Search

Your search keyword '"Shenkman, Elizabeth A."' showing total 879 results
Start Over Author "Shenkman, Elizabeth A."
879 results on '"Shenkman, Elizabeth A."'

1. Epidemiology, Trajectories and Outcomes of Acute Kidney Injury Among Hospitalized Patients: A Retrospective Multicenter Large Cohort Study

Author

Adiyeke, Esra, Ren, Yuanfang, Fogel, Shmuel, Rashidi, Parisa, Segal, Mark, Shenkman, Elizabeth A., Bihorac, Azra, and Ozrazgat-Baslanti, Tezcan

Subjects
Statistics - Applications
Abstract

Background: Acute kidney injury (AKI) is a clinical syndrome affecting almost one fifth of hospitalized patients, as well as more than half of the patients who are admitted to the intensive care unit (ICU). Stratifying AKI patients into groups based on severity and duration would facilitate more targeted efforts for treating AKI. Methods: In a retrospective, multicenter and longitudinal cohort study of 935,679 patients who were admitted between 2012 and 2020 to health centers included in OneFlorida+ Network, we analyzed the impact of AKI trajectories which are rapidly reversed AKI, persistent AKI with renal recovery, and persistent AKI without renal recovery on patients' clinical outcomes, including hospital, 30-day, 1-year, and 3-year mortality, kidney replacement therapy, new chronic kidney disease (CKD) within 90 days or 1-year of discharge, CKD progression within 1-year of discharge, resource utilization, hospital disposition, and major complications during hospitalization. As analytical approaches, Kaplan-Meier estimators and survival curves, Cox proportional-hazards regression model, logistic regression model, Kruskal-Wallis test, analysis of variance, chi-square, Fisher's exact test were used. Results: Among 2,187,254 encounters, 14% had AKI, of which 63%, 21%, and 16% had Stage 1, 2, and 3, respectively, as the worst AKI stage. Fraction of patients with persistent AKI was 31%. Patients with AKI had worse clinical outcomes and increased resource utilization compared to patients without the condition. One-year mortality was 5 times greater for patients with persistent AKI compared to those without AKI. Conclusions: Persistent AKI was associated with prolonged hospitalization, increased ICU admission and mortality compared to the other groups. This may emphasize the critical need for devising strategies targeting effective management of AKI and prevention of persisting AKI., Comment: 61 pages, 2 tables, 3 figures, 13 supplemental tables, 3 supplemental figures

Published
2024

4. The impact of electronic health records (EHR) data continuity on prediction model fairness and racial-ethnic disparities

Author

Huang, Yu, Guo, Jingchuan, Chen, Zhaoyi, Xu, Jie, Donahoo, William T, Carasquillo, Olveen, Adloori, Hrushyang, Bian, Jiang, and Shenkman, Elizabeth A

Subjects
Statistics - Applications
Abstract

Electronic health records (EHR) data have considerable variability in data completeness across sites and patients. Lack of "EHR data-continuity" or "EHR data-discontinuity", defined as "having medical information recorded outside the reach of an EHR system" can lead to a substantial amount of information bias. The objective of this study was to comprehensively evaluate (1) how EHR data-discontinuity introduces data bias, (2) case finding algorithms affect downstream prediction models, and (3) how algorithmic fairness is associated with racial-ethnic disparities. We leveraged our EHRs linked with Medicaid and Medicare claims data in the OneFlorida+ network and used a validated measure (i.e., Mean Proportions of Encounters Captured [MPEC]) to estimate patients' EHR data continuity. We developed a machine learning model for predicting type 2 diabetes (T2D) diagnosis as the use case for this work. We found that using cohorts selected by different levels of EHR data-continuity affects utilities in disease prediction tasks. The prediction models trained on high continuity data will have a worse fit on low continuity data. We also found variations in racial and ethnic disparities in model performances and model fairness in models developed using different degrees of data continuity. Our results suggest that careful evaluation of data continuity is critical to improving the validity of real-world evidence generated by EHR data and health equity.

