Develop and validate a computable phenotype for the identification of Alzheimer's disease patients using electronic health record data.

INTRODUCTION: Alzheimer's disease (AD) is often misclassified in electronic health records (EHRs) when relying solely on diagnosis codes. This study aimed to develop a more accurate, computable phenotype (CP) for identifying AD patients using structured and unstructured EHR data. METHODS: We used EHRs from the University of Florida Health (UFHealth) system and created rule-based CPs iteratively through manual chart reviews. The CPs were then validated using data from the University of Texas Health Science Center at Houston (UTHealth) and the University of Minnesota (UMN). RESULTS: Our best-performing CP was "patient has at least 2 AD diagnoses and AD-related keywords in AD encounters," with an F1-score of 0.817 at UF, 0.961 at UTHealth, and 0.623 at UMN, respectively. DISCUSSION: We developed and validated rule-based CPs for AD identification with good performance, which will be crucial for studies that aim to use real-world data like EHRs. Highlights: Developed a computable phenotype (CP) to identify Alzheimer's disease (AD) patients using EHR data.Utilized both structured and unstructured EHR data to enhance CP accuracy.Achieved a high F1-score of 0.817 at UFHealth, and 0.961 and 0.623 at UTHealth and UMN.Validated the CP across different demographics, ensuring robustness and fairness.

Detection of Personal and Family History of Suicidal Thoughts and Behaviors using Deep Learning and Natural Language Processing: A Multi-Site Study.

Objective: Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with future suicide events. These are often captured in narrative clinical notes in electronic health records (EHRs). Collaboratively, Weill Cornell Medicine (WCM), Northwestern Medicine (NM), and the University of Florida (UF) developed and validated deep learning (DL)-based natural language processing (NLP) tools to detect PSH and FSH from such notes. The tool's performance was further benchmarked against a method relying exclusively on ICD-9/10 diagnosis codes. Materials and Methods: We developed DL-based NLP tools utilizing pre-trained transformer models Bio_ClinicalBERT and GatorTron, and compared them with expert-informed, rule-based methods. The tools were initially developed and validated using manually annotated clinical notes at WCM. Their portability and performance were further evaluated using clinical notes at NM and UF. Results: The DL tools outperformed the rule-based NLP tool in identifying PSH and FHS. For detecting PSH, the rule-based system obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based NLP tool's F1-score was 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. For the gold standard corpora across the three sites, only 2.2% (WCM), 9.3% (NM), and 7.8% (UF) of patients reported to have an ICD-9/10 diagnosis code for suicidal thoughts and behaviors prior to the clinical notes report date. The best performing GatorTron DL tool identified 93.0% (WCM), 80.4% (NM), and 89.0% (UF) of patients with documented PSH, and 85.0%(WCM), 89.5%(NM), and 100%(UF) of patients with documented FSH in their notes. Discussion: While PSH and FSH are significant risk factors for future suicide events, little effort has been made previously to identify individuals with these history. To address this, we developed a transformer based DL method and compared with conventional rule-based NLP approach. The varying effectiveness of the rule-based tools across sites suggests a need for improvement in its dictionary-based approach. In contrast, the performances of the DL tools were higher and comparable across sites. Furthermore, DL tools were fine-tuned using only small number of annotated notes at each site, underscores its greater adaptability to local documentation practices and lexical variations. Conclusion: Variations in local documentation practices across health care systems pose challenges to rule-based NLP tools. In contrast, the developed DL tools can effectively extract PSH and FSH information from unstructured clinical notes. These tools will provide clinicians with crucial information for assessing and treating patients at elevated risk for suicide who are rarely been diagnosed.

Develop and Validate a Computable Phenotype for the Identification of Alzheimer's Disease Patients Using Electronic Health Record Data.

