ONCOCIN: An Expert System for Oncology Protocol Management

We d e s c r i b e an oncology p r o t o c o l management system, named ONCOCIN, t h a t is designed to a s s i s t p h y s i c i a n s i n the t r e a t m e n t o f cancer p a t i e n t s . The system is a c t u a l l y a se t of programs, one of which is a r u l e b a s e d reasoner t h a t encompasses the necessary knowledge of cancer chemotherapy. Represen ta t i on and c o n t r o l t echn iques are d i s c u s s e d , and ONCOCIN is c o n t r a s t e d w i t h systems t h a t cou ld be b u i l t u s i ng EMYCIN. Of p a r t i c u l a r i n t e r e s t is the need to p r o v i d e ONCOCIN w i t h an i n t e r f a c e t h a t w i l l make the system accep tab le t o o n c o l o g i s t s . I I n t r o d u c t i o n Th i s r e p o r t d e s c r i b e s an oncology p r o t o c o l management sys tem, named ONCOCIN a f t e r i t s domain o f e x p e r t i s e (cancer t h e r a p y ) and i t s h i s t o r i c a l debt to MYCIN [ 5 ] . The program c o n s i s t s of a se t o f i n t e r r e l a t e d subsystems, the p r i n c i p a l ones b e i n g : (1 ) the Reasoner, a r u l e b a s e d e x p e r t c o n s u l t a n t t h a t i s t he core o f the system and the major s u b j e c t o f t h i s r e p o r t ; and (2) the I n t e r v i e w e r , an i n t e r f a c e program t h a t c o n t r o l s a h igh-speed t e r m i n a l and the i n t e r a c t i o n w i t h the p h y s i c i a n s u s i n g the sys tem. Work on ONCOCIN began in m id -1979 , and the system was i n s t a l l e d f o r p r e l i m i a n r y use in May 1981. Th is paper d e s c r i b e s o n l y the Reasoner, a l t hough o the r system components are ment ioned when t h e i r i n t e r f a c e w i t h the Reasoner is p e r t i n e n t . We a l s o c o n t r a s t ONCOCIN w i t h EMYCIN [ 8 ] , e x p l a i n i n g why the EMYCIN fo rma l i sm was inadequate f o r our purposes a l t hough i t d i d s t r o n g l y i n f l u e n c e the sys tem 's r u l e -based d e s i g n . I I Overview of t he Problem Domain ONCOCIN i s des igned t o a s s i s t c l i n i c a l -------------------------------------------------Th i s work was suppor ted by the N a t i o n a l L i b r a r y of Medic ine under Program P r o j e c t Grant LM03395 and resea rch career development award LM00048. The program was developed on the SUMEX Computer P r o j e c t a t S t a n f o r d U n i v e r s i t y , a shared n a t i o n a l resource suppor ted by the B io techno logy Resources Program of the NIH under g r a n t RR-00785. o n c o l o g i s t s i n the t r e a t m e n t o f cancer p a t i e n t s . Because the op t ima l the rapy f o r most cancers is not y e t known, c l i n i c a l oncology research i s commonly based on fo rma l exper iments t h a t compare the t h e r a p e u t i c b e n e f i t s and s i de e f f e c t s ( t o x i c i t y ) o f proposed a l t e r n a t i v e d isease t r e a t m e n t s . "Cancer" is a genera l term f o r many d iseases hav ing d i f f e r e n t prognoses and n a t u r a l h i s t o r i e s . A t r e a t m e n t t h a t is e f f e c t i v e a g a i n s t one tumor may be i n e f f e c t i v e a g a i n s t a n o t h e r . Thus a t y p i c a l cancer research cen te r may conduct many s imu l taneous expe r imen ts , each concerned w i t h a d i f f e r e n t k i n d o f cancer and i t s o p t i m a l the rapy ( i . e . , the t r ea tmen t p lan w i t h the best chance o f c u r e , r e m i s s i o n , o r r e d u c t i o n i n tumor s i z e , and the l e a s t chance o f s e r i o u s s i de e f f e c t s ) . Each of these exper iments is termed a " p r o t o c o l " . P a t i e n t s w i t h tumors o f t he type be ing s t u d i e d , and who are accepted f o r p r o t o c o l t r e a t m e n t , are randomly ass igned to r e c e i v e one o f two or more p o s s i b l e t r e a t m e n t s . The exper iment r e q u i r e s c l ose m o n i t o r i n g o f each p a t i e n t ' s c l i n i c a l response and t r e a t m e n t t o x i c i t y . These data are t a l l i e d f o r a l l p a t i e n t s t r e a t e d under the a l t e r n a t i v e reg imens, and in t h i s way the " s t a t e o f t h e a r t " i s updated over t i m e . Each p r o t o c o l i s d e s c r i b e d in a d e t a i l e d document, o f t e n 40 to 60 pages in l e n g t h , which s p e c i f i e s the a l t e r n a t i v e t h e r a p i e s be ing compared and the da ta t h a t need to be c o l l e c t e d . No s i n g l e p h y s i c i a n i s l i k e l y t o remember the d e t a i l s i n even one o f these p r o t o c o l documents, no t to ment ion the 30 to 60 p r o t o c o l s t h a t may be used in a major cancer c e n t e r . A l though an e f f o r t is made to have the documents a v a i l a b l e i n t he oncology c l i n i c s when p a t i e n t s are be ing t r e a t e d f o r t h e i r tumors , i t i s o f t e n the case t h a t a busy c l i n i c schedu le , coupled w i t h a complex p r o t o c o l d e s c r i p t i o n , leads a p h y s i c i a n to r e l y on h i s memory when d e c i d i n g drug doses o r what l a b o r a t o r y t e s t s to o r d e r . Fu r the rmore , s o l u t i o n s f o r a l l p o s s i b l e t r ea tmen t problems cannot be s p e l l e d ou t in p r o t o c o l s . Phys i c i ans use t h e i r own Judgment in t r e a t i n g these p a t i e n t s , r e s u l t i n g i n some v a r i a b i l i t y i n t r e a t m e n t from p a t i e n t t o p a t i e n t . Thus p a t i e n t s be ing t r e a t e d on a p r o t o c o l do not always r e c e i v e the rapy i n e x a c t l y the manner t h a t the expe r imen ta l des ign sugges ts , and the da ta needed f o r fo rma l a n a l y s i s o f t r ea tmen t r e s u l t s are not always comp le te l y and a c c u r a t e l y c o l l e c t e d .