Published
2023

5. Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)

Author

Huang, Yu, Guo, Jingchuan, Donahoo, William T, Fan, Zhengkang, Lu, Ying, Chen, Wei-Han, Tang, Huilin, Bilello, Lori, Shenkman, Elizabeth A, and Bian, Jiang

Subjects
Computer Science - Machine Learning, Computer Science - Computers and Society
Abstract

Background: Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications. It is therefore crucial to implement effective social risk management strategies at the point of care. Objective: To develop an EHR-based machine learning (ML) analytical pipeline to identify the unmet social needs associated with hospitalization risk in patients with T2D. Methods: We identified 10,192 T2D patients from the EHR data (from 2012 to 2022) from the University of Florida Health Integrated Data Repository, including contextual SDoH (e.g., neighborhood deprivation) and individual-level SDoH (e.g., housing stability). We developed an electronic health records (EHR)-based machine learning (ML) analytic pipeline, namely individualized polysocial risk score (iPsRS), to identify high social risk associated with hospitalizations in T2D patients, along with explainable AI (XAI) techniques and fairness assessment and optimization. Results: Our iPsRS achieved a C statistic of 0.72 in predicting 1-year hospitalization after fairness optimization across racial-ethnic groups. The iPsRS showed excellent utility for capturing individuals at high hospitalization risk; the actual 1-year hospitalization rate in the top 5% of iPsRS was ~13 times as high as the bottom decile. Conclusion: Our ML pipeline iPsRS can fairly and accurately screen for patients who have increased social risk leading to hospitalization in T2D patients.

Published
2023

7. A Study of Generative Large Language Model for Medical Research and Healthcare

Author

Peng, Cheng, Yang, Xi, Chen, Aokun, Smith, Kaleb E, PourNejatian, Nima, Costa, Anthony B, Martin, Cheryl, Flores, Mona G, Zhang, Ying, Magoc, Tanja, Lipori, Gloria, Mitchell, Duane A, Ospina, Naykky S, Ahmed, Mustafa M, Hogan, William R, Shenkman, Elizabeth A, Guo, Yi, Bian, Jiang, and Wu, Yonghui

Subjects
Computer Science - Computation and Language
Abstract

There is enormous enthusiasm and concerns in using large language models (LLMs) in healthcare, yet current assumptions are all based on general-purpose LLMs such as ChatGPT. This study develops a clinical generative LLM, GatorTronGPT, using 277 billion words of mixed clinical and English text with a GPT-3 architecture of 20 billion parameters. GatorTronGPT improves biomedical natural language processing for medical research. Synthetic NLP models trained using GatorTronGPT generated text outperform NLP models trained using real-world clinical text. Physicians Turing test using 1 (worst) to 9 (best) scale shows that there is no significant difference in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights on the opportunities and challenges of LLMs for medical research and healthcare.

Published
2023
Full Text
View/download PDF

9. Hydroxychloroquine for pre-exposure prophylaxis of COVID-19 in health care workers: a randomized, multicenter, placebo-controlled trial Healthcare Worker Exposure Response and Outcomes of Hydroxychloroquine (HERO-HCQ)

Author

Naggie, Susanna, Milstone, Aaron, Castro, Mario, Collins, Sean P, Lakshmi, Seetha, Anderson, Deverick J, Cahuayme-Zuniga, Lizbeth, Turner, Kisha Batey, Cohen, Lauren W, Currier, Judith, Fraulo, Elizabeth, Friedland, Anne, Garg, Jyotsna, George, Anoop, Mulder, Hillary, Olson, Rachel E, O'Brien, Emily C, Rothman, Russell L, Shenkman, Elizabeth, Shostak, Jack, Woods, Christopher W, Anstrom, Kevin J, Hernandez, Adrian F, and Program, HERO Research

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Prevention, Emerging Infectious Diseases, Lung, Infectious Diseases, Clinical Research, Clinical Trials and Supportive Activities, Evaluation of treatments and therapeutic interventions, 6.1 Pharmaceuticals, Infection, Good Health and Well Being, Humans, COVID-19, SARS-CoV-2, Hydroxychloroquine, Pre-Exposure Prophylaxis, COVID-19 Drug Treatment, Health Personnel, Treatment Outcome, Health care workers, Trial design, HERO Research Program, Microbiology, Medical Microbiology, Public Health and Health Services, Clinical sciences, Epidemiology, Public health
Abstract

