IL) OPc /K44*K 92.4M,*,*+7140L Cz{_a]y H6/2*K3*-7*Nl
9
0
0
全文
(2)
(3) .
(4) . . . ! "#$%&'(&)*+',. .
(5) ! " # $ % & ' ( )*+,-./0-.1/2/345-2 )4-36/7.45 )*5474/68900/+.8:7.*,;< =>?@ABCDECFG HI*6*+-24J*KL247.*+463)47*-7*7MIL)N OPQRSTUV W6.*+6*. XY Z[\C] ^^^ _`abcde fghijk$ W6.*+6*. _bcl mnopqrstuvXwxT $V=> tyz{|x}m ~C IL) OPc /K44*K 92.4M,*,*+7140L-:*74-6 /+,92-.4/6 |Cz{_a]y H6/2*K3*-7*Nl g c H6/2*K3* 6346**+463N%OPy T ( ¡¢=> ty£¤¥;¦§ ¥ ¨©! ªT «(!" ¬(®¯°a± ^^^ e ²³e ´qrH8:7.*,81*22Nµe´qr¡¢ z{¶·¸bcde ¹º»¼½( ® ¾%±¿ÀÁ¸ q. r«ÃÄÅÆÇÈÉqÊËÌÍÎT %yÏ IL) OPÐ Ñ(Ò '( L-:*74-6 Ó²H +-,*N _ÔlÑ(Ó²Õ$Ò Ö ×H 46K4637NØÅÇ©~Ñ(Ó² Ù0+4/+4¸Ñ(Ö× Ú+9*Û/74.4Ü* Ý-.*HÚÛÝNÞ -27*Û/74.4Ü*Ý-.*H ÛÝN $ ªßàá{]=> ty £¤âã¥äÕ_%&å Ö×ÞÙ0+4/+4ÞÚÛÝÞ ÛÝÇæyç èéêëìíîïXâã; <XÄ«CðñC ÄÅÆòómô=> ty£¤; <fjhõöC÷øù )*2014,*.1/K úÅûôXðñü{T ýþyçèé}a tá{ ]cËÌ Ç Q Æ
(6) T L-:*74-6 /+,92-.4/6 |Cz {Ï © Ñ(Ó²Ð Ö ×X¾ Ö× &H5/6K4.4/6 46K*0*6K*6.Nqràîï Ö × | z Î Y H/Ü*+5/64K*65*N !"Õ@Ö ×&H6/6M46K*0*6K*65*NÖ× \¦«ÚÛݸ ÛÝQY Æ|!CT. 1 9 .
(7) (qrû% (Ô In recent "information explosion" IL) OPÒ Ó²¿ÀÁÂûh decades, it is difficult for practicing (Ö×þÒ ÷øÑ(Ó² h physicians to keep up with all the (Ô¥ y !"# t information for making optimal clinical yÏ Ö×û $ (ÔÙ0+4/+4Þ judgements. This project tried to build a ÚÛÝÞ ÛÝ |âãT dermatopathological decision support system æyçèé\% &' ( t to help physicians make optimal clinical QËÌ ( & (ËÌ decisions. ] jÒ |!±_) In light of the uncertainty involved in bm qr (Ò ÷øl ( the dermatopathological reasoning process, Ò *+ qrg!± we proposed a probabilistic knowledge , º¼(-+jÒ ì¸!" representation under the scope of => ty£¤.(qr/Ãjc "non-infectious generalized blistering CT diseases". In order to create the knowledge % *M-7*Ke´qrRS base, we employed a technique called 01qrh÷23HN môsP4 “knowledge engineering”. This knowledge 5bcdjô 67ô'y engineering process involved one 89mô¤y£¤jûôà dermatopathological expert, one coordinator o%ô'qrTH&N:;<=º} and one knowledge engineer. This group W6.*+6*.Ç>h^^^?@AB met every two weeks during a six-month CDjbc qrÇmEFGH period to build up a data dictionary and IþJKLMNTHONmôy?POP knowledge base. Programming engineers 5QyRûô%K ô'q developed the inference engine and user rQ 9y?POPRS0 interface in a web-based architecture. 1¸SycTT Vigorous evaluation process was performed !"%K|Cz{ *M-7*K after all the parts of the system were put => ty01qrU R together. Both theoretical performance S01¸SycThgV<XG indices (including accuracy, reliability and a(yOP discriminating power) and clinical RhWXY.]_a performance are to be tested. Published =>? Ü4K*65*ML-7*K*K4546*,] CPC (clinical-pathologic conference) cases hg<ZT and patient charts will be used in the final evaluation. [=> tyRS01qr£ This prototype knowledge base ¤qr|Cz{y represents 11 disease frames with 88 findings T in the data dictionary. Each disease frame Abstract. consists of 5~10 findings, which represent clinical, light microscopic and immunopathologic clues to diagnose a 2 9 .
