Health Information Technology Commons^™

A Multi-Institutional Natural Language Processing Pipeline To Extract Performance Status From Electronic Health Records, Arash Maghsoudi, Yvonne H Sada, Sara Nowakowski, Danielle Guffey, Huili Zhu, Sudha R Yarlagadda, Ang Li, Javad Razjouyan

Faculty, Staff and Students Publications

PURPOSE: Performance status (PS), an essential indicator of patients' functional abilities, is often documented in clinical notes of patients with cancer. The use of natural language processing (NLP) in extracting PS from electronic medical records (EMRs) has shown promise in enhancing clinical decision-making, patient monitoring, and research studies. We designed and validated a multi-institute NLP pipeline to automatically extract performance status from free-text patient notes.

PATIENTS AND METHODS: We collected data from 19,481 patients in Harris Health System (HHS) and 333,862 patients from veteran affair's corporate data warehouse (VA-CDW) and randomly selected 400 patients from each data source to train …

Perceptions Of Acute Care Telemedicine Among Caregivers For Persons Living With Dementia: A Qualitative Study, Anita Chary, Norvin Hernandez, Ana Paulina Rivera, Vivian Ramont, Tracey Obi, Ilianna Santangelo, Christine Ritchie, Hardeep Singh, Emily Hayden, Aanand D Naik, Shan Liu, Maura Kennedy

Faculty, Staff and Student Publications

Persons living with dementia (PLWD) have high emergency department (ED) utilization. Little is known about using telemedicine with PLWD and caregivers as an alternative to ED visits for minor acute health problems. This qualitative interview-based study elicited caregivers' perspectives about the acceptability of telemedicine for acute complaints. We performed telephone interviews with 28 caregivers of PLWD from two academic EDs, one in the Northeast and another in the South. Using a combined deductive-inductive approach, we coded interview transcripts and elucidated common themes by consensus. All caregivers reported they would need to participate in the telemedicine visit to help overcome communication …

Comparing The Use And Effectiveness Of In-Person And Remote Physical Education Delivery During The Covid-19 Pandemic, Kempson Onadeko, Timothy J Walker, Derek W Craig, Jacob Szeszulski, Andjelka Pavlovic, Laura F Defina, Harold W Kohl

Faculty, Staff and Student Publications

BACKGROUND: Physical Education is a key component to improve youth health, but there is limited information on Physical Education delivery in different formats.

PURPOSE: We compared PE formats (in-person versus remote) across evaluation aspects: weekly minutes; perceived effectiveness; and student-to-teacher ratio.

METHODS: We distributed questionnaires (2020-2021 school year) to school contacts who represented NFL Play 60 FitnessGram

RESULTS: Among 165 schools, 10% (n=17) offered in-person instruction, 31% (n=51) offered remote instruction, and 59% offered both (n=97). Results revealed higher in-person PE minutes (77.2±7.3) compared to remote minutes (67.1±14.6), but results were not significantly different (p=0.19). School contacts reported significantly more …

Patients With Floaters: Answers From Virtual Assistants And Large Language Models, Gloria Wu, Weichen Zhao, Adrial Wong, David A Lee

Faculty, Staff and Student Publications

OBJECTIVES: "Floaters," a common complaint among patients of all ages, was used as a query term because it affects 30% of all people searching for eye care. The American Academy of Ophthalmology website's "floaters" section was used as a source for questions and answers (www.aao.org). Floaters is a visual obstruction that moves with the movement of the eye. They can be associated with retinal detachment, which can lead to vision loss. With the advent of large language model (LLM) chatbots ChatGPT, Bard versus virtual assistants (VA), Google Assistant, and Alexa, we analyzed their responses to "floaters."

METHODS: Using AAO.org, "Public …

Stroke Survivors’ Telemedicine Experiences During The Covid-19 Pandemic: A Phenomenological Investigation, Barbara Kimmel, Annette Walder, Anette Ovalle, Chethan P Venkatasubba Rao, Sean I Savitz, Mark Goldberg, Steven Warach, Salvador Cruz-Flores, Daiwai M Olson, Jane A Anderson

Faculty, Staff and Student Publications

PURPOSE: This study aimed to describe stroke survivors' experiences receiving telemedicine visits at the Lone Star Stroke Consortium during the COVID-19 pandemic.

