Performance evaluation of three versions of a convolutional neural network for object detection and segmentation using a multiclass and reduced panoramic radiograph dataset.

OBJECTIVES: To evaluate the diagnostic performance of three versions of a deep-learning convolutional neural network in terms of object detection and segmentation using a multiclass panoramic radiograph dataset. METHODS: A total of 600 orthopantomographies were randomly selected for this study and manually annotated by a single operator using an image annotation tool (COCO Annotator v.11.0.1) to establish ground truth. The annotation classes included teeth, maxilla, mandible, inferior alveolar nerve, dento- and implant-supported crowns/pontics, endodontic treatment, resin-based restorations, metallic restorations, and implants. The dataset was then divided into training, validation, and testing subsets, which were used to train versions 5, 7, and 8 of You Only Look Once (YOLO) Neural Network. Results were stored, and a posterior performance analysis was carried out by calculating the precision (P), recall (R), F1 Score, Intersection over Union (IoU), and mean average precision (mAP) at 0.5 and 0.5-0.95 thresholds. The confusion matrix and recall precision graphs were also sketched. RESULTS: YOLOv5s showed an improvement in object detection results with an average R = 0.634, P = 0.781, mAP0.5 = 0.631, and mAP0.5-0.95 = 0.392. YOLOv7m achieved the best object detection results with average R = 0.793, P = 0.779, mAP0.5 = 0.740, and mAP0.5-0.95 = 0,481. For object segmentation, YOLOv8m obtained the best average results (R = 0.589, P = 0.755, mAP0.5 = 0.591, and mAP0.5-0.95 = 0.272). CONCLUSIONS: YOLOv7m was better suited for object detection, while YOLOv8m demonstrated superior performance in object segmentation. The most frequent error in object detection was related to background classification. Conversely, in object segmentation, there is a tendency to misclassify True Positives across different dental treatment categories. CLINICAL SIGNIFICANCE: General diagnostic and treatment decisions based on panoramic radiographs can be enhanced using new artificial intelligence-based tools. Nevertheless, the reliability of these neural networks should be subjected to training and validation to ensure their generalizability.

ICD-10-CM extension with ICD-9 diagnosis codes to support integrated access to clinical legacy data.

INTRODUCTION: ICD is currently the most widely used terminology to code diagnosis and procedures. The transition from ICD-9-CM to ICD-10-CM became effective on October 1, 2015 in US and many other countries. Projects that use this codification for research purposes, requires advanced methods to exploit data with both versions of ICD. Although the General Equivalence Mappings (GEMs), provided by the Centers for Medicare and Medicaid Services, might help to overcome these challenges, their direct use as translation mappings is not possible, mostly due to the further specificity of ICD-10-CM concepts. OBJECTIVE: We propose a methodology to generate an extended version of ICD-10-CM with selected ICD-9-CM diagnosis codes. METHODS: The extension was generated using the GEMs relations between concepts of both terminologies and the hierarchical relations of ICD-10-CM. RESULTS: This extended ICD-10-CM, together with modifications to the mapping of ICD-9-CM concepts that were not inserted, allows the generation of an improved translation of legacy data, raising the number of 1-to-1 correspondences by +13.81%. CONCLUSION: The extended ICD-10-CM enables the accurate integration of ICD-9-CM and ICD-10-CM diagnosis data into a single terminology. With such analysis of data possible without having to specify both ICD-9-CM and ICD-10-CM separately for each query.

ICD-10-PCS extension with ICD-9 procedure codes to support integrated access to clinical legacy data.

Since the creation of The International Classification of Diseases (ICD), new versions have been released to keep updated with the current medical knowledge. Migrations of Electronic Health Records (EHR) from ICD-9 to ICD-10-PCS as clinical procedure codification system, has been a significant challenge and involved large resources. In addition, it created new barriers for integrated access to legacy medical procedure data (frequently ICD-9 coded) with current data (frequently ICD-10-PCS coded). This work proposes a solution based on extending ICD-10-PCS with a subgroup of ICD-9-CM concepts to facilitate such integrated access. The General Equivalence Mappings (GEMs) has been used as foundation to set the terminology relations of these inserted concepts in ICD-10-PCS hierarchy, but due to the existence of 1-to-many mappings, advanced rules are required to seamlessly integrate both terminologies. With the generation of rules based on GEMs relationships, 2014 ICD-9 concepts were included within the ICD-10-PCS hierarchy. For the rest of the concepts, a new method is also proposed to increase 1-to-1 mappings. As results, with the suggested approach, the percentage of ICD-9-CM procedure concepts that can be mapped accurately (avoiding mappings to a large number of concepts) rise from 11.56% to 69.01% of ICD-9-Proc, through the extended ICD-10-PCS hierarchy.

