BIOMEDICAL LANGUAGE UNDERSTANDING AND EXTRACTION (BLUE-TEXT): A MINIMAL SYNTACTIC, SEMANTIC METHOD

Clinical text understanding (CTU) is of interest to health informatics because critical clinical information frequently represented as unconstrained text in electronic health records are extensively used by human experts to guide clinical practice, decision making, and to document delivery of care, but are largely unusable by information systems for queries and computations. Recent initiatives advocating for translational research call for generation of technologies that can integrate structured clinical data with unstructured data, provide a unified interface to all data, and contextualize clinical information for reuse in multidisciplinary and collaborative environment envisioned by CTSA program. This implies that technologies for the processing and interpretation of clinical text should be evaluated not only in terms of their validity and reliability in their intended environment, but also in light of their interoperability, and ability to support information integration and contextualization in a distributed and dynamic environment. This vision adds a new layer of information representation requirements that needs to be accounted for when conceptualizing implementation or acquisition of clinical text processing tools and technologies for multidisciplinary research. On the other hand, electronic health records frequently contain unconstrained clinical text with high variability in use of terms and documentation practices, and without commitmentto grammatical or syntactic structure of the language (e.g. Triage notes, physician and nurse notes, chief complaints, etc). This hinders performance of natural language processing technologies which typically rely heavily on the syntax of language and grammatical structure of the text. This document introduces our method to transform unconstrained clinical text found in electronic health information systems to a formal (computationally understandable) representation that is suitable for querying, integration, contextualization and reuse, and is resilient to the grammatical and syntactic irregularities of the clinical text. We present our design rationale, method, and results of evaluation in processing chief complaints and triage notes from 8 different emergency departments in Houston Texas. At the end, we will discuss significance of our contribution in enabling use of clinical text in a practical bio-surveillance setting.

Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

Bio-QA-GNN: Reasoning with Language Models and Knowledge Graphs for Interpretable Biomedical Question Answering

Nowadays the idea of injecting world or domain-specific structured knowledge into pre-trained language models (PLMs) is becoming an increasingly popular approach for solving problems such as biases, hallucinations, huge architectural sizes, and explainability lack—critical for real-world natural language processing applications in sensitive fields like bioinformatics. One recent work that has garnered much attention in Neuro-symbolic AI is QA-GNN, an end-to-end model for multiple-choice open-domain question answering (MCOQA) tasks via interpretable text-graph reasoning. Unlike previous publications, QA-GNN mutually informs PLMs and graph neural networks (GNNs) on top of relevant facts retrieved from knowledge graphs (KGs). However, taking a more holistic view, existing PLM+KG contributions mainly consider commonsense benchmarks and ignore or shallowly analyze performances on biomedical datasets. This thesis start from a propose of a deep investigation of QA-GNN for biomedicine, comparing existing or brand-new PLMs, KGs, edge-aware GNNs, preprocessing techniques, and initialization strategies. By combining the insights emerged in DISI's research, we introduce Bio-QA-GNN that include a KG. Working with this part has led to an improvement in state-of-the-art of MCOQA model on biomedical/clinical text, largely outperforming the original one (+3.63\% accuracy on MedQA). Our findings also contribute to a better understanding of the explanation degree allowed by joint text-graph reasoning architectures and their effectiveness on different medical subjects and reasoning types. Codes, models, datasets, and demos to reproduce the results are freely available at: \url{https://github.com/disi-unibo-nlp/bio-qagnn}.

Génération de résumés par abstraction

Cette thèse présente le résultat de plusieurs années de recherche dans le domaine de la génération automatique de résumés. Trois contributions majeures, présentées sous la forme d'articles publiés ou soumis pour publication, en forment le coeur. Elles retracent un cheminement qui part des méthodes par extraction en résumé jusqu'aux méthodes par abstraction. L'expérience HexTac, sujet du premier article, a d'abord été menée pour évaluer le niveau de performance des êtres humains dans la rédaction de résumés par extraction de phrases. Les résultats montrent un écart important entre la performance humaine sous la contrainte d'extraire des phrases du texte source par rapport à la rédaction de résumés sans contrainte. Cette limite à la rédaction de résumés par extraction de phrases, observée empiriquement, démontre l'intérêt de développer d'autres approches automatiques pour le résumé. Nous avons ensuite développé un premier système selon l'approche Fully Abstractive Summarization, qui se situe dans la catégorie des approches semi-extractives, comme la compression de phrases et la fusion de phrases. Le développement et l'évaluation du système, décrits dans le second article, ont permis de constater le grand défi de générer un résumé facile à lire sans faire de l'extraction de phrases. Dans cette approche, le niveau de compréhension du contenu du texte source demeure insuffisant pour guider le processus de sélection du contenu pour le résumé, comme dans les approches par extraction de phrases. Enfin, l'approche par abstraction basée sur des connaissances nommée K-BABS est proposée dans un troisième article. Un repérage des éléments d'information pertinents est effectué, menant directement à la génération de phrases pour le résumé. Cette approche a été implémentée dans le système ABSUM, qui produit des résumés très courts mais riches en contenu. Ils ont été évalués selon les standards d'aujourd'hui et cette évaluation montre que des résumés hybrides formés à la fois de la sortie d'ABSUM et de phrases extraites ont un contenu informatif significativement plus élevé qu'un système provenant de l'état de l'art en extraction de phrases.