MATERIALS AND METHODS: A qualitative descriptive phenomenological design was applied to gather patients' telemedicine experiences through in-depth interviews, using a study guide. Audio-recorded interviews were conducted via ZOOM and transcribed verbatim. Two independent reviewers used the Giorgi descriptive method to analyze the data and search for the essence of stroke survivors' follow-up telemedicine experiences during the COVID-19 pandemic.

RESULTS: Fifteen underserved patients were recruited: mean age, 51.8 (15.7), and 9 (60%) females. Three themes emerged: (1) vivid memory …

Analyzing The Relationship Between Socioeconomic Deprivation And Outpatient Medicare Part D Fluoroquinolone Claim Rates In Texas, Mayar Al Mohajer, Edgar Samarasundera, Judite Gonçalves, Alicia Heath

Faculty, Staff and Students Publications

INTRODUCTION: Only a few studies have assessed the relationship between deprivation and excessive antibiotic use. In Texas, antimicrobial prescription rates are particularly high compared with the rest of the US. This study analyzed the association between local area socioeconomic deprivation and providers' fluoroquinolone claim rates among beneficiaries 65 years and older in Texas.

METHODS: This ecological study utilized provider- and area-level data from Medicare Part D Prescribers and the Social Deprivation Index (SDI) repositories. Negative binomial regression models were employed to evaluate the relationship between provider- and area-level characteristics (prescriber's gender, specialty, rural-urban community area, beneficiaries' demographics, area-level population, and …

Post-Covid-19 Cognitive Symptoms In Patients Assisted By A Teleassistance Service: A Retrospective Cohort Study, Lívia Paula Freire Bonfim, Thais Rotsen Correa, Bruno Cabaleiro Cortizo Freire, Thais Marques Pedroso, Daniella Nunes Pereira, Thalita Baptisteli Fernandes, Luciane Kopittke, Clara Rodrigues Alves De Oliveira, Antonio Lucio Teixeira, Milena Soriano Marcolino

Faculty, Staff and Student Publications

INTRODUCTION: Four years after the onset of the COVID-19 pandemic, the frequency of long-term post-COVID-19 cognitive symptoms is a matter of concern given the impact it may have on the work and quality of life of affected people.

OBJECTIVE: To evaluate the incidence of post-acute COVID-19 cognitive symptoms, as well as the associated risk factors.

METHODS: Retrospective cohort, including outpatients with laboratory-confirmed COVID-19 and who were assisted by a public telehealth service provided by the Telehealth Network of Minas Gerais (TNMG), during the acute phase of the disease, between December/2020 and March/2022. Data were collected through a structured questionnaire, applied …

Acceptability And Use Of An Online Health Priorities Self-Identification Tool For Older Adults: A Qualitative Investigation, Emily L Mroz, Kizzy Hernandez-Bigos, Jessica Esterson, Eliza Kiwak, Aanand Naik, Mary E Tinetti

Faculty, Staff and Student Publications

OBJECTIVE: To examine the use of a web-based, self-directed health priorities identification tool for older adults with multiple chronic conditions (MCCs).

METHODS: We recruited a gender- and racially-diverse, highly educated sample of older adults with MCCs to engage with our My Health Priorities tool, then complete a semi-structured interview. Thematic analysis was used to examine interview transcripts.

RESULTS: Twenty-one participants shared perspectives on the acceptability and use of the tool. Three themes (with eleven subthemes) were generated to describe: website

CONCLUSION: Participants found this tool acceptable and easy to use, describing a variety of benefits of the priorities self-identification process …

Selecting Patient-Reported Outcome Measures For A Patient-Facing Technology, Priyank Raj, Youmin Cho, Yun Jiang, Yang Gong

Faculty, Staff and Student Publications

OBJECTIVE: This article provides insight into our process and considerations for selecting patient-reported outcome measures (PROMs) designed for self-reporting symptoms and quality-of-life among breast cancer (BCA) patients undergoing oral anticancer agent treatment via a patient-facing technology (PFT) platform.