SNOMED2HL7: A tool to normalize and bind SNOMED CT concepts to the HL7 Reference Information Model.

BACKGROUND: Current clinical research and practice requires interoperability among systems in a complex and highly dynamic domain. There has been a significant effort in recent years to develop integrative common data models and domain terminologies. Such efforts have not completely solved the challenges associated with clinical data that are distributed among different and heterogeneous institutions with different systems to encode the information. Currently, when providing homogeneous interfaces to exploit clinical data, certain transformations still involve manual and time-consuming processes that could be automated. OBJECTIVES: There is a lack of tools to support data experts adopting clinical standards. This absence is especially significant when links between data model and vocabulary are required. The objective of this work is to present SNOMED2HL7, a novel tool to automatically link biomedical concepts from widely used terminologies, and the corresponding clinical context, to the HL7 Reference Information Model (RIM). METHODS: Based on the recommendations of the International Health Terminology Standards Development Organisation (IHTSDO), the SNOMED Normal Form has been implemented within SNOMED2HL7 to decompose and provide a method to reduce the number of options to store the same information. The binding of clinical terminologies to HL7 RIM components is the core of SNOMED2HL7, where terminology concepts have been annotated with the corresponding options within the interoperability standard. A web-based tool has been developed to automatically provide information from the normalization mechanisms and the terminology binding. RESULTS: SNOMED2HL7 binding coverage includes the majority of the concepts used to annotate legacy systems. It follows HL7 recommendations to solve binding overlaps and provides the binding of the normalized version of the concepts. The first version of the tool, available at http://kandel.dia.fi.upm.es:8078, has been validated in EU funded projects to integrate real world data for clinical research with an 88.47% of accuracy. CONCLUSIONS: This paper presents the first initiative to automatically retrieve concept-centered information required to transform legacy data into widely adopted interoperability standards. Although additional functionality will extend capabilities to automate data transformations, SNOMED2HL7 already provides the functionality required for the clinical interoperability community.

An agent- and ontology-based system for integrating public gene, protein, and disease databases.

In this paper, we describe OntoFusion, a database integration system. This system has been designed to provide unified access to multiple, heterogeneous biological and medical data sources that are publicly available over Internet. Many of these databases do not offer a direct connection, and inquiries must be made via Web forms, returning results as HTML pages. A special module in the OntoFusion system is needed to integrate these public 'Web-based' databases. Domain ontologies are used to do this and provide database mapping and unification. We have used the system to integrate seven significant and widely used public biomedical databases: OMIM, PubMed, Enzyme, Prosite and Prosite documentation, PDB, SNP, and InterPro. A case study is detailed in depth, showing system performance. We analyze the system's architecture and methods and discuss its use as a tool for biomedical researchers.

Designing new methodologies for integrating biomedical information in clinical trials.

OBJECTIVES: To propose a modification to current methodologies for clinical trials, improving data collection and cost-efficiency. To describe a system to integrate distributed and heterogeneous medical and genetic databases for improving information access, retrieval and analysis of biomedical information. METHODS: Data for clinical trials can be collected from remote, distributed and heterogeneous data sources. In this distributed scenario, we propose an ontologybased approach, with two basic operations: mapping and unification. Mapping outputs the semantic model of a virtual repository with the information model of a specific database. Unification provides a single schema for two or more previously available virtual repositories. In both processes, domain ontologies can improve other traditional approaches. RESULTS: Private clinical databases and public genomic and disease databases (e.g., OMIM, Prosite and others) were integrated. We successfully tested the system using thirteen databases containing clinical and biological information and biomedical vocabularies. CONCLUSIONS: We present a domain-independent approach to biomedical database integration, used in this paper as a reference for the design of future models of clinico-genomic trials where information will be integrated, retrieved and analyzed. Such an approach to biomedical data integration has been one of the goals of the IST INFOBIOMED Network of Excellence in Biomedical Informatics, funded by the European Commission, and the new ACGT (Advanced Clinico-Genomic Trials on Cancer) project, where the authors will apply these methods to research experiments.

ONTOFUSION: ontology-based integration of genomic and clinical databases.

ONTOFUSION is an ontology-based system designed for biomedical database integration. It is based on two processes: mapping and unification. Mapping is a semi-automated process that uses ontologies to link a database schema with a conceptual framework-named virtual schema. There are three methodologies for creating virtual schemas, according to the origin of the domain ontology used: (1) top-down--e.g. using an existing ontology, such as the UMLS or Gene Ontology--, (2) bottom-up--building a new domain ontology-- and (3) a hybrid combination. Unification is an automated process for integrating ontologies and hence the database to which they are linked. Using these methods, we employed ONTOFUSION to integrate a large number of public genomic and clinical databases, as well as biomedical ontologies.