Nomenclature Of Medicine-Clinical Terms Research Articles

Evaluation of SNOMED CT Grouper Accuracy and Coverage in Organizing the Electronic Health Record Problem List by Clinical System: Observational Study

Abstract Background The problem list (PL) is a repository of diagnoses for patients’ medical conditions and health-related issues. Unfortunately, over time, our PLs have become overloaded with duplications, conflicting entries, and no-longer-valid diagnoses. The lack of a standardized structure for review adds to the challenges of clinical use. Previously, our default electronic health record (EHR) organized the PL primarily via alphabetization, with other options available, for example, organization by clinical systems or priority settings. The system’s PL was built with limited groupers, resulting in many diagnoses that were inconsistent with the expected clinical systems or not associated with any clinical systems at all. As a consequence of these limited EHR configuration options, our PL organization has poorly supported clinical use over time, particularly as the number of diagnoses on the PL has increased. Objective We aimed to measure the accuracy of sorting PL diagnoses into PL system groupers based on Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) concept groupers implemented in our EHR. Methods We transformed and developed 21 system- or condition-based groupers, using 1211 SNOMED CT hierarchal concepts refined with Boolean logic, to reorganize the PL in our EHR. To evaluate the clinical utility of our new groupers, we extracted all diagnoses on the PLs from a convenience sample of 50 patients with 3 or more encounters in the previous year. To provide a spectrum of clinical diagnoses, we included patients from all ages and divided them by sex in a deidentified format. Two physicians independently determined whether each diagnosis was correctly attributed to the expected clinical system grouper. Discrepancies were discussed, and if no consensus was reached, they were adjudicated by a third physician. Descriptive statistics and Cohen κ statistics for interrater reliability were calculated. Results Our 50-patient sample had a total of 869 diagnoses (range 4-59; median 12, IQR 9-24). The reviewers initially agreed on 821 system attributions. Of the remaining 48 items, 16 required adjudication with the tie-breaking third physician. The calculated κ statistic was 0.7. The PL groupers appropriately associated diagnoses to the expected clinical system with a sensitivity of 97.6%, a specificity of 58.7%, a positive predictive value of 96.8%, and an F1-score of 0.972. Conclusions We found that PL organization by clinical specialty or condition using SNOMED CT concept groupers accurately reflects clinical systems. Our system groupers were subsequently adopted by our vendor EHR in their foundation system for PL organization.

Review of codelists used to define hypertension in electronic health records and development of a codelist for research

Background and aimsHypertension is a leading risk factor for cardiovascular disease. Electronic health records (EHRs) are routinely collected throughout a person’s care, recording all aspects of health status, including current...

The Diagnostic Odyssey in Children and Adolescents With X-linked Hypophosphatemia: Population-Based, Case–Control Study

Abstract Context X-linked hypophosphatemia (XLH) is a rare genetic disorder causing renal phosphate wasting, which predicates musculoskeletal manifestations such as rickets. Diagnosis is often delayed. Objective To explore the recording of clinical features, and the diagnostic odyssey of children and adolescents with XLH in primary care electronic healthcare records (EHRs) in the United Kingdom. Methods Using the Optimum Patient Care Research Database, individuals aged 20 years or younger after January 1, 2000, at date of recorded XLH diagnosis were identified using Systematized Nomenclature of Medicine Clinical Terms (SNOMED)/Read codes and age-matched to 100 controls. Recording of XLH-related clinical features was summarized then compared between cases and controls using chi-squared or Fisher's exact test. Results In total, 261 XLH cases were identified; 99 met the inclusion criteria. Of these, 84/99 had at least 1 XLH-related clinical feature recorded in their primary care EHR. Clinical codes for rickets, genu varum, and low phosphate were recorded prior to XLH diagnosis in under 20% of cases (median of 1, 1, and 3 years prior, respectively). Rickets, genu varum, low phosphate, nephrocalcinosis, and growth delay were significantly more likely to be recorded in cases. Conclusion This characterization of the EHR phenotypes of children and adolescents with XLH may inform future case-finding approaches to expedite diagnosis in primary care.

Mental Health Polypharmacy in "Non-Coded" Primary Care Patients: The Effect of Deprescribing.

