-
[show abstract]
[hide abstract]
ABSTRACT: The Internet has become one of the most important means to obtain health and medical information. It is often the first step in checking for basic information about a disease and its treatment. The search results are often useful to general users. Various search engines such as Google, Yahoo!, Bing, and Ask.com can play an important role in obtaining medical information for both medical professionals and lay people. However, the usability and effectiveness of various search engines for medical information have not been comprehensively compared and evaluated.
To compare major Internet search engines in their usability of obtaining medical and health information.
We applied usability testing as a software engineering technique and a standard industry practice to compare the four major search engines (Google, Yahoo!, Bing, and Ask.com) in obtaining health and medical information. For this purpose, we searched the keyword breast cancer in Google, Yahoo!, Bing, and Ask.com and saved the results of the top 200 links from each search engine. We combined nonredundant links from the four search engines and gave them to volunteer users in an alphabetical order. The volunteer users evaluated the websites and scored each website from 0 to 10 (lowest to highest) based on the usefulness of the content relevant to breast cancer. A medical expert identified six well-known websites related to breast cancer in advance as standards. We also used five keywords associated with breast cancer defined in the latest release of Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) and analyzed their occurrence in the websites.
Each search engine provided rich information related to breast cancer in the search results. All six standard websites were among the top 30 in search results of all four search engines. Google had the best search validity (in terms of whether a website could be opened), followed by Bing, Ask.com, and Yahoo!. The search results highly overlapped between the search engines, and the overlap between any two search engines was about half or more. On the other hand, each search engine emphasized various types of content differently. In terms of user satisfaction analysis, volunteer users scored Bing the highest for its usefulness, followed by Yahoo!, Google, and Ask.com.
Google, Yahoo!, Bing, and Ask.com are by and large effective search engines for helping lay users get health and medical information. Nevertheless, the current ranking methods have some pitfalls and there is room for improvement to help users get more accurate and useful information. We suggest that search engine users explore multiple search engines to search different types of health information and medical knowledge for their own needs and get a professional consultation if necessary.
Journal of Medical Internet Research 01/2012; 14(3):e74. · 4.41 Impact Factor
-
Proceedings of the ISCA 3rd International Conference on Bioinformatics and Computational Biology, BICoB-2011, March 23-25, 2011, Holiday Inn Downtown-Superdome, New Orleans, Louisiana, USA; 01/2011
-
[show abstract]
[hide abstract]
ABSTRACT: Identifying genes with essential roles in resisting environmental stress rates high in agronomic importance. Although massive DNA microarray gene expression data have been generated for plants, current computational approaches underutilize these data for studying genotype-trait relationships. Some advanced gene identification methods have been explored for human diseases, but typically these methods have not been converted into publicly available software tools and cannot be applied to plants for identifying genes with agronomic traits.
In this study, we used 22 sets of Arabidopsis thaliana gene expression data from GEO to predict the key genes involved in water tolerance. We applied an SVM-RFE (Support Vector Machine-Recursive Feature Elimination) feature selection method for the prediction. To address small sample sizes, we developed a modified approach for SVM-RFE by using bootstrapping and leave-one-out cross-validation. We also expanded our study to predict genes involved in water susceptibility.
We analyzed the top 10 genes predicted to be involved in water tolerance. Seven of them are connected to known biological processes in drought resistance. We also analyzed the top 100 genes in terms of their biological functions. Our study shows that the SVM-RFE method is a highly promising method in analyzing plant microarray data for studying genotype-phenotype relationships. The software is freely available with source code at http://ccst.jlu.edu.cn/JCSB/RFET/.
PLoS ONE 01/2011; 6(7):e21750. · 4.09 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: More and more people use internet search engines, especially Google, to learn about diseases and possible treatments. We conducted a hallway testing to evaluate the effectiveness of Google in obtaining medical information. We searched 'Breast Cancer' using Google. Six volunteers scored their experience for each of the top 500 websites. Our study shows that 50 hits of Google often help lay users in getting medical information, but some highly useful websites may be buried beyond top 200. Hence, the specificity of using Google in searching for medical information is satisfactory while the sensitivity of the search has significant room for improvement.
International Journal of Data Mining and Bioinformatics 01/2011; 5(6):626-39. · 0.43 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: MicroRNA is a type of small non-coding RNAs, which usually has a stem-loop structure. As an important stage of microRNA, the pre-microRNA is transported from nuclear to cytoplasm by exportin5 and finally cleaved into mature microRNA. Structure-sequence features and minimum of free energy of secondary structure have been used for predicting pre-microRNA. Meanwhile, the double helix structure with free nucleotides and base-pairing features is used to identify pre-miRNA for the first time.
We applied support vector machine for a novel hybrid coding scheme using left-triplet method, the free nucleotides, the minimum of free energy of secondary structure and base-pairings features. Data sets of human pre-microRNA, other 11 species and the latest pre-microRNA sequences were used for testing.
In this study we developed an improved method for pre-microRNA prediction using a combination of various features and a web server called PMirP. The prediction specificity and sensitivity for real and pseudo human pre-microRNAs are as high as 98.4% and 94.9%, respectively. The web server is freely available to the public at http://ccst.jlu.edu.cn/ci/bioinformatics/MiRNA (accessed: 26 February 2010).
Experimental results show that the proposed method improves the prediction efficiency and accuracy over existing methods. In addition, the PMirP has lower computational complexity and higher throughput prediction capacity than Mipred web server.
Artificial intelligence in medicine 06/2010; 49(2):127-32. · 1.65 Impact Factor
