| 1. |
- Alemu Argaw, Atelach, et al.
(författare)
-
General-Purpose Text Categorization Applied to the Medical Domain.
- 2007
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents work where a general-purpose text categorization method was applied to categorize medical free-texts. The purpose of the experiments was to examine how such a method performs without any domain-specific knowledge, hand-crafting or tuning. Additionally, we compare the results from the general-purpose method with results from runs in which a medical thesaurus as well as automatically extracted keywords were used when building the classifiers. We show that standard text categorization techniques using stemmed unigrams as the basis for learning can be applied directly to categorize medical reports, yielding an F-measure of 83.9, and outperforming the more sophisticated methods.
|
|
| 2. |
|
|
| 3. |
- Cakici, Baki, 1984-, et al.
(författare)
-
CASE : a framework for computer supported outbreak detection
- 2010
-
Ingår i: BMC Medical Informatics and Decision Making. - : Springer Science and Business Media LLC. - 1472-6947. ; 10, s. 14-
-
Tidskriftsartikel (refereegranskat)abstract
- Background: In computer supported outbreak detection, a statistical method is applied to a collection of cases to detect any excess cases for a particular disease. Whether a detected aberration is a true outbreak is decided by a human expert. We present a technical framework designed and implemented at the Swedish Institute for Infectious Disease Control for computer supported outbreak detection, where a database of case reports for a large number of infectious diseases can be processed using one or more statistical methods selected by the user. Results: Based on case information, such as diagnosis and date, different statistical algorithms for detecting outbreaks can be applied, both on the disease level and the subtype level. The parameter settings for the algorithms can be configured independently for different diagnoses using the provided graphical interface. Input generators and output parsers are also provided for all supported algorithms. If an outbreak signal is detected, an email notification is sent to the persons listed as receivers for that particular disease. Conclusions: The framework is available as open source software, licensed under GNU General Public License Version 3. By making the code open source, we wish to encourage others to contribute to the future development of computer supported outbreak detection systems, and in particular to the development of the CASE framework.
|
|
| 4. |
- Cars, Otto, et al.
(författare)
-
Building bridges to operationalise one health : A Sino-Swedish collaboration to tackle antibiotic resistance
- 2016
-
Ingår i: One Health. - : Elsevier. - 2352-7714. ; 2, s. 139-143
-
Tidskriftsartikel (refereegranskat)abstract
- Antibiotic resistance is a complex global health challenge. The recent Global Action Plan on antimicrobial resistance highlights the importance of adopting One Health approaches that can cross traditional disciplinary boundaries. We report on the early experiences of a multisectoral Sino-Swedish research project that aims to address gaps in our current knowledge and seeks to improve the situation through system-wide interventions. Our research project is investigating antibiotic use and resistance in a rural area of China through a combination of epidemiological, health systems and laboratory investigations. We reflect here on the challenges inherent in conducting long distance cross-disciplinary collaborations, having now completed data and sample collection for a baseline situation analysis. In particular, we recognise the importance of investing in aspects such as effective communication, shared conceptual frameworks and leadership. We suggest that our experiences will be instructive to others planning to develop similar international One Health collaborations.
|
|
| 5. |
- Hansdotter, Frida I., et al.
(författare)
-
The incidence of acute gastrointestinal illness in Sweden
- 2015
-
Ingår i: Scandinavian Journal of Public Health. - : SAGE Publications. - 1651-1905 .- 1403-4948. ; 43:5, s. 540-547
-
Tidskriftsartikel (refereegranskat)abstract
- Aims: The aim of this study was to estimate the self-reported domestic incidence of acute gastrointestinal illness in the Swedish population irrespective of route of transmission or type of pathogen causing the disease. Previous studies in Sweden have primarily focused on incidence of acute gastrointestinal illness related to consumption of contaminated food and drinking water. Methods: In May 2009, we sent a questionnaire to 4000 randomly selected persons aged 0-85 years, asking about the number of episodes of stomach disease during the last 12 months. To validate the data on symptoms, we compared the study results with anonymous queries submitted to a Swedish medical website. Results: The response rate was 64%. We estimated that a total number of 2744,778 acute gastrointestinal illness episodes (95% confidence intervals 2475,641-3013,915) occurred between 1 May 2008 and 30 April 2009. Comparing the number of reported episodes with web queries indicated that the low number of episodes during the first 6 months was an effect of seasonality rather than recall bias. Further, the result of the recall bias analysis suggested that the survey captured approximately 65% of the true number of episodes among the respondents. Conclusions: The estimated number of Swedish acute gastrointestinal illness cases in this study is about five times higher than previous estimates. This study provides valuable information on the incidence of gastrointestinal symptoms in Sweden, irrespective of route of transmission, indicating a high burden of acute gastrointestinal illness, especially among children, and large societal costs, primarily due to production losses.
|
|
| 6. |
- Hulth, Anette, et al.
