Browsing by Subject "Triage"
Now showing 1 - 10 of 11
Results Per Page
Sort Options
Item Accuracy of a Commercial Large Language Model (ChatGPT) to Perform Disaster Triage of Simulated Patients Using the Simple Triage and Rapid Treatment (START) Protocol: Gage Repeatability and Reproducibility Study(JMIR, 2024-09-30) Franc, Jeffrey Micheal; Hertelendy, Attila Julius; Cheng, Lenard; Hata, Ryan; Verde, Manuela; Emergency Medicine, School of MedicineBackground: The release of ChatGPT (OpenAI) in November 2022 drastically reduced the barrier to using artificial intelligence by allowing a simple web-based text interface to a large language model (LLM). One use case where ChatGPT could be useful is in triaging patients at the site of a disaster using the Simple Triage and Rapid Treatment (START) protocol. However, LLMs experience several common errors including hallucinations (also called confabulations) and prompt dependency. Objective: This study addresses the research problem: "Can ChatGPT adequately triage simulated disaster patients using the START protocol?" by measuring three outcomes: repeatability, reproducibility, and accuracy. Methods: Nine prompts were developed by 5 disaster medicine physicians. A Python script queried ChatGPT Version 4 for each prompt combined with 391 validated simulated patient vignettes. Ten repetitions of each combination were performed for a total of 35,190 simulated triages. A reference standard START triage code for each simulated case was assigned by 2 disaster medicine specialists (JMF and MV), with a third specialist (LC) added if the first two did not agree. Results were evaluated using a gage repeatability and reproducibility study (gage R and R). Repeatability was defined as variation due to repeated use of the same prompt. Reproducibility was defined as variation due to the use of different prompts on the same patient vignette. Accuracy was defined as agreement with the reference standard. Results: Although 35,102 (99.7%) queries returned a valid START score, there was considerable variability. Repeatability (use of the same prompt repeatedly) was 14% of the overall variation. Reproducibility (use of different prompts) was 4.1% of the overall variation. The accuracy of ChatGPT for START was 63.9% with a 32.9% overtriage rate and a 3.1% undertriage rate. Accuracy varied by prompt with a maximum of 71.8% and a minimum of 46.7%. Conclusions: This study indicates that ChatGPT version 4 is insufficient to triage simulated disaster patients via the START protocol. It demonstrated suboptimal repeatability and reproducibility. The overall accuracy of triage was only 63.9%. Health care professionals are advised to exercise caution while using commercial LLMs for vital medical determinations, given that these tools may commonly produce inaccurate data, colloquially referred to as hallucinations or confabulations. Artificial intelligence-guided tools should undergo rigorous statistical evaluation-using methods such as gage R and R-before implementation into clinical settings.Item Altered standards of care for health care providers in the pandemic influenza(Indiana University, 2009) Kinney, Eleanor D.; McCabe, Heather A.; Gilbert, Amy Lewis; Shisler, Janna JoPandemic influenza will pose tremendous challenges to health care providers, state public health authorities, and the public. All will have to conduct business under the most adverse of circumstances. It will be difficult for providers to meet the customary legal standards of care imposed by state and federal regulatory authorities, as well as the common law tort system. This white paper will explore the legal issues associated with altered standards of care in pandemic influenza.Item An ethics framework for consolidating and prioritizing COVID-19 clinical trials(Sage, 2021) Meyer, Michelle N.; Gelinas, Luke; Bierer, Barbara E.; Chandros Hull, Sara; Joffe, Steven; Magnus, David; Mohapatra, Seema; Sharp, Richard R.; Spector-Bagdady, Kayte; Sugarman, Jeremy; Wilfond, Benjamin S.; Fernandez Lynch, Holly; Robert H. McKinney School of LawGiven the dearth of established safe and effective interventions to respond to COVID-19, there is an urgent ethical imperative to conduct meaningful clinical research. The good news is that interventions to be tested are not in short supply. Unfortunately, the human and material resources needed to conduct these trials are finite. It is essential that trials be robust and meet enrollment targets and that lower-quality