ObjectivesTo determine whether hydroxychloroquine (HCQ) is safe and effective at preventing COVID-19 infections among health care workers (HCWs).MethodsIn a 1: 1 randomized, placebo-controlled, double-blind, parallel-group, superiority trial at 34 US clinical centers, 1360 HCWs at risk for COVID-19 infection were enrolled between April and November 2020. Participants were randomized to HCQ or matched placebo. The HCQ dosing included a loading dose of HCQ 600 mg twice on day 1, followed by 400 mg daily for 29 days. The primary outcome was a composite of confirmed or suspected COVID-19 clinical infection by day 30, defined as new-onset fever, cough, or dyspnea and either a positive SARS-CoV-2 polymerase chain reaction test (confirmed) or a lack of confirmatory testing due to local restrictions (suspected).ResultsStudy enrollment closed before full accrual due to recruitment challenges. The primary end point occurred in 41 (6.0%) participants receiving HCQ and 53 (7.8%) participants receiving placebo. No difference in the proportion of participants experiencing clinical infection (estimated difference of -1.8%, 95% confidence interval -4.6-0.9%, P = 0.20) was identified nor any significant safety issues.ConclusionOral HCQ taken as prescribed appeared safe among HCWs. No significant clinical benefits were observed. The study was not powered to detect a small but potentially important reduction in infection.Trial registrationNCT04334148.

Published
2023

10. GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records

Author

Yang, Xi, Chen, Aokun, PourNejatian, Nima, Shin, Hoo Chang, Smith, Kaleb E, Parisien, Christopher, Compas, Colin, Martin, Cheryl, Flores, Mona G, Zhang, Ying, Magoc, Tanja, Harle, Christopher A, Lipori, Gloria, Mitchell, Duane A, Hogan, William R, Shenkman, Elizabeth A, Bian, Jiang, and Wu, Yonghui

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model - GatorTron - using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on 5 clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve 5 clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og., Comment: 24 pages, 2 figures, 3 tables

Published
2022

12. Applications of artificial intelligence in drug development using real-world data

Author

Chen, Zhaoyi, Liu, Xiong, Hogan, William, Shenkman, Elizabeth, and Bian, Jiang

Subjects
Computer Science - Computers and Society, Computer Science - Computation and Language, Computer Science - Machine Learning, Quantitative Biology - Quantitative Methods
Abstract

The US Food and Drug Administration (FDA) has been actively promoting the use of real-world data (RWD) in drug development. RWD can generate important real-world evidence reflecting the real-world clinical environment where the treatments are used. Meanwhile, artificial intelligence (AI), especially machine- and deep-learning (ML/DL) methods, have been increasingly used across many stages of the drug development process. Advancements in AI have also provided new strategies to analyze large, multidimensional RWD. Thus, we conducted a rapid review of articles from the past 20 years, to provide an overview of the drug development studies that use both AI and RWD. We found that the most popular applications were adverse event detection, trial recruitment, and drug repurposing. Here, we also discuss current research gaps and future opportunities.

Published
2021
Full Text
View/download PDF

16. Design of the healthcare worker exposure response and outcomes (HERO) research platform

Author

Friedland, Anne, Hernandez, Adrian F, Anstrom, Kevin J, Chen-Lim, Mei Lin, Cohen, Lauren W, Currier, Judith S, Forrest, Christopher B, Fraser, Ryan, Fraulo, Elizabeth, George, Anoop, Handberg, Eileen, Jackman, Jennifer, Koellhoffer, Jayne, Lawrence, Daryl, Leverty, Renee, McAdams, Patty, McCourt, Brian, Mickley, Brenda, Naqvi, Syed Hasan, O'Brien, Emily C, Olson, Rachel, Prater, Clyde, Rothman, Russell L, Shenkman, Elizabeth, Shostak, Jack, Turner, Kisha Batey, Webb, Laura, Woods, Chris, Naggie, Susanna, and Program, on behalf of the HERO Research

Subjects
Clinical Trials and Supportive Activities, Infectious Diseases, Lung, Prevention, Clinical Research, Evaluation of treatments and therapeutic interventions, 6.1 Pharmaceuticals, Good Health and Well Being, COVID-19, Health Personnel, Humans, Quality of Life, SARS-CoV-2, Treatment Outcome, Healthcare workers, Registry, Study platform, Hydroxychloroquine, Pragmatic trial, HERO Research Program, Medical and Health Sciences, General Clinical Medicine, Public Health
Abstract

