Artificial intelligence model for tumoral clinical decision support systems.

BACKGROUND AND OBJECTIVE: Comparative diagnostic in brain tumor evaluation makes possible to use the available information of a medical center to compare similar cases when a new patient is evaluated. By leveraging Artificial Intelligence models, the proposed system is able of retrieving the most similar cases of brain tumors for a given query. The primary objective is to enhance the diagnostic process by generating more accurate representations of medical images, with a particular focus on patient-specific normal features and pathologies. A key distinction from previous models lies in its ability to produce enriched image descriptors solely from binary information, eliminating the need for costly and difficult to obtain tumor segmentation. METHODS: The proposed model uses Artificial Intelligence to detect patient features to recommend the most similar cases from a database. The system not only suggests similar cases but also balances the representation of healthy and abnormal features in its design. This not only encourages the generalization of its use but also aids clinicians in their decision-making processes. This generalization makes possible for future research in different medical diagnosis areas with almost not any change in the system. RESULTS: We conducted a comparative analysis of our approach in relation to similar studies. The proposed architecture obtains a Dice coefficient of 0.474 in both tumoral and healthy regions of the patients, which outperforms previous literature. Our proposed model excels at extracting and combining anatomical and pathological features from brain Magnetic Resonances (MRs), achieving state-of-the-art results while relying on less expensive label information. This substantially reduces the overall cost of the training process. Our findings highlight the significant potential for improving the efficiency and accuracy of comparative diagnostics and the treatment of tumoral pathologies. CONCLUSIONS: This paper provides substantial grounds for further exploration of the broader applicability and optimization of the proposed architecture to enhance clinical decision-making. The novel approach presented in this work marks a significant advancement in the field of medical diagnosis, particularly in the context of Artificial Intelligence-assisted image retrieval, and promises to reduce costs and improve the quality of patient care using Artificial Intelligence as a support tool instead of a black box system.

Using Machine Learning to Collect and Facilitate Remote Access to Biomedical Databases: Development of the Biomedical Database Inventory.

BACKGROUND: Currently, existing biomedical literature repositories do not commonly provide users with specific means to locate and remotely access biomedical databases. OBJECTIVE: To address this issue, we developed the Biomedical Database Inventory (BiDI), a repository linking to biomedical databases automatically extracted from the scientific literature. BiDI provides an index of data resources and a path to access them seamlessly. METHODS: We designed an ensemble of deep learning methods to extract database mentions. To train the system, we annotated a set of 1242 articles that included mentions of database publications. Such a data set was used along with transfer learning techniques to train an ensemble of deep learning natural language processing models targeted at database publication detection. RESULTS: The system obtained an F1 score of 0.929 on database detection, showing high precision and recall values. When applying this model to the PubMed and PubMed Central databases, we identified over 10,000 unique databases. The ensemble model also extracted the weblinks to the reported databases and discarded irrelevant links. For the extraction of weblinks, the model achieved a cross-validated F1 score of 0.908. We show two use cases: one related to "omics" and the other related to the COVID-19 pandemic. CONCLUSIONS: BiDI enables access to biomedical resources over the internet and facilitates data-driven research and other scientific initiatives. The repository is openly available online and will be regularly updated with an automatic text processing pipeline. The approach can be reused to create repositories of different types (ie, biomedical and others).

A method and software framework for enriching private biomedical sources with data from public online repositories.

Modern biomedical research relies on the semantic integration of heterogeneous data sources to find data correlations. Researchers access multiple datasets of disparate origin, and identify elements-e.g. genes, compounds, pathways-that lead to interesting correlations. Normally, they must refer to additional public databases in order to enrich the information about the identified entities-e.g. scientific literature, published clinical trial results, etc. While semantic integration techniques have traditionally focused on providing homogeneous access to private datasets-thus helping automate the first part of the research, and there exist different solutions for browsing public data, there is still a need for tools that facilitate merging public repositories with private datasets. This paper presents a framework that automatically locates public data of interest to the researcher and semantically integrates it with existing private datasets. The framework has been designed as an extension of traditional data integration systems, and has been validated with an existing data integration platform from a European research project by integrating a private biological dataset with data from the National Center for Biotechnology Information (NCBI).

A machine learning approach to identify clinical trials involving nanodrugs and nanodevices from ClinicalTrials.gov.