studies not be permitted to displace higher-quality studies, delaying answers to critical questions. Yet, with few exceptions, existing research review bodies and processes are not designed to ensure these conditions are satisfied. To meet this challenge, we offer guidance for research institutions about how to ethically consolidate and prioritize COVID-19 clinical trials, while recognizing that consolidation and prioritization should also take place upstream (among manufacturers and funders) and at a higher level (e.g., nationally). In our proposed three-stage process, trials must first meet threshold criteria. Those that do are evaluated in a second stage to determine whether the institution has sufficient capacity to support all proposed trials. If it does not, the third stage entails evaluating studies against two additional sets of comparative prioritization criteria: those specific to the study and those that aim to advance diversification of an institution’s research portfolio. To implement these criteria fairly, we propose that research institutions form COVID-19 research prioritization committees. We briefly discuss some important attributes of these committees, drawing on the authors’ experiences at our respective institutions. Although we focus on clinical trials of COVID-19 therapeutics, our guidance should prove useful for other kinds of COVID-19 research, as well as non-pandemic research, which can raise similar challenges due to the scarcity of research resources.Item Analytical and Clinical Sample Performance Characteristics of the Onclarity Assay for the Detection of Human Papillomavirus(American Society for Microbiology, 2020-12-17) Young, Stephen; Vaughan, Laurence; Yanson, Karen; Eckert, Karen; Li, Aojun; Harris, James; Ermel, Aaron; Williams, James A.; Al-Ghoul, Mohammad; Cammarata, Catherine L.; Taylor, Stephanie N.; Luff, Ronald; Cooper, Charles K.; Van Der Pol, Barbara; Medicine, School of MedicineThe objective of this study was to determine the result reproducibility and performance of the BD Onclarity human papillomavirus (HPV) assay (Onclarity) on the BD Viper LT platform using both contrived and clinical specimens. Reproducibility was assessed in BD SurePath liquid-based cytology (LBC) medium (SurePath) using contrived panels (HPV genotype 16 [HPV16] positive, HPV18 positive, or HPV45 positive) or clinical specimens (HPV16, -18, -31, -33/58, -45, or -52 positive or HPV negative). In addition, specimens from 3,879 individuals from the Onclarity trial were aliquoted prior to or following cytology processing and tested for HPV. Finally, specimens were collected using either the Cervex-Brush or Cytobrush (or Cytobrush/spatula) for comparison of HPV results. Contrived specimens showed >95% concordance with the expected results, and pooled clinical specimens had standard deviations and coefficients of variation ranging from 0.87 to 1.86 and 2.9% to 5.6%, respectively. For precytology and postcytology aliquot analyses, specimens showed >98.0% overall agreement and mean differences in cycle threshold (CT ) scores for HPV ranging from -0.07 to 0.31. Positivity rates were close between the Cervex-Brush and Cytobrush/spatula for all age groups tested. Onclarity results are reproducible and reliable, regardless of sample collection before or after cytology aliquoting. Onclarity performs well regardless of the method of specimen collection (Cervex-Brush or Cytobrush/spatula) for cervical cancer screening.Item Assessing Risk of Future Suicidality in Emergency Department Patients(Wiley, 2020-04-02) Brucker, Krista; Duggan, Carter; Niezer, Joseph; Roseberry, Kyle; Le-Niculescu, Helen; Niculescu, Alexander B.; Kline, Jeffrey A.; Emergency Medicine, School of MedicineBackground. Emergency Departments (ED) are the first line of evaluation for patients at risk and in crisis, with or without overt suicidality (ideation, attempts). Currently employed triage and assessments methods miss some of the individuals who subsequently become suicidal. The Convergent Functional Information for Suicidality (CFI-S) 22 item checklist of risk factors, that does not ask directly about suicidal ideation, has demonstrated good predictive ability for suicidality in previous studies in psychiatric outpatients, but has not been tested in the real world-setting of emergency departments (EDs). Methods. We administered CFI-S prospectively to a convenience sample of consecutive ED patients. Median administration time was 3 minutes. Patients