BackgroundThe SARS CoV-2 virus has caused one of the deadliest pandemics in recent history, resulting in over 170 million deaths and global economic disruption. There remains an urgent need for clinical trials to test therapies for treatment and prevention.DesignAn online research platform was created to support a registry community of healthcare workers (HCWs) to understand their experiences and conduct clinical studies to address their concerns. The first study, HERO-HCQ, was a double-blind, multicenter, randomized, pragmatic trial to evaluate the superiority of hydroxychloroquine (HCQ) vs placebo for pre-exposure prophylaxis (PrEP) of COVID-19 clinical infection in HCWs. Secondary objectives were to assess the efficacy of HCQ in preventing viral shedding of COVID-19 among HCWs and to assess the safety and tolerability of HCQ.MethodsHCWs joined the Registry and were pre-screened for trial interest and eligibility. Trial participants were randomized 1:1 to receive HCQ or placebo. On-site baseline assessment included a COVID-19 nasopharyngeal PCR and blood serology test. Weekly follow-up was done via an online portal and included screening for symptoms of COVID-19, self-reported testing, adverse events, and quality of life assessments. The on-site visit was repeated at Day 30.DiscussionThe HERO research platform offers an approach to rapidly engage, screen, invite and enroll into clinical studies using a novel participant-facing online portal interface and remote data collection, enabling limited onsite procedures for conduct of a pragmatic clinical trial. This platform may be an example for future clinical trials of common conditions to enable more rapid evidence generation.

Published
2021

17. Design, Development and Evaluation of the Citizen Science Cancer Curriculum (CSCC): A Design and Development Case Study

Author

Valle, Natercia, Brishke, Janet, Shenkman, Elizabeth, and Ritzhaupt, Albert D.

Abstract

The purpose of this design and development case study is to provide an in-depth account of the needs analysis (through surveys and interviews), design, development and formative evaluation of the Citizen Science Cancer Curriculum (CSCC). The curriculum was developed as an online, self-paced educational program distributed as an Open Educational Resource using Creative Commons licensing. The instructional approach described in this design and development case study was informed by the Self-Determination Theory (SDT) framework. The case reflects a new frontier in the development of community stakeholder engagement models and describes how evidence-based instructional design practices and approaches (e.g., storytelling) can be used to support Citizen Scientists' interests, learning and motivation to engage in cancer-related research. Results from quantitative and qualitative analyses indicate that the CSCC supported Citizen Scientists' learning performance and motivation. More specifically, the use of storytelling as an instructional approach supported Citizen Scientists' psychological needs, especially relatedness and competence, which translated into their behavioral intentions to contribute to cancer-related research. We share context-specific challenges and opportunities in working with Citizen Scientists as well as with cancer researchers and clinicians during the design and development of the curriculum.

Published
2022
Full Text
View/download PDF

18. Comparative Effectiveness of Aspirin Dosing in Cardiovascular Disease

Author

Jones, W Schuyler, Mulder, Hillary, Wruck, Lisa M, Pencina, Michael J, Kripalani, Sunil, Muñoz, Daniel, Crenshaw, David L, Effron, Mark B, Re, Richard N, Gupta, Kamal, Anderson, R David, Pepine, Carl J, Handberg, Eileen M, Manning, Brittney R, Jain, Sandeep K, Girotra, Saket, Riley, Danielle, DeWalt, Darren A, Whittle, Jeff, Goldberg, Ythan H, Roger, Veronique L, Hess, Rachel, Benziger, Catherine P, Farrehi, Peter, Zhou, Li, Ford, Daniel E, Haynes, Kevin, VanWormer, Jeffrey J, Knowlton, Kirk U, Kraschnewski, Jennifer L, Polonsky, Tamar S, Fintel, Dan J, Ahmad, Faraz S, McClay, James C, Campbell, James R, Bell, Douglas S, Fonarow, Gregg C, Bradley, Steven M, Paranjape, Anuradha, Roe, Matthew T, Robertson, Holly R, Curtis, Lesley H, Sharlow, Amber G, Berdan, Lisa G, Hammill, Bradley G, Harris, Debra F, Qualls, Laura G, Marquis-Gravel, Guillaume, Modrow, Madelaine F, Marcus, Gregory M, Carton, Thomas W, Nauman, Elizabeth, Waitman, Lemuel R, Kho, Abel N, Shenkman, Elizabeth A, McTigue, Kathleen M, Kaushal, Rainu, Masoudi, Frederick A, Antman, Elliott M, Davidson, Desiree R, Edgley, Kevin, Merritt, James G, Brown, Linda S, Zemon, Doris N, McCormick, Thomas E, Alikhaani, Jacqueline D, Gregoire, Kenneth C, Rothman, Russell L, Harrington, Robert A, and Hernandez, Adrian F