BACKGROUND: Clinical Trials (CTs) are essential for bridging the gap between experimental research on new drugs and their clinical application. Just like CTs for traditional drugs and biologics have helped accelerate the translation of biomedical findings into medical practice, CTs for nanodrugs and nanodevices could advance novel nanomaterials as agents for diagnosis and therapy. Although there is publicly available information about nanomedicine-related CTs, the online archiving of this information is carried out without adhering to criteria that discriminate between studies involving nanomaterials or nanotechnology-based processes (nano), and CTs that do not involve nanotechnology (non-nano). Finding out whether nanodrugs and nanodevices were involved in a study from CT summaries alone is a challenging task. At the time of writing, CTs archived in the well-known online registry ClinicalTrials.gov are not easily told apart as to whether they are nano or non-nano CTs-even when performed by domain experts, due to the lack of both a common definition for nanotechnology and of standards for reporting nanomedical experiments and results. METHODS: We propose a supervised learning approach for classifying CT summaries from ClinicalTrials.gov according to whether they fall into the nano or the non-nano categories. Our method involves several stages: i) extraction and manual annotation of CTs as nano vs. non-nano, ii) pre-processing and automatic classification, and iii) performance evaluation using several state-of-the-art classifiers under different transformations of the original dataset. RESULTS AND CONCLUSIONS: The performance of the best automated classifier closely matches that of experts (AUC over 0.95), suggesting that it is feasible to automatically detect the presence of nanotechnology products in CT summaries with a high degree of accuracy. This can significantly speed up the process of finding whether reports on ClinicalTrials.gov might be relevant to a particular nanoparticle or nanodevice, which is essential to discover any precedents for nanotoxicity events or advantages for targeted drug therapy.

NCBI2RDF: enabling full RDF-based access to NCBI databases.

RDF has become the standard technology for enabling interoperability among heterogeneous biomedical databases. The NCBI provides access to a large set of life sciences databases through a common interface called Entrez. However, the latter does not provide RDF-based access to such databases, and, therefore, they cannot be integrated with other RDF-compliant databases and accessed via SPARQL query interfaces. This paper presents the NCBI2RDF system, aimed at providing RDF-based access to the complete NCBI data repository. This API creates a virtual endpoint for servicing SPARQL queries over different NCBI repositories and presenting to users the query results in SPARQL results format, thus enabling this data to be integrated and/or stored with other RDF-compliant repositories. SPARQL queries are dynamically resolved, decomposed, and forwarded to the NCBI-provided E-utilities programmatic interface to access the NCBI data. Furthermore, we show how our approach increases the expressiveness of the native NCBI querying system, allowing several databases to be accessed simultaneously. This feature significantly boosts productivity when working with complex queries and saves time and effort to biomedical researchers. Our approach has been validated with a large number of SPARQL queries, thus proving its reliability and enhanced capabilities in biomedical environments.

RDFBuilder: a tool to automatically build RDF-based interfaces for MAGE-OM microarray data sources.

This paper presents RDFBuilder, a tool that enables RDF-based access to MAGE-ML-compliant microarray databases. We have developed a system that automatically transforms the MAGE-OM model and microarray data stored in the ArrayExpress database into RDF format. Additionally, the system automatically enables a SPARQL endpoint. This allows users to execute SPARQL queries for retrieving microarray data, either from specific experiments or from more than one experiment at a time. Our system optimizes response times by caching and reusing information from previous queries. In this paper, we describe our methods for achieving this transformation. We show that our approach is complementary to other existing initiatives, such as Bio2RDF, for accessing and retrieving data from the ArrayExpress database.

The impact of computer science in molecular medicine: enabling high-throughput research.

The Human Genome Project and the explosion of high-throughput data have transformed the areas of molecular and personalized medicine, which are producing a wide range of studies and experimental results and providing new insights for developing medical applications. Research in many interdisciplinary fields is resulting in data repositories and computational tools that support a wide diversity of tasks: genome sequencing, genome-wide association studies, analysis of genotype-phenotype interactions, drug toxicity and side effects assessment, prediction of protein interactions and diseases, development of computational models, biomarker discovery, and many others. The authors of the present paper have developed several inventories covering tools, initiatives and studies in different computational fields related to molecular medicine: medical informatics, bioinformatics, clinical informatics and nanoinformatics. With these inventories, created by mining the scientific literature, we have carried out several reviews of these fields, providing researchers with a useful framework to locate, discover, search and integrate resources. In this paper we present an analysis of the state-of-the-art as it relates to computational resources for molecular medicine, based on results compiled in our inventories, as well as results extracted from a systematic review of the literature and other scientific media. The present review is based on the impact of their related publications and the available data and software resources for molecular medicine. It aims to provide information that can be useful to support ongoing research and work to improve diagnostics and therapeutics based on molecular-level insights.

