RESUMO
BACKGROUND: This article provides an overview of the first BIOASQ challenge, a competition on large-scale biomedical semantic indexing and question answering (QA), which took place between March and September 2013. BIOASQ assesses the ability of systems to semantically index very large numbers of biomedical scientific articles, and to return concise and user-understandable answers to given natural language questions by combining information from biomedical articles and ontologies. RESULTS: The 2013 BIOASQ competition comprised two tasks, Task 1a and Task 1b. In Task 1a participants were asked to automatically annotate new PUBMED documents with MESH headings. Twelve teams participated in Task 1a, with a total of 46 system runs submitted, and one of the teams performing consistently better than the MTI indexer used by NLM to suggest MESH headings to curators. Task 1b used benchmark datasets containing 29 development and 282 test English questions, along with gold standard (reference) answers, prepared by a team of biomedical experts from around Europe and participants had to automatically produce answers. Three teams participated in Task 1b, with 11 system runs. The BIOASQ infrastructure, including benchmark datasets, evaluation mechanisms, and the results of the participants and baseline methods, is publicly available. CONCLUSIONS: A publicly available evaluation infrastructure for biomedical semantic indexing and QA has been developed, which includes benchmark datasets, and can be used to evaluate systems that: assign MESH headings to published articles or to English questions; retrieve relevant RDF triples from ontologies, relevant articles and snippets from PUBMED Central; produce "exact" and paragraph-sized "ideal" answers (summaries). The results of the systems that participated in the 2013 BIOASQ competition are promising. In Task 1a one of the systems performed consistently better from the NLM's MTI indexer. In Task 1b the systems received high scores in the manual evaluation of the "ideal" answers; hence, they produced high quality summaries as answers. Overall, BIOASQ helped obtain a unified view of how techniques from text classification, semantic indexing, document and passage retrieval, question answering, and text summarization can be combined to allow biomedical experts to obtain concise, user-understandable answers to questions reflecting their real information needs.
Assuntos
Indexação e Redação de Resumos/métodos , Algoritmos , Medical Subject Headings , Processamento de Linguagem Natural , PubMed , Semântica , Software , Humanos , National Library of Medicine (U.S.) , Estados UnidosRESUMO
A crucial challenge in critical settings like medical diagnosis is making deep learning models used in decision-making systems interpretable. Efforts in Explainable Artificial Intelligence (XAI) are underway to address this challenge. Yet, many XAI methods are evaluated on broad classifiers and fail to address complex, real-world issues, such as medical diagnosis. In our study, we focus on enhancing user trust and confidence in automated AI decision-making systems, particularly for diagnosing skin lesions, by tailoring an XAI method to explain an AI model's ability to identify various skin lesion types. We generate explanations using synthetic images of skin lesions as examples and counterexamples, offering a method for practitioners to pinpoint the critical features influencing the classification outcome. A validation survey involving domain experts, novices, and laypersons has demonstrated that explanations increase trust and confidence in the automated decision system. Furthermore, our exploration of the model's latent space reveals clear separations among the most common skin lesion classes, a distinction that likely arises from the unique characteristics of each class and could assist in correcting frequent misdiagnoses by human professionals.
RESUMO
Modelling complex systems, like the human heart, has made great progress over the last decades. Patient-specific models, called 'digital twins', can aid in diagnosing arrhythmias and personalizing treatments. However, building highly accurate predictive heart models requires a delicate balance between mathematical complexity, parameterization from measurements and validation of predictions. Cardiac electrophysiology (EP) models range from complex biophysical models to simplified phenomenological models. Complex models are accurate but computationally intensive and challenging to parameterize, while simplified models are computationally efficient but less realistic. In this paper, we propose a hybrid approach by leveraging deep learning to complete a simplified cardiac model from data. Our novel framework has two components, decomposing the dynamics into a physics based and a data-driven term. This construction allows our framework to learn from data of different complexity, while simultaneously estimating model parameters. First, using in silico data, we demonstrate that this framework can reproduce the complex dynamics of cardiac transmembrane potential even in the presence of noise in the data. Second, using ex vivo optical data of action potentials (APs), we demonstrate that our framework can identify key physical parameters for anatomical zones with different electrical properties, as well as to reproduce the AP wave characteristics obtained from various pacing locations. Our physics-based data-driven approach may improve cardiac EP modelling by providing a robust biophysical tool for predictions.
RESUMO
We investigate a new approach for online handwritten shape recognition. Interesting features of this approach include learning without manual tuning, learning from very few training samples, incremental learning of characters, and adaptation to the user-specific needs. The proposed system can deal with two-dimensional graphical shapes such as Latin and Asian characters, command gestures, symbols, small drawings, and geometric shapes. It can be used as a building block for a series of recognition tasks with many applications.
Assuntos
Algoritmos , Inteligência Artificial , Processamento Eletrônico de Dados/métodos , Escrita Manual , Interpretação de Imagem Assistida por Computador/métodos , Armazenamento e Recuperação da Informação/métodos , Reconhecimento Automatizado de Padrão/métodos , Humanos , Aumento da Imagem/métodos , Cadeias de Markov , Modelos Estatísticos , Sistemas On-LineRESUMO
In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such cases, so that we introduce, in the framework of Tikhonov regularization, a matricial reformulation of the problem which allows us to use the condition number as a diagnostic tool for identification of instability. By imposing well-conditioning requirements on the relevant matrices, our theoretical analysis allows the identification of an optimal value for the regularization parameter from the standpoint of stability. We compare with the value derived by cross-validation for overfitting control and optimization of the generalization performance. We test our method for both regression and classification tasks. The proposed method is quite effective in terms of predictivity, often with some improvement on performance with respect to the reference cases considered. This approach, due to analytical determination of the regularization parameter, dramatically reduces the computational load required by many other techniques.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Algoritmos , Classificação , Reprodutibilidade dos TestesRESUMO
OBJECTIVE: Information about medications is critical in supporting decision-making during the prescription process and thus in improving the safety and quality of care. In this work, we propose a methodology for the automatic recognition of drug-related entities (active ingredient, interaction effects, etc.) in textual drug descriptions, and their further location in a previously developed domain ontology. METHODS AND MATERIAL: The summary of product characteristics (SPC) represents the basis of information for health professionals on how to use medicines. However, this information is locked in free-text and, as such, cannot be actively accessed and elaborated by computerized applications. Our approach exploits a combination of machine learning and rule-based methods. It consists of two stages. Initially it learns to classify this information in a structured prediction framework, relying on conditional random fields. The classifier is trained and evaluated using a corpus of about a hundred SPCs. They have been hand-annotated with different semantic labels that have been derived from the domain ontology. At a second stage the extracted entities are added in the domain ontology corresponding concepts as new instances, using a set of rules manually-constructed from the corpus. RESULTS: Our evaluations show that the extraction module exhibits high overall performance, with an average F1-measure of 88% for contraindications and 90% for interactions. CONCLUSION: SPCs can be exploited to provide structured information for computer-based decision support systems.