were also asked at triage about suicidal thoughts or intentions per standard ED suicide clinical screening (SCS), and the treating ED physician was asked to fill a physician gestalt visual analog scale (VAS) for likelihood of future suicidality spectrum events (SSE) (ideation, preparatory acts, attempts, completed suicide). We performed structured chart review and telephone follow-up at 6 months post index visit. Results. The median time to complete the CFI-S was three minutes (1st to 3rd quartile 3–6 minutes). Of the 338 patients enrolled, 45 (13.3%) were positive on the initial SCS, and 32 (9.5%) experienced a SSE in the 6 months follow-up. Overall, across genders, SCS had a modest diagnostic discrimination for future SSE (ROC AUC 0.63,). The physician VAS was better (AUC 0.76 CI 0.66–0.85), and the CFI-S was slightly higher (AUC 0.81, CI 0.76–0.87). The top CFI-S differentiating items were psychiatric illness, perceived uselessness, and social isolation. The top CFI-S items were family history of suicide, age, and past history of suicidal acts. Conclusions. Using CFI-S, or some of its items, in busy EDs may help improve the detection of patients at high risk for future suicidality.Item Cost Minimization Analysis of a Teledermatology Triage System in a Managed Care Setting(American Medical Association, 2021) Zakaria, Adam; Miclau, Theodore A.; Maurer, Toby; Leslie, Kieron S.; Amerson, Erin; Dermatology, School of MedicineImportance: Teledermatology (TD) enables remote triage and management of dermatology patients. Previous analyses of TD systems have demonstrated improved access to care but an inconsistent fiscal impact. Objective: To compare the organizationwide cost of managing newly referred dermatology patients within a TD triage system vs a conventional dermatology care model at the Zuckerberg San Francisco General Hospital and Trauma Center (hereafter referred to as the ZSFG) in California. Design, setting, and participants: A retrospective cost minimization analysis was conducted of 2098 patients referred to the dermatology department at the ZSFG between June 1 and December 31, 2017. Intervention: Implementation of the TD triage system in January 2015. Main outcomes and measures: The main outcome was mean cost to the health care organization to manage newly referred dermatology patients with or without TD triage. To estimate costs, decision-tree models were constructed to characterize possible care paths with TD triage and within a conventional dermatology care model. Costs associated with primary care visits, dermatology visits, and TD visits were then applied to the decision-tree models to estimate the mean cost of managing patients following each care path for 6 months. The mean cost for each visit type incorporated personnel costs, with the mean cost per TD consultation also incorporating software implementation and maintenance costs. Finally, ZSFG patient data were applied within the models to evaluate branch probabilities, enabling calculation of mean cost per patient within each model. Results: The analysis captured 2098 patients (1154 men [55.0%]; mean [SD] age, 53.4 [16.8] years), with 1099 (52.4%) having Medi-Cal insurance and 879 (41.9%) identifying as non-White. In the decision-tree model with TD triage, the mean (SD) cost per patient to the health care organization was $559.84 ($319.29). In the decision-tree model for conventional dermatology care, the mean (SD) cost per patient was $699.96 ($390.24). Therefore, the TD model demonstrated a statistically significant mean (SE) cost savings of $140.12 ($11.01) per patient. Given an annual dermatology referral volume of 3150 patients, the analysis estimates an annual savings of $441 378. Conclusions and relevance: Implementation of a TD triage system within the dermatology department at the ZSFG was associated with cost savings, suggesting that managed health care settings may experience significant cost savings from using TD to triage and manage patients.Item Ethics guide for health care practitioners: working under conditions of an influenza pandemic. Plan, Prepare, Practice [Pocket version].