Background: Mental health (MH) polypharmacy, defined as prescribing multiple mental health medications for the same condition, presents significant challenges in clinical practice. With varying prevalence rates and an increasing trend, particularly in the UK, this deprescribing prospective quality improvement project aimed to address the complexities and risks associated with MH polypharmacy. Patients and Methods: A large primary care centre in London was selected for this project. Electronic records of 667 patients (non-coded in mental health lists) were analysed as a result of the absence of a Systematised Nomenclature of Medicine Clinical Terms (SNOMED CT) for mental health. Seventy-two non-coded patients exhibiting "same-class" as well as "adjunctive" and "augmentation" polypharmacy were identified. Their demographic and health data, including MH diagnoses, physical status, and lifestyle habits, were evaluated. This deprescribing prospective project included 68 patients and employed a model inspired by the Plan-Do-Study-Act (PDSA) cycle, focusing on reducing psychotropic, adjunctive, and augmentative medications while monitoring mental health control through face-to-face consultations using the Patient Health Questionnaire-9 (PHQ-9) and Generalised Anxiety Disorder Assessment-7 (GAD-7) scores, alongside physical health parameters. Results: The project revealed a significant decrease in the average number of psychotropic and adjunct medications from initial consultations to the end of the 18-month period. Additionally, a marked reduction in reported side effects and drug interactions was observed. Improvements in mental health control, as evidenced by PHQ-9 and GAD-7 scores, were noted. Physical health parameters, including BMI, blood pressure, heart rate, HbA1c, and cholesterol levels, also showed significant improvements. Educational initiatives for patients and clinicians were successfully implemented, contributing to these positive outcomes. Discussion: The project faced challenges like balancing medication reduction with mental health stability, patient apprehension, and the absence of standardised protocols. However, the successful reduction in medication numbers and the improvement in health outcomes highlight the effectiveness of the model. This project underscores the necessity of a tailored approach to MH polypharmacy, emphasising continuous education, clinical titration, and adherence to guidelines. Future research is needed to develop clear guidelines for medication combination in mental health care and to understand the long-term effects of polypharmacy in mental health populations. Conclusions: This project demonstrates the potential for significant improvements in the management of MH polypharmacy. By carefully managing medication reductions and employing a comprehensive care approach, including patient education and clinician training, the project achieved improvements in both mental and physical health outcomes. These findings suggest a promising direction for future practices in MH polypharmacy management.

Predicting disease onset from electronic health records for population health management: a scalable and explainable Deep Learning approach.

The move from a reactive model of care which treats conditions when they arise to a proactive model which intervenes early to prevent adverse healthcare events will benefit from advances in the predictive capabilities of Artificial Intelligence and Machine Learning. This paper investigates the ability of a Deep Learning (DL) approach to predict future disease diagnosis from Electronic Health Records (EHR) for the purposes of Population Health Management. In this study, embeddings were created using a Word2Vec algorithm from structured vocabulary commonly used in EHRs e.g., Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) codes. This study is based on longitudinal medical data from ~50 m patients in the USA. We introduced a novel method of including binned observation values into an embeddings model. We also included novel features associated with wider determinants of health. Patient records comprising these embeddings were then fed to a Bidirectional Gated Recurrent Unit (GRU) model to predict the likelihood of patients developing Type 2 Diabetes Mellitus, Chronic Obstructive Pulmonary Disorder (COPD), Hypertension or experiencing an Acute Myocardial Infarction (MI) in the next 3 years. SHapley Additive exPlanations (SHAP) values were calculated to achieve model explainability. Increasing the data scope to include binned observations and wider determinants of health was found to improve predictive performance. We achieved an area under the Receiver Operating Characteristic curve value of 0.92 for Diabetes prediction, 0.94 for COPD, 0.92 for Hypertension and 0.94 for MI. The SHAP values showed that the models had learned features known to be associated with these outcomes. The DL approach outlined in this study can identify clinically-relevant features from large-scale EHR data and use these to predict future disease outcomes. This study highlights the promise of DL solutions for identifying patients at future risk of disease and providing clinicians with the means to understand and evaluate the drivers of those predictions.

A Bibliographic Dataset of Health Artificial Intelligence Research.