Subjects
Clinical Trials and Supportive Activities, Heart Disease - Coronary Heart Disease, Cardiovascular, Patient Safety, Comparative Effectiveness Research, Clinical Research, Heart Disease, Evaluation of treatments and therapeutic interventions, 6.1 Pharmaceuticals, Good Health and Well Being, Aged, Aspirin, Atherosclerosis, Cardiovascular Diseases, Female, Hemorrhage, Hospitalization, Humans, Male, Medication Adherence, Middle Aged, Myocardial Infarction, Platelet Aggregation Inhibitors, Secondary Prevention, Stroke, ADAPTABLE Team, Medical and Health Sciences, General & Internal Medicine
Abstract

BackgroundThe appropriate dose of aspirin to lower the risk of death, myocardial infarction, and stroke and to minimize major bleeding in patients with established atherosclerotic cardiovascular disease is a subject of controversy.MethodsUsing an open-label, pragmatic design, we randomly assigned patients with established atherosclerotic cardiovascular disease to a strategy of 81 mg or 325 mg of aspirin per day. The primary effectiveness outcome was a composite of death from any cause, hospitalization for myocardial infarction, or hospitalization for stroke, assessed in a time-to-event analysis. The primary safety outcome was hospitalization for major bleeding, also assessed in a time-to-event analysis.ResultsA total of 15,076 patients were followed for a median of 26.2 months (interquartile range [IQR], 19.0 to 34.9). Before randomization, 13,537 (96.0% of those with available information on previous aspirin use) were already taking aspirin, and 85.3% of these patients were previously taking 81 mg of daily aspirin. Death, hospitalization for myocardial infarction, or hospitalization for stroke occurred in 590 patients (estimated percentage, 7.28%) in the 81-mg group and 569 patients (estimated percentage, 7.51%) in the 325-mg group (hazard ratio, 1.02; 95% confidence interval [CI], 0.91 to 1.14). Hospitalization for major bleeding occurred in 53 patients (estimated percentage, 0.63%) in the 81-mg group and 44 patients (estimated percentage, 0.60%) in the 325-mg group (hazard ratio, 1.18; 95% CI, 0.79 to 1.77). Patients assigned to 325 mg had a higher incidence of dose switching than those assigned to 81 mg (41.6% vs. 7.1%) and fewer median days of exposure to the assigned dose (434 days [IQR, 139 to 737] vs. 650 days [IQR, 415 to 922]).ConclusionsIn this pragmatic trial involving patients with established cardiovascular disease, there was substantial dose switching to 81 mg of daily aspirin and no significant differences in cardiovascular events or major bleeding between patients assigned to 81 mg and those assigned to 325 mg of aspirin daily. (Funded by the Patient-Centered Outcomes Research Institute; ADAPTABLE ClinicalTrials.gov number, NCT02697916.).

Published
2021

22. Mixed methods evaluation of vaping and tobacco product use prevention interventions among youth in the Florida 4-H program

Author

Bteddini, Dima S., LeLaurin, Jennifer H., Chi, Xiaofei, Hall, Jaclyn M., Theis, Ryan P., Gurka, Matthew J., Lee, Ji-Hyun, Mobley, Erin M., Khalil, George E., Polansky, Caroline J., Kellner, Allie M., Fahnlander, Alexandra M., Kelder, Steven H., Fiellin, Lynn E., Gutter, Michael S., Shenkman, Elizabeth A., and Salloum, Ramzi G.

Published
2023
Full Text
View/download PDF

25. Cancer Informatics for Cancer Centers (CI4CC): Building a Community Focused on Sharing Ideas and Best Practices to Improve Cancer Care and Patient Outcomes.

