Xavier Pastor Duran

The advancement of clinical natural language processing systems is crucial to exploit the wealth of textual data contained in medical records. Diverse data sources are required in different languages and from different sites to represent global health services. To this end, we have released CARMEN-I, a corpus of anonymized clinical records from the Hospital Clinic of Barcelona written during the COVID-19 pandemic spanning a period of two years. In addition to COVID-19 cases of adult patients, CARMEN-I features multiple comorbidities such as cardiovascular conditions, oncology treatments, post-transplant complications, and infectious diseases. This resource is publicly accessible together with detailed annotation guidelines and granular text-bound annotations generated in a collaborative effort between clinicians, linguists, and engineers to enable training and evaluation of automatic anonymization systems. Moreover, for information extraction purposes, a subset of 500 records is annotated with six relevant clinical concept classes: diseases, symptoms, procedures, medications, pathogens and humans.

This study aims to describe implementing a SNOMED CT-coded health problem (HP) list at Hospital Clínic de Barcelona. The project focuses on enhancing the accuracy and efficiency of clinical coding by automating the process from patient admission, while simultaneously enabling the reuse of coded data for research and management purposes. SNOMED CT was selected as the reference terminology for recording HPs. A subset of terms (our Health Problems Catalogue -HPC-) was created to meet local needs. An NLP tool was integrated into the clinical workstation to assist in primary coding HPs from natural language inputs. The system architecture included four servers (Coder, Reviewer, Manager, and Terminology Server) supporting real-time coding and review processes. Clinical and operational data from April to October 2024 were analyzed to evaluate the system’s performance. Between April 9 and October 4, 2024, a total of 118,534 HPs were recorded. Of these, 74.2% were coded in real-time using the NLP tool, 23.3% were coded by documentation specialists, and 2.5% remained uncoded. The system significantly reduced coding delays and enriched the institutional data warehouse, facilitating real-time research and management activities. Implementing a SNOMED CT-coded HP list supported by NLP and terminology services improved coding accuracy and clinician efficiency. This system enhances clinical understanding, enables evidence-based recommendations, and supports data-driven decision-making in healthcare management and research. Clinical Trial Number Not applicable

BACKGROUND The Urban Health combine quantitative data with community knowledge to evaluate and prioritize urban health inequities. OBJECTIVE To describe the characteristics of tuberculosis in the city of Barcelona. To explore the relationships between the incidence levels of tuberculosis and socioeconomic factor. To apply the linear regression model to analyze and predict the tuberculosis rate by districts and neighborhoods in Barcelona. METHODS The description and analysis of relationships between the socioeconomic factors and the tuberculosis rate is carried out through an ecological approach RESULTS The relationship between Disposable Family Income (DFI) and Habitability Index (HI) with the tuberculosis rate (TR) in the neighborhoods and districts shows values of 0.66 [(95% CI 0.50 ÷ 0.77); p = 2.818e-10] and 0.89 [(95% CI 0.60 ÷ 0.97); p = 0.0004845] respectively for HI indicator and -0.41 [(95% CI -0.59 ÷ -0.20); p = 0.0002812] and -0.70 [(95% CI -0.92 ÷ -0.11); p = 0.02554] respectively for DFI indicator. The linear regression model of the TR as a function of the HI predicts 43.12% (p = 2.818e-10) and 79.93% (p = 0.0004845) of the cases in the neighborhoods and districts. CONCLUSIONS There is a strong association to predict the TR based on the HI.

Background: Inappropriate medication in older patients with multimorbidity results in a greater risk of adverse drug events. Clinical decision support systems (CDSSs) are intended to improve medication appropriateness. One approach to improving CDSSs is to use ontologies instead of relational databases. Previously, we developed OntoPharma—an ontology-based CDSS for reducing medication prescribing errors. Objective: The primary aim was to model a domain for improving medication appropriateness in older patients (chronic patient domain). The secondary aim was to implement the version of OntoPharma containing the chronic patient domain in a hospital setting. Methods: A 4-step process was proposed. The first step was defining the domain scope. The chronic patient domain focused on improving medication appropriateness in older patients. A group of experts selected the following three use cases: medication regimen complexity, anticholinergic and sedative drug burden, and the presence of triggers for identifying possible adverse events. The second step was domain model representation. The implementation was conducted by medical informatics specialists and clinical pharmacists using Protégé-OWL (Stanford Center for Biomedical Informatics Research). The third step was OntoPharma-driven alert module adaptation. We reused the existing framework based on SPARQL to query ontologies. The fourth step was implementing the version of OntoPharma containing the chronic patient domain in a hospital setting. Alerts generated from July to September 2022 were analyzed. Results: We proposed 6 new classes and 5 new properties, introducing the necessary changes in the ontologies previously created. An alert is shown if the Medication Regimen Complexity Index is ≥40, if the Drug Burden Index is ≥1, or if there is a trigger based on an abnormal laboratory value. A total of 364 alerts were generated for 107 patients; 154 (42.3%) alerts were accepted. Conclusions: We proposed an ontology-based approach to provide support for improving medication appropriateness in older patients with multimorbidity in a scalable, sustainable, and reusable way. The chronic patient domain was built based on our previous research, reusing the existing framework. OntoPharma has been implemented in clinical practice and generates alerts, considering the following use cases: medication regimen complexity, anticholinergic and sedative drug burden, and the presence of triggers for identifying possible adverse events.