Objective: The aim of this study is to construct a curated bibliographic dataset for a landscape analysis on Health Artificial Intelligence (HAI) research. Data Source: We integrated HAI-related bibliographic records, including publications, open research datasets, patents, research grants, and clinical trials from Medline and Dimensions. Methods: Searching: Relevant documents were identified using Medical Subject Headings (MeSH) and Field of Research (FoR) indexed by 2 bibliographic databases, Medline and Dimensions. Extracting: MeSH terms annotated from the aforementioned bibliographic databases served as the primary information for our processing. For document records lacking MeSH terms, we re-extracted them using the Medical Text Indexer (MTI). Mapping: In order to enhance interoperability, HAI multi-documents were organized using a mapping system incorporating MeSH, FoR, The International Classification of Diseases (ICD-10), and Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). Integrating: All documents were curated based on a pre-defined ontology of health problems and AI technologies from the MeSH hierarchy. Results: We collected 96,332 HAI documents (publications: 75,820, open research datasets: 638, patents: 11,226, grants: 6,113, and clinical trials: 2,535) during 2009 to 2021. On average, 75.12% of the documents were tagged with at least one label related to either health problems or AI technologies (with 92.9% of publications tagged). Summary: This study presents a comprehensive pipeline for processing and curating HAI bibliographic documents following the FAIR (Findable, Accessible, Interoperable, Reusable) standard, offering a valuable multidimensional collection for the community. This dataset serves as a crucial resource for horizontally scanning the funding, research, clinical assessments, and innovations within the HAI field.

The Necessity of Interoperability to Uncover the Full Potential of Digital Health Devices.

Personalized health care can be optimized by including patient-reported outcomes. Standardized and disease-specific questionnaires have been developed and are routinely used. These patient-reported outcome questionnaires can be simple paper forms given to the patient to fill out with a pen or embedded in digital devices. Regardless of the format used, they provide a snapshot of the patient's feelings and indicate when therapies need to be adjusted. The advantage of digitizing these questionnaires is that they can be automatically analyzed, and patients can be monitored independently of doctor visits. Although the questions of most clinical patient-reported outcome questionnaires follow defined standards and are evaluated by clinical trials, these standards do not exist for data processing. Interoperable data formats and structures would benefit multilingual and cross-study data exchange. Linking questionnaires to standardized terminologies such as the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Logical Observation Identifiers, Names, and Codes (LOINC) would improve this interoperability. However, linking clinically validated patient-reported outcome questionnaires to clinical terms available in SNOMED CT or LOINC is not as straightforward as it sounds. Here, we report our approach to link patient-reported outcomes from health applications to SNOMED CT or LOINC codes. We highlight current difficulties in this process and outline ways to minimize them.

Hepatitis A Vaccination Coverage Among People With Chronic Liver Disease in England (HEALD): Protocol for a Retrospective Cohort Study.

Hepatitis A outbreaks in the United Kingdom are uncommon. Most people develop mild to moderate symptoms that resolve, without sequelae, within months. However, in high-risk groups, including those with underlying chronic liver disease (CLD), hepatitis A infection can be severe, with a higher risk of mortality and morbidity. The Health Security Agency and the National Institute of Health and Care Excellence recommend preexposure hepatitis A vaccination given in 2 doses to people with CLD, regardless of its cause. There are currently no published reports of vaccination coverage for people with CLD in England or internationally. This study aims to describe hepatitis A vaccination coverage in adults with CLD in a UK primary care setting and compare liver disease etiology, sociodemographic characteristics, and comorbidities in people who are and are not exposed to the hepatitis A vaccine. We will conduct a retrospective cohort study with data from the Primary Care Sentinel Cohort of the Oxford-Royal College of General Practitioners Clinical Informatics Digital Hub database, which is nationally representative of the English population. We will include people aged 18 years and older who have been registered in general practices in the Research and Surveillance Centre network and have a record of CLD between January 1, 2012, and December 31, 2022, including those with alcohol-related liver disease, chronic hepatitis B, chronic hepatitis C, nonalcohol fatty liver disease, Wilson disease, hemochromatosis, and autoimmune hepatitis. We will carefully curate variables using the Systematized Nomenclature of Medicine Clinical Terms. We will report the sociodemographic characteristics of those who are vaccinated. These include age, gender, ethnicity, population density, region, socioeconomic status (measured using the index of multiple deprivation), obesity, alcohol consumption, and smoking. Hepatitis A vaccination coverage for 1 and 2 doses will be calculated using an estimate of the CLD population as the denominator. We will analyze the baseline characteristics using descriptive statistics, including measures of dispersion. Pairwise comparisons of case-mix characteristics, comorbidities, and complications will be reported according to vaccination status. A multistate survival model will be fitted to estimate the transition probabilities among four states: (1) diagnosed with CLD, (2) first dose of hepatitis A vaccination, (3) second dose of hepatitis A vaccination, and (4) death. This will identify any potential disparities in how people with CLD get vaccinated. The Research and Surveillance Centre population comprises over 8 million people. The reported incidence of CLD is 20.7 cases per 100,000. International estimates of hepatitis A vaccine coverage vary between 10% and 50% in this group. This study will describe the uptake of the hepatitis A vaccine in people with CLD and report any disparities or differences in the characteristics of the vaccinated population. PRR1-10.2196/51861.