Author

Barnholtz-Sloan, Jill S, Rollison, Dana E, Basu, Amrita, Borowsky, Alexander D, Bui, Alex, DiGiovanna, Jack, Garcia-Closas, Montserrat, Genkinger, Jeanine M, Gerke, Travis, Induni, Marta, Lacey, James V, Jr, Mirel, Lisa, Permuth, Jennifer B, Saltz, Joel, Shenkman, Elizabeth A, Ulrich, Cornelia M, Zheng, W Jim, Nadaf, Sorena, and Kibbe, Warren A

Abstract

Cancer Informatics for Cancer Centers (CI4CC) is a grassroots, nonprofit 501c3 organization intended to provide a focused national forum for engagement of senior cancer informatics leaders, primarily aimed at academic cancer centers anywhere in the world but with a special emphasis on the 70 National Cancer Institute-funded cancer centers. Although each of the participating cancer centers is structured differently, and leaders' titles vary, we know firsthand there are similarities in both the issues we face and the solutions we achieve. As a consortium, we have initiated a dedicated listserv, an open-initiatives program, and targeted biannual face-to-face meetings. These meetings are a place to review our priorities and initiatives, providing a forum for discussion of the strategic and pragmatic issues we, as informatics leaders, individually face at our respective institutions and cancer centers. Here we provide a brief history of the CI4CC organization and meeting highlights from the latest CI4CC meeting that took place in Napa, California from October 14-16, 2019. The focus of this meeting was "intersections between informatics, data science, and population science." We conclude with a discussion on "hot topics" on the horizon for cancer informatics.

Published
2020

27. The All of Us Research Program: Data quality, utility, and diversity

Author

Ahmedani, Brian, Cole Johnson, Christine D., Ahsan, Habib, Antoine-LaVigne, Donna, Singleton, Glendora, Anton-Culver, Hoda, Topol, Eric, Baca-Motes, Katie, Steinhubl, Steven, Wade, James, Begale, Mark, Jain, Praduman, Sutherland, Scott, Lewis, Beth, Korf, Bruce, Behringer, Melissa, Gharavi, Ali G., Goldstein, David B., Hripcsak, George, Bier, Louise, Boerwinkle, Eric, Brilliant, Murray H., Murali, Narayana, Hebbring, Scott Joseph, Farrar-Edwards, Dorothy, Burnside, Elizabeth, Drezner, Marc K., Taylor, Amy, Channamsetty, Veena, Montalvo, Wanda, Sharma, Yashoda, Chinea, Carmen, Jenks, Nancy, Cicek, Mine, Thibodeau, Steve, Holmes, Beverly Wilson, Schlueter, Eric, Collier, Ever, Winkler, Joyce, Corcoran, John, D’Addezio, Nick, Daviglus, Martha, Winn, Robert, Wilkins, Consuelo, Roden, Dan, Denny, Joshua, Doheny, Kim, Nickerson, Debbie, Eichler, Evan, Jarvik, Gail, Funk, Gretchen, Philippakis, Anthony, Rehm, Heidi, Lennon, Niall, Kathiresan, Sekar, Gabriel, Stacey, Gibbs, Richard, Gil Rico, Edgar M., Glazer, David, Grand, Joannie, Greenland, Philip, Harris, Paul, Shenkman, Elizabeth, Hogan, William R., Igho-Pemu, Priscilla, Pollan, Cliff, Jorge, Milena, Okun, Sally, Karlson, Elizabeth W., Smoller, Jordan, Murphy, Shawn N., Ross, Margaret Elizabeth, Kaushal, Rainu, Winford, Eboni, Wallace, Febe, Khatri, Parinda, Kheterpal, Vik, Ojo, Akinlolu, Moreno, Francisco A., Kron, Irving, Peterson, Rachele, Menon, Usha, Lattimore, Patricia Watkins, Leviner, Noga, Obedin-Maliver, Juno, Lunn, Mitchell, Malik-Gagnon, Lynda, Mangravite, Lara, Marallo, Adria, Marroquin, Oscar, Visweswaran, Shyam, Reis, Steven, Marshall, Gailen, Jr., McGovern, Patrick, Mignucci, Deb, Moore, John, Munoz, Fatima, Talavera, Gregory, O'Connor, George T., O'Donnell, Christopher, Ohno-Machado, Lucila, Orr, Greg, Randal, Fornessa, Theodorou, Andreas A., Reiman, Eric, Roxas-Murray, Mercedita, Stark, Louisa, Tepp, Ronnie, Zhou, Alicia, Topper, Scott, Trousdale, Rhonda, Tsao, Phil, Weidman, Lisa, Weiss, Scott T., Wellis, David, Whittle, Jeffrey, Wilson, Amanda, Zuchner, Stephan, Zwick, Michael E., Ramirez, Andrea H., Sulieman, Lina, Schlueter, David J., Halvorson, Alese, Qian, Jun, Ratsimbazafy, Francis, Loperena, Roxana, Mayo, Kelsey, Basford, Melissa, Deflaux, Nicole, Muthuraman, Karthik N., Natarajan, Karthik, Kho, Abel, Xu, Hua, Clark, Cheryl R., Cohn, Elizabeth, Schully, Sheri D., Ahmedani, Brian K., Argos, Maria, Cronin, Robert M., O’Donnell, Christopher, Fouad, Mona, Hebbring, Scott J., Smoller, Jordan W., Sodeke, Stephen, Wilbanks, John, Hentges, Justin, Mockrin, Stephen, Lunt, Christopher, Devaney, Stephanie A., Gebo, Kelly, Denny, Joshua C., Carroll, Robert J., Harris, Paul A., and Roden, Dan M.

