1Decision Supportvia Expert Systems6.872/HST950April 1, 2004Components of an Expert System• Knowledge– In various forms: associations, models, etc.• Strategy– Baconian, exhaustive enumeration, on-line, etc.• Implementation– Programs, pattern matching, rules, etc.FlowchartBI/Lincoln LabsClinical Protocols1978Codifying Human Knowledge• Decomposition into “chunks” of knowledge, chaining of inferences• Matching of case data to prototypical situations• Using causal models (pathophysiology) to figure out casesMycin—Rule-based Systems• Task: Diagnosis and prescription for bacterial infections of the blood (and later meningitis)• Method: – Collection of modular rules– Backward chaining– Certainty factorsRULE037IF the organism1) stains grampos2) has coccusshape3) grows in chains THENThere is suggestive evidence (.7) that the identity of the organism is streptococcus.Mycin consult--------PATIENT-1--------1) Patient's name: FRED SMITH2) Sex: MALE3) Age: 554) Have you been able to obtain positive cultures from a site at which Fred Smith has an infection? YES--------INFECTION-1--------5) What is the infection? PRIMARY-BACTEREMIA6) Please give the date when signs of INFECTION-1 appeared. 5/5/75The most recent positive culture associated with the primary-bacteremia will be referred to as:--------CULTURE-1--------7) From what site was the specimen for CULTURE-1 taken? BLOOD8) Please give the date when this culture was obtained. 5/9/75The first significant organism from this blood culture will be called:--------ORGANISM-1--------9) Enter the identity of ORGANISM-1. UNKNOWN10) Is ORGANISM-1 a rod or coccus (etc.)? ROD11) The gram stain of ORGANISM-1: GRAMNEG. . .Davis, et al., Artificial Intelligence 8: 15-45 (1977)2How Mycin Works• To find out a fact– If there are rules that can conclude it, try them– Ask the user• To “run” a rule– Try to find out if the facts in the premises are true– If they all are, then assert the conclusion(s), with a suitable certainty• Backward chaining from goal to given facts Dynamically traces out behavior of (what might be) a flowchart Information used everywhere appropriate Single expression of any piece of knowledgeExplore Mycin’s Use of Knowledge** Did you use RULE 163 to find out anything about ORGANISM-1?RULE163 was tried in the context of ORGANISM-1, but it failed because it is not true that the patient has had a genito-urinary tract manipulative procedure (clause 3).** Why didn't you consider streptococcus as a possibility?The following rule could have been used to determine that the identity of ORGANISM-1 was streptococcus: RULE033But clause 2 (“the morphology of the organism is coccus”) was already known to be false for ORGANISM-1, so the rule was never tried.Davis, et al., Artificial Intelligence 8: 15-45 (1977)Even Simpler RepresentationDiseases1s2s3s4s5s6s7s8s9s10s...Diseases1s2s3s4s5s6s7s8s9s10s...Diagnosis by Card SelectionDiseases1s2s3s4s5s6s7s8s9s10s...Diseases1s2s3s4s5s6s7s8s9s10s...Diseases1s2s3s4s5s6s7s8s9s10s...Diseases1s2s3s4s5s6s7s8s9s10s...Diagnosis by Edge-Punched Cards¾Dx is intersection of sets of diseases that may cause all the observed symptoms¾Difficulties:¾Uncertainty¾Multiple diseases~ “Problem-Knowledge Coupler” of WeedTaking the Present Illness—Diagnosis by Pattern Directed MatchingHypothesisFacts about Patient3PIP's Theory of Diagnosis• From initial complaints, guess suitable hypothesis.• Use current active hypotheses to guide questioning• Failure to satisfy expectations is the strongest clue to a better hypothesis; differential diagnosis• Hypotheses are activated, de-activated, confirmed or rejected based on (1) logical criteria (2) probabilities based on:findings local to hypothesiscausal relations to other hypothesesThe Scientific MethodMemory Structure in PIPHypothesisLogical CriteriaProbabilisticScoringFunctionDifferentialDiagnosisHeuristicsTriggersCausally andAssociationallyRelated Hyp'sManifestationsPIP's Model of Nephrotic SyndromeNEPHROTIC SYNDROME, a clinical stateFINDINGS:1* Low serum albumin concentration2. Heavy proteinuria3* >5 gm/day proteinuria4* Massive symmetrical edema5* Facial or peri-orbital symmetric edema6. High serum cholesterol7. Urine lipids presentIS-SUFFICIENT: Massive pedal edema & >5 gm/day proteinuriaMUST-NOT-HAVE: Proteinuria absentSCORING . . .MAY-BE-CAUSED-BY: AGN, CGN, nephrotoxic drugs, insect bite, idiopathic nephrotic syndrome, lupus, diabetes mellitusMAY-BE-COMPLICATED-BY: hypovolemia, cellulitisMAY-BE-CAUSE-OF: sodium retentionDIFFERENTIAL DIAGNOSIS:neck veins elevated Æ constrictive pericarditisascites present Æ cirrhosispulmonary emboli present Æ renal vein thrombosisQMR PartitioningM1M2M3M4M5M6H1 H2CompetitorsM1M2M3M4M5M6H1 H2Still CompetitorsM1M2M3M4M5M6H1 H24Probably ComplementaryM1M2M3M4M5M6H1 H2Multi-Hypothesis Diagnosis¾Set aside complementary hypotheses¾… and manifestations predicted by them¾Solve diagnostic problem among competitors¾Eliminate confirmed hypotheses and manifestations explained by them¾Repeat as long as there are coherent problems among the remaining dataInternist/QMR¾ Knowledge Base:¾ 956 hypotheses¾ 4090 manifestations (about 75/hypothesis)¾ Evocation like P(H|M)¾ Frequency like P(M|H)¾ Importance of each M¾ Causal relations between H’s¾ Diagnostic Strategy:¾ Scoring function¾ Partitioning¾ Several questioning strategiesQMR DatabaseQMR Scoring¾Positive Factors¾Evoking strength of observed Manifestations¾Scaled Frequency of causal links from confirmed Hypotheses¾Negative Factors¾Frequency of predicted but absent Manifestations¾Importance of unexplained Manifestations¾Various scaling parameters (roughly exponential)Example Case5Initial Solution— Tom Wu, Ph.D. 1991Assume a bipartite graph representation of diseases/symptomsGiven a set of symptoms, how to proceed?If we could “guess” an appropriate clustering of the symptoms so that each cluster has a single cause …… then the solution is (d5, d6) x (d3, d7, d8, d9) x (d1, d2, d4)d1 d2 … dks1 s2 s3 … sn(s2, s3, s7) (s1) (s5, s9)d5 d6d3 d7 d8 d9d1 d2 d4Symptom Clustering forMulti-Disorder DiagnosisClustering AlternativesTB, Asthma, Bronchitis, EmphysemaCoughTB, Hepatitis, MalariaFeverPossible CausesSymptomTBHepMalAsthBronEmphTBHepMalAsthBronEmphTBFever, CoughAsthBronEmphHepMalCoughFeverH1H2Synopsis in Renal Disease• Diseases– Hypertension (HTN)– Acute