(2009-12-01T18:49:23Z) Indiana University Center for Bioethics; Indiana State Department of HealthThe Ethics Toolkit is designed to assist health care providers in carrying out their ethical responsibilities of caring for patients and families within the clinical environment during an influenza pandemic. In particular, the Toolkit is designed to give practical input on key issues facing health care practitioners, specifically: Altered Standards of Care; Vaccine and Antiviral Provision; Triage; and Workforce Management. Other issues are discussed in the Toolkit, but receive less comprehensive attention. The input for each of these issues is based on an Ethical Framework that provides a reasoned basis for decision making. In addition to this pocket-sized version, a 16 page, full-sized, color brochure is also available. Likewise, a separate, single sheet, "Patient Guide" (page 15) is available.Item Ethics guide for health care practitioners: working under conditions of an influenza pandemic. Plan, prepare, practice.(2009-12-01T18:37:50Z) Indiana University Center for Bioethics; Indiana State Department of HealthThe Ethics Toolkit is designed to assist health care providers in carrying out their ethical responsibilities of caring for patients and families within the clinical environment during an influenza pandemic. In particular, the Toolkit is designed to give practical input on key issues facing health care practitioners, specifically: Altered Standards of Care; Vaccine and Antiviral Provision; Triage; and Workforce Management. Other issues are discussed in the Toolkit, but receive less comprehensive attention. The input for each of these issues is based on an Ethical Framework that provides a reasoned basis for decision making. In addition to this full sized, 16 page color brochure, the Toolkit is also available in a pocket-sized version. Likewise, a separate, single sheet, "Patient Guide" (page 15) is available.Item Fallacy of Median Door-to-ECG Time: Hidden Opportunities for STEMI Screening Improvement(American Heart Association, 2022) Yiadom, Maame Yaa A.B.; Gong, Wu; Patterson, Brian W.; Baugh, Christopher W.; Mills, Angela M.; Gavin, Nicholas; Podolsky, Seth R.; Salazar, Gilberto; Mumma, Bryn E.; Tanski, Mary; Hadley, Kelsea; Azzo, Caitlin; Dorner, Stephen C.; Ulintz, Alexander; Liu, Dandan; Emergency Medicine, School of MedicineBackground: ST‐segment elevation myocardial infarction (STEMI) guidelines recommend screening arriving emergency department (ED) patients for an early ECG in those with symptoms concerning for myocardial ischemia. Process measures target median door‐to‐ECG (D2E) time of 10 minutes. Methods and Results: This 3‐year descriptive retrospective cohort study, including 676 ED‐diagnosed patients with STEMI from 10 geographically diverse facilities across the United States, examines an alternative approach to quantifying performance: proportion of patients meeting the goal of D2E≤10 minutes. We also identified characteristics associated with D2E>10 minutes and estimated the proportion of patients with screening ECG occurring during intake, triage, and main ED care periods. We found overall median D2E was 7 minutes (IQR:4–16; range: 0–1407 minutes; range of ED medians: 5–11 minutes). Proportion of patients with D2E>10 minutes was 37.9% (ED range: 21.5%–57.1%). Patients with D2E>10 minutes, compared to those with D2E≤10 minutes, were more likely female (32.8% versus 22.6%, P=0.005), Black (23.4% versus 12.4%, P=0.005), non‐English speaking (24.6% versus 19.5%, P=0.032), diabetic (40.2% versus 30.2%, P=0.010), and less frequently reported chest pain (63.3% versus 87.4%, P<0.001). ECGs were performed during ED intake in 62.1% of visits, ED triage in 25.3%, and main ED care in 12.6%. Conclusions: Examining D2E>10 minutes can identify opportunities to improve care for more ED patients with STEMI. Our findings suggest sex, race, language, and diabetes are associated with STEMI diagnostic delays. Moving the acquisition of ECGs completed during triage to intake could achieve the D2E≤10 minutes goal for 87.4% of ED patients with STEMI. Sophisticated screening, accounting for differential risk and diversity in STEMI presentations, may further improve timely detection.Item Patient guide: Questions and answers about Altered Standards of Care. Plan, prepare, practice.(2009-12-01T18:57:14Z) Indiana State Department of Health; Indiana University Center for BioethicsThis patient guide address the following questions: What is an influenza (flu) pandemic? What are Altered Standards of Care? Will vaccines ("flu shot") and antiviral medicines work? and How will my family and I get vaccines and antiviral medicine? In addition to this patient guide, see the related: "Ethics guide for health care practitioners: working under conditions of an influenza pandemic. Plan, Prepare, Practice."