(8) disease. There are several benefits with the web-based system shell and the user interface. First, multiple users in different geographical areas can update the knowledge base in the same time, so that international cooperation is feasible. Second, those who like to use the system need only a connection to the Internet to do so. No additional software should be sent or installed. Third, multiple knowledge bases in different medical domains can be incorporated to the system for cross-domain diagnostic decision support and clinical teaching. This project proposes to apply probabilistic reasoning to a web-based dermatopathological diagnostic decision support system. The system can be useful in both clinical teaching and diagnostic decision support. In the process of knowledge engineering, we also felt that the domain medical knowledge was better clarified and may contribute to the future of evidence-based medicine in dermatology. Keywords: dermatopathological, decision support system, expert system, probabilistic inference, knowledge engineering, medical knowledge base.
(9) . \]X^æ_ o `abc]dgyy c }ef ghi jÌklÆmnopqrsS ?tgyuívwxyy
(10) z¸gy{|iah. }~T]RS01qr yoSy Xcb( ýgs ¥gy ¥ XGW5 yy|àT ùqr \~¥Ò Æj }ʱågEíUP XÒ QÒ gEíÖ ×fy
(11) RQD C uí¸yy \Ö×! mô|ÆjpqztÉ 3Çpqu ívwTÉ yymxj jÌklBCyyj dóSS g R ¡¢£¤¥¦yyT §l¬yRS01qrL N¨©gaªoqr«mîô j «+|¨ ¬64 qrþ ( ®ho¯°±²qrga QLN³ môMNä´m îµ¹¶·¸¹V(yRS01q rhº»m¼½3dd: a qry¨aacs 2 ¾ à o a b c 9 ý à o H92.4M5*6.*+N y R S0 1 q r]d: ¿ÀÁÂþf « +à ~( qr }ÄÉ ¨%K ÅÅÆ ^* e ]j ÇÈdyRS01qr%K¸ bc} ¾¥st¥LMNBC¹QQ wx:bcdR=} W6.*+6*.D jc( ù ^* ?@Abcy RS01qrmò ¬efHI ÉÊLN¦«©<TËk$ W6.*+6*. ¿ À ª ¥ H6/2*K3**6346**+N¸y?POP £¤HK/,-46*0*+.Nj môsÏûô Äŵ!"DÌÍgh¸£¤ij. 3 9 .
(12) k$ W6.*+6*. _bcµqrò}c W6.*+6*.ÎÏÐÑàöqr%&9ý Ãoqr]byRS01qr Xa¸bcWmnopqr ¾s tuvXwxaÒ( ¥[ H94Ó94./97NX3jfqrºn9ý OP£¤;<ËÌbcaÒ «Ô ÕT Ö¥ ×%=>?@ABCDECFG yRS01qr(ØÙ j Ú ÛÜ H6/2*K3* Ý*0+*7*6.-.4/6N X % & Û&Ü^*M-7*K e´qrHÝz{¶·bcde ¨N X % & ÛOÜ H6/2*K3* 6346**+463NXH6/2*K3* L-7*NX%&ÛÞÜ6/2*K3*ß-24K-.4/6 8:7.*,Ü-29-.4/6TµàØÙá[ ÛÜ H6/2*K3* Ý*0+*7*6.-.4/6NX%&[ R~'(yRS 0 1 q r X ² ³â ¡ ¢ H6/2*K3*6346**+463NÏ¥ H6/2*K3* L-7*N ü ³ z { ¶ · HW6*+*65* 6346*N ã H-23/+4.1,N T | ¨ HÛ+/-4247.45 W6*+*65*Ncc|_ m~CH965*+.-46.:NÇcc| yâyϨ_!z{üäj Ä«súz{m~CÇ#$| t{åæs ,-64092-.* åm~CT ( ))8 X¿ÀdcXϨç è~tHL-:*74-6/+,92-.4/6Ná¨é ¨çè~tH84,02*L-:*7N5ê¨çè ~tH,92.4M,*,*+7140L-:*7N¼. \ Ï ± X ç è Å Æ HL-:*74-6 ë*./+7NÕ üÃ|yìy| CT P ( Di | S ) =. P (S | Di ) × P (Di ) ∑ (P ( S | Di) × P ( Di )) i. hUV|C y} XícCc$ ^-+6*+*.-2îgaX /K44*K 92.4M,*,*+7140 L-:*74-6 /+,92-.4/6 _a qrTµ X23¡¢[-Nj¥tï5ð Nj¥tï¾ðHW6.*+,*K4-.* )4-36/747N5N|xo L-:*74-6ë*./+ µ¼( j Ãtñò ¾Ðz ±îïXUPT Û&Ü^*M-7*K e´qrHÝz{¶·b cde ¨NX%&[ z{¶·HW6*+*65*6346*N}b cde ¨H¬7*+W6.*+-5*N'å6 7 X ; ¨ó ô e ´ q r H8:7.*,81*22Nµe´qrX%&, % qrmjþ½XØÙT z{¶·]õögcX /K44*K 92.4M,*,*+7140 L-:*74-6 /+,92-.4/6 ã_%&fbcd÷ø ¿ÀñùüäXbcde ¨ ! " c W6.*+6*. ^^^úûe ü< V ( o ý þ X ì + bc d e W6.*+6*. a ¾¥sPC3Ï 9ý9?POPbcdXªoTbc dù ^^^ ?@Aæ W6.*+6*. }Èø qr ^^^ Å3" Æ^^^ ?@A) Éù /,,/6I-.*-:W6.*+-5*HIWN |xe _[\ ^^^ A} lga± *M-7*Ke´qrÔ h 3 2 3 [ ¥ [ H 94Ó94./97 N ú û C H 46.*+-5.4Ü* N 5 ô [ \. 4 9 .