Improving Causal Bayesian Networks Using Expertise in Authoritative Medical Ontologies

Discovering causal relationships among symptoms is a topical issue in the analysis of observational patient datasets. A Causal Bayesian Network (CBN) is a popular analytical framework for causal inference. While there are many methods and algorithms capable of learning a Bayesian network, they are reliant on the complexity and thoroughness of the algorithm and do not consider prior expertise from authoritative sources. This article proposes a novel method of extracting prior causal knowledge contained in Authoritative Medical Ontologies (AMOs) and using this prior knowledge to orient arcs in a CBN learned from observational patient data. Since AMOs are robust biomedical ontologies containing the collective knowledge of the experts who created them, utilizing the ordering information contained within them produces improved CBNs that provide additional insight into the disease domain. To demonstrate our method, we obtained prior causal ordering information among symptoms from three AMOs: (1) the Medical Dictionary for Regulatory Activities Terminology (MedDRA), (2) the International Classification of Diseases Version 10 Clinical Modification (ICD-10-CM), and (3) Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). The prior ontological knowledge from these three AMOs is then used to orient arcs in a series of CBNs learned from the National Institutes of Mental Health study on Sequenced Treatment Alternatives to Relieve Depression (STAR*D) patient dataset using the Max-Min Hill-Climbing (MMHC) algorithm. Six distinct CBNs are generated using MMHC: an unmodified baseline model using only the algorithm, three CBNs oriented with ordered-variable pairs from MedDRA, ICD-10-CM, and SNOMED CT, and two more with ordered pairs from a combination of these AMOs. The resulting CBNs modified using ordered-variable pairs significantly change the structure of the network. The agreement between the Modified networks and the Baseline ranges from 50% to 90%. A modified network using ordering information from all ontologies obtained an agreement of 50% (10 out of 20 arcs exist in both the Baseline and Modified models) while maintaining comparable predictive accuracy. This indicates that the Modified CBN reflects the causal claims in the AMOs and agrees with both the AMOs and the observational STAR*D dataset. Furthermore, the Modified models discovered new potentially causal relationships among symptoms in the model, while eliminating weaker edges in a qualitative analysis of the significance of these relationships in existing epidemiological research.

Creating a SNOMED CT reference set for common endocrine disorders based on routine clinic correspondence.

Routine clinical coding of clinical outcomes in outpatient consultations still lags behind the coding of episodes of inpatient care. Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) offers an opportunity for standardised coding of key clinical information. Identifying the most commonly required SNOMED terms and grouping these into a reference set will aid future adoption in routine clinical care. To create a common endocrinology reference set to standardise the coding for outcomes of outpatient endocrine consultations, using a semi-automated extraction of information from existing clinical correspondence. Retrospective review of data from an adult tertiary outpatient endocrine clinic between 2018 and 2019. A total of 1870 patients from postcodes within two regional areas of NHS Grampian (Aberdeen City and Aberdeenshire) attended the clinic. Following consultation, an automated script extracted each problem statement which was manually coded using the 'disorder' concepts from SNOMED CT (UK edition). The review identified 298 relevant endocrine diagnoses, 99 findings and 142 procedures. There were a total of 88 (29.5%) commonly seen endocrine conditions (e.g., Graves' disease, anterior hypopituitarism and Addison's disease) and 210 (70.5%) less commonly seen endocrine conditions. Subsequently, consultant endocrinologists completed a survey regarding the common endocrine conditions; 28 conditions have 100% agreement, 25 have 90%-99% agreement, 31 have 50%-89% agreement and 4 have less than 59% agreement (which were excluded). Automated text parsing of structured endocrine correspondence allowed the creation of a SNOMED CT reference set for common endocrine disorders. This will facilitate funding and planning of service provision in endocrinology by allowing more accurate characterisation of the patient cohorts needing specialist endocrine care.

Representation of Environmental Concepts Associated with Health Impacts in Computer Standardized Clinical Terminologies.

