Chute, Christopher G.

<p class="MsoNormal"> <span lang="EN-US">The Semantic Web has the ultimate goal of making a machine understand Internet data. To enable the encoding of semantics with the data, well-known technologies are used such as RDF (Resource Description Framework) and OWL (Web Ontology Language). These technologies formally represent the meaning involved in information. For example, ontology can describe concepts, relationships between things, and categories of things. These embedded semantics offer significant advantages such as reasoning over data and dealing with heterogeneous data sources.<o:p></o:p></span> </p>

Abstract The Human Phenotype Ontology (HPO) is a widely used resource that comprehensively organizes and defines the phenotypic features of human disease, enabling computational inference and supporting genomic and phenotypic analyses through semantic similarity and machine learning algorithms. The HPO has widespread applications in clinical diagnostics and translational research, including genomic diagnostics, gene-disease discovery, and cohort analytics. In recent years, groups around the world have developed translations of the HPO from English to other languages, and the HPO browser has been internationalized, allowing users to view HPO term labels and in many cases synonyms and definitions in ten languages in addition to English. Since our last report, a total of 2239 new HPO terms and 49235 new HPO annotations were developed, many in collaboration with external groups in the fields of psychiatry, arthrogryposis, immunology and cardiology. The Medical Action Ontology (MAxO) is a new effort to model treatments and other measures taken for clinical management. Finally, the HPO consortium is contributing to efforts to integrate the HPO and the GA4GH Phenopacket Schema into electronic health records (EHRs) with the goal of more standardized and computable integration of rare disease data in EHRs.

Abstract Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federated annotation and evaluation to resolve several pitfalls encountered in the course of these efforts.

e13552 Background: Real-world data from Electronic Health Records (EHR) have been widely used for patient identification to build study cohorts for clinical research. Traditionally, diagnosis codes in the EHR, such International Classification of Diseases (ICD), are used to identify the target patients. However, the accuracy of this approach is dependent on the accuracy of ICD coding, with potential errors especially for tumor types that are frequent locations for metastases (which may contribute to mis-coding). In this study, we attempted to develop a Machine Learning (ML) based approach on EHR data to improve the accuracy of identification of patients with lung cancer. Methods: We used survey respondents in the Enhanced, EHR-facilitated Cancer Symptom Control (E2C2, NCT03892967) cluster-randomized trial at Mayo Clinic as our initial pan-cancer cohort. E2C2 includes adults receiving Medical Hematology/Oncology care for a solid or liquid tumor at Mayo Clinic. We collected cancer diagnoses from the individually abstracted Mayo Clinic Cancer Registry to annotate the cancer type for the patients. Lung cancer related ICD-9 (162.X) and ICD-10 (C34.X) codes were used to build a search query on the Mayo’s EHR to find target patients from the E2C2 cohort, and to investigate the ICD-based lung cancer patient identification performance. Diagnosis, radiation oncology treatment (CPT 77261 - 77799), and antineoplastic drug administration data were collected from EHR as variables. Logistic Regression (LR), Support vector machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) were selected to build models for lung cancer patient identification. 10-fold cross-validation was implemented to assess the models. Precision, Recall, F1 Score, and area under the curve (AUC) were selected to measure the performance. Results: We collected 13,893 patients with a specific cancer diagnosis, and 1,394 were identified as having lung cancer. The identification performance across different methods is shown. The ICD-based method only had 0.65 precision. It means we collected a lot of false positive cases (other cancer but no lung cancer patient), as we mentioned in the background. SVM gets the best precision results, but its recall and F1 score are not good enough. XGB shows the best F1 Score and AUC, which also means this method achieved the best and most balanced performance. Conclusions: In this study, we found that XGB-based methods achieved the best identification performance for lung cancer. In the future, we will investigate if this is also true for the identification of other cancer types. [Table: see text]

AbstractAn increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP‐assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP‐derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP‐assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.

AbstractObjectiveThe aim of this study was to analyze a publicly available sample of rule-based phenotype definitions to characterize and evaluate the variability of logical constructs used.Materials and MethodsA sample of 33 preexisting phenotype definitions used in research that are represented using Fast Healthcare Interoperability Resources and Clinical Quality Language (CQL) was analyzed using automated analysis of the computable representation of the CQL libraries.ResultsMost of the phenotype definitions include narrative descriptions and flowcharts, while few provide pseudocode or executable artifacts. Most use 4 or fewer medical terminologies. The number of codes used ranges from 5 to 6865, and value sets from 1 to 19. We found that the most common expressions used were literal, data, and logical expressions. Aggregate and arithmetic expressions are the least common. Expression depth ranges from 4 to 27.DiscussionDespite the range of conditions, we found that all of the phenotype definitions consisted of logical criteria, representing both clinical and operational logic, and tabular data, consisting of codes from standard terminologies and keywords for natural language processing. The total number and variety of expressions are low, which may be to simplify implementation, or authors may limit complexity due to data availability constraints.ConclusionsThe phenotype definitions analyzed show significant variation in specific logical, arithmetic, and other operators but are all composed of the same high-level components, namely tabular data and logical expressions. A standard representation for phenotype definitions should support these formats and be modular to support localization and shared logic.