(13) H 5/659++*6. N µ ¼ W H*-7:M./M90K-.* N « N ê ë H5/22*5.4Ü*2:7*-+51-2*NT ÛOÜH6/2*K3*6346**+463NX H6/2*K3*L-7*NX%&[ «(yRS01qrqr % & X ¹ H6/2*K3* Ù5Ó9474.4/6N]à X T]yH6/2*K3*. 8:7.*,Ü-29-.4/6 Ï
(14) ^*M-7*K e´qrÄÅÈÉ ¨ 8:7.*,Ü-29-.4/6 6/2*K3* Ü-24K-.4/6 X¿Àâ ýþyç èé}a tá{ ] cËÌ Ç Q Æ
(15) T !] O o ËÌ
(16) H.*7.5-7*7N£¤( ºsã_ÍÎ . îÄÅXã[ Q X | C z { | x c /K44*K 92.4M,*,*+7140 L-:*74-6 /+,92-.4/6 |Cz{_ a]yH6/2*K3* -7*N l g c H6/2*K3*6346**+463N% OPyT &îÄÅX W6.*+6*.^*M-7*K | Cz{¶·e´qr[E°h W6.*+6*. ^*M-7*K e´qrÏ`ÎÏ °ÄÅ-+Xe´qr w¨TH 439+*MÞN . -7*Nlgcô” ” ( ¡¢=> ty£¤¥;¦§ ¥ ¨©! ªT|C qrljccQÏ [ HN 9,-6 )/,-46 0*+. H&N 4.*+-.9+* 7*-+51 HON24645-2 K-.--7*7HÞN)*2014,*.1/KT %yÏ IL) OPÐ Ñ(Ò '( L-:*74-6 Ó²H +-,*N _ÔlÑ(Ó²Õ$Ò Ö ×H 46K4637NØÅÇ©~Ñ(Ó² Ù0+4/+4¸Ñ(Ö× Ú+9*Û/74.4Ü* Ý-.*HÚÛÝNÞ -27*Û/74.4Ü*Ý-.*H ÛÝN $ ªßàá{]=> ty £¤âã¥äÕ_%&å Ö×ÞÙ0+4/+4ÞÚÛÝÞ ÛÝÇæyç èéêëìíîïXâã; <XÄ«CðñC ÄÅÆ]òómô=> ty£¤; <fjhõöC÷øù )*2014,*.1/K úÅûôXðñü{T ýþyçèé}a tá{ ]cËÌ Ç Q Æ
(17) T ÛÞÜ6/2*K3* ß-24K-.4/6 8:7.*, Ü-29-.4/6[ 439+*î 5 9 . .