METHODS: Following established guidelines, we conducted a thorough assessment of a specific set of PROMs, comparing their content to identify the most suitable options for studying BCA patients.

RESULTS: We recommend utilizing the combination of EORTC QLQ-C30 + EORTC QLQ-BR45 as the preferred instrument, especially when developing a dedicated "breast cancer-only" application.

DISCUSSION: When developing and maintaining a dashboard for a PFT …

Acute And Chronic Kidney Injury During Therapy For Pediatric Acute Leukemia: A Report From The Leukemia Electronic Abstraction Of Records Network (Learn), Wendy Hsiao, Yimei Li, Kelly Getz, Lusha Cao, Edward Krause, Mark Ramos, Judy Lee, Maria Monica Gramatges, Karen R Rabin, Michael E Scheurer, Richard Aplenc, Michelle Denburg, Tamara P Miller

Center for Medical Ethics and Health Policy Staff Publications

Children with acute leukemia are at increased risk of kidney injury. Using electronic health record data from three centers between 2010 and 2018, this study retrospectively described acute kidney injury (AKI) and chronic kidney disease (CKD) prevalence in children with acute lymphoblastic or myeloid leukemia (ALL, AML) using Common Terminology Criteria for Adverse Events (CTCAE) and Kidney Disease Improving Global Outcomes (KDIGO) definitions. AKI during therapy was 25% (ALL) and 32% (AML) using CTCAE, versus 84% (ALL) and 74% (AML) using KDIGO. CKD prevalence was low and Grade 1/Stage 2. Further investigation is needed to optimally define kidney injury in …

Will You Go The Distance? A Satisfaction Survey Of Telemedicine In Sexual Medicine, Gal Saffati, Taher Naeem, Jordan Kassab, Daniela Orozco Rendon, Charles Green, Larry I Liphsultz, Mohit Khera

Faculty, Staff and Student Publications

BACKGROUND: The success of telemedicine depends on patient satisfaction with the care that they receive, which is impacted by the ease of use of the technology, quality of the connection, and perceived effectiveness of care.

AIM: The study sought to evaluate patient satisfaction with telemedicine services in a high-volume andrology clinic.

METHODS: We included all patients who had a telemedicine appointment between January 1, 2020, and August 22, 2022. Demographic information was gathered, and a satisfaction survey was conducted using REDCap software. Data were grouped into 2 age categories, with ≥50 years as the cutoff (19-50 years; >50 years). The …

Innovation Process And Industrial System Of Us Food And Drug Administration-Approved Software As A Medical Device: Review And Content Analysis, Jiakan Yu, Jiajie Zhang, Shintaro Sengoku

Faculty, Staff and Student Publications

BACKGROUND: There has been a surge in academic and business interest in software as a medical device (SaMD). SaMD enables medical professionals to streamline existing medical practices and make innovative medical processes such as digital therapeutics a reality. Furthermore, SaMD is a billion-dollar market. However, SaMD is not clearly understood as a technological change and emerging industry.

OBJECTIVE: This study aims to review the landscape of SaMD in response to increasing interest in SaMD within health systems and regulation. The objectives of the study are to (1) clarify the innovation process of SaMD, (2) identify the prevailing typology of such …

Evaluation Of Negative Binomial And Zero-Inflated Negative Binomial Models For The Analysis Of Zero-Inflated Count Data: Application To The Telemedicine For Children With Medical Complexity Trial, Kyung Hyun Lee, Claudia Pedroza, Elenir B C Avritscher, Ricardo A Mosquera, Jon E Tyson

Faculty, Staff and Student Publications

BACKGROUND: Two characteristics of commonly used outcomes in medical research are zero inflation and non-negative integers; examples include the number of hospital admissions or emergency department visits, where the majority of patients will have zero counts. Zero-inflated regression models were devised to analyze this type of data. However, the performance of zero-inflated regression models or the properties of data best suited for these analyses have not been thoroughly investigated.

