Using the internet in patient-centred diabetes care for communication, education, and decision support.

The New England Journal of Medicine 329 (1993) 977- The present paper describes two systems for communication, education, and decision support in patient-centred diabetes care. Both systems are developed under the assumption that while the clinical resources in the health care sector are limited, patients' resources and new information technology may be able to play a much more central role. With DiasNet patients can experiment with their own data. They can, retrospectively, adjust insulin doses or meals sizes, and thereby learn how to cope with various situations. DiabVision, brings together algorithms for detection of retinal lesions in digital images and for aligning time series of retinal images. While the former algorithms are aimed at automated procedures for screening for diabetic retinopathy, the latter can be used to enable motivated patients to see the actual retinal lesions in their own eyes, illustrating how the changes appear, and perhaps disappear, as a consequence of changes in lifestyle and glycaemic control. One of the long-term goals of our work is to assess the potential of integrating all health related information for patients with diabetes and other major chronic diseases. One solution to these problems would be to organise data and information as one virtual database, which then could be accessed by both health professionals and by patients. This structure would facilitate easy access, a clear overview, and quality control. A web site taking the first step in this process has been launched.

The Virtual Brain Project--development of a neurosurgical simulator.

As a joined project between Aalborg University and Aalborg Hospital Denmark, a neuro-surgical simulator is being developed. In this paper the objective of the project is outlined and an overview of the research activities within the project is given. Focus is on 3D modelling of the brain, deformable models and the development of two demonstrators, including one for training of punctuation of ventricle using visual and haptic feedback.

Screening for diabetic retinopathy using computer based image analysis and statistical classification.

Diabetic retinopathy is one of the most common causes of blindness in Europe. However, efficient therapies do exist. An accurate and early diagnosis and correct application of treatment can prevent blindness in more than 50% of all cases. Digital imaging is becoming available as a means of screening for diabetic retinopathy. As well as providing a high quality permanent record of the retinal appearance, which can be used for monitoring of progression or response to treatment, and which can be reviewed by an ophthalmologist, digital images have the potential to be processed by automatic analysis systems. We have described the preliminary development of a tool to provide automatic analysis of digital images taken as part of routine monitoring of diabetic retinopathy in our clinic. Various statistical classifiers, a Bayesian, a Mahalanobis, and a KNN classifier were tested. The system was tested on 134 retinal images. The Mahalanobis classifier had the best results: microaneurysms, haemorrhages, exudates, and cotton wool spots were detected with a sensitivity of 69, 83, 99, and 80%, respectively.