Using nanoinformatics methods for automatically identifying relevant nanotoxicology entities from the literature.

Nanoinformatics is an emerging research field that uses informatics techniques to collect, process, store, and retrieve data, information, and knowledge on nanoparticles, nanomaterials, and nanodevices and their potential applications in health care. In this paper, we have focused on the solutions that nanoinformatics can provide to facilitate nanotoxicology research. For this, we have taken a computational approach to automatically recognize and extract nanotoxicology-related entities from the scientific literature. The desired entities belong to four different categories: nanoparticles, routes of exposure, toxic effects, and targets. The entity recognizer was trained using a corpus that we specifically created for this purpose and was validated by two nanomedicine/nanotoxicology experts. We evaluated the performance of our entity recognizer using 10-fold cross-validation. The precisions range from 87.6% (targets) to 93.0% (routes of exposure), while recall values range from 82.6% (routes of exposure) to 87.4% (toxic effects). These results prove the feasibility of using computational approaches to reliably perform different named entity recognition (NER)-dependent tasks, such as for instance augmented reading or semantic searches. This research is a "proof of concept" that can be expanded to stimulate further developments that could assist researchers in managing data, information, and knowledge at the nanolevel, thus accelerating research in nanomedicine.

Nanoinformatics: a new area of research in nanomedicine.

Over a decade ago, nanotechnologists began research on applications of nanomaterials for medicine. This research has revealed a wide range of different challenges, as well as many opportunities. Some of these challenges are strongly related to informatics issues, dealing, for instance, with the management and integration of heterogeneous information, defining nomenclatures, taxonomies and classifications for various types of nanomaterials, and research on new modeling and simulation techniques for nanoparticles. Nanoinformatics has recently emerged in the USA and Europe to address these issues. In this paper, we present a review of nanoinformatics, describing its origins, the problems it addresses, areas of interest, and examples of current research initiatives and informatics resources. We suggest that nanoinformatics could accelerate research and development in nanomedicine, as has occurred in the past in other fields. For instance, biomedical informatics served as a fundamental catalyst for the Human Genome Project, and other genomic and -omics projects, as well as the translational efforts that link resulting molecular-level research to clinical problems and findings.

e-MIR2: a public online inventory of medical informatics resources.

BACKGROUND: Over the past years, the number of available informatics resources in medicine has grown exponentially. While specific inventories of such resources have already begun to be developed for Bioinformatics (BI), comparable inventories are as yet not available for the Medical Informatics (MI) field, so that locating and accessing them currently remains a difficult and time-consuming task. DESCRIPTION: We have created a repository of MI resources from the scientific literature, providing free access to its contents through a web-based service. We define informatics resources as all those elements that constitute, serve to define or are used by informatics systems, ranging from architectures or development methodologies to terminologies, vocabularies, databases or tools. Relevant information describing the resources is automatically extracted from manuscripts published in top-ranked MI journals. We used a pattern matching approach to detect the resources' names and their main features. Detected resources are classified according to three different criteria: functionality, resource type and domain. To facilitate these tasks, we have built three different classification schemas by following a novel approach based on folksonomies and social tagging. We adopted the terminology most frequently used by MI researchers in their publications to create the concepts and hierarchical relationships belonging to the classification schemas. The classification algorithm identifies the categories associated with resources and annotates them accordingly. The database is then populated with this data after manual curation and validation. CONCLUSIONS: We have created an online repository of MI resources to assist researchers in locating and accessing the most suitable resources to perform specific tasks. The database contains 609 resources at the time of writing and is available at http://www.gib.fi.upm.es/eMIR2. We are continuing to expand the number of available resources by taking into account further publications as well as suggestions from users and resource developers.

CDAPubMed: a browser extension to retrieve EHR-based biomedical literature.

