Named Entity Extraction: la piattaforma Gate/Annie

In questo lavoro si introducono i concetti di base di Natural Language Processing, soffermandosi su Information Extraction e analizzandone gli ambiti applicativi, le attività principali e la differenza rispetto a Information Retrieval. Successivamente si analizza il processo di Named Entity Recognition, focalizzando l’attenzione sulle principali problematiche di annotazione di testi e sui metodi per la valutazione della qualità dell’estrazione di entità. Infine si fornisce una panoramica della piattaforma software open-source di language processing GATE/ANNIE, descrivendone l’architettura e i suoi componenti principali, con approfondimenti sugli strumenti che GATE offre per l'approccio rule-based a Named Entity Recognition.

The accuracy of self-reported medical history: A preliminary analysis of the promise of internet-based research in Inflammatory Bowel Diseases

BACKGROUND AND AIMS: Internet-based surveys provide a potentially important tool for Inflammatory Bowel Disease (IBD) research. The advantages include low cost, large numbers of participants, rapid study completion and less extensive infrastructure than traditional methods. The aim was to determine the accuracy of patient self-reporting in internet-based IBD research and identify predictors of greater reliability. METHODS: 197 patients from a tertiary care center answered an online survey concerning personal medical history and an evaluation of disease specific knowledge. Self-reported medical details were compared with data abstracted from medical records. Agreement was assessed by kappa (κ) statistics. RESULTS: Participants responded correctly with excellent agreement (κ=0.96-0.97) on subtype of IBD and history of surgery. The agreement was also excellent for colectomy (κ=0.88) and small bowel resection (κ=0.91), moderate for abscesses and fistulas (κ=0.60 and 0.63), but poor regarding partial colectomy (κ=0.39). Time since last colonoscopy was self-reported with better agreement (κ=0.84) than disease activity. For disease location/extent, moderate agreements at κ=69% and 64% were observed for patients with Crohn's disease and ulcerative colitis, respectively. Subjects who scored higher than the average in the IBD knowledge assessment were significantly more accurate about disease location than their complementary group (74% vs. 59%, p=0.02). CONCLUSION: This study demonstrates that IBD patients accurately report their medical history regarding type of disease and surgical procedures. More detailed medical information is less reliably reported. Disease knowledge assessment may help in identifying the most accurate individuals and could therefore serve as validity criteria. Internet-based surveys are feasible with high reliability about basic disease features only. However, the participants in this study were engaged at a tertiary center, which potentially leads to a bias and compromises generalization to an unfiltered patient group.

Doctor-patient communication in the medical interaction: Context, implications, and practice

Effective communication; whether from an interpersonal, mass media, or global perspective, is a critical component in public health. It is an essential conduit in increasing public awareness of available health resources, potential health hazards and related disease prevention strategies, and in delivering better health care. Within this context, available literature asserts doctor-patient communication as central to healthcare delivery. It has been shown to affect patient health outcomes, satisfaction with care, adherence to treatment recommendations, and even understanding of medical information. While research supports the essential imperative of interventions aimed at teaching doctors and patients the communication skills necessary for a successful and meaningful medical interaction, most interventions to date, focus on teaching these communication skills to doctors and seem to rely, largely, on mass media for providing patients with the information needed to increase communication efficacy. This study sought to fill a significant gap in the doctor-patient communication literature by reviewing the context of the doctor-patient exchange in the medical interaction, the implications of this exchange in resulting care of the patient, and the potential improvements to practice through interventions aimed at improving the communication exchange. Closing with an evaluation of a patient-centered communication intervention, the “How to Talk to Your Doctor” (HTTTYD) program that combines previously identified optimal strategies for improving communication between doctors and patients, this study examined the patients’ perspective of their potential as better communicators in the medical interaction. ^ Specific Aims, Hypotheses or Questions (Aim I) To examine the context of health communication within a public health framework and its relation to health care delivery. (Aim II) To review doctor-patient communication as a central focus within health care delivery and the resulting implications to patient care. (Aim III) To assess the utility of interventions to improve doctor-patient communication. Specifically, to evaluate the effectiveness of a patient-centered community education intervention, the “How to Talk to Your Doctor” (HTTTYD) program, aimed at improving patient communication efficacy.^

Concept-based document readability in domain specific information retrieval

Domain specific information retrieval has become in demand. Not only domain experts, but also average non-expert users are interested in searching domain specific (e.g., medical and health) information from online resources. However, a typical problem to average users is that the search results are always a mixture of documents with different levels of readability. Non-expert users may want to see documents with higher readability on the top of the list. Consequently the search results need to be re-ranked in a descending order of readability. It is often not practical for domain experts to manually label the readability of documents for large databases. Computational models of readability needs to be investigated. However, traditional readability formulas are designed for general purpose text and insufficient to deal with technical materials for domain specific information retrieval. More advanced algorithms such as textual coherence model are computationally expensive for re-ranking a large number of retrieved documents. In this paper, we propose an effective and computationally tractable concept-based model of text readability. In addition to textual genres of a document, our model also takes into account domain specific knowledge, i.e., how the domain-specific concepts contained in the document affect the document’s readability. Three major readability formulas are proposed and applied to health and medical information retrieval. Experimental results show that our proposed readability formulas lead to remarkable improvements in terms of correlation with users’ readability ratings over four traditional readability measures.

