Vlado Stankovski from the Laboratory for Biomedical Engineering, University Medical Centre, Ljubljana, Slovenia, gave a lecture at the Lodge on "Induction of Hypotheses concerning Hip Arthroplasty : A Modified Methodology for Medical Research".
The lecturer advocated a methodology for medical research that, in contrast to traditional medical methodology, exploits the flexibility of machine learning to determine the kind of statistical results that are generally accepted in the medical field for the confirmation of hypotheses.
Vlado explained that first the medical problem is defined and data for a given population is 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 hypothesis.
Vlado illustrated the approach by describing the problem of defining indication for hip arthroplasty after an acute medical femoral neck fracture.
The methodology is similar to the usual way of applying machine learning; but relies on a link to the technologies of the type of statistical tests which are normally used in medicine. The new methodology aims for a more flexible and economical use of experimental data than is applied in medical research. This is possible by employing machine learning techniques. This approach is expected to lead to improved applications of machine learning in many other fields as well as medicine.
The concept can easily be extended to many other applications in engineering and science. This idea was the subject of lively discussion after the lecture.
WIT is collaborating with the Medical Centre at Ljubljana in organising the Vth International Conference on Biomedicine, which is to take place from April 2nd to 4th, 2003. It is expected that this collaboration will lead to other joint projects and initiatives.