A5043082025- Emergency and Acute Care Studies
- Innovations in Medical Education
- Clinical Reasoning and Diagnostic Skills
- Sepsis Diagnosis and Treatment
- Machine Learning in Healthcare
- Clostridium difficile and Clostridium perfringens research
- Nosocomial Infections in ICU
- Radiology practices and education
- Trauma and Emergency Care Studies
- Surgical Simulation and Training
- COVID-19 diagnosis using AI
- COVID-19 and healthcare impacts
- Healthcare Policy and Management
- Bacterial Identification and Susceptibility Testing
- Primary Care and Health Outcomes
- Artificial Intelligence in Healthcare
- Health Systems, Economic Evaluations, Quality of Life
- Frailty in Older Adults
- Healthcare cost, quality, practices
- Streptococcal Infections and Treatments
- Traffic and Road Safety
- Occupational Health and Safety Research
- Artificial Intelligence in Healthcare and Education
- Economic and Financial Impacts of Cancer
- Multiple and Secondary Primary Cancers
Michigan Medicine
2025
University of Michigan
2020-2024
University of Wisconsin–Madison
2015-2016
Madison Group (United States)
2015
<h3>Importance</h3> The Epic Sepsis Model (ESM), a proprietary sepsis prediction model, is implemented at hundreds of US hospitals. ESM's ability to identify patients with has not been adequately evaluated despite widespread use. <h3>Objective</h3> To externally validate the ESM in and evaluate its potential clinical value compared usual care. <h3>Design, Setting, Participants</h3> This retrospective cohort study was conducted among 27 697 aged 18 years or older admitted Michigan Medicine,...
Rationale: The Epic Deterioration Index (EDI) is a proprietary prediction model implemented in over 100 U.S. hospitals that was widely used to support medical decision-making during the coronavirus disease (COVID-19) pandemic. EDI has not been independently evaluated, and other models have shown be biased against vulnerable populations. Objectives: To evaluate hospitalized patients with COVID-19 overall disproportionately affected subgroups. Methods: We studied adult admitted units than...
To create and validate a simple transferable machine learning model from electronic health record data to accurately predict clinical deterioration in patients with covid-19 across institutions, through use of novel paradigm for development code sharing.Retrospective cohort study.One US hospital during 2015-21 was used training internal validation. External validation conducted on admitted at 12 other medical centers 2020-21.33 119 adults (≥18 years) respiratory distress or covid-19.An...
This descriptive study evaluates the association between nursing reports of sepsis overalerting and alert volume by quantifying number alerts generated Epic Sepsis Model at 24 US hospitals before during COVID-19 pandemic.
Abstract Objective We evaluated the effect of emergency department ( ED ) census on disposition decisions made by physicians. Methods performed a retrospective analysis using 18 months all adult patient encounters seen in main at an academic tertiary care center. Patient information was calculated time physician assignment for each individual and included number patients waiting room (waiting census) being managed patient's attending (physician load census). A multiple logistic regression...
Purpose Learning is markedly improved with high-quality feedback, yet assuring the quality of feedback difficult to achieve at scale. Natural language processing (NLP) algorithms may be useful in this context as they can automatically classify large volumes narrative data. However, it unknown if NLP models accurately evaluate surgical trainee feedback. This study evaluated which techniques best formative recorded part a workplace assessment. Method During 2016–2017 academic year, SIMPL...
Abstract Background Infections with Clostridioides difficile are associated prolonged hospital stays, higher costs, and significant morbidity. Artificial intelligence (AI) tools can accurately predict which hospitalized patients most likely to acquire C. infection (CDI). However, date, such have not been used in clinical practice. We investigated how AI for CDI risk stratification could be integrated into workflows promote targeted prevention efforts. Details of the bundle (a) Screenshot BPA...
We aimed to evaluate the association between patient chief complaint and time interval rooming resident physician self-assignment ("pickup time"). hypothesized that significant variation in pickup would exist based on complaint, thereby uncovering preferences presentations.A retrospective medical record review was performed consecutive patients at a single, academic, university-based emergency department with over 50,000 visits per year. All who presented from August 1, 2012, July 31, 2013,...
ABSTRACT Introduction The Epic Deterioration Index (EDI) is a proprietary prediction model implemented in over 100 U.S. hospitals that was widely used to support medical decision-making during the COVID-19 pandemic. EDI has not been independently evaluated, and other models have shown be biased against vulnerable populations. Methods We studied adult patients admitted with non-ICU care at large academic center from March 9 through May 20, 2020. EDI, calculated 15-minute intervals, predict...
Screening individuals admitted to the hospital for Clostridioides difficile presents opportunities limit transmission and hospital-onset C. infection (HO-CDI). However, detection from rectal swabs is resource intensive. In contrast, machine learning (ML) models may accurately assess patient risk without significant usage. this study, we compared effectiveness of swab surveillance daily estimates produced by an ML model identify patients who will likely develop HO-CDI in intensive care unit...
No AccessJournal of UrologyAdult Urology1 Feb 2022Development and Validation Models to Predict Pathological Outcomes Radical Prostatectomy in Regional National CohortsThis article is commented on by the following:Editorial CommentEditorial Comment Erkin Ötleş, Brian T. Denton, Bo Qu, Adharsh Murali, Selin Merdan, Gregory B. Auffenberg, Spencer C. Hiller, R. Lane, Arvin K. George, Karandeep Singh ÖtleşErkin Ötleş http://orcid.org/0000-0003-3169-6832 Department Industrial & Operations...
Once integrated into clinical care, patient risk stratification models may perform worse compared to their retrospective performance. To date, it is widely accepted that performance will degrade over time due changes in care processes and populations. However, the extent which this occurs poorly understood, part because few researchers report prospective validation In study, we compare 2020-2021 ('20-'21) of a model for predicting healthcare-associated infections 2019-2020 ('19-'20) same...
Abstract Many data-driven patient risk stratification models have not been evaluated prospectively. We performed and compared the prospective retrospective evaluations of 2 Clostridioides difficile infection (CDI) risk-prediction at large academic health centers, we discuss models’ robustness to data-set shifts.
Purpose To report an uncommon, isolated presentation of bilateral choroidal detachments in a patient diagnosed with P-ANCA-associated vasculitis and to highlight the importance inflammatory work-up such cases.
ABSTRACT Background The cumulative, health system‐wide survival benefit of immune checkpoint inhibitors (ICIs) is unclear, particularly among real‐world patients with limited life expectancies and subgroups poorly represented on clinical trials. We sought to determine the impact ICIs. Methods identified all receiving PD‐1/PD‐L1 or CTLA‐4 from 2010 2023 in national Veterans Health Administration (VHA) system (ICI cohort) who received non‐ICI systemic therapy years before ICI approval...
Abstract Objective Occupational injuries (OIs) cause an immense burden on the US population. Prediction models help focus resources those at greatest risk of a delayed return to work (RTW). RTW depends factors that develop over time; however, existing methods only utilize information collected time injury. We investigate performance benefits dynamically estimating RTW, using longitudinal observations diagnoses and treatments beyond initial Materials Methods characterize difference in...