Biomedical events extraction using the hidden vector state model

Objective: Biomedical events extraction concerns about events describing changes on the state of bio-molecules from literature. Comparing to the protein-protein interactions (PPIs) extraction task which often only involves the extraction of binary relations between two proteins, biomedical events extraction is much harder since it needs to deal with complex events consisting of embedded or hierarchical relations among proteins, events, and their textual triggers. In this paper, we propose an information extraction system based on the hidden vector state (HVS) model, called HVS-BioEvent, for biomedical events extraction, and investigate its capability in extracting complex events. Methods and material: HVS has been previously employed for extracting PPIs. In HVS-BioEvent, we propose an automated way to generate abstract annotations for HVS training and further propose novel machine learning approaches for event trigger words identification, and for biomedical events extraction from the HVS parse results. Results: Our proposed system achieves an F-score of 49.57% on the corpus used in the BioNLP'09 shared task, which is only 2.38% lower than the best performing system by UTurku in the BioNLP'09 shared task. Nevertheless, HVS-BioEvent outperforms UTurku's system on complex events extraction with 36.57% vs. 30.52% being achieved for extracting regulation events, and 40.61% vs. 38.99% for negative regulation events. Conclusions: The results suggest that the HVS model with the hierarchical hidden state structure is indeed more suitable for complex event extraction since it could naturally model embedded structural context in sentences.

Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.

Browsing for information by highlighting automatically generated annotations:a user study and evaluation

The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated. Copyright 2005 ACM.

Application of the Artificial Intelligence Algorithms for System Analysis of Multi Dimension Physiological Data for Developing Polyparametric Information System of Public Health Diagnostics

The polyparametric intelligence information system for diagnostics human functional state in medicine and public health is developed. The essence of the system consists in polyparametric describing of human functional state with the unified set of physiological parameters and using the polyparametric cognitive model developed as the tool for a system analysis of multitude data and diagnostics of a human functional state. The model is developed on the basis of general principles geometry and symmetry by algorithms of artificial intelligence systems. The architecture of the system is represented. The model allows analyzing traditional signs - absolute values of electrophysiological parameters and new signs generated by the model – relationships of ones. The classification of physiological multidimensional data is made with a transformer of the model. The results are presented to a physician in a form of visual graph – a pattern individual functional state. This graph allows performing clinical syndrome analysis. A level of human functional state is defined in the case of the developed standard (“ideal”) functional state. The complete formalization of results makes it possible to accumulate physiological data and to analyze them by mathematics methods.

Medical-miner at TREC 2011 medical records track

This paper presents work done at Medical Minner Project on the TREC-2011 Medical Records Track. The paper proposes four models for medical information retrieval based on Lucene index approach. Our retrieval engine used an Lucen Index scheme with traditional stopping and stemming, enhanced with entity recognition software on query terms. Our aim in this first competition is to set a broader project that involves the develop of a configurable Apache Lucene-based framework that allows the rapid development of medical search facilities. Results around the track median have been achieved. In this exploratory track, we think that these results are a good beginning and encourage us for future developments.

Criação de uma ontologia e respectiva povoação a partir do processamento de relatórios médicos

A evolução tecnológica tem provocado uma evolução na medicina, através de sistemas computacionais voltados para o armazenamento, captura e disponibilização de informações médicas. Os relatórios médicos são, na maior parte das vezes, guardados num texto livre não estruturado e escritos com vocabulário proprietário, podendo ocasionar falhas de interpretação. Através das linguagens da Web Semântica, é possível utilizar antologias como modo de estruturar e padronizar a informação dos relatórios médicos, adicionando¬ lhe anotações semânticas. A informação contida nos relatórios pode desta forma ser publicada na Web, permitindo às máquinas o processamento automático da informação. No entanto, o processo de criação de antologias é bastante complexo, pois existe o problema de criar uma ontologia que não cubra todo o domínio pretendido. Este trabalho incide na criação de uma ontologia e respectiva povoação, através de técnicas de PLN e Aprendizagem Automática que permitem extrair a informação dos relatórios médicos. Foi desenvolvida uma aplicação, que permite ao utilizador converter relatórios do formato digital para o formato OWL. ABSTRACT: Technological evolution has caused a medicine evolution through computer systems which allow storage, gathering and availability of medical information. Medical reports are, most of the times, stored in a non-structured free text and written in a personal way so that misunderstandings may occur. Through Semantic Web languages, it’s possible to use ontology as a way to structure and standardize medical reports information by adding semantic notes. The information in those reports can, by these means, be displayed on the web, allowing machines automatic information processing. However, the process of creating ontology is very complex, as there is a risk creating of an ontology that not covering the whole desired domain. This work is about creation of an ontology and its population through NLP and Machine Learning techniques to extract information from medical reports. An application was developed which allows the user to convert reports from digital for¬ mat to OWL format.

