Author/Editor     Stankovski, V; Bratko, I; Demšar, J; Smrke, D
Title     Induction of hypotheses concerning hip arthroplasty: a modified methodology for medical research
Type     članek
Source     Methods Inf Med
Vol. and No.     Letnik 40, št. 5
Publication year     2001
Volume     str. 392-6
Language     eng
Abstract     0bjectives: The objective of this study is to advocate a methodology for medical research that, in contrast to traditional medical methodology, exploits the flexibility of machine learning and retains the kind of stotistical tests that are generally accepted in the medical field for the confirmation of hypotheses. Methods: First, the medicol problem is defined and data for an observed population are collected; then a machine learning tool is used to generate hypotheses regarding the problem; finally statistical methods are used to determine the validity of the generated hypotheses. Results: To illustrate this approach, the problem of defining indications for hip arthroplasty after on acute medial femoral neck fracture is investigated as a case study. Condusions: The methodology is similar to the usual slyle of applying machine learning, but insists on a link to the techniques of statistical tests that are normally used in medicine. It aims at a more flexible and economical use of experimenta) data than in the usual medical research, which is enabled by techniques of machine learning. At the same time, by reference to traditional statistical tests, it is hoped that this approach will lead to improved acceptance of machine learning in the medical field.
Descriptors     HIP FRACTURES
HIP PROSTHESIS
ARTIFICIAL INTELLIGENCE
RESEARCH DESIGN
AGED
DECISION TREES
OUTCOME ASSESSMENT (HEALTH CARE)
REGRESSION ANALYSIS