INTRODUCTION: Alzheimer's Disease (AD) are often misclassified in electronic health records (EHRs) when relying solely on diagnostic codes. This study aims to develop a more accurate, computable phenotype (CP) for identifying AD patients by using both structured and unstructured EHR data. METHODS: We used EHRs from the University of Florida Health (UF Health) system and created rule-based CPs iteratively through manual chart reviews. The CPs were then validated using data from the University of Texas Health Science Center at Houston (UT Health) and the University of Minnesota (UMN). RESULTS: Our best-performing CP is " patient has at least 2 AD diagnoses and AD-related keywords " with an F1-score of 0.817 at UF, and 0.961 and 0.623 at UT Health and UMN, respectively. DISCUSSION: We developed and validated rule-based CPs for AD identification with good performance, crucial for studies that aim to use real-world data like EHRs.

The role of health system penetration rate in estimating the prevalence of type 1 diabetes in children and adolescents using electronic health records.

OBJECTIVE: Having sufficient population coverage from the electronic health records (EHRs)-connected health system is essential for building a comprehensive EHR-based diabetes surveillance system. This study aimed to establish an EHR-based type 1 diabetes (T1D) surveillance system for children and adolescents across racial and ethnic groups by identifying the minimum population coverage from EHR-connected health systems to accurately estimate T1D prevalence. MATERIALS AND METHODS: We conducted a retrospective, cross-sectional analysis involving children and adolescents <20 years old identified from the OneFlorida+ Clinical Research Network (2018-2020). T1D cases were identified using a previously validated computable phenotyping algorithm. The T1D prevalence for each ZIP Code Tabulation Area (ZCTA, 5 digits), defined as the number of T1D cases divided by the total number of residents in the corresponding ZCTA, was calculated. Population coverage for each ZCTA was measured using observed health system penetration rates (HSPR), which was calculated as the ratio of residents in the corresponding ZTCA and captured by OneFlorida+ to the overall population in the same ZCTA reported by the Census. We used a recursive partitioning algorithm to identify the minimum required observed HSPR to estimate T1D prevalence and compare our estimate with the reported T1D prevalence from the SEARCH study. RESULTS: Observed HSPRs of 55%, 55%, and 60% were identified as the minimum thresholds for the non-Hispanic White, non-Hispanic Black, and Hispanic populations. The estimated T1D prevalence for non-Hispanic White and non-Hispanic Black were 2.87 and 2.29 per 1000 youth, which are comparable to the reference study's estimation. The estimated prevalence of T1D for Hispanics (2.76 per 1000 youth) was higher than the reference study's estimation (1.48-1.64 per 1000 youth). The standardized T1D prevalence in the overall Florida population was 2.81 per 1000 youth in 2019. CONCLUSION: Our study provides a method to estimate T1D prevalence in children and adolescents using EHRs and reports the estimated HSPRs and prevalence of T1D for different race and ethnicity groups to facilitate EHR-based diabetes surveillance.

The PRISM semantic cohort builder: a novel tool to search and access clinical data in TCIA imaging collections.

The cancer imaging archive (TICA) receives and manages an ever-increasing quantity of clinical (non-image) data containing valuable information about subjects in imaging collections. To harmonize and integrate these data, we have first cataloged the types of information occurring across public TCIA collections. We then produced mappings for these diverse instance data using ontology-based representation patterns and transformed the data into a knowledge graph in a semantic database. This repository combined the transformed instance data with relevant background knowledge from domain ontologies. The resulting repository of semantically integrated data is a rich source of information about subjects that can be queried across imaging collections. Building on this work we have implemented and deployed a REST API and a user-facing semantic cohort builder tool. This tool allows allow researchers and other users to search and identify groups of subject-level records based on non-image data that were not queryable prior to this work. The search results produced by this interface link to images, allowing users to quickly identify and view images matching the selection criteria, as well as allowing users to export the harmonized clinical data.

A scoping review of semantic integration of health data and information.