To evaluate the representation of environmental concepts associated with health impacts in standardized clinical terminologies. This study used a descriptive approach with methods informed by a procedural framework for standardized clinical terminology mapping. The United Nations Global Indicator Framework for the Sustainable Development Goals and Targets was used as the source document for concept extraction. The target terminologies were the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and the International Classification for Nursing Practice (ICNP). Manual and automated mapping methods were utilized. The lists of candidate matches were reviewed and iterated until a final mapping match list was achieved. A total of 119 concepts with 133 mapping matches were added to the final SNOMED CT list. Fifty-three (39.8%) were direct matches, 37 (27.8%) were narrower than matches, 35 (26.3%) were broader than matches, and 8 (6%) had no matches. A total of 26 concepts with 27 matches were added to the final ICNP list. Eight (29.6%) were direct matches, 4 (14.8%) were narrower than, 7 (25.9%) were broader than, and 8 (29.6%) were no matches. Following this evaluation, both strengths and gaps were identified. Gaps in terminology representation included concepts related to cost expenditures, affordability, community engagement, water, air and sanitation. The inclusion of these concepts is necessary to advance the clinical reporting of these environmental and sustainability indicators. As environmental concepts encoded in standardized terminologies expand, additional insights into data and health conditions, research, education, and policy-level decision-making will be identified.

Digital Health Information Systems in the Member States of the Commonwealth of Independent States: Status and Prospects

This paper examines the status of the development of national digital health information systems (HIS) in Commonwealth of Independent States (CIS) member states. Data for research were collected using a questionnaire adapted from the questionnaire of the WHO’s Third Global Survey on eHealth. The results showed that the digital transformation of HIS was occurring in all seven CIS member states (participating in the study), which were financed by different resources. Laws and regulations on electronic medical records (EMR) use were present in almost all participating CIS member states. Various international standards and classifications were used to support development and the interoperability of digital health information system (d-HIS), including International Classification of Diseases (ICD), Digital Imaging and Communications in Medicine (DICOM), ISO 18308, Logical Observation Identifiers, Names, and Codes (LOINC), Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT), and ISO TC 215. Several CIS member states had adopted a national information security strategy for the safe processing of both personal data and medical confidential information. The digital transformation of healthcare and the Empowerment through Digital Health initiative are taking place in all CIS member states, which are at different stages of introducing electronic medical and health records.

Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers-Assisted Sublanguage Analysis.

A patient's family history (FH) information significantly influences downstream clinical care. Despite this importance, there is no standardized method to capture FH information in electronic health records and a substantial portion of FH information is frequently embedded in clinical notes. This renders FH information difficult to use in downstream data analytics or clinical decision support applications. To address this issue, a natural language processing system capable of extracting and normalizing FH information can be used. In this study, we aimed to construct an FH lexical resource for information extraction and normalization. We exploited a transformer-based method to construct an FH lexical resource leveraging a corpus consisting of clinical notes generated as part of primary care. The usability of the lexicon was demonstrated through the development of a rule-based FH system that extracts FH entities and relations as specified in previous FH challenges. We also experimented with a deep learning-based FH system for FH information extraction. Previous FH challenge data sets were used for evaluation. The resulting lexicon contains 33,603 lexicon entries normalized to 6408 concept unique identifiers of the Unified Medical Language System and 15,126 codes of the Systematized Nomenclature of Medicine Clinical Terms, with an average number of 5.4 variants per concept. The performance evaluation demonstrated that the rule-based FH system achieved reasonable performance. The combination of the rule-based FH system with a state-of-the-art deep learning-based FH system can improve the recall of FH information evaluated using the BioCreative/N2C2 FH challenge data set, with the F1 score varied but comparable. The resulting lexicon and rule-based FH system are freely available through the Open Health Natural Language Processing GitHub.

Concept Coverage Analysis of Ophthalmic Infections and Trauma among the Standardized Medical Terminologies SNOMED-CT, ICD-10-CM, and ICD-11

