Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µö·¯´× ±â¹Ý ÀÓ»ó °ü°è ÇнÀÀ» ÅëÇÑ Áúº´ ¿¹Ãø |
¿µ¹®Á¦¸ñ(English Title) |
Disease Prediction By Learning Clinical Concept Relations |
ÀúÀÚ(Author) |
Á¶½ÂÇö
ÀÌ°æ¼ø
Seung-Hyeon Jo
Kyung-Soon Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11 NO. 01 PP. 0035 ~ 0040 (2022. 01) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ÀÓ»ó ÀÇ»ç °áÁ¤ Áö¿øÀ» À§ÇÏ¿© ÀÇÇÐ Áö½ÄÀ» ÅëÇØ ÀÓ»ó °ü°è¸¦ ÃßÃâÇÏ°í µö·¯´× ¸ðµ¨À» ÀÌ¿ëÇÏ¿© Áúº´À» ¿¹ÃøÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÀÇÇÐ »çÀüÀÎ UMLS(Unified Medical Language System)¿Í ¾Ï °ü·Ã ÀÇÇÐ Áö½Ä¿¡ Æ÷ÇÔµÈ ÀÓ»ó ¿ë¾î¸¦ 5°¡Áö·Î ºÐ·ùÇÑ´Ù. ºÐ·ùµÈ ÀÓ»ó ¿ë¾îµéÀ» »ç¿ëÇÏ¿© À§Å°Çǵð¾Æ ÀÇÇÐ ¹®¼¸¦ ÃßÃâÇÑ´Ù. ÃßÃâÇÑ À§Å°Çǵð¾Æ ÀÇÇÐ ¹®¼¿Í ÃßÃâÇÑ ÀÓ»ó ¿ë¾î¸¦ ¸ÅĪÇÏ¿© ÀÓ»ó °ü°è¸¦ ±¸ÃàÇÑ´Ù. ±¸ÃàÇÑ ÀÓ»ó °ü°è¸¦ ÀÌ¿ëÇÏ¿© µö·¯´× ÇнÀÀ» ÁøÇàÇÑ ÈÄ ÁúÀÇ¿¡¼ Ç¥ÇöµÈ ÀÇÇÐ ¿ë¾î¸¦ ¹ÙÅÁÀ¸·Î ÁúÀÇ¿Í ¿¬°üµÈ Áúº´À» ¿¹ÃøÇÑ´Ù. ÀÌÈÄ, ¿¹ÃøÇÑ Áúº´°ú °ü°è°¡ ÀÖ´Â ÀÇÇÐ ¿ë¾î¸¦ È®Àå ÁúÀÇ·Î ¼±ÅÃÇÑ µÚ ÁúÀǸ¦ È®ÀåÇÑ´Ù. Á¦¾È ¹æ¹ýÀÇ À¯È¿¼ºÀ» °ËÁõÇϱâ À§ÇØ TREC Clinical Decision Support(CDS), TREC Precision Medicine(PM) Å×½ºÆ® Ä÷º¼Ç¿¡ ´ëÇØ ºñ±³ Æò°¡ÇÑ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases based on a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-related medical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinical terms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medical terms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, we have experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections. |
Å°¿öµå(Keyword) |
ÀÓ»ó ÀÇ»ç °áÁ¤ Áö¿ø
ÀÓ»ó °ü°è
µö·¯´×
Áúº´ ¿¹Ãø
ÁúÀÇ È®Àå
Cninical Decision Support
Clinical Concept Relation
Deep Learning
Disaese Prediction
Query Expansion
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|