OBJECTIVE: We summarized a decade of new research focusing on semantic data integration (SDI) since 2009, and we aim to: (1) summarize the state-of-art approaches on integrating health data and information; and (2) identify the main gaps and challenges of integrating health data and information from multiple levels and domains. MATERIALS AND METHODS: We used PubMed as our focus is applications of SDI in biomedical domains and followed the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) to search and report for relevant studies published between January 1, 2009 and December 31, 2021. We used Covidence-a systematic review management system-to carry out this scoping review. RESULTS: The initial search from PubMed resulted in 5,326 articles using the two sets of keywords. We then removed 44 duplicates and 5,282 articles were retained for abstract screening. After abstract screening, we included 246 articles for full-text screening, among which 87 articles were deemed eligible for full-text extraction. We summarized the 87 articles from four aspects: (1) methods for the global schema; (2) data integration strategies (i.e., federated system vs. data warehousing); (3) the sources of the data; and (4) downstream applications. CONCLUSION: SDI approach can effectively resolve the semantic heterogeneities across different data sources. We identified two key gaps and challenges in existing SDI studies that (1) many of the existing SDI studies used data from only single-level data sources (e.g., integrating individual-level patient records from different hospital systems), and (2) documentation of the data integration processes is sparse, threatening the reproducibility of SDI studies.

Biases in using social media data for public health surveillance: A scoping review.

OBJECTIVES: A landscape scan of the methods that are used to either assess or mitigate biases when using social media data for public health surveillance, through a scoping review. MATERIALS AND METHODS: Following best practices, we searched two literature databases (i.e., PubMed and Web of Science) and covered literature published up to July 2021. Through two rounds of screening (i.e., title/abstract screening, and then full-text screening), we extracted study objectives, analysis methods, and the methods used to assess or address the different biases from the eligible articles. RESULTS: We identified a total of 2,856 articles from the two databases. After the screening processes, we extracted and synthesized 20 studies that either assessed or mitigated biases when leveraging social media data for public health surveillance. Researchers have tried to assess or address several different types of biases such as demographic bias, keyword bias, and platform bias. In particular, we found 11 studies that tried to measure the reliability of the research findings from social media data by comparing them with other data sources. DISCUSSION AND CONCLUSION: We synthesized the types of biases and the methods used to assess or address the biases in studies that use social media data for public health surveillance. We found very few studies, despite the large number of publications using social media data, considered the various bias issues that are present from data collection to analysis methods. Overlooking bias can distort the study results and lead to unintended consequences, especially in the field of public health surveillance. These research gaps warrant further investigations more systematically. Strategies from other fields for addressing biases can be introduced for future public health surveillance systems that use social media data.

Assessing the Need for Semantic Data Integration for Surgical Biobanks-A Knowledge Representation Perspective.

To improve patient outcomes after trauma, the need to decrypt the post-traumatic immune response has been identified. One prerequisite to drive advancement in understanding that domain is the implementation of surgical biobanks. This paper focuses on the outcomes of patients with one of two diagnoses: post-traumatic arthritis and osteomyelitis. In creating surgical biobanks, currently, many obstacles must be overcome. Roadblocks exist around scoping of data that is to be collected, and the semantic integration of these data. In this paper, the generic component model and the Semantic Web technology stack are used to solve issues related to data integration. The results are twofold: (a) a scoping analysis of data and the ontologies required to harmonize and integrate it, and (b) resolution of common data integration issues in integrating data relevant to trauma surgery.

Syndromic Surveillance Systems for Mass Gatherings: A Scoping Review.