METHODS: We conducted a simulation study to evaluate the performance of two generalized linear models, negative binomial and zero-inflated negative binomial, for analyzing zero-inflated count data. Simulation scenarios assumed a randomized …

Narrative Review Of The Role Of Technology In Pediatric Diabetes: From Testing Blood Glucose To Subcutaneous Automated Therapy And Hope For Cure, Michael Yafi, Avni Shah, Katherine Velez

Faculty, Staff and Student Publications

BACKGROUND AND OBJECTIVE: Type 1 diabetes, the most common cause of diabetes in pediatrics, is defined by the hyperglycemia that results from the permanent autoimmune damage to the pancreas. The Diabetes Control and Complications Trial (DCCT) demonstrated that strict glycemic control targeting lower HbA1c goals can both delay the onset and progression of its complications that include diabetic neuropathy, nephropathy, retinopathy, and increased cardiovascular events. Our primary objective is to review the literature available regarding the technology applied for the treatment of diabetes, not only aiding patients' quality of life but addressing its effects on hypoglycemia and reduced risk of …

Abnormal Motion Capture In Acute Stroke (Bionics): A Low-Cost Tele-Evaluation Tool For Automated Assessment Of Upper Extremity Function In Stroke Patients, Syed A Zamin, Kaichen Tang, Emily A Stevens, Melissa Howard, Dorothea M Parker, Allyson Seals, Xiaoqian Jiang, Sean Savitz, Shayan Shams

Faculty, Staff and Student Publications

BACKGROUND: The incidence of stroke and stroke-related hemiparesis has been steadily increasing and is projected to become a serious social, financial, and physical burden on the aging population. Limited access to outpatient rehabilitation for these stroke survivors further deepens the healthcare issue and estranges the stroke patient demographic in rural areas. However, new advances in motion detection deep learning enable the use of handheld smartphone cameras for body tracking, offering unparalleled levels of accessibility.

METHODS: In this study we want to develop an automated method for evaluation of a shortened variant of the Fugl-Meyer assessment, the standard stroke rehabilitation scale …

Cancer Patients' Preferences And Perceptions Of Advantages And Disadvantages Of Telehealth Visits During The Covid-19 Pandemic, Deepika Kumar, Nancy Gordon, Constanza Zamani, Tammy Sheehan, Ernesto Martin, Olga Egorova, Jessica Payne, Tatjana Kolevska, Elad Neeman, Raymond Liu

Faculty, Staff and Student Publications

PURPOSE: We aimed to ascertain oncology patients' perceptions of telehealth versus in-person (IP) visits for different types of clinical encounters.

METHODS: We surveyed adults undergoing cancer treatment at Kaiser Permanente Northern California infusion centers between November 2021 and May 2022 using a self-administered questionnaire. Patients were asked about visit modality preferences (video, phone, and IP) for six types of clinical discussions, overall advantages and disadvantages of telehealth (video or phone) versus IP modalities, and barriers to video visit use.

RESULTS: The 839 patients who completed surveys in English were 63% female; median age 63 years; 64% White; and 73% college-educated …

Wearable Biosensor With Molecularly Imprinted Conductive Polymer Structure To Detect Lentivirus In Aerosol, Jaskirat Singh Batra, Ting-Yen Chi, Mo-Fan Huang, Dandan Zhu, Zheyuan Chen, Dung-Fang Lee, Jun Kameoka

Faculty, Staff and Student Publications

The coronavirus disease (COVID-19) pandemic has increased pressure to develop low-cost, compact, user-friendly, and ubiquitous virus sensors for monitoring infection outbreaks in communities and preventing economic damage resulting from city lockdowns. As proof of concept, we developed a wearable paper-based virus sensor based on a molecular imprinting technique, using a conductive polyaniline (PANI) polymer to detect the lentivirus as a test sample. This sensor detected the lentivirus with a 4181 TU/mL detection limit in liquid and 0.33% to 2.90% detection efficiency in aerosols at distances ranging from 30 cm to 60 cm. For fabrication, a mixture of a PANI monomer …

