Abstract
The objective was to develop a methodology for predicting death in patients with burn injury using regression analysis methods.Methods and Materials. The analysis of the results of treatment of 330 burned with a shock injury, hospitalized in the Department of Anesthesiology and Resuscitation of the Department of Thermal Lesions of Saint-Petersburg I. I. Dzhanelidze research institute of emergency medicine in the period 2013–2019.Results. In the course of the study, 52 indicators were identified that characterized the condition of the victim with burn injury in the dynamics of treatment measures. To build a predictive model, only statistically significant parameters (p<0.05) were used, which were used to build a model of logistic regression. The final algorithm included 18 predictors. The model allows predicting a positive outcome of treatment and the likelihood of a fatal outcome with an accuracy of 93 and 87 % respectively.Conclusion. The use of a multivariate mathematical model made it possible to develop a method for predicting a fatal outcome, taking into account the peculiarities of the pathogenesis of burn disease and the principles of therapeutic measures in the first three days after injury. The use of linear regression analysis using new indicators of thermal injury in a retrospective cohort of 330 patients allowed us to achieve a high predictive value.
Highlights
Received 13.05.20; accepted 07.10.20 The OBJECTIVE was to develop a methodology for predicting death in patients with burn injury using regression analysis methods
In the course of the study, 52 indicators were identified that characterized the condition of the victim with burn injury in the dynamics of treatment measures
To build a predictive model, only statistically significant parameters (p
Summary
ROC-анализ представляет собой графический метод оценки качества работы бинарного классификатора и выбора дискриминационного порога для разделения классов. Средняя величина площади глубокого ожога у пациентов при поступлении составила (14,9±16,2) % п. Отбор переменных для модели прогнозирования летального исхода при термической травме был реализован с помощью выявления статистически значимых различий между умершими и выписанными пациентами по t-критерию Стьюдента для независимых выборок, приведенных в табл. Количество выпитой воды в 1-е сутки (t=–3,14 при р=0,00), объем инфузионной терапии в 1-е (t=–3,40 при р=0,00), 2-е (t=–7,12 при р=0,00) и 3-и сутки госпитализации (t=–6,19 при р=0,00) также выше в группе пациентов с летальным исходом. В группе пострадавших с благоприятным исходом лечения значимо выше такие показатели, как температура тела (t=5,70 при р=0,00), концентрация гемоглобина в 1-е сутки (t=2,43 при р=0,02), средняя концентрация гемоглобина в эритроците (t=3,87 при р=0,00), концентрация общего белка (t=5,74 при р=0,00), ВЕ (t=4,50 при р=0,00), рН мочи (t=5,48 при р=0,00), объем выпитой воды на 3-й день госпитализации (t=2,41 при р=0, 02). Дескриптивные статистики по выборке пациентов Descriptive statistics for a sample of patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