Syndromic surveillance involves the near-real-time collection of data from a potential multitude of sources to detect outbreaks of disease or adverse health events earlier than traditional forms of public health surveillance. The purpose of the present study is to elucidate the role of syndromic surveillance during mass gathering scenarios. In the present review, the use of syndromic surveillance for mass gathering scenarios is described, including characteristics such as methodologies of data collection and analysis, degree of preparation and collaboration, and the degree to which prior surveillance infrastructure is utilized. Nineteen publications were included for data extraction. The most common data source for the included syndromic surveillance systems was emergency departments, with first aid stations and event-based clinics also present. Data were often collected using custom reporting forms. While syndromic surveillance can potentially serve as a method of informing public health policy regarding specific mass gatherings based on the profile of syndromes ascertained, the present review does not indicate that this form of surveillance is a reliable method of detecting potentially critical public health events during mass gathering scenarios.

A Prospective Observational Comparison of Two Approaches to Anesthetizing the Trachea for Awake Intubation.

BACKGROUND: Multiple techniques have been described for anesthetizing the lower glottis and trachea prior to awake fiberoptic intubation. The primary aim of this study is to evaluate whether direct application of local anesthetic to the lower airway via an epidural catheter under direct vision is equally efficacious when compared to use of a transtracheal block in adult patients with an anticipated difficult airway. METHODS: Patients age >18 years requiring awake fiberoptic intubation who underwent upper and lower airway topicalization were observed prospectively. Following topicalization of the upper airway, patients underwent either a transtracheal block or had their trachea and lower glottis anesthetized under direct vision via dispersion of local anesthetic through a multi-orifice epidural catheter. Choice of technique was at the discretion of the attending anesthesiologist. The primary outcome was defined as the degree of coughing observed at the time of intubation based on a 4-point ordinal scale. RESULTS: Awake intubations in 88 patients were observed with 44 patients undergoing transtracheal block and 44 patients undergoing the epidural catheter technique. Degree of coughing with intubation was similar for each approach with a coughing score of (0, IQR (0,1)) versus (0, IQR (0,1)) in the epidural catheter and transtracheal groups respectively (p = 0.385). Duration of procedure was less in the transtracheal group (1.35 ± 1.54 min) vs. epidural catheter approach (2.86 ± 2.20 min) (p< 0.001). CONCLUSION: The epidural catheter and transtracheal approach appear to be equally effective at preventing coughing with intubation during awake fiberoptic intubation.

Understanding the Gap Between Information Models and Realism-Based Ontologies Using the Generic Component Model.

The wide-spread use of Common Data Models and information models in biomedical informatics encourages assumptions that those models could provide the entirety of what is needed for knowledge representation purposes. Based on the lack of computable semantics in frequently used Common Data Models, there appears to be a gap between knowledge representation requirements and these models. In this use-case oriented approach, we explore how a system-theoretic, architecture-centric, ontology-based methodology can help to better understand this gap. We show how using the Generic Component Model helps to analyze the data management system in a way that allows accounting for data management procedures inside the system and knowledge representation of the real world at the same time.

Collecting data on organizational structures of trauma centers: the CAFE web service.

BACKGROUND: During the past several decades, the American College of Surgeons has led efforts to standardize trauma care through their trauma center verification process and Trauma Quality Improvement Program. Despite these endeavors, great variability remains among trauma centers functioning at the same level. Little research has been conducted on the correlation between trauma center organizational structure and patient outcomes. We are attempting to close this knowledge gap with the Comparative Assessment Framework for Environments of Trauma Care (CAFE) project. METHODS: Our first action was to establish a shared terminology that we then used to build the Ontology of Organizational Structures of Trauma centers and Trauma systems (OOSTT). OOSTT underpins the web-based CAFE questionnaire that collects detailed information on the particular organizational attributes of trauma centers and trauma systems. This tool allows users to compare their organizations to an aggregate of other organizations of the same type, while collecting their data. RESULTS: In collaboration with the American College of Surgeons Committee on Trauma, we tested the system by entering data from three trauma centers and four trauma systems. We also tested retrieval of answers to competency questions. DISCUSSION: The data we gather will be made available to public health and implementation science researchers using visualizations. In the next phase of our project, we plan to link the gathered data about trauma center attributes to clinical outcomes.