Widespread electronic health record adoption has generated a large volume of data and emphasized the need for standardized terminology to describe clinical concepts. Here, we undertook a systematic concept coverage analysis to determine the representation of clinical concepts in ophthalmic infection and ophthalmic trauma among standardized medical terminologies, including the Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT), the International Classification of Diseases (ICD) version 10 with clinical modifications (ICD-10-CM), and ICD version 11 (ICD-11). Extraction of concepts related to ophthalmic infection and ophthalmic trauma and structured search in terminology browsers. The American Academy of Ophthalmology Basic and Clinical Science Course (BCSC), SNOMED-CT, and ICD-10-CM terminologies from the Observational Health Data Sciences and Informatics Athena browser, and the ICD-11 terminology browser. Concepts pertaining to ophthalmic infection and ophthalmic trauma were extracted from the 2022 BCSC free text and index terms. We searched terminology browsers to identify corresponding codes and classified the extent of semantic alignment as equal, wide, narrow, or unmatched in each terminology. The overlap of equal concepts in each terminology was represented in a Venn diagram. Proportions of clinical concepts with corresponding codes at various levels of semantic alignment. A total of 443 concepts were identified: 304 concepts related to ophthalmic infection and 139 concepts related to ophthalmic trauma. The SNOMED-CT had the highest proportion of equal coverage, with 82.0% (249 of 304) among concepts related to ophthalmic infection and 82.0% (115 of 139) among concepts related to ophthalmic trauma. Across all concepts, 28% (124 of 443) were classified as equal in ICD-10-CM and 52.8% (234 of 443) were classified as equal in ICD-11. The SNOMED-CT had significantly better semantic alignment than ICD-10-CM and ICD-11 for ophthalmic infections and ophthalmic trauma. This demonstrates opportunity for continuing advancement of representation of ophthalmic concepts in standardized medical terminologies.

Standardized Database of 12-Lead Electrocardiograms with a Common Standard for the Promotion of Cardiovascular Research: KURIAS-ECG.

Electrocardiography (ECG)-based diagnosis by experts cannot maintain uniform quality because individual differences may occur. Previous public databases can be used for clinical studies, but there is no common standard that would allow databases to be combined. For this reason, it is difficult to conduct research that derives results by combining databases. Recent commercial ECG machines offer diagnoses similar to those of a physician. Therefore, the purpose of this study was to construct a standardized ECG database using computerized diagnoses. The constructed database was standardized using Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Observational Medical Outcomes Partnership-common data model (OMOP-CDM), and data were then categorized into 10 groups based on the Minnesota classification. In addition, to extract high-quality waveforms, poor-quality ECGs were removed, and database bias was minimized by extracting at least 2,000 cases for each group. To check database quality, the difference in baseline displacement according to whether poor ECGs were removed was analyzed, and the usefulness of the database was verified with seven classification models using waveforms. The standardized KURIAS-ECG database consists of high-quality ECGs from 13,862 patients, with about 20,000 data points, making it possible to obtain more than 2,000 for each Minnesota classification. An artificial intelligence classification model using the data extracted through SNOMED-CT showed an average accuracy of 88.03%. The KURIAS-ECG database contains standardized ECG data extracted from various machines. The proposed protocol should promote cardiovascular disease research using big data and artificial intelligence.

Surgical procedure prediction using medical ontological information

Background and Objective: Predicting the duration of surgical procedures is an important step in scheduling operating rooms. Many factors have been shown to influence the duration of a procedure, in this research we aim to use medical ontological information to improve the predictions.Methods: This paper presents two methods for incorporating the medical information about a surgical procedure into the prediction of the duration of the procedure. The first method uses the Systematised Nomenclature of Medicine Clinical Terms to relate different procedures to each other. The second uses simple text fragments. The relationships between types of procedures are included in a regression model for the procedure duration. These methods are applied to data from New Zealand healthcare facilities and the accuracy of the estimations of the durations is compared. In addition a simulation of scheduling the procedures in an operating room is performed.Results: It is shown that both of the methods provide an improvement in the prediction of procedure durations. When compared to a traditional categorical encoding, the ontological information provides an improvement in the continuous ranked probability scores of the prediction of procedure durations from 18.4 min to 17.1 min, and from 25.3 to 21.3 min for types of procedures that are not performed very often.Conclusions: Different methods for encoding medical ontological information in surgery procedure duration predictions are presented, and show an improvement over traditional models. The improvement in duration prediction is shown to improve the efficiency of scheduling in a simple simulation.

Extracting Medical Information From Free-Text and Unstructured Patient-Generated Health Data Using Natural Language Processing Methods: Feasibility Study With Real-world Data.