Published
2022
Full Text
View/download PDF

29. Developing an automated algorithm for identification of children and adolescents with diabetes using electronic health records from the OneFlorida+ clinical research network.

Author

Li, Piaopiao, Spector, Eliot, Alkhuzam, Khalid, Patel, Rahul, Donahoo, William T., Bost, Sarah, Lyu, Tianchen, Wu, Yonghui, Hogan, William, Prosperi, Mattia, Dixon, Brian E., Dabelea, Dana, Utidjian, Levon H., Crume, Tessa L., Thorpe, Lorna, Liese, Angela D., Schatz, Desmond A., Atkinson, Mark A., Haller, Michael J., and Shenkman, Elizabeth A.

Subjects
TYPE 2 diabetes, TYPE 1 diabetes, DIABETES in children, ELECTRONIC health records, BLOOD sugar
Abstract

Aim: To develop an automated computable phenotype (CP) algorithm for identifying diabetes cases in children and adolescents using electronic health records (EHRs) from the UF Health System. Materials and Methods: The CP algorithm was iteratively derived based on structured data from EHRs (UF Health System 2012–2020). We randomly selected 536 presumed cases among individuals aged <18 years who had (1) glycated haemoglobin levels ≥ 6.5%; or (2) fasting glucose levels ≥126 mg/dL; or (3) random plasma glucose levels ≥200 mg/dL; or (4) a diabetes‐related diagnosis code from an inpatient or outpatient encounter; or (5) prescribed, administered, or dispensed diabetes‐related medication. Four reviewers independently reviewed the patient charts to determine diabetes status and type. Results: Presumed cases without type 1 (T1D) or type 2 diabetes (T2D) diagnosis codes were categorized as non‐diabetes/other types of diabetes. The rest were categorized as T1D if the most recent diagnosis was T1D, or otherwise categorized as T2D if the most recent diagnosis was T2D. Next, we applied a list of diagnoses and procedures that can determine diabetes type (e.g., steroid use suggests induced diabetes) to correct misclassifications from Step 1. Among the 536 reviewed cases, 159 and 64 had T1D and T2D, respectively. The sensitivity, specificity, and positive predictive values of the CP algorithm were 94%, 98% and 96%, respectively, for T1D and 95%, 95% and 73% for T2D. Conclusion: We developed a highly accurate EHR‐based CP for diabetes in youth based on EHR data from UF Health. Consistent with prior studies, T2D was more difficult to identify using these methods. [ABSTRACT FROM AUTHOR]

Published
2025
Full Text
View/download PDF

34. A large language model for electronic health records

Author

Yang, Xi, Chen, Aokun, PourNejatian, Nima, Shin, Hoo Chang, Smith, Kaleb E., Parisien, Christopher, Compas, Colin, Martin, Cheryl, Costa, Anthony B., Flores, Mona G., Zhang, Ying, Magoc, Tanja, Harle, Christopher A., Lipori, Gloria, Mitchell, Duane A., Hogan, William R., Shenkman, Elizabeth A., Bian, Jiang, and Wu, Yonghui

Published
2022
Full Text
View/download PDF

42. PCORnet® 2020: current state, accomplishments, and future directions

Author

Forrest, Christopher B., McTigue, Kathleen M., Hernandez, Adrian F., Cohen, Lauren W., Cruz, Henry, Haynes, Kevin, Kaushal, Rainu, Kho, Abel N., Marsolo, Keith A., Nair, Vinit P., Platt, Richard, Puro, Jon E., Rothman, Russell L., Shenkman, Elizabeth A., Waitman, Lemuel Russell, Williams, Neely A., and Carton, Thomas W.