Add-On Soft Electronic Interfaces For Continuous Cuffless Blood Pressure Monitoring, Myeong Namkoong, Balaji Baskar, Lakhvir Singh, Heng Guo, Justin Mcmurray, Kimberly Branan, Md Saifur Rahman, Chin-To Hsiao, Josh Kuriakose, Joanna Hernandez, Arda A Arikan, Luis E Garza-Rivera, Gerard L Coté, Limei Tian

Faculty, Staff and Student Publications

Continuous monitoring of arterial blood pressure is clinically important for the diagnosis and management of cardiovascular diseases. Soft electronic devices with skin-like properties show promise in a wide range of applications, including the human-machine interface, the Internet of things, and health monitoring. Here, we report the use of add-on soft electronic interfaces to address the connection challenges between soft electrodes and rigid data acquisition circuitry for bioimpedance monitoring of cardiac signals, including heart rate and cuffless blood pressure. Nanocomposite films in add-on electrodes provide robust electrical and mechanical contact with the skin and the rigid circuitry. We demonstrate bioimpedance sensors …

Effectiveness Of An Emergency Department-Based Machine Learning Clinical Decision Support Tool To Prevent Outpatient Falls Among Older Adults: Protocol For A Quasi-Experimental Study, Daniel J Hekman, Amy L Cochran, Apoorva P Maru, Hanna J Barton, Manish N Shah, Douglas Wiegmann, Maureen A Smith, Frank Liao, Brian W Patterson

Faculty, Staff and Student Publications

Background

Emergency department (ED) providers are important collaborators in preventing falls for older adults because they are often the first health care providers to see a patient after a fall and because at-home falls are often preceded by previous ED visits. Previous work has shown that ED referrals to falls interventions can reduce the risk of an at-home fall by 38%. Screening patients at risk for a fall can be time-consuming and difficult to implement in the ED setting. Machine learning (ML) and clinical decision support (CDS) offer the potential of automating the screening process. However, it remains unclear whether …

Feasibility Of Delivering A Virtual 1-Day Acceptance And Commitment Therapy Workshop To Rural Veterans Through Community Partnerships, Lilian Dindo, Angelic Chaison, Merlyn Rodrigues, Ken Woods, Alicia Mark, Derrecka Boykin

Faculty, Staff and Students Publications

Background: This single-arm, open pilot study examined the feasibility and initial efficacy of a 1-day virtual Acceptance and Commitment Therapy (ACT) group workshop for distressed veterans.

Methods: We collaborated with veteran-serving community-based organizations to enhance outreach to veterans, especially those in rural areas. Veterans completed a baseline assessment and two follow-up assessments (1 month, 3 months) after workshop participation. Feasibility outcomes included reach (workshop recruitment and completion rates; veteran characteristics) and acceptability (open-ended survey question about satisfaction). Clinical outcomes included psychological distress (Outcome Questionnaire-45), stressor-related distress (PTSD Checklist-5), community reintegration (Military to Civilian Questionnaire), and meaning and purpose (PROMIS Short …

Strategies For Advancing Equity In Frontline Clinical Assessment, Chavon M Onumah, Amber T Pincavage, Cindy J Lai, Diane L Levine, Nadia J Ismail, Irene Alexandraki, Nora Y Osman

Faculty and Staff Publications

Educational equity in medicine cannot be achieved without addressing assessment bias. Assessment bias in health professions education is prevalent and has extensive implications for learners and, ultimately, the health care system. Medical schools and educators desire to minimize assessment bias, but there is no current consensus on effective approaches. Frontline teaching faculty have the opportunity to mitigate bias in clinical assessment in real time. Based on their experiences as educators, the authors created a case study about a student to illustrate ways bias affects learner assessment. In this paper, the authors use their case study to provide faculty with evidence-based …

Candidemia In Patients With Cardiovascular Implantable Electronic Devices: Uncertainty In Management Based On Current International Guidelines, Supavit Chesdachai, Larry M Baddour, M Rizwan Sohail, Bharath Raj Palraj, Malini Madhavan, Hussam Tabaja, Madiha Fida, Douglas W Challener, Daniel C Desimone

Faculty, Staff and Students Publications

BACKGROUND: In contrast to bloodstream infection due to a variety of bacteria in patients with cardiovascular implantable electronic devices (CIED), there are limited data regarding candidemia and risk of CIED infection.

