Search

Background. With the development of personalized medicine based on the achievements of fundamental science, there is a need to introduce the acquired knowledge into practical healthcare. Objective. To evaluate the validity of the express method with a computer support program to determine the probability of developing congenital pneumonia in premature newborns with low birth weight. Materials and methods. A comparative analysis of 214 life history data, outcomes of previous pregnancies, complications of present pregnancy in mothers, clinical and laboratory methods of research in 172 premature infants with low body weight who were in the department of anesthesiology and intensive care (with wards for newborns) and the pediatric department for premature newborns in the first three days of life was carried out. Results. According to the data of a comprehensive examination of 108 premature newborns with low birth weight, a mathematical model (z) of the express method z=- 1.56+1.53SM+2.76NP+1.01CFPI+0.87SRGF+0.63TTP+ 2.42RFIII was developed with a universal coefficient χ²=46.84, p<0.001, sensitivity - 76.4%, specificity - 83.0%, the area under the ROC curve AUC=0,84±0,056 (0,76-0,91), p<0.001 and a computer support program to determine the probability of developing congenital pneumonia (http://pneu.bsmu.by). The power test was carried out with an additional set of 64 premature newborns with low birth weight, not included in the resulting model. Conclusions. According to the results of the study of the power of the express method, the sensitivity was 0.94, the specificity was 0.63, the prognostic significance of a positive test result was 0.71, the prognostic significance of a negative test result was 0.91 and the likelihood ratio was 2.50, which indicates the high validity of the proposed model. [ABSTRACT FROM AUTHOR]