Trustworthiness and relevance in web-based clinical question answering.

Question answering systems try to give precise answers to a user's question posed in natural language. It is of utmost importance that the answers returned are relevant to the user's question. For clinical QA, the trustworthiness of answers is another important issue. Limiting the document collection to certified websites helps to improve the trustworthiness of answers. On the other hand, limited document collections are known to harm the relevancy of answers. We show, however, in a comparative evaluation, that promoting trustworthiness has no negative effect on the relevance of the retrieved answers in our clinical QA system. On the contrary, the answers found are in general more relevant.

Results of the 10 HON survey on health and medical internet use.

The Internet is increasingly being used as a means to search and communicate health information. As the mission of Health on the Net Foundation (HON) is to guide healthcare consumers and professionals to trustworthy online information, we have been interested in seeing the trend of the attitudes towards Internet use for health purposes since 1996. This article presents the results of the 10th HON survey conducted in July-August 2010 (in English and French). It was hosted on the HON site with links from Facebook and Twitter and from HONcode certified web sites. There were 524 participants coming mainly from France (28%), the UK (18%) and the USA (18%). 65% of participants represented the "general public", while the remaining 35% were professionals. Information quality remains the main barrier users encounter while looking for health information online; at the same time, 79% believe they critically assess online content. Both patients and physicians consider the Internet to be helpful in facilitating their communication during consultations, although professionals are more sceptic than the general public. These results justify the continuing efforts of HON to raise public awareness regarding online health information and the ethical, quality and transparency issues, and to educate and guide users towards trustworthy health information.

Enriching the trustworthiness of health-related web pages.

We present an experimental mechanism for enriching web content with quality metadata. This mechanism is based on a simple and well-known initiative in the field of the health-related web, the HONcode. The Resource Description Framework (RDF) format and the Dublin Core Metadata Element Set were used to formalize these metadata. The model of trust proposed is based on a quality model for health-related web pages that has been tested in practice over a period of thirteen years. Our model has been explored in the context of a project to develop a research tool that automatically detects the occurrence of quality criteria in health-related web pages.

Supervised approach to recognize question type in a QA system for health.

Many attempts have been made in the QA domain but no system applicable to the field of health is currently available on the Internet. This paper describes a bilingual French/English question answering system adapted to the health domain and more particularly the detection of the question's model. Indeed, the Question Analyzer module for identifying the question's model has a greater effect on the rest of the QA system. Our original hypothesis for the QA is that a question can be defined by two criteria: type of answer expected and medical type. These two must appear in the step of detection of the model in order to better define the type of question and thus, the corresponding answer. For this, questions were searched on the Internet and then given to experts in order to obtain classifications according to criteria such as type of question and type of medical context as mentioned above. In addition, tests of supervised and non-supervised classification were made to determine features of questions. The result of this first step was that algorithms of classification were chosen. The results obtained showed that categorizers giving the best results were the SVM. Currently, for a set of 100 questions, 84 are well categorized in English and 68 in French according to the type of answer expected. This figures fall to less than 50% for the medical type. Evaluations have showed that the system was good to identify the type of answer expected and could be enhanced for the medical type. It leads us to use an external source of knowledge: UMLS. A future improvement will be the usage of UMLS semantic network to better categorize a query according to the medical domain.