Theresearchandapplicationofintelligentquestionansweringsysteminthefieldofbreastdiseasesimaging / 实用放射学杂志

Objective Tofacilitatetheradiologiststoinquireinformationrelatedtobreastdiseasesandimprovetheefficiencyand accuracyofsearchingdata.Methods Inthispaper,amultilevelstrategyhybridquestion-and-answermodelwasusedtodesignanautomatic question-and-answersysteminthefieldofbreastdiseasesimaging.Thefirstlayerofthismodelwasthequick matchingofquestion sentencesandFAQknowledgebase.Thesecondlayerwastoobtaintheanswersinthebasicknowledgebaseaccordingtothethresholdsetby processingthequestionsandcalculatingthesimilarityofthequestions.Thethirdlayerwastoacquiretheanswerparagraphfromthe webdocumentreturnedbythefull-textsearchengine.Results Thetestresultsshowedthattheaccuracyofthesystemansweracquisitionreached 85%.Thesystemcouldgivesatisfactoryanswerstotheproblemsexistingintheknowledgebase.Conclusion Theintelligentquestion answeringsystemforbreastdiseaseisconvenientandfast,anditisaneffectivetoolforradiologiststoinquiretheknowledgeofbreast diseases.

Mass spectrometry based proteomics profiling of human monocytes

Human monocyte is an important cell type which is involved in various complex human diseases. To better understand the biology of human monocytes and facilitate further studies, we developed the first comprehensive proteome knowledge base specifically for human monocytes by integrating both in vivo and in vitro datasets. The top 2000 expressed genes from in vitro datasets and 779 genes from in vivo experiments were integrated into this study. Altogether, a total of 2237 unique monocyte-expressed genes were cataloged. Biological functions of these monocyte-expressed genes were annotated and classified via Gene Ontology (GO) analysis. Furthermore, by extracting the overlapped genes from in vivo and in vitro datasets, a core gene list including 541 unique genes was generated. Based on the core gene list, further gene-disease associations, pathway and network analyses were performed. Data analyses based on multiple bioinformatics tools produced a large body of biologically meaningful information, and revealed a number of genes such as SAMHD1, G6PD, GPD2 and ENO1, which have been reported to be related to immune response, blood biology, bone remodeling, and cancer respectively. As a unique resource, this study can serve as a reference map for future in-depth research on monocytes biology and monocyte-involved human diseases.

Development of Renal Dosing System at a University Hospital / 대한의료정보학회지

OBJECTIVE: This report is describing the development and implementation process of the knowledge-based renal dose adjustment system at a university hospital. METHOD: From the hospital drug formulary which included about 1500 medications, clinical pharmacists selected 243 nephrotoxic medications which require dose adjustment in patients with renal impairment. Through literature review and consultation of clinical pharmacists, nephrologist, and infectious disease specialist, we developed an accordant renal dosing knowledge-base and used them to build the rules for dosage adjustment alerts and to provide information related to alerts such as patients' age, gender, most recent weight, latest serum creatinine, calculated creatinine clearance, and recommended dosage for renal insufficiency. STATUS REPORT: As of August 2006, the renal dosing system which monitored drug prescription and generated real-time alerting window to help physician to adjust drug doses in patients with renal impairment was implemented and has been operated well since initial implementation. CONCLUSION: Renal dosing system based upon knowledge-based renal dosing guideline was successfully developed and implemented into a local clinical practicesetting.

XPERNATO-TOX: an Integrated Toxicogenomics Knowledgebase

Toxicogenomics combines transcriptome, proteome and metabolome profiling with conventional toxicology to investigate the interaction between biological molecules and toxicant or environmental stress in disease caution. Toxicogenomics faces the problems of comparison and integration across different sources of data. Cause of unusual characteristics of toxicogenomic data, researcher should be assisted by data analysis and annotation for getting meaningful information. There are already existing repositories which claim to stand for toxicogenomics database. However, those just contain limited abilities for toxicogenomic research. For supporting toxicologist who comes up against toxicogenomic data flood, now we propose novel toxicogenomics knowledgebase system, XPERANTO-TOX. XPERANTO-TOX is an integrated system for toxicogenomic data management and analysis. It is composed of three distinct but closely connected parts. Firstly, Data Storage System is for reposit many kinds of '-omics' data and conventional toxicology data. Secondly, Data Analysis System consists of analytical modules for integrated toxicogenomics data. At last, Data Annotation System is for giving extensive insight of data to researcher.