Methodological principles in medical knowledge programming: Part I

Hucklenbroich P

Forschungsartikel (Zeitschrift) | Peer reviewed

Zusammenfassung

The impact of methodology on knowledge programming in medicine has been, until now, rather scarce. The reasoning strategies of most systems are variations on probabilistic themes like the BAYES formula. An analysis of the INTERNIST-I/CADUCEUS project of Myers and Pople shows that there are serious shortcomings in the probabilistic approach that impair the knowledge representation as well as the correctness of the clinical conclusions. An outline is given of how more adequate representations and decisions may be arrived at on the basis of logico-methodological reconstructions of clinical knowledge and reasoning.

Details zur Publikation

FachzeitschriftArtificial Intelligence in Medicine (Artif Intell Med)
Jahrgang / Bandnr. / Volume3
Ausgabe / Heftnr. / Issue2
Seitenbereich113-123
StatusVeröffentlicht
Veröffentlichungsjahr1991 (31.12.1991)
Sprache, in der die Publikation verfasst istEnglisch
DOI10.1016/0933-3657(91)90022-4
Link zum Volltexthttp://www.scopus.com/inward/record.url?partnerID=yv4JPVwI&eid=2-s2.0-0026139986&md5=5159dc90cec1ab129fc0bcd6ea0f0276
StichwörterMethodology; philosophy of medicine; knowledge-based systems; expert systems; probabilism; BAYES' theorem; INTERNIST-I; CADUCEUS

Autor*innen der Universität Münster

Hucklenbroich, Peter
Institut für Ethik, Geschichte und Theorie der Medizin