAI models (ChatGPT 3.5, 4, 4o) identified patients with hepatic steatosis. We evaluated model performance regarding accuracy, inter-rater reliability, sensitivity, and specificity compared to physician reviews. The accuracy for the models was 96.2% for v3.5, 98.3% for v4, and 98.8% for v4o. Inter-rater reliability ranged from 0.99 to 1.00 across 10 iterations. Mean model confidence scores were 2.9 (SD 0.8) for v3.5, 3.9 (SD 0.3) for v4, and 4.0 (SD 0.07) for v4o. Incorrect evaluations were 76 (3.8%) for v3.5, 34 (1.7%) for v4, and 25 (1.3%) for v4o. All models showed sensitivity and specificity above 0.9. Large language models can assist in identifying incidental conditions from imaging reports that otherwise may be missed opportunities for early disease intervention. Large language models are a democratization of natural language processing by allowing for a user-friendly, expansive analyses of electronic medical records without requiring the development of complex natural language processing models.


  • Open Access

    Effect of Hypokalemia on Screening for Primary Aldosteronism

    by Nicholas W Rizer, Xiruo Ding, Debbie L Cohen, Daniel S Herman

    Context: Primary aldosteronism (PA) is a common, underdiagnosed, and treatable cause of hypertension. Guidelines recommend testing for hypokalemia, but current practices and their impact are unknown. Objective: To estimate the impact of hypokalemia on the results of PA screening in clinical practice. Methods: We studied electronic health records for adults who received longitudinal care within a large, integrated health system between 2007 and 2017 and underwent paired blood aldosterone and renin testing. Patients were grouped based on concurrent blood potassium concentrations. Results: We found that 2,940 (82%) of the 3,571 patients screened for PA had concurrent potassium testing. Among all patients with a negative PA screen, 18% of patients did not have concurrent potassium testing and 14% of those tested were hypokalemic. Of the screen-negative hypokalemic patients, 77% were not retested. Among patients with repeated screens, we found that initial potassium concentration was a predictor of PA screen positivity on repeat. A one standard deviation lower initial potassium concentration was associated with a 74% higher odds of screen positivity on repeat, independent of initial aldosterone and renin results. Conclusions: In-practice clinical data demonstrate that unrecognized and uncorrected hypokalemia contributes to the underdiagnosis of PA. Universal potassium testing and rescreening for PA in the setting of hypokalemia would likely substantially improve the identification and thereby management of PA.