Decision Support via Expert Systems 6.872/HST950 Harvard-MIT Division of Health Sciences and TechnologyHST.950J: Medical ComputingPeter Szolovits, PHDComponents of an Expert System •Knowledge –In various forms: associations, models, etc. •Strategy –Baconian, exhaustive enumeration, on-line, etc. •Implementation –Programs, pattern matching, rules, etc.Last Time •Naïve Bayesian Inference –Exhaustive and Mutually Exclusive disease hypotheses (1 and only 1) –Conditionally independent observables (manifestations) –P(Di), P(Mij|Di) M1 M2 M3 M4 M5 M6 DTaking the Present Illness—Diagnosis by Pattern Directed MatchingPIP'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 hypothesis •causal relations to other hypothesesMemory Structure in PIP Triggers Manifestations Causally and Associationally Related Hyp's Logical Criteria Probabilistic Scoring Function Differential Diagnosis Heuristics HypothesisPIP's Model of Nephrotic Syndrome •NEPHROTIC SYNDROME, a clinical state •FINDINGS: –1* Low serum albumin concentration –2. Heavy proteinuria –3* >5 gm/day proteinuria –4* Massive symmetrical edema –5* Facial or peri-orbital symmetric edema –6. High serum cholesterol –7. Urine lipids present •IS-SUFFICIENT: Massive pedal edema & >5 gm/day proteinuria •MUST-NOT-HAVE: Proteinuria absent •SCORING . . . •MAY-BE-CAUSED-BY: AGN, CGN, nephrotoxic drugs, insect bite, idiopathic nephrotic syndrome, lupus, diabetes mellitus •MAY-BE-COMPLICATED-BY: hypovolemia, cellulitis •MAY-BE-CAUSE-OF: sodium retention •DIFFERENTIAL DIAGNOSIS: –neck veins elevatedQMR Partitioning M1 M2 M3 M4 M5 M6 H1 H2Competitors H1 H2 M1 M2 M3 M4 M5 M6Still Competitors H1 H2 M1 M2 M3 M4 M5 M6Still Competitors H1 H2 M1 M2 M3 M4 M5 M6Multi-Hypothesis Diagnosis •Set aside complementary hypotheses •… and manifestations predicted by them •Solve diagnostic problem among competitors •Eliminate confirmed hypotheses and manifestations explained by them •Repeat as long as there are coherent problems among the remaining dataInternist/QMR •Knowledge Base: •956 hypotheses •4090 manifestations (about 75/hypothesis) •Evocation like P(H|M) •Frequency like P(M|H) •Importance of each M •Causal relations between H’s •Diagnostic Strategy: •Scoring function •Partitioning •Several questioning strategiesQMR Scoring •Positive Factors •Evoking strength of observed Manifestations •Scaled Frequency of causal links from • confirmed Hypotheses •Negative Factors •Frequency of predicted but absent • Manifestations •Importance of unexplained Manifestations •Various scaling parameters (roughly exponential)Symptom Clustering for Multi-Disorder Diagnosis — Tom Wu, Ph.D. 1991Clustering Alternatives Symptom Fever Cough Possible Causes TB, Hepatitis, Malaria TB, Asthma, Bronchitis, Emphysema TB Hep Mal Asth Bron Emph H1 H2 Fever, Cough TB Fever Cough Hep Mal Asth Bron Emph TB Hep Mal Asth Bron EmphSymptom Clustering is Efficient Like in any “planning island” approach, reducing an exponential problem to several smaller exponential problems vastly improves efficiency, if it captures some insight into the problem. Wu's algorithm (SYNOPSIS) will keep a compact encoding even if it overgenerates slightly. E.g., suppose that of the set of diseases represented by (d5, d6) x (d3, d7, d8, d9) x (d1, d2, d4), d6 x d8 x d1 is not a candidate. To represent this precisely would require enumerating the 23 valid candidates. Instead, the factored representation is kept. In a diagnostic problem drawn from a small subset of the Internist database, it is a power of 3 faster and a power of 5 more compact than standard symptom clustering. Guide search via probabilities, if we have a reasonable
View Full Document