METHODS: All patients with candidemia and a CIED at Mayo Clinic Rochester between 2012 and 2019 were reviewed. Cardiovascular implantable electronic device infection was defined by (1) clinical signs of pocket site infection or (2) echocardiographic evidence of lead vegetations.

RESULTS: A total of 23 patients with candidemia had underlying CIED; 9 (39.1%) cases were community onset. None of the patients had pocket site infection. The duration between CIED …

Non-Melanoma Skin Cancer Detection In The Age Of Advanced Technology: A Review, Haleigh Stafford, Jane Buell, Elizabeth Chiang, Uma Ramesh, Michael Migden, Priyadharsini Nagarajan, Moran Amit, Dan Yaniv

Faculty, Staff and Student Publications

Skin cancer is the most common cancer diagnosis in the United States, with approximately one in five Americans expected to be diagnosed within their lifetime. Non-melanoma skin cancer is the most prevalent type of skin cancer, and as cases rise globally, physicians need reliable tools for early detection. Artificial intelligence has gained substantial interest as a decision support tool in medicine, particularly in image analysis, where deep learning has proven to be an effective tool. Because specialties such as dermatology rely primarily on visual diagnoses, deep learning could have many diagnostic applications, including the diagnosis of skin cancer. Furthermore, with …

Deep Single-Cell Rna-Seq Data Clustering With Graph Prototypical Contrastive Learning, Junseok Lee, Sungwon Kim, Dongmin Hyun, Namkyeong Lee, Yejin Kim, Chanyoung Park

Faculty, Staff and Student Publications

MOTIVATION: Single-cell RNA sequencing enables researchers to study cellular heterogeneity at single-cell level. To this end, identifying cell types of cells with clustering techniques becomes an important task for downstream analysis. However, challenges of scRNA-seq data such as pervasive dropout phenomena hinder obtaining robust clustering outputs. Although existing studies try to alleviate these problems, they fall short of fully leveraging the relationship information and mainly rely on reconstruction-based losses that highly depend on the data quality, which is sometimes noisy.

RESULTS: This work proposes a graph-based prototypical contrastive learning method, named scGPCL. Specifically, scGPCL encodes the cell representations using Graph …

Reviewing Internal Medicine Clerkship Grading Through A Proequity Lens: Results Of A National Survey, Cindy J Lai, Irene Alexandraki, Nadia Ismail, Diane Levine, Chavon Onumah, Amber T Pincavage, Jackcy Jacob, Melissa Osborn Jenkins, Amulya Nagarur, Michael Kisielewski, Nora Y Osman

Faculty and Staff Publications

Purpose: Equity in assessment and grading has become imperative across medical education. Although strategies to promote equity exist, there may be variable penetrance across institutions. The objectives of this study were to identify strategies internal medicine (IM) clerkship directors (CDs) use to reduce inequities in assessment and grading and explore IM CDs' perceptions of factors that impede or facilitate the implementation of these strategies.

Method: From October to December 2021, the Clerkship Directors in Internal Medicine of the Alliance for Academic Internal Medicine conducted its annual survey of IM core CDs at 137 U.S. and U.S. territory-based medical schools. This …

Use Of Telemedicine For Postdischarge Assessment Of The Surgical Wound: International Cohort Study, And Systematic Review With Meta-Analysis, Nihr Global Health Research Unit On Global Surgery, Globalsurg Collaborative

Faculty, Staff and Student Publications

OBJECTIVE: This study aimed to determine whether remote wound reviews using telemedicine can be safely upscaled, and if standardized assessment tools are needed.

BACKGROUND: Surgical site infection (SSI) is the most common complication of surgery worldwide, and frequently occurs after hospital discharge. Evidence to support implementation of telemedicine during postoperative recovery will be an essential component of pandemic recovery.