A secure framework and related protocols for ubiquitous access to electronic health records using Java sim cards

Ubiquitous access to patient medical records is an important aspect of caring for patient safety. Unavailability of sufficient medical information at the point-ofcare could possibly lead to a fatality. The U.S. Institute of Medicine has reported that between 44,000 and 98,000 people die each year due to medical errors, such as incorrect medication dosages, due to poor legibility in manual records, or delays in consolidating needed information to discern the proper intervention. In this research we propose employing emergent technologies such as Java SIM Cards (JSC), Smart Phones (SP), Next Generation Networks (NGN), Near Field Communications (NFC), Public Key Infrastructure (PKI), and Biometric Identification to develop a secure framework and related protocols for ubiquitous access to Electronic Health Records (EHR). A partial EHR contained within a JSC can be used at the point-of-care in order to help quick diagnosis of a patient’s problems. The full EHR can be accessed from an Electronic Health Records Centre (EHRC) when time and network availability permit. Moreover, this framework and related protocols enable patients to give their explicit consent to a doctor to access their personal medical data, by using their Smart Phone, when the doctor needs to see or update the patient’s medical information during an examination. Also our proposed solution would give the power to patients to modify the Access Control List (ACL) related to their EHRs and view their EHRs through their Smart Phone. Currently, very limited research has been done on using JSCs and similar technologies as a portable repository of EHRs or on the specific security issues that are likely to arise when JSCs are used with ubiquitous access to EHRs. Previous research is concerned with using Medicare cards, a kind of Smart Card, as a repository of medical information at the patient point-of-care. However, this imposes some limitations on the patient’s emergency medical care, including the inability to detect the patient’s location, to call and send information to an emergency room automatically, and to interact with the patient in order to get consent. The aim of our framework and related protocols is to overcome these limitations by taking advantage of the SIM card and the technologies mentioned above. Briefly, our framework and related protocols will offer the full benefits of accessing an up-to-date, precise, and comprehensive medical history of a patient, whilst its mobility will provide ubiquitous access to medical and patient information everywhere it is needed. The objective of our framework and related protocols is to automate interactions between patients, healthcare providers and insurance organisations, increase patient safety, improve quality of care, and reduce the costs.

A secure framework and related protocols for ubiquitous access to electronic health records using Java SIM cards

Ubiquitous access to patient medical records is an important aspect of caring for patient safety. Unavailability of sufficient medical information at the patient point-of-care could possibly lead to a fatality. In this paper we propose employing emergent technologies such as Java SIM Cards (JSC),Smart Phones (SP), Next Generation Networks (NGN), Near Field Communications (NFC), Public Key Infrastructure (PKI), and Biometric Identification to develop a secure framework and related protocols for ubiquitous access to Electronic Health Records (EHRs). A partial EHR contained within a JSC can be used at the patient point-of-care in order to help quick diagnosis of a patient’s problems. The full EHR can be accessed from an Electronic Healthcare Records Centre (EHRC).

Role of ubiquitous sensor network in patient care

Efficient caring for the patient's information is an important aspect of caring for the patient. If these processes are possible to monitor anytime anywhere as per the patients' and doctors desecrations the cost of patient care could be minimised. In this connection, Ubiquitous Sensor Network is playing a key role on communication between physicians and patients as well as information sharing among health care providers with rapid access to medical information through reliable and trusted computer network systems. This paper argues possibilities of such scenarios by introducing a ubiquitous sensor network in patient care for 21st century's requirements and standards.

WebPut : Efficient web-based data imputation

In this paper, we present WebPut, a prototype system that adopts a novel web-based approach to the data imputation problem. Towards this, Webput utilizes the available information in an incomplete database in conjunction with the data consistency principle. Moreover, WebPut extends effective Information Extraction (IE) methods for the purpose of formulating web search queries that are capable of effectively retrieving missing values with high accuracy. WebPut employs a confidence-based scheme that efficiently leverages our suite of data imputation queries to automatically select the most effective imputation query for each missing value. A greedy iterative algorithm is also proposed to schedule the imputation order of the different missing values in a database, and in turn the issuing of their corresponding imputation queries, for improving the accuracy and efficiency of WebPut. Experiments based on several real-world data collections demonstrate that WebPut outperforms existing approaches.