Background: To discover new knowledge from data, they must be correct and in a consistent format. OntoCR, a clinical repository developed at Hospital Clínic de Barcelona, uses ontologies to represent clinical knowledge and map locally defined variables to health information standards and common data models. Objective: The aim of the study is to design and implement a scalable methodology based on the dual-model paradigm and the use of ontologies to consolidate clinical data from different organizations in a standardized repository for research purposes without loss of meaning. Methods: First, the relevant clinical variables are defined, and the corresponding European Norm/International Organization for Standardization (EN/ISO) 13606 archetypes are created. Data sources are then identified, and an extract, transform, and load process is carried out. Once the final data set is obtained, the data are transformed to create EN/ISO 13606–normalized electronic health record (EHR) extracts. Afterward, ontologies that represent archetyped concepts and map them to EN/ISO 13606 and Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) standards are created and uploaded to OntoCR. Data stored in the extracts are inserted into its corresponding place in the ontology, thus obtaining instantiated patient data in the ontology-based repository. Finally, data can be extracted via SPARQL queries as OMOP CDM–compliant tables. Results: Using this methodology, EN/ISO 13606–standardized archetypes that allow for the reuse of clinical information were created, and the knowledge representation of our clinical repository by modeling and mapping ontologies was extended. Furthermore, EN/ISO 13606–compliant EHR extracts of patients (6803), episodes (13,938), diagnosis (190,878), administered medication (222,225), cumulative drug dose (222,225), prescribed medication (351,247), movements between units (47,817), clinical observations (6,736,745), laboratory observations (3,392,873), limitation of life-sustaining treatment (1,298), and procedures (19,861) were created. Since the creation of the application that inserts data from extracts into the ontologies is not yet finished, the queries were tested and the methodology was validated by importing data from a random subset of patients into the ontologies using a locally developed Protégé plugin (“OntoLoad”). In total, 10 OMOP CDM–compliant tables (“Condition_occurrence,” 864 records; “Death,” 110; “Device_exposure,” 56; “Drug_exposure,” 5609; “Measurement,” 2091; “Observation,” 195; “Observation_period,” 897; “Person,” 922; “Visit_detail,” 772; and “Visit_occurrence,” 971) were successfully created and populated. Conclusions: This study proposes a methodology for standardizing clinical data, thus allowing its reuse without any changes in the meaning of the modeled concepts. Although this paper focuses on health research, our methodology suggests that the data be initially standardized per EN/ISO 13606 to obtain EHR extracts with a high level of granularity that can be used for any purpose. Ontologies constitute a valuable approach for knowledge representation and standardization of health information in a standard-agnostic manner. With the proposed methodology, institutions can go from local raw data to standardized, semantically interoperable EN/ISO 13606 and OMOP repositories.

BACKGROUND Inappropriate medication in older patients with multimorbidity leads to a greater risk of adverse drug events. Clinical decision support systems (CDSS) are intended to improve medication appropriateness. One approach to improve CDSS is to use ontologies instead of relational databases. Previously, we developed OntoPharma, an ontology based CDSS to reduce medication prescribing errors. OBJECTIVE The primary aim was to model a domain to improve medication appropriateness in older patients (chronic patient domain). The secondary aim was to implement OntoPharma containing chronic patient domain in a hospital setting. METHODS A four-step process was proposed. 1) Defining the domain scope. Chronic patient domain focused on improving medication appropriateness in older patients. A group of experts selected three uses cases: medication regimen complexity; anticholinergic and/or sedative drug burden, and presence of triggers to identify possible adverse events. 2) Domain model representation. The implementation was conducted by Medical Informatics specialists and Clinical Pharmacists using Protégé-OWL. 3) OntoPharma-driven alert module adaptation. We reused the existing framework based on SPARQL to query ontologies. 4) Implementing OntoPharma containing the chronic patient domain in a hospital setting. Alerts generated between July to September 2022 were analysed. RESULTS We proposed six new classes and five new properties introducing the necessary changes in the ontologies previously created. An alert is shown if: Medication Regimen Complexity Index ≥40 and/or Drug Burden Index ≥1 and/or there is a trigger based on abnormal laboratory value. 364 alerts were generated in 107 patients. 154 (42.3%) alerts were accepted. CONCLUSIONS We propose an ontology-based approach to provide support for improving medication appropriateness in older patients with multimorbidity in a scalable, sustainable, and reusable way. The chronic-patient domain was built on our previous research reusing the existing framework. OntoPharma is implemented in clinical practice and generates alerts considering the following use cases: medication regimen complexity; anticholinergic and/or sedative drug burden and presence of triggers to identify possible adverse events. CLINICALTRIAL Not applicable