Back to the future: the novel art of digital auscultation applied in a prospective observational study of critically ill Covid-19 patients.

BACKGROUND: The Covid-19 pandemic has caused immense pressure on Intensive Care Units (ICU). In patients with severe ARDS due to Covid-19, respiratory mechanics are important for determining the severity of lung damage. Lung auscultation could not be used during the pandemic despite its merit. The main objective of this study was to investigate associations between lung auscultatory sound features and lung mechanical properties, length of stay (LOS) and survival, in adults with severe Covid-19 ARDS. METHODS: Consecutive patients admitted to a large ICU between 2020 and 2021 (n = 173) were included. Digital stethoscopes obtained auscultatory sounds and stored them in an on-line database for replay and further processing using advanced AI techniques. Correlation and regression analysis explored relationships between digital auscultation findings and lung mechanics or the ICU outcome. The resulting annotated lung sounds database is also publicly available as supplementary material. RESULTS: The presence of squawks was associated with the ICU LOS, outcome and 90-day mortality. Other features (age, SOFA score & oxygenation index upon admission, minimum crackle entropy) had significant impact on outcome. Additional features affecting the 90-d survival were age and mean crackle entropy. Multivariate logistic regression showed that survival was affected by age, baseline SOFA, baseline oxygenation index and minimum crackle entropy. CONCLUSIONS: Respiratory mechanics were associated with various adventitious sounds, whereas the lung sound analytics and the presence of certain adventitious sounds correlated with the ICU outcome and the 90-d survival. Spectral features of crackles sounds can serve as prognostic factors for survival, highlighting the importance of digital auscultation.

CoCross: An ICT Platform Enabling Monitoring Recording and Fusion of Clinical Information Chest Sounds and Imaging of COVID-19 ICU Patients.

Monitoring and treatment of severely ill COVID-19 patients in the ICU poses many challenges. The effort to understand the pathophysiology and progress of the disease requires high-quality annotated multi-parameter databases. We present CoCross, a platform that enables the monitoring and fusion of clinical information from in-ICU COVID-19 patients into an annotated database. CoCross consists of three components: (1) The CoCross4Pros native android application, a modular application, managing the interaction with portable medical devices, (2) the cloud-based data management services built-upon HL7 FHIR and ontologies, (3) the web-based application for intensivists, providing real-time review and analytics of the acquired measurements and auscultations. The platform has been successfully deployed since June 2020 in two ICUs in Greece resulting in a dynamic unified annotated database integrating clinical information with chest sounds and diagnostic imaging. Until today multisource data from 176 ICU patients were acquired and imported in the CoCross database, corresponding to a five-day average monitoring period including a dataset with 3477 distinct auscultations. The platform is well accepted and positively rated by the users regarding the overall experience.

A Methodology for an Auto-Generated and Auto-Maintained HL7 FHIR OWL Ontology for Health Data Management.

The process of maintenance of an underlying semantic model that supports data management and addresses the interoperability challenges in the domain of telemedicine and integrated care is not a trivial task when performed manually. We present a methodology that leverages the provided serializations of the Health Level Seven International (HL7) Fast Health Interoperability Resources (FHIR) specification to generate a fully functional OWL ontology along with the semantic provisions for maintaining functionality upon future changes of the standard. The developed software makes a complete conversion of the HL7 FHIR Resources along with their properties and their semantics and restrictions. It covers all FHIR data types (primitive and complex) along with all defined resource types. It can operate to build an ontology from scratch or to update an existing ontology, providing the semantics that are needed, to preserve information described using previous versions of the standard. All the results based on the latest version of HL7 FHIR as a Web Ontology Language (OWL-DL) ontology are publicly available for reuse and extension.

Supporting integrated care with a flexible data management framework built upon Linked Data, HL7 FHIR and ontologies.

In this paper we present the methodology and decisions behind an implementation of a telehealth data management framework, aiming to support integrated care services for chronic and multimorbid patients. The framework leverages an OWL ontology, built upon HL7 FHIR resources, to provide storage and representation of semantically enriched EHR data following Linked Data principles. This is presented along with the realization of the persistent storage solution and communication web services that allow the management of EHR data, ensuring the validity and integrity of the exchanged patient data as self-describing ontology instances. The framework concentrates on flexibility and reusability, which is addressed by regarding the aforementioned ontology as a single point of change. This solution has been implemented in the scope of the EU project WELCOME for managing data in a telemonitoring system for patients with COPD and co-morbidities and was also successfully deployed for the INLIFE EU project with minimal effort. The results of the two applications suggest it can be adopted and properly adapted in a series of integrated care scenarios with minimal effort.

A sustainable HL7 FHIR based ontology for PHR data.

One of the most widely acknowledged standards in health informatics is HL7 (Health Level 7 International). HL7 FHIR® (Fast Healthcare Interoperability Resources) is a new HL7 standard for exchanging electronic health data. It builds upon previous HL7 data format standards, but also leverages more modern technical concepts and approaches, aiming to be more developer-friendly. We present a developed ontology that, not only represents the domain entities of a personal health record (PHR) focusing on tele-health and integrated care, but also stores the actual data as instances of the defined ontology classes. Inspired and based on HL7 FHIR we defined a methodology for representing FHIR data types and FHIR resources in OWL and we have extended or restricted the resources to match specific domain needs. Additionally, since HL7 FHIR is a developing standard, we present a methodology for maintaining backward compatibility as the ontology is updated to match the latest definition of the standard. All the effort is represented as an OWL-DL ontology that is publicly available for reuse and extension.

A reusable ontology for primitive and complex HL7 FHIR data types.

HL7(®) FHIR(®) standard is a new standard aiming to offer more flexible interoperability mechanisms. We present a stand-alone RDF vocabulary as an OWL ontology that defines the primitive and complex data types of the FHIR framework, alongside their validation rules. We address the non-trivial questions of representing FHIR data types as RDF/OWL constructs in a coherent and complete manner. The proposed ontology can be used as a basic framework, where the complexity of a FHIR-based EHR is not required, while still maintaining semantic cohesion with an industry-based standard. It can also be the base for a complete representation of FHIR model as an ontology.

Evaluation of the performance of open-source RDBMS and triplestores for storing medical data over a web service.

An integral part of a system that manages medical data is the persistent storage engine. For almost twenty five years Relational Database Management Systems(RDBMS) were considered the obvious decision, yet today new technologies have emerged that require our attention as possible alternatives. Triplestores store information in terms of RDF triples without necessarily binding to a specific predefined structural model. In this paper we present an attempt to compare the performance of Apache JENA-Fuseki and the Virtuoso Universal Server 6 triplestores with that of MySQL 5.6 RDBMS for storing and retrieving medical information that it is communicated as RDF/XML ontology instances over a RESTful web service. The results show that the performance, calculated as average time of storing and retrieving instances, is significantly better using Virtuoso Server while MySQL performed better than Fuseki.