BACKGROUND: Over the last few decades, the ever-increasing output of scientific publications has led to new challenges to keep up to date with the literature. In the biomedical area, this growth has introduced new requirements for professionals, e.g., physicians, who have to locate the exact papers that they need for their clinical and research work amongst a huge number of publications. Against this backdrop, novel information retrieval methods are even more necessary. While web search engines are widespread in many areas, facilitating access to all kinds of information, additional tools are required to automatically link information retrieved from these engines to specific biomedical applications. In the case of clinical environments, this also means considering aspects such as patient data security and confidentiality or structured contents, e.g., electronic health records (EHRs). In this scenario, we have developed a new tool to facilitate query building to retrieve scientific literature related to EHRs. RESULTS: We have developed CDAPubMed, an open-source web browser extension to integrate EHR features in biomedical literature retrieval approaches. Clinical users can use CDAPubMed to: (i) load patient clinical documents, i.e., EHRs based on the Health Level 7-Clinical Document Architecture Standard (HL7-CDA), (ii) identify relevant terms for scientific literature search in these documents, i.e., Medical Subject Headings (MeSH), automatically driven by the CDAPubMed configuration, which advanced users can optimize to adapt to each specific situation, and (iii) generate and launch literature search queries to a major search engine, i.e., PubMed, to retrieve citations related to the EHR under examination. CONCLUSIONS: CDAPubMed is a platform-independent tool designed to facilitate literature searching using keywords contained in specific EHRs. CDAPubMed is visually integrated, as an extension of a widespread web browser, within the standard PubMed interface. It has been tested on a public dataset of HL7-CDA documents, returning significantly fewer citations since queries are focused on characteristics identified within the EHR. For instance, compared with more than 200,000 citations retrieved by breast neoplasm, fewer than ten citations were retrieved when ten patient features were added using CDAPubMed. This is an open source tool that can be freely used for non-profit purposes and integrated with other existing systems.

A knowledge engineering approach to recognizing and extracting sequences of nucleic acids from scientific literature.

In this paper we present a knowledge engineering approach to automatically recognize and extract genetic sequences from scientific articles. To carry out this task, we use a preliminary recognizer based on a finite state machine to extract all candidate DNA/RNA sequences. The latter are then fed into a knowledge-based system that automatically discards false positives and refines noisy and incorrectly merged sequences. We created the knowledge base by manually analyzing different manuscripts containing genetic sequences. Our approach was evaluated using a test set of 211 full-text articles in PDF format containing 3134 genetic sequences. For such set, we achieved 87.76% precision and 97.70% recall respectively. This method can facilitate different research tasks. These include text mining, information extraction, and information retrieval research dealing with large collections of documents containing genetic sequences.

PubDNA Finder: a web database linking full-text articles to sequences of nucleic acids.

SUMMARY: PubDNA Finder is an online repository that we have created to link PubMed Central manuscripts to the sequences of nucleic acids appearing in them. It extends the search capabilities provided by PubMed Central by enabling researchers to perform advanced searches involving sequences of nucleic acids. This includes, among other features (i) searching for papers mentioning one or more specific sequences of nucleic acids and (ii) retrieving the genetic sequences appearing in different articles. These additional query capabilities are provided by a searchable index that we created by using the full text of the 176 672 papers available at PubMed Central at the time of writing and the sequences of nucleic acids appearing in them. To automatically extract the genetic sequences occurring in each paper, we used an original method we have developed. The database is updated monthly by automatically connecting to the PubMed Central FTP site to retrieve and index new manuscripts. Users can query the database via the web interface provided. AVAILABILITY: PubDNA Finder can be freely accessed at http://servet.dia.fi.upm.es:8080/pubdnafinder

A method for automatically extracting infectious disease-related primers and probes from the literature.

BACKGROUND: Primer and probe sequences are the main components of nucleic acid-based detection systems. Biologists use primers and probes for different tasks, some related to the diagnosis and prescription of infectious diseases. The biological literature is the main information source for empirically validated primer and probe sequences. Therefore, it is becoming increasingly important for researchers to navigate this important information. In this paper, we present a four-phase method for extracting and annotating primer/probe sequences from the literature. These phases are: (1) convert each document into a tree of paper sections, (2) detect the candidate sequences using a set of finite state machine-based recognizers, (3) refine problem sequences using a rule-based expert system, and (4) annotate the extracted sequences with their related organism/gene information. RESULTS: We tested our approach using a test set composed of 297 manuscripts. The extracted sequences and their organism/gene annotations were manually evaluated by a panel of molecular biologists. The results of the evaluation show that our approach is suitable for automatically extracting DNA sequences, achieving precision/recall rates of 97.98% and 95.77%, respectively. In addition, 76.66% of the detected sequences were correctly annotated with their organism name. The system also provided correct gene-related information for 46.18% of the sequences assigned a correct organism name. CONCLUSIONS: We believe that the proposed method can facilitate routine tasks for biomedical researchers using molecular methods to diagnose and prescribe different infectious diseases. In addition, the proposed method can be expanded to detect and extract other biological sequences from the literature. The extracted information can also be used to readily update available primer/probe databases or to create new databases from scratch.