Patient-generated health data (PGHD) captured via smart devices or digital health technologies can reflect an individual health journey. PGHD enables tracking and monitoring of personal health conditions, symptoms, and medications out of the clinic, which is crucial for self-care and shared clinical decisions. In addition to self-reported measures and structured PGHD (eg, self-screening, sensor-based biometric data), free-text and unstructured PGHD (eg, patient care note, medical diary) can provide a broader view of a patient's journey and health condition. Natural language processing (NLP) is used to process and analyze unstructured data to create meaningful summaries and insights, showing promise to improve the utilization of PGHD. Our aim is to understand and demonstrate the feasibility of an NLP pipeline to extract medication and symptom information from real-world patient and caregiver data. We report a secondary data analysis, using a data set collected from 24 parents of children with special health care needs (CSHCN) who were recruited via a nonrandom sampling approach. Participants used a voice-interactive app for 2 weeks, generating free-text patient notes (audio transcription or text entry). We built an NLP pipeline using a zero-shot approach (adaptive to low-resource settings). We used named entity recognition (NER) and medical ontologies (RXNorm and SNOMED CT [Systematized Nomenclature of Medicine Clinical Terms]) to identify medication and symptoms. Sentence-level dependency parse trees and part-of-speech tags were used to extract additional entity information using the syntactic properties of a note. We assessed the data; evaluated the pipeline with the patient notes; and reported the precision, recall, and F1 scores. In total, 87 patient notes are included (audio transcriptions n=78 and text entries n=9) from 24 parents who have at least one CSHCN. The participants were between the ages of 26 and 59 years. The majority were White (n=22, 92%), had more than one child (n=16, 67%), lived in Ohio (n=22, 92%), had mid- or upper-mid household income (n=15, 62.5%), and had higher level education (n=24, 58%). Out of 87 notes, 30 were drug and medication related, and 46 were symptom related. We captured medication instances (medication, unit, quantity, and date) and symptoms satisfactorily (precision >0.65, recall >0.77, F1>0.72). These results indicate the potential when using NER and dependency parsing through an NLP pipeline on information extraction from unstructured PGHD. The proposed NLP pipeline was found to be feasible for use with real-world unstructured PGHD to accomplish medication and symptom extraction. Unstructured PGHD can be leveraged to inform clinical decision-making, remote monitoring, and self-care including medical adherence and chronic disease management. With customizable information extraction methods using NER and medical ontologies, NLP models can feasibly extract a broad range of clinical information from unstructured PGHD in low-resource settings (eg, a limited number of patient notes or training data).

Mapping of UK Biobank clinical codes: Challenges and possible solutions.

The UK Biobank provides a rich collection of longitudinal clinical data coming from different healthcare providers and sources in England, Wales, and Scotland. Although extremely valuable and available to a wide research community, the heterogeneous dataset contains inconsistent medical terminology that is either aligned to several ontologies within the same category or unprocessed. To make these data useful to a research community, data cleaning, curation, and standardization are needed. Significant efforts to perform data reformatting, mapping to any selected ontologies (such as SNOMED-CT) and harmonization are required from any data user to integrate UK Biobank hospital inpatient and self-reported data, data from various registers with primary care (GP) data. The integrated clinical data would provide a more comprehensive picture of one's medical history. We evaluated several approaches to map GP clinical Read codes to International Classification of Diseases (ICD) and Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) terminologies. The results were compared, mapping inconsistencies were flagged, a quality category was assigned to each mapping to evaluate overall mapping quality. We propose a curation and data integration pipeline for harmonizing diagnosis. We also report challenges identified in mapping Read codes from UK Biobank GP tables to ICD and SNOMED CT. Some of the challenges-the lack of precise one-to-one mapping between ontologies or the need for additional ontology to fully map terms-are general reflecting trade-offs to be made at different steps. Other challenges are due to automatic mapping and can be overcome by leveraging existing mappings, supplemented with automated and manual curation.

Characterization of patients with idiopathic normal pressure hydrocephalus using natural language processing within an electronic healthcare record system.

Idiopathic normal pressure hydrocephalus (iNPH) is an underdiagnosed, progressive, and disabling condition. Early treatment is associated with better outcomes and improved quality of life. In this paper, the authors aimed to identify features associated with patients with iNPH using natural language processing (NLP) to characterize this cohort, with the intention to later target the development of artificial intelligence-driven tools for early detection. The electronic health records of patients with shunt-responsive iNPH were retrospectively reviewed using an NLP algorithm. Participants were selected from a prospectively maintained single-center database of patients undergoing CSF diversion for probable iNPH (March 2008-July 2020). Analysis was conducted on preoperative health records including clinic letters, referrals, and radiology reports accessed through CogStack. Clinical features were extracted from these records as SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) concepts using a named entity recognition machine learning model. In the first phase, a base model was generated using unsupervised training on 1 million electronic health records and supervised training with 500 double-annotated documents. The model was fine-tuned to improve accuracy using 300 records from patients with iNPH double annotated by two blinded assessors. Thematic analysis of the concepts identified by the machine learning algorithm was performed, and the frequency and timing of terms were analyzed to describe this patient group. In total, 293 eligible patients responsive to CSF diversion were identified. The median age at CSF diversion was 75 years, with a male predominance (69% male). The algorithm performed with a high degree of precision and recall (F1 score 0.92). Thematic analysis revealed the most frequently documented symptoms related to mobility, cognitive impairment, and falls or balance. The most frequent comorbidities were related to cardiovascular and hematological problems. This model demonstrates accurate, automated recognition of iNPH features from medical records. Opportunities for translation include detecting patients with undiagnosed iNPH from primary care records, with the aim to ultimately improve outcomes for these patients through artificial intelligence-driven early detection of iNPH and prompt treatment.

