Predicting patient's long-term clinical status after hip arthroplasty using hierarchical decision modelling and data mining.

Construction of a prognostic model is presented for the long-term outcome after femoral neck fracture treatment with implantation of hip endoprosthesis. While the model is induced from the follow-up data, we show that the use of additional expert knowledge is absolutely crucial to obtain good predictive accuracy. A schema is proposed where domain knowledge is encoded as a hierarchical decision model of which only a part is induced from the data while the rest is specified by the expert. Although applied to hip endoprosthesis domain, the proposed schema is general and can be used for the construction of other prognostic models where both follow-up data and human expertise is available.

Induction of hypotheses concerning hip arthroplasty: a modified methodology for medical research.

OBJECTIVES: 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 statistical tests that are generally accepted in the medical field for the confirmation of hypotheses. METHODS: First, the medical 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 an acute medial femoral neck fracture is investigated as a case study. CONCLUSIONS: The methodology is similar to the usual style 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 experimental 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.

Bipolar versus total hip endoprosthesis: functional results.

Some functional parameters of the hip-joint 3.3 years on average (range 2-8.6 years) after hip arthroplasty are compared with regard to two types of hip endoprostheses: the total (TEP) and the bipolar (BPEP). Flexion, extension, abduction, adduction, and internal and external rotation were measured for 75 patients with BPEP type Self-Locking, for 11 patients with BPEP type Vario-Cup, and for 43 with TEP type Lubinus. One-way analysis of variance with respect to co-variances was used for statistical testing of the measured data. It was found that flexion, abduction and adduction were significantly higher in the BPEP endoprosthesis (P < 0.05). The results obtained are favourable for the bipolar hip endoprosthesis, and they can be related to the biomechanical differences between both types of hip endoprosthesis.

The hip status: a telemedical application.

Biomedical informatics and biomedical engineering are interdisciplinary sciences that are growing fast and have a significant impact on healthcare delivery. The University Medical Centre in Ljubljana and the Medical Faculty through its institutes have initiated the building of their own telemedicine systems. These systems concern only the medical informatics field. However, in this work a telemedical application that uses a combination of biomedical engineering methods and methods of biomedical informatics is presented. This telemedical application was built at the Department of Surgery and it was named "The Hip Status Application". Its aims are to provide services of preventive medicine and health promotion for people with potential problems with the hip-joint, guidance for people that have already underwent an operation of implantation of hip endoprosthesis, or have in any other way affected hip-joints, remote system consultation for diagnostic purposes, etc. The application is still under evaluation, and it is meant as a start of a new era of engineering-powered telemedical applications at the Department of Surgery following the trends in the most developed countries of the World.

The hip-joint resultant force in healthy male and female population: a comparative study.

The geometrical parameters of the pelvis and the femur which influence the hip-joint reaction force were obtained automatically for 21 male and 79 female healthy human subjects from standard AP radiographs, by using a computeraided system. To calculate the hip-joint reaction force a three-dimensional mathematical model of the hip in one-legged stance was used. In order to prepare the data as input to the mathematical model of the hip a nonhomogeneous scaling method based on a reference model of the hip musculature by Dostal and Andrews was applied. Our results show that the magnitude of the hip-joint reaction force and its inclination angle are significantly greater for females than for males. Since females have in addition significantly smaller femoral head radius than males, it may be concluded that the stress in the hip-joint articular surface is higher in the female population relative to the male population. Because the increased stress in the hip-joint articular surface is unfavourable regarding the arthrosis development, the presented results could partially explain the fact that females have greater incidence of arthrosis in the hip-joint than males.This is related not only to femoral, but also to pelvic geometry.