BIRI: a new approach for automatically discovering and indexing available public bioinformatics resources from the literature.

BACKGROUND: The rapid evolution of Internet technologies and the collaborative approaches that dominate the field have stimulated the development of numerous bioinformatics resources. To address this new framework, several initiatives have tried to organize these services and resources. In this paper, we present the BioInformatics Resource Inventory (BIRI), a new approach for automatically discovering and indexing available public bioinformatics resources using information extracted from the scientific literature. The index generated can be automatically updated by adding additional manuscripts describing new resources. We have developed web services and applications to test and validate our approach. It has not been designed to replace current indexes but to extend their capabilities with richer functionalities. RESULTS: We developed a web service to provide a set of high-level query primitives to access the index. The web service can be used by third-party web services or web-based applications. To test the web service, we created a pilot web application to access a preliminary knowledge base of resources. We tested our tool using an initial set of 400 abstracts. Almost 90% of the resources described in the abstracts were correctly classified. More than 500 descriptions of functionalities were extracted. CONCLUSION: These experiments suggest the feasibility of our approach for automatically discovering and indexing current and future bioinformatics resources. Given the domain-independent characteristics of this tool, it is currently being applied by the authors in other areas, such as medical nanoinformatics. BIRI is available at http://edelman.dia.fi.upm.es/biri/.

An automatic method for retrieving and indexing catalogues of biomedical courses.

Although there is wide information about Biomedical Informatics education and courses in different Websites, information is usually not exhaustive and difficult to update. We propose a new methodology based on information retrieval techniques for extracting, indexing and retrieving automatically information about educational offers. A web application has been developed to make available such information in an inventory of courses and educational offers.

A method for indexing biomedical resources over the internet.

A large number of biomedical resources are publicly available over the Internet. This number grows every day. Biomedical researchers face the problem of locating, identifying and selecting the most appropriate resources according to their interests. Some resource indexes can be found in the Internet, but they only provide information and links related to resources created by the owner institution of each website. In this paper we propose a novel method for extracting information from the literature and create a Resourceome, i.e. an index of biomedical resources (databases, tools and services) in a semi-automatic way. In this approach we consider only the information provided by the abstracts of relevant papers in the area. Building a comprehensive resource index is the first step towards the development of new methodologies for the automatic or semi-automatic construction of complex biomedical workflows which allow combining several resources to obtain higher-level functionalities.

An algebraic approach to detect logical inconsistencies in medical appropriateness criteria.

In this paper, we present a computerized approach to detect inconsistencies in medical knowledge bases. The method has been applied to a set of medical appropriateness criteria developed for the review of coronary artery disease management. One of the main problems associated to medical appropriateness criteria is to detect logical inconsistencies in the criteria set, a process often manually carried out by health services specialists. In our approach, appropriateness criteria are automatically translated to rules containing propositional variables, using three-valued Lukasiewicz's logic augmented with modal operators to manage uncertainty. The method assigns a polynomial to each of the rules, integrity constraints, and facts from the rule-based set. This rule set is then checked for inconsistencies. The problem of determining if a formula is a tautological consequence of a set of formulae is reduced by our method into an ideal membership problem in computer algebra. Finally, the set of medical appropriateness criteria is represented in a flowchart format that can be disseminated and remotely accessed over Internet, and can be prospectively used for patient care and management. The method reported in this paper can be applied to other knowledge bases represented by means of IF-THEN rules.

Semantic data integration in the European ACGT project.

ACGT is an IST-FP6 Integrated Project, funded by the European Commission, for the development of services to support clinico-genomic trials on cancer in a grid-based environment. In these trials, physicians and researchers need to access heterogeneous and disparate data sources. Semantic access to these data and the possibility to integrate them seamlessly are issues that ACGT aim to solve.