(18) 439+*&î . 439+*Oî . 439+*Þî
(19) OîÄÅXX%&[ L-:*74-6 /+,92-.4/6 |Cz{. Ï © Ñ(Ó²Ð Ö × X ¾ Ö × & H5/6K4.4/6 46K*0*6K*6.Nqràîï Ö × | z Î Y H/Ü*+5/64K*65*N !"Õ@Ö ×&H6/6M46K*0*6K*65*NÖ× \¦«ÚÛݸ ÛÝQY Æ|!CT ¼½(® ¾%±¿ÀÁ¸ (qrû% (Ô IL) OPÒ Ó²¿ÀÁÂûh (Ö×þÒ ÷øÑ(Ó² h (Ô¥ y !"# t y Ï Ö × û $ ( Ô Ù0+4/+4ÞÚÛÝÞ ÛÝ |âãT . !"V< hD. Cí¸y¸u ívwyyhgD C Vky V ~uí ¨ `pQ( !S"`#(u ívw$ XS"cTT % *M-7*Ke´qrRS 01qrh÷23HN môsP4 5bcdjô 67ô'y 89mô¤y£¤jûôà o%ô'qrTH&N:;<=º} W6.*+6*.Ç>h^^^?@AB CDjbc qrÇmEFGH IþJKLMNTHONmôy?POP 5QyRûô%K ô'q rQ 9y?POPRS0 1¸SycTTc ^* e ¸ÅÆ ojô êë¥%& gh¿ÀT:ícVô' '(yRS01qr. 6 9 .
(20) Dj%K 9y?Pô'q r } a Ò « N ê ë H5/22*5.4Ü*2: 7*-+51-2*N3lQ ô êëgh ?PÔ] h WD Cí¸T !"%K|Cz{ *M-7*K => ty01qrU R S01¸SycThgV<XG a(yOP RhWXY.]_a =>? Ü4K*65*ML-7*K*K4546*,] hg<ZT !"#$. ÐG»)=>?îïyçèé. \îïÒ X t *+ & ,û &' ÈÉÅÕÍÎÑÚPD ¥ y !"# tg UP Ô]ï-.÷ø%&!± jÒ |Tüäh & k !g% X j//Ã- èéXT)bm qr (Ò ÷øl (*+HÜ-+4-6.Nk$ qrg!±, º¼(+jÒ T0G O XËÌüäg !± Y|Ò 1@/ÃèéXx2]èéX Ê g!± jX34©T 5ËÌl6(7Cú & Ã&'H'8NTì ¸!"=> ty£¤.(qr/ ÃjcCTHÚ-2*N.
(21) . . . . . ! !" !#. . $. . . . . . . . . . . $. . . %. . . . . . . . . . %. . . . &. . . . . . . . . &. *+,- ./ . . . . &. . . . . . . . &. . . . . &. . . . . . . &. . . . . . '. . . . . . '. . . . . . . . . . . . . (. !. &. . . . &. . . ). . . . %. !". . . . . . . . . '. . . '. . . . . . . . . . . &. . &. !#. . . &. . . . . . . . . &. Total. '0. Accuracy value = 25 / 28 = 89.29% 1234&56&75
(22) 6'75
(23)
(24) 6875 6)7 5 697 5 6%7
(25) 5
(26) 6$7 5 ! 607 5 " 6:75 " # 6&(75$ ! 6&&75" % % . %. &'(. 1. Shortliffe EH, Perreault EL (eds), Fagan 7 9 .
(27) LM, Wiederhold G (assoc eds). Medical informatics: computer applications in health care. Addison-Wesley, Reading, Massachusetts, 1990. 2. Homer R. Warner, Dean K. Sorenson, Omar Bouhaddou, Knowledge Engineering in Health Informatics, 1997 Springer-Verlag New York. Inc. 3. Sox HC, Blatt MA, Higgins MC, Marton KI. Medical decision making. Butterworth-Heinemann, Boston. 1988. 4. Patrice Degoulet, Marius Fieschi, Introduction to clinical Informatics, 1997 Springer-Verlag New York. Inc. 5. Eta S. Berner Editor, Clinical Decision Support Systems Theory and Practice, 1999 Springer-Verlag New York. Inc 6. J. Van Bemmel, Mark A. Musen, Handbook of Medical Informatics, 1997, Springer Verlag. 7. Randolph A. Miller, M.D., Medical Diagnostic Decision Support Systems Past, Present, and Future: A Threaded Bibliography and Brief Commentary, JAMIA, 1(1):8-27, 1994 8. Li YC, Haug PJ. Evaluation of the quality of a probabilistic diagnostic system using different inferencing strategies. Proceedings of the 17th Symposium on Computer Applications in Medical Care, Washington DC, 1993:471-77 9. Camma C. Garofalo G. Almasio P. Tine F. Craxi A. Palazzo U. Pinzello G. Fiorello F. Angelo PM. Pagliaro L. A performance evaluation of the expert system 'Jaundice' in comparison with that of three hepatologists. Journal of Hepatology. 13(3):279-85, 1991 Nov. . 10. Warner HR, Toronto AF, Veasey LG.,. Stephenson RA. Mathematical approach to medical diagnosis. JAMA. 1961;177:75-81. 11. Warner HR, Toronto AF, Veasy LG. Experience with Bayes' theorem for computer diagnosis of congenital heart disease. Ann N.Y. Acad Sci 1964; 115:558-67. 12. Warner HR, Olmsted CM, Rutherford BD. HELP - A program for medical decision making. Comp Biomed Res 1972; 5:65-74. 13. Warner HR Jr. Iliad - Moving medical decision-making into new frontiers. In: Proceedings of International Symposium of Medical Informatics and Education. Salamon R, Protti D, Moehr J. eds. University of Victoria, B.C., Canada, 1989:267-70. 14. Miller RA. Pople HEJ, Myers JD. Internist-I: An experimental computer-based diagnostic consultation for general internal medicine. N Engl J Med 1982;307:468-76. 15. Barnett GO, Cimino JJ, Hupp JA, Hoffer EP. Dxplan: An evolving diagnostic decision-support system. JAMA 1987;258:67-74. 16. Bankowiz RA, McNeil MA, Challinor SM, Parker RC, Kapoor WN, Miller RA. A computer-assisted medical diagnostic consultation service - implementation and prospective evaluation of a prototype. Ann Int Med 1989; 110:824-32. 17. Ben-Bassat M. Multimembership and multiperspective classification: introduction, applications, and a Bayesian model. IEEE Trans Syst Man Cybern. SMC-ID 6. 1980;331-6.. 8 9 .