S1558 Risk of Clostridioides difficile Infection in Patients With Celiac Disease: Insight From a U.S.-Based Population Study

Introduction: Little is known about the association between Clostridioides difficile infection (CDI) and celiac disease. The aim of the study is to describe the risk of CDI in patients with celiac disease and to describe the clinical outcomes in patients with celiac and CDI. Methods: We queried a commercial database (Explorys IncTM, Cleveland, OH, United States), and obtained an aggregate of electronic health record data from 26 major integrated United States healthcare systems comprising 360 hospitals in the United States from 2017 to 2022. Diagnoses were organized into the Systematized Nomenclature of Medicine Clinical Terms (SNOMED–CT) hierarchy. We compared the incidence of new CDI among patients with celiac disease versus those without celiac disease (controls). Univariate and multivariate analyses were performed on the data, and associations were reported as adjusted odds ratios (aOR) with 95% confidence intervals (CI). Results: We identified 90,060 patients with celiac disease and 25,807,720 controls. The incidence of new CDI was 1.31% (1,180) in celiac disease patients, and 0.35% (92,330) in controls, yielding an odds ratio (OR) of 3.69 (95% CI 3.49-3.91; P< 0.0001). Treatment and clinical outcomes were not significantly different. After controlling for common CDI risk factors, the multivariate analysis model uncovered that celiac patients were more likely to develop CDI OR: 1.34 (95% CI: 1.2-1.4, P < 0.0001) compared to controls (Table). Conclusion: In a large US population-based study, patients with celiac disease had a significantly higher incidence of CDI than controls. Clinical outcomes were similar between the groups. Clinicians should be vigilant and consider CDI in celiac patients with new or recurrent diarrhea. Table 1. - Demographics Celiac Patients (n=90,060) Control Patients (n=25,807,720) Age 18-65 years (%) 65,220 (72.4%) 18,331,970 (71%) Age >65 years (%) 24,840 (27.6%) 7,475,750 (29%) Female (%) 66,800 (74.2%) 13,219,060 (51.2%) Race: White (%) 73540 (81.7%) 14,072,590 (54.5%) Smoker (%) 15,120 (16.8%) 2,327,950 (9%) Alcohol abuse (%) 2,530 (2.8%) 552,010 (2.1%) Hypertension (%) 42,250 (46.9%) 8,063,140 (31.2%) Diabetes (%) 25,560 (28.4%) 3,446,990 (13.4%) Obesity (%) 26,170 (29.1%) 3,535,170 (13.7%) Clostridioides difficile infection management and clinical outcomes Developed Clostridioides difficile infection* 1,180 (1.31%) 92,330 (0.35%) Treated with metronidazole 820 (69%) 56,490 (61.1%) Treated with vancomycin 770 (65.2%) 55,270 (59%) Treated with fidaxomicin 70 (5.9%) 4,370 (4.7%) Colectomy** 10 (0.84%) 970 (1.05%) Multivariable model with Clostridioides difficile infection being the outcome Risk Factors Odds Ratio 95% CI; P-value Age ≥65 yr vs < 65yr 2.988 2.962-3.014; < 0.0001 Gender (female vs male) 1.194 1.184-1.204; < 0.0001 Race (White vs rest) 1.483 1.467-1.498; < 0.0001 Antibiotics 3.657 3.6-3.7; < 0.0001 Acid suppressive therapy*** 4.268 4.224-4.313; < 0.0001 Inflammatory bowel disease 6.031 5.93-6.13; < 0.0001 Celiac disease 1.342 1.284-1.403; < 0.0001 *1st occurrence of CDI after celiac diagnosis.**Colectomy performed within 60 days of CDI diagnosis (excluded patients with a history of IBD, ischemic colitis, and neoplasia of the colon).***Acid suppressive therapy includes prior use of proton pump inhibitors or H2 blockers