METHODS: The primary outcome of this study was SSI reported up to 30 days after surgery (SSI), comparing rates reported using telemedicine (telephone and/or video assessment) to those with in-person review. The first part of this study analyzed primary data from …

Machine Learning-Based Aggression Detection In Children With Adhd Using Sensor-Based Physical Activity Monitoring, Catherine Park, Mohammad Dehghan Rouzi, Md Moin Uddin Atique, M G Finco, Ram Kinker Mishra, Griselda Barba-Villalobos, Emily Crossman, Chima Amushie, Jacqueline Nguyen, Chadi Calarge, Bijan Najafi

Center on Aging Staff Publications

Aggression in children is highly prevalent and can have devastating consequences, yet there is currently no objective method to track its frequency in daily life. This study aims to investigate the use of wearable-sensor-derived physical activity data and machine learning to objectively identify physical-aggressive incidents in children. Participants (n = 39) aged 7 to 16 years, with and without ADHD, wore a waist-worn activity monitor (ActiGraph, GT3X+) for up to one week, three times over 12 months, while demographic, anthropometric, and clinical data were collected. Machine learning techniques, specifically random forest, were used to analyze patterns that identify physical-aggressive incident …

Quehry: A Question Answering System To Query Electronic Health Records, Sarvesh Soni, Surabhi Datta, Kirk Roberts

Faculty, Staff and Student Publications

OBJECTIVE: We propose a system, quEHRy, to retrieve precise, interpretable answers to natural language questions from structured data in electronic health records (EHRs).

MATERIALS AND METHODS: We develop/synthesize the main components of quEHRy: concept normalization (MetaMap), time frame classification (new), semantic parsing (existing), visualization with question understanding (new), and query module for FHIR mapping/processing (new). We evaluate quEHRy on 2 clinical question answering (QA) datasets. We evaluate each component separately as well as holistically to gain deeper insights. We also conduct a thorough error analysis for a crucial subcomponent, medical concept normalization.

RESULTS: Using gold concepts, the precision of quEHRy …

Development Of A Computable Phenotype Using Electronic Health Records For Venous Thromboembolism In Medical Inpatients: The Medical Inpatient Thrombosis And Hemostasis Study, Ryan M Thomas, Katherine Wilkinson, Insu Koh, Ang Li, Janine S A Warren, Nicholas S Roetker, Nicholas L Smith, Chris E Holmes, Timothy B Plante, Allen B Repp, Mary Cushman, Neil A Zakai

Faculty, Staff and Students Publications

BACKGROUND: Accurate and efficient methods to identify venous thromboembolism (VTE) events in hospitalized people are needed to support large-scale studies. Validated computable phenotypes using a specific combination of discrete, searchable elements in electronic health records to identify VTE and distinguish between hospital-acquired (HA)-VTE and present-on-admission (POA)-VTE would greatly facilitate the study of VTE, obviating the need for chart review.

OBJECTIVES: To develop and validate computable phenotypes for POA- and HA-VTE in adults hospitalized for medical reasons.

METHODS: The population included admissions to medical services from 2010 to 2019 at an academic medical center. POA-VTE was defined as VTE diagnosed within …

Leveraging The Electronic Health Record To Implement Emergency Department Delirium Screening, Anita N Chary, Elise Brickhouse, Beatrice Torres, Ilianna Santangelo, Christopher R Carpenter, Shan W Liu, Kyler M Godwin, Aanand D Naik, Hardeep Singh, Maura Kennedy

Faculty, Staff and Students Publications

OBJECTIVE: The aim of this study is to understand how emergency departments (EDs) use health information technology (HIT), and specifically the electronic health record (EHR), to support implementation of delirium screening.

METHODS: We conducted semi-structured interviews with 23 ED clinician-administrators, representing 20 EDs, about how they used HIT resources to implement delirium screening. Interviews focused on challenges participants experienced when implementing ED delirium screening and EHR-based strategies they used to overcome them. We coded interview transcripts using dimensions from the Singh and Sittig sociotechnical model, which addresses use of HIT in complex adaptive health care systems. Subsequently, we analyzed data …