In the review, the results provided of clinical and epidemiological trials confirming high prevalence of the risk factors of chronic noncommunicable diseases among medical workers, common comorbidity and hence adverse influence on the health. Analysis of literature data underscores the necessity of further long term populational studies of epidemiology, age range, relation to occupation positions, for the main risk factors. Organization of various preventive events is required, that obviously will impact not only health state and life quality, but furthermore, will increase medical care in general.
Increased prevalence of chronic non-communicable diseases (NCD) and increased related mortality stimulate development of effective methods of their prevention. To date, there are little data on the combined effect of various risk factors on the development of a particular chronic disease, and how much the risk of developing chronic non-communicable diseases increases or decreases with a different combination of risk factors. Purpose. To assess contribution of the combined effect of risk factors into the development of chronic NCD using the method of neural network. Material and methods. Data on 9505 visitors seeking care at the Tomsk health centers were analyzed. To build a multidimensional decision-making model, the authors used the multi-layer perceptron algorithm implemented on the IBM Watson platform. Results. The highest accuracy of disease recognition in the test sample added up to 95.8% for diabetes mellitus. Chronic obstructive pulmonary disease (84.5%) and coronary heart disease (80.4%) rank second. Lower accuracy was registered for such diseases as asthma (73.6%) and arterial hypertension (73.3%). For the development of diabetes mellitus, such factors as patient’s age, level of systolic and diastolic blood pressure, and body mass index (BMI) are equally important. Smoking and gender are identified as the most significant factors for the development of chronic obstructive pulmonary disease. The most significant contribution to the development of arterial hypertension is made by body mass index only. Age and BMI turned out to be most significant for coronary heart disease and arterial hypertension. Conclusion. Use of the neural network method makes it possible to determine contribution of risk factors to the development of chronic ICD, to predict the risk of developing a disease depending on the combination of risk factors and to carry out preventive measures in a personalized manner, taking into account clinical situation of every person. Scope of application. The results of the study can be used by managers of medical organizations to optimize approaches to preventive activities. Keywords: risk factors; chronic non-communicable diseases; neural networks
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.