Obstacles to Inter-Racial Understanding: Some Clinical Implications for Mental Health Practitioners in Predominantly White Institutions

in the context of predominantly white institutions. In this paper concepts such as projection, projective identification, splitting, scapegoating, superiority and denial will be employed to illustrate why racial prejudice is a deeply-rooted collective psychological disorder that affects even educated mental health practitioners. Clinicians have an ethical responsibility to demonstrate cultural sensitivity and empathy when working with minority clients, colleagues, staff and students, to examine and root out their own prejudices, and to encourage others to do the same.

Understanding and choosing clinical performance measures for quality improvement : development of a typology : final report /

"Contract no. 282-92-0038, delivery order #3."

Understanding uveitis, Clinical Center.

Mode of access: Internet.

The documentation of clinical psychotropic drug trials; [a workbook and user's guide to understanding and interpreting the data processing and output of the Biometric Laboratory Information Processing System (BLIPS), George Washington University, and the Early Clinical Drug Evaluation Unit (ECDEU), NIMH.

On cover of v. 2: Early clinical drug evaluation units, analyses.

Understanding the dynamics of information technology implementation: The case of clinical information systems

The ultimate intent of this dissertation was to broaden and strengthen our understanding of IT implementation by emphasizing research efforts on the dynamic nature of the implementation process. More specifically, efforts were directed toward opening the "black box" and providing the story that explains how and why contextual conditions and implementation tactics interact to produce project outcomes. In pursuit of this objective, the dissertation was aimed at theory building and adopted a case study methodology combining qualitative and quantitative evidence. Precisely, it examined the implementation process, use and consequences of three clinical information systems at Jackson Memorial Hospital, a large tertiary care teaching hospital.^ As a preliminary step toward the development of a more realistic model of system implementation, the study proposes a new set of research propositions reflecting the dynamic nature of the implementation process.^ Findings clearly reveal that successful implementation projects are likely to be those where key actors envision end goals, anticipate challenges ahead, and recognize the presence of and seize opportunities. It was also found that IT implementation is characterized by the systems theory of equifinality, that is, there are likely several equally effective ways to achieve a given end goal. The selection of a particular implementation strategy appears to be a rational process where actions and decisions are largely influenced by the degree to which key actors recognize the mediating role of each tactic and are motivated to action. The nature of the implementation process is also characterized by the concept of "duality of structure," that is, context and actions mutually influence each other. Another key finding suggests that there is no underlying program that regulates the process of change and moves it form one given point toward a subsequent and already prefigured end. For this reason, the implementation process cannot be thought of as a series of activities performed in a sequential manner such as conceived in stage models. Finally, it was found that IT implementation is punctuated by a certain indeterminacy. Results suggest that only when substantial efforts are focused on what to look for and think about, it is less likely that unfavorable and undesirable consequences will occur. ^

Photodynamic therapy for acne vulgaris: A critical review from basics to clinical practice Part II. Understanding parameters for acne treatment with photodynamic therapy

Photodynamic therapy requires a photosensitizer, oxygen, and activating light. For acne, pilosebaceous units are ""target"" structures. Porphyrins are synthesized in vivo from 5-aminolevulinic acid (ALA), particularly in pilosebaceous units. Different photosensitizers and drug delivery methods have been reported for acne treatment. There are a variety of porphyrin precursors with different pharmacokinetic properties. Among them, ALA and methyl-ester of ALA (MAT.) are available for possible off-label treatment of acne vulgaris. In addition, various light sources, light dosimetry, drug incubation time, and pre- and posttreatment care also change efficacy and side effects. None of these variables has been optimized for acne treatment, but a number of clinical trials provide helpful guidance. In this paper, we critically analyze clinical trials, case reports, and series of cases published through 2009. (J Am Acad Dermatol 2010;63:195-211.)

Standardizing assessment of adverse effects in rheumatology clinical trials. Status of OMERACT Toxicity Working Group March 2000: Towards a common understanding of comparative toxicity/safety profiles for antirheumatic therapies

This paper describes the background and current status of an OMERACT facilitated effort to improve the consistency of adverse event reporting in rheumatology clinical trials, The overall goal is the development of an adverse event assessment tool that would provide a basis for use of common terminology and improve the consistency of reporting severity of side effects within rheumatology clinical trials and during postmarketing surveillance. The resulting Rheumatology Common Toxicity Criteria Index encompassed the following organ systems: allergic/immunologic, cardiac, ENT, gastrointestinal, musculoskeletal, neuropsychiatric, ophthalmologic, pulmonary and skin/integument. Before this tool is widely accepted, its validity, consistency, and feasibility need to be assessed in clinical trials.