Published
2021
Full Text
View/download PDF

44. Pandemic Perceptions and Healthcare Decisions: Exploring Perceived COVID-19 Threat's Impact on Perinatal Healthcare in Florida.

Author

Ulfat, Farah, Thayagabalu, Sionika, Iglesias, Alejandra, Ke Xu, Reeder, Callie, Smith, Erica, Cardel, Michelle, Loop, Matthew, Rodriguez, Paola, Montalvo-Ortiz, Janitza, Hall, Jaclyn, Silva, Lauren, Rodriguez, Marcella, Wen, Tony, Smulian, John, Louis-Jacques, Adetola, Francois, Magda, Shenkman, Elizabeth, and Lemas, Dominick

Subjects
HEALTH services accessibility, MATERNAL health services, RESEARCH funding, MEDICAL care, DECISION making, PREGNANT women, HEALTH behavior, MEDICAL needs assessment, COVID-19
Abstract

The COVID-19 pandemic directly impacted well-being and healthcare delivery, but its indirect effects on health services utilization among pregnant women and new mothers remain less understood. Understanding how big events like pandemics impact health behaviors is essential for anticipating healthcare needs during future crises. This study examined how the perceived COVID-19 threat influenced health concerns and service utilization among 378 participants who were either pregnant or mothers of infants less than 12 months old, 18 years or older, and lived within a 50-mile radius of healthcare sites in the OneFlorida+ Clinical Research Consortium. An online Qualtrics survey assessed COVID-19 threat perception, distress related to health and resource concerns (e.g., access to medicine, baby supplies, mental and general healthcare, and social interactions), and changes to health service utilizations (e.g., induction schedule, hospital/birthing center choices, prenatal provider, and visit frequency) during the pandemic. Participants who perceived COVID-19 as a significant threat were more likely to report concerns about reduced access to general healthcare (p = 0.043). Pregnant participants, compared to mothers with infants under 12 months of age, expressed greater concern about reduced access to mental healthcare (p = 0.015). Additionally, the perceived COVID-19 threat was linked to changes in prenatal care providers and labor induction schedules (p < 0.001). These findings highlight the importance of integrating the perceived threat of pandemics or other major events into mental health screenings. Healthcare providers should proactively address potential changes in patient behavior during major events in anticipation of future crises. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Evaluating site-of-care-related racial disparities in kidney graft failure using a novel federated learning framework

Author

Tong, Jiayi, primary, Shen, Yishan, additional, Xu, Alice, additional, He, Xing, additional, Luo, Chongliang, additional, Edmondson, Mackenzie, additional, Zhang, Dazheng, additional, Lu, Yiwen, additional, Yan, Chao, additional, Li, Ruowang, additional, Siegel, Lianne, additional, Sun, Lichao, additional, Shenkman, Elizabeth A, additional, Morton, Sally C, additional, Malin, Bradley A, additional, Bian, Jiang, additional, Asch, David A, additional, and Chen, Yong, additional

Published
2024
Full Text
View/download PDF

49. Development and validation of a race-agnostic computable phenotype for kidney health in adult hospitalized patients

Author

Ozrazgat-Baslanti, Tezcan, primary, Ren, Yuanfang, additional, Adiyeke, Esra, additional, Islam, Rubab, additional, Hashemighouchani, Haleh, additional, Ruppert, Matthew, additional, Miao, Shunshun, additional, Loftus, Tyler, additional, Johnson-Mann, Crystal, additional, Madushani, R. W. M. A., additional, Shenkman, Elizabeth A., additional, Hogan, William, additional, Segal, Mark S., additional, Lipori, Gloria, additional, Bihorac, Azra, additional, and Hobson, Charles, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results