There is a need for multimodal strategies to keep research participants informed about study results. Our aim was to characterize preferences of genomic research participants from two institutions along four dimensions of general research result updates: content, timing, mechanism, and frequency. Methods: We conducted a web-based cross-sectional survey that was administered from 25 June 2018 to 5 December 2018. Results: 397 participants completed the survey, most of whom (96%) expressed a desire to receive research updates. Preferences with high endorsement included: update content (brief descriptions of major findings, descriptions of purpose and goals, and educational material); update timing (when the research is completed, when findings are reviewed, when findings are published, and when the study status changes); update mechanism (email with updates, and email newsletter); and update frequency (every three months). Hierarchical cluster analyses based on the four update preferences identified four profiles of participants with similar preference patterns. Very few participants in the largest profile were comfortable with budgeting less money for research activities so that researchers have money to set up services to send research result updates to study participants. Conclusion: Future studies may benefit from exploring preferences for research result updates, as we have in our study. In addition, this work provides evidence of a need for funders to incentivize researchers to communicate results to participants.

Background The incidence of VTE in African-Americans (AAs) is similar to or higher than in Americans of European ancestry. However, the carrier frequencies of inherited thrombophilias common in whites (i.e., Factor V Leiden, Prothrombin G20210A) are very low in AAs, suggesting that other inherited thrombophilias may be associated with VTE in AAs. Objective To identify potentially novel non-hypothesis-driven single nucleotide polymorphisms (SNPs) associated with VTE in AAs. Methods We used the resources of the eMERGE Network to perform a GWAS of VTE in AAs. The eMERGE Network (funded by NHGRI) is comprised of nine sites each with DNA biobanks linked to electronic health records (EHRs). Approximately 39,206 unique DNA samples have been genotyped using either Affymetrix or Illumina genome-wide SNP arrays. Led by the Coordinating Center and eMERGE genomics workgroup, an imputation pipeline was developed for merging genomic data across the different SNP arrays used by the eMERGE sites, to maximize sample size and the power to detect associations. The imputation was performed using the 1000 Genomes Cosmopolitan reference panel which includes 1092 individuals and over 36 million SNPs. From our previously-identified cohort of Olmsted County, MN residents with incident or recurrent VTE, 1996-2005, we derived and validated an EHR-driven phenotype extraction algorithm that leveraged structured data based on ICD-9-CM codes and unstructured data from clinical notes via natural language processing to identify VTE cases and controls with 100% and 94% positive and negative predictive values, respectively. We tested for an association between each SNP and VTE among AAs using unconditional logistic regression, adjusting for age, sex and eMERGE site. Results Among 294 AA VTE cases and 3,661 AA controls (total n=3,955; females, n=2,512), the Factor V Leiden (F5 rs6025) was not analyzed due to a very low minor allele frequency (MAF=0.0036). The prothrombin G20210A (F2 rs1799963) and ABO blood type O (ABO rs8176719) SNPs were not genotyped in any of the arrays and could not be imputed. Among SNPs with an imputation score >0.8, the most significant SNPs associated with VTE were ITPR3 (inositol 1,4,5-triphosphate receptor type 3) rs2229637 (OR=1.65; p=3.61E-07; MAF=0.19) and CLEC7A (C-type lectin domain family 7, member A) rs59819090 (OR=2.16; p=1.06E-06; MAF=0.056). ITPR3 SNPs have been associated with coronary artery aneurysm in Kawasaki disease, type 1 diabetes mellitus and other autoimmune disorders. CLEC7A rs59819090 encodes for a serine82 to leucine nonsynonymous amino acid change in dectin-1. Dectin-1 is a transmembrane innate immune pattern recognition receptor on myeloid cells that upon binding it’s agonist, β-glucans, stimulates cytokine production and the respiratory burst, a prerequisite for formation of neutrophil extracelluar traps (NETs). NETs have been associated with VTE (van Montfoort, et al. Ateriosclero Thromb Vasc Biol 2013;33:147-51). Dectin-1 serine82 is not evolutionarily conserved and the serine82 to leucine amino acid change is predicted to be tolerated, with a moderate effect on protein function. Conclusions ITPR3 rs2229637 and CLAC7A rs59819090 may be associated with VTE in African-Americans. These observations require replication and functional studies toward understanding how they may lie on the causal pathway to VTE. Disclosures: No relevant conflicts of interest to declare.

Background: Proteomic approaches allow measurement of thousands of proteins in a single specimen, which can accelerate biomarker discovery. However, applying these technologies to massive biobanks is not currently feasible because of the practical barriers and costs of implementing such assays at scale. To overcome these challenges, we used a “virtual proteomic” approach, linking genetically predicted protein levels to clinical diagnoses in >40 000 individuals. Methods: We used genome-wide association data from the Framingham Heart Study (n=759) to construct genetic predictors for 1129 plasma protein levels. We validated the genetic predictors for 268 proteins and used them to compute predicted protein levels in 41 288 genotyped individuals in the Electronic Medical Records and Genomics (eMERGE) cohort. We tested associations for each predicted protein with 1128 clinical phenotypes. Lead associations were validated with directly measured protein levels and either low-density lipoprotein cholesterol or subclinical atherosclerosis in the MDCS (Malmö Diet and Cancer Study; n=651). Results: In the virtual proteomic analysis in eMERGE, 55 proteins were associated with 89 distinct diagnoses at a false discovery rate q<0.1. Among these, 13 associations involved lipid (n=7) or atherosclerosis (n=6) phenotypes. We tested each association for validation in MDCS using directly measured protein levels. At Bonferroni-adjusted significance thresholds, levels of apolipoprotein E isoforms were associated with hyperlipidemia, and circulating C-type lectin domain family 1 member B and platelet-derived growth factor receptor-β predicted subclinical atherosclerosis. Odds ratios for carotid atherosclerosis were 1.31 (95% CI, 1.08–1.58; P =0.006) per 1-SD increment in C-type lectin domain family 1 member B and 0.79 (0.66–0.94; P =0.008) per 1-SD increment in platelet-derived growth factor receptor-β. Conclusions: We demonstrate a biomarker discovery paradigm to identify candidate biomarkers of cardiovascular and other diseases.