Balkan endemic nephropathy (BEN) presents an unsolved puzzle despite fifty years of its investigation. Academy of Medical Sciences of the Serbian Medical Society organized a round table discussion on current unsolved problems related to BEN. The present paper summarizes presentations, discussion and conclusions of this meeting. During the last fifty years, the course of BEN prolonged and it shifted towards the older age in all endemic foci. Data on the incidence of BEN have been controversial and frequently based on the data on the number of BEN patients starting haemodialysis treatment. In Serbia, BEN patients present 6.5% of haemodialysis population and this percentage differs among different centres ranging from 5% (Leskovac) to 46% (Lazarevac). Maintenance of high prevalence of BEN patients on regular haemodialysis indicates that BEN is not an expiring disease. In addition, recent data have shown more frequent microalbuminuria and low-molecular weight proteinuria in children from endemic than from nonendemic families. Aetiology of BEN is still unknown despite numerous investigations of environmental and genetic factors. Today, there is a very current hypothesis on the aetiological role of aristolochic acid but the role of viruses, geochemical factors and genetic factors must not be neglected. Morphological features of BEN are nonspecific and characterized by acellular interstitial fibrosis, tubular atrophy and changes on pre- and postglomerular vessels. New immunohistochemical and molecular biology methods offer a new approach to BEN investigation. Association of BEN with high incidence of upper-urothelial tumours is well-known. Recent studies have shown significant changes of demographic characteristics of patients suffering upper-urothelial tumours, their prevalence in different endemic foci and characteristics of tumours. Further studies of BEN should be directed to determination of incidence and prevalence of disease in different endemic foci, investigations of different insufficiently examined aetiological factors as well as pathomorphological features of the disease by the use of modern methods.
Background and Aims
The application of artificial intelligence and neural networks in medicine is used to help solve problems that cannot be handled by the classical approach. The common name “cybernetics” encompassed the fields of management, information technology and biomedicine, but these disciplines continued to evolve independently due to the explosion of new knowledge. Over time, the development of neural networks has been turbulent and is now widely used in various fields of medicine and even in nephrology.
The aim of the paper is to analyze the history of the development of artificial intelligence and its application in nephrology.
Method
Data were collected from books, magazines, encyclopedias and databases.
Results
Basic research on cybernetics and medicine was done by Golgi and Kelley doctors after Isaak Newton and Hermann von Helmholtz. The first theoretical mathematical models were derived in 1943 by Warren Mc Culloch and Walter Pitts. A few years later, a more contemporary contribution to the development of neural networks was given by Norbert Wiener and John von Neumann because they thought that research into biomedicine based on human brain function would be very interesting. In addition, in 1948 Norbert Wiener was the first to publish a work explaining the term cybernetics. At that time, the first experiments were made and new theories in the field of artificial intelligence were put forward by Marvin Misnki. The first training of neurons and the basis of all methods for training neurons was described by the Canadian Donald O Hebb. After the first successful neurocomputer in 1957, on which Rosenblatt worked, scientists have perfected various models of neural networks to this day. So far, mostly retrospective studies have been done in clinical nephrology, transplantation and dialysis with the help of algorithms used in neural networks.
Particularly complex nephrologic patient relationships as well as assistance with timely implementation of new good clinical practice guidelines, patient prediction in at least the next month, and patient selection for palliative care are just some segments in nephrology that require the introduction of such tools into daily clinical practice with the aim of sensitive patient populations have better treatment outcomes, with physicians having more comprehensive insight and control over the mass of data.
Conclusion
Today‘s application of artificial intelligence in nephrology is based on retrospective research. The dizzying rise in technological development so far will allow the use of cybernetics and available tools based on neural network algorithms to enable and improve the nephrologists’ dedication and effectiveness.
ventricular (LV) hypertrophy, LV diastolic function, and microalbuminuria in patients with hypertension and metabolic syndrome (MS). METHODS: Sixty four patients with moderate to severe hypertension and metabolic syndrome were provided to T (80mg) þ A (5mg) in combination once a day (31 males and 33 females). CONCLUSIONS: These data suggest significant antihypertensive and nephroprotective efficacy of the combination of T 80 mg þ A 5 mg. Combination therapy with T þ A has been demonstrated positive effect on the echocardiographic indexes of the heart by reducing LV hypertrophy and improving LV diastolic function, and renal function by reducing albuminuria in patients with moderate to severe hypertension and metabolic syndrome.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.