(28) 18. Chang PL, Li YC, WU CJ, Huang MH, 26. Reed M. Gardner, PhD, Henry P Haug PJ. Clinical evaluation of a renal Lundsgaarde, PhD, Evaluation of User mass diagnosis expert system. Computer Acceptance of a Clinical Expert System, in Biology and Medicine. JAMIA, 1(6), pp. 428-438. 1994(24):315-22. 27. Eric L. Eisenstein, M.B.A., Farrokh 19. Chang PL, Li YC, WU CJ, Huang MH. Alemi, Ph.D, An Evaulation of Factors Using Iliad system shell to create an Influencing Bayesian Learning Systems, expert system for differential diagnosis of JAMIA, 1(3), pp. 272-284. renal masses. Journal of Medical Systems. 1993(17):289-97. 20. Chang PL, Li YC, Huang, Wang TM and Hsieh ML. The effects of a medical expert system on differential diagnosis of renal masses: A prospective study. Comput Med Imag Graph (1996). 21. Yu-Chuan Li , Finding Medical Resources on the Internet , Yearbook of Medical Informatics 98 ; 108-112. 22. Anderson MF. Moazamipour H. Hudson DL. Cohen ME. The role of the Internet in medical decision making. International Journal of Medical Informatics. 47(1-2):43-9, 1997 Nov. 23. Jacobs RA. Tanner MA. Peng F. Bayesian inference for hierarchical mixtures-of-experts with applications to regression and classification. Statistical Methods in Medical Research. 5(4):375-90, 1996 Dec. 24. Zelic I. Kononenko I. Lavrac N. Vuga V. Induction of decision trees and Bayesian classification applied to diagnosis of sport injuries. Journal of Medical Systems. 21(6):429-44, 1997 Dec. 25. Eta S. Berner, EdD, James R. Jackson, PhD, James Algina, PhD, Relationships among Performance Scores of Four Diagnostic Decision Support Systems, JAMIA,3(3), pp. 208-215. 9 9 .
(29)
相關文件
Because both sets R m and L h i ði ¼ 1; 2; :::; JÞÞ are second-order regular, similar to [19, Theorem 3.86], we state in the following theorem that there is no gap between
We compare the results of analytical and numerical studies of lattice 2D quantum gravity, where the internal quantum metric is described by random (dynamical)
At least one can show that such operators has real eigenvalues for W 0 . Æ OK. we did it... For the Virasoro
Total energies and Cartesian coordinates for the lowest singlet and triplet states of n-acenes (n = 2 to 46) by spin-unrestricted TAO-LDA (θ = 7 mHartree)/6-31G ∗ (S3 to S88)..
where L is lower triangular and U is upper triangular, then the operation counts can be reduced to O(2n 2 )!.. The results are shown in the following table... 113) in
[7] C-K Lin, and L-S Lee, “Improved spontaneous Mandarin speech recognition by disfluency interruption point (IP) detection using prosodic features,” in Proc. “ Speech
• involves teaching how to connect the sounds with letters or groups of letters (e.g., the sound /k/ can be represented by c, k, ck or ch spellings) and teaching students to
For a 4-connected plane triangulation G with at least four exterior vertices, the size of the grid can be reduced to (n/2 − 1) × (n/2) [13], [24], which is optimal in the sense