(författare)
-
A Study on Automatically Extracted Keywords in Text Categorization
- 2006
-
Ingår i: Proceedings of International Conference of Association for Computational Linguistics.
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a study on if and how automatically extractedkeywords can be used to improve text categorization. In summary weshow that a higher performance --- as measured by micro-averagedF-measure on a standard text categorization collection --- is achievedwhen the full-text representation is combined with the automaticallyextracted keywords. The combination is obtained by giving higherweights to words in the full-texts that are also extracted askeywords. We also present results for experiments in which thekeywords are the only input to the categorizer, either represented asunigrams or intact. Of these two experiments, the unigrams have thebest performance, although neither performs as well as headlines only.
|
|
| 7. |
- Hulth, Anette, et al.
(författare)
-
An Experimental Digital Library Platform - A Demonstrator Prototype for the DigLib Project at SICS
- 1999. - 1
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Within the framework of the Digital Library project at SICS, this thesis describes the implementation of a demonstrator prototype of a digital library (DigLib); an experimental platform integrating several functions in one common interface. It includes descriptions of the structure and formats of the digital library collection, the tailoring of the search engine Dienst, the construction of a keyword extraction tool, and the design and development of the interface. The platform was realised through sicsDAIS, an agent interaction and presentation system, and is to be used for testing and evaluating various tools for information seeking. The platform supports various user interaction strategies by providing: search in bibliographic records (Dienst); an index of keywords (the Keyword Extraction Function (KEF)); and browsing through the hierarchical structure of the collection. KEF was developed for this thesis work, and extracts and presents keywords from Swedish documents. Although based on a comparatively simple algorithm, KEF contributes by supplying a long-felt want in the area of Information Retrieval. Evaluations of the tasks and the interface still remain to be done, but the digital library is very much up and running. By implementing the platform through sicsDAIS, DigLib can deploy additional tools and search engines without interfering with already running modules. If wanted, agents providing other services than SICS can supply, can be plugged in.
|
|
| 8. |
- Hulth, Anette, et al.
(författare)
-
Automatic Keyword Extraction Using Domain Knowledge
- 2008. - 1
-
Ingår i: Computational Linguistics and Intelligent Text Processing. - Berlin / Heidelberg : Springer. - 9783540416876
-
Bokkapitel (refereegranskat)abstract
- Documents can be assigned keywords by frequency analysis of the terms found in the document text, which arguably is the primary source of knowledge about the document itself. By including a hierarchi- cally organised domain specific thesaurus as a second knowledge source the quality of such keywords was improved considerably, as measured by match to previously manually assigned keywords. In the presented ex- periment, the combination of the evidence from frequency analysis and the hierarchically organised thesaurus was done using inductive logic programming.
|
|
| 9. |
|
|
| 10. |
- Hulth, Anette, 1968-
(författare)
-
Combining Machine Learning and Natural Language Processing for Automatic Keyword Extraction
- 2004
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Automatic keyword extraction is the task of automatically selecting a small set of terms describing the content of a single document. That a keyword is extracted means that it is present verbatim in the document to which it is assigned. This dissertation discusses the development of an algorithm for automatic keyword extraction, and presents a number of experiments, in which the performance of the algorithm is incrementally improved.The approach taken is that of supervised machine learning, that is, prediction models are constructed from documents with known keywords. Before any learning can take place, the data must be pre-processed and represented. In the presented research, two problems concerning the representation for keyword extraction are tackled. Since a keyword may consist of more than one token, the first problem concerns where a keyword begins and ends in a running text, that is, how a candidate term is defined. In this dissertation, three term selection approaches are defined and evaluated. The first approach extracts all uni-, bi-, and trigrams, the second approach extracts all noun phrase chunks, while the third approach extracts all terms matching any of a number of empirically defined part-of-speech patterns.Since the majority of the extracted candidate terms are not keywords, the second problem concerns how these terms can be limited, to only keep those that are appropriate as keywords. In the presented research, four features for filtering the candidate terms are investigated. These are term frequency, inverse document frequency, relative position of the first occurrence, and the part-of-speech tag or tags assigned to the candidate term.The research presented in this dissertation is linguistically oriented in the sense that the output from natural language processing tools is a considerable factor both for the pre-processing of the data, as well as for the performance of the prediction models. Of the three term selection approaches, the best individual performance ― as measured by keywords previously assigned by professional indexers ― is achieved by the noun phrase chunk approach. The part-of-speech tag feature dramatically improves the performance of the models, independently of which term selection approach is applied. The highest performance is, however, achieved when the predictions of all three models are combined.
|
|
