Abstract
>ENG >RUSIntroduction
One of the central problems in medicine is diagnostics of disease. It’s really difficult to solve sometimes is patient healthy or sick. The conclusion we make is based on some data, e.g. case record and current health of the patient. However, it is still impossible to create systems that provide full diagnostics of the patient. That’s why we have to decrease decision space and create a system works only on some disease classes.
The human body is precision biological mechanism. One of the most important guesses in diagnostics is fact that we can predict well some reactions of the human body to various factors. It’s early to say, that skilled doctor could be replaced with such prediction system, but the similar system can assist effectively for the expert who will make the final decision. Practice approaches shows, that similar cooperation of the person and analytical system can be rather productive.
The Purposes and Problems
The purpose of the given work is development of evolutionary prediction system in rheumatoid arthritis. There are some assumptions that neurogenic mechanisms could explain some unexplained clinical char-acteristic. In my work I’ll try to prove possibility of regulation neuropeptide and neuropeptidase activity in treatment of arthritis using perspective data analysis technique of evolutionary programming.
An Overview of Existing Researches
Rheumatoid arthritis is a chronic disease, mainly characterized by inflammation of the lining, or synovium, of the joints. It can lead to long-term joint damage, resulting in chronic pain, loss of function and disability.
Rheumatoid arthritis (RA) progresses in three stages. The first stage is the swelling of the synovial lining, causing pain, warmth, stiffness, redness and swelling around the joint. Second is the rapid division and growth of cells, or pannus, which causes the synovium to thicken. In the third stage, the inflamed cells release enzymes that may digest bone and cartilage, often causing the involved joint to lose its shape and alignment, more pain, and loss of movement.
RA currently affect more than 100 million of people in Europe and cause severe damage to the European economies. Currently, the cause of RA is unknown, although there are several theories. And while there is no cure, it is easier than ever to control RA through the use of new drugs, exercise, joint protection techniques and self-management techniques.
Because it is a chronic disease, RA continues indefinitely and may not go away. Frequent flares in disease activity can occur. RA is a systemic disease, which means it can affect other organs in the body. Early diagnosis and treatment of RA is critical if patient want to continue living a productive lifestyle. Studies have shown that early aggressive treatment of RA can limit joint damage, which in turn limits loss of movement, decreased ability to work, higher medical costs and potential surgery. Advancements in research and drug development mean that more people with RA are living happier, healthier and more fulfilling lives.
Diagnosing rheumatoid arthritis is a process. There isn’t a sure-fire test that can tell positively that someone have RA. The sense of my master’s work is to create a system to help doctor not only in this difficult process of diagnosing but also to help him determine the best treatment for current symptoms.
Data Analysis and Prediction
A major impediment to scientific progress in many fields is the inability to make sense of the huge amounts of data that have been collected via experiment or computer simulation. In the fields of statistics and machine learning there have been major efforts to develop automatic methods for finding significant and interesting patterns in complex data, and for forecasting the future from such data; in general, however, the success of such efforts has been limited, and the automatic analysis of complex data remains an open problem. Data analysis and prediction can often be formulated as search problems — for example, a search for a model explaining the data, a search for prediction rules, or a search for a particular structure or scenario well predicted by the data. In my master’s work a genetic algorithm is used to solve such search problems.
Genetic algorithms (GAs) were invented by John Holland in the 1960s and were developed by Holland and his students and colleagues at the University of Michigan in the 1960s and the 1970s. In contrast with evolution strategies and evolutionary programming, Holland's original goal was not to design algorithms to solve specific problems, but rather to formally study the phenomenon of adaptation as it occurs in nature and to develop ways in which the mechanisms of natural adaptation might be imported into computer systems. Holland's 1975 book Adaptation in Natural and Artificial Systems presented the genetic algorithm as an abstraction of biological evolution and gave a theoretical framework for adaptation under the GA. Holland's GA is a method for moving from one population of "chromosomes" (e.g., strings of ones and zeros, or "bits") to a new population by using a kind of "natural selection" together with the genetics-inspired operators of crossover, mutation, and inversion. Each chromosome consists of "genes" (e.g., bits), each gene being an instance of a particular "allele" (e.g., 0 or 1). The selection operator chooses those chromosomes in the population that will be allowed to reproduce, and on average the fitter chromosomes produce more offspring than the less fit ones. Crossover exchanges subparts of two chromosomes, roughly mimicking biological recombination between two single-chromosome ("haploid") organisms; mutation randomly changes the allele values of some locations in the chromosome; and inversion reverses the order of a contiguous section of the chromosome, thus rearranging the order in which genes are arrayed.
Planned Results
There are some classic chapters in my master’s work. For the first the filtration and selection of data from training sample is made, then own program realization of genetic algorithm is created. Then the processing of training data is made. At this stage program realization gradually adapts for the given subject domain. On this stage fixing some program bugs and testing diagnostics system on real data will be done. The second aim is to create subsystem to help determine the best treatment for given symptoms of rheumatoid arthritis. Then a long testing in real-life conditions should be done. If high adequacy and performance will be proved then implementation of diagnostics systems in medical practice should be done.
Conclusions and Future Directions
The research reported here is work in progress. In the short term, I plan to study more carefully the role of some neuropeptides in pathogenesis of synovial inflammation in rheumatoid arthritis using my own program realization of genetic algorithm. I also interested in developing statistical measures that could determine the presence or absence the correlation of neuropeptides and treatment strategies for given symptoms of disease. If such measures could be developed, they could be used to help predict clinical course of rheumatoid arthritis.
References
