Investigating factors affecting the interval between a burn and the start of treatment using data mining methods and logistic regression.

BACKGROUND: Burn is a tragic event for an individual, the family, and community. It can cause irreparable physical, mental, economic, and social injury. Researches well documented that a quick visit to a healthcare center can greatly reduce burn injuries. Therefore, the aim of this study is to identify the effective factors in the interval between a burn and start of treatment in burn patients by comparing three classification data mining methods and logistic regression. METHODS: This cross-sectional study conducted on 389 hospitalized patients in Imam Khomeini Hospital of Kermanshah city since 2012 to 2015. The data collection instrument was a three-part questionnaire, including demographic information, geographical information, and burn information. Four classification methods (decision tree (DT), random forest (RF), support vector machine (SVM) and logistic regression (LR)) were used to identify the effective factors in the interval between burn and start of treatment (less than two hours and equal or more than two hours). RESULTS: The mean total accuracy of all models is higher than 0.8. The DT model has the highest mean total accuracy (0.87), sensitivity (0.44), positive likelihood ratio (14.58), negative predictive value (0.89) and positive predictive value (0.71). However, the specificity of the SVM model and RF model (0.99) was higher than other models, and the mean negative likelihood ratio (0.98) of the SVM model are higher than other models. CONCLUSIONS: The results of this study shows that DT model performed better that data mining models in terms of total accuracy, sensitivity, positive likelihood ratio, negative predictive value and positive predictive value. Therefore, this method is a promising classifier for investigating the factors affecting the interval between a burn and the start of treatment in burn patients. Also, key factors based on DT model were location of transfer to hospital, place of occurrence, time of accident, religion, history and degree of burn, income, province of residence, burnt limbs and education.

Predictive factors of mortality in burn patients.

BACKGROUND: Burn injuries impose a considerable burden on healthcare systems in Iran. It is among the top ten causes of mortality and a main cause of disability. OBJECTIVES: This study aimed to examine factors influencing mortality in burn patients admitted to the main educational tertiary referral hospital in Kermanshah. PATIENTS AND METHODS: All patients admitted to the Imam Khomeini Hospital (from March 2011 to March 2012), due to thermal burn injuries were included in the study. We applied multiple logistic regressions to identify risk and protective factors of mortality. Also we calculated lethal area fifty percent (LA50), as an aggregate index for hospital quality. RESULTS: During the study period, 540 burn patients were admitted. Male to female ratio was 1.12:1. Twenty three percent of the patients were less than 15 years-old. Median of age was 25 years (Inter Quartile Range, 16 - 37). Overall, probability of death was 25.8%. Lethal area fifty percent (LA50) was 50.82 (CI 95%: 47.76 - 54.48). In the final model, after adjustment of sex, age, total body surface area (TBSA), cause of burn and it's severity, female gender (P < 0.05), age ≥ 60 years (in comparison with age less than 15 years, P < 0.05) and larger burn size (P < 0.0001) were identified as the main risk factors of death in these patients. CONCLUSIONS: Findings showed that the main risk factors of death were female gender, burn size and old age. Directing more attention to these vulnerable patients is required to reduce mortality and improve patient survival.

Two-year hospital records of burns from a referral center in Western Iran: March 2010-March 2012.

BACKGROUND: Burns are among the most common injuries affecting a great number of people worldwide annually. In Iran, especially in its western region and in Kermanshah province, burns have a relatively high incidence. The present study was aimed at investigating epidemiological characteristics in Western Iran. METHODS: Within a cross-sectional study, the data on all patients attending the Burns Center at Imam Khomeini Hospital (Kermanshah, Iran) during 2010-2011 and 2011-2012 (24 months) were collected. Then, age, gender, cause of burns, total body surface area, and time of the occurrence were extracted from the hospital records. The data were analyzed using the SPSS statistical package (Version 19, for Windows). We used chi-squared test when we compared the categorical responses between two or more groups. For comparing means between two groups we used t-test. In addition, trends were investigated using linear regression. RESULTS: Overall 13,248 people were referred to the Burns Center at Imam Khomeini Hospital (Kermanshah, Iran) during the period of study, including 328 cases of self-immolation. The mean age of the patients was 27±19 years and 29±13 years for unintentional burns and self-immolation respectively. Out of the total number of unintentional cases, 6,519 (50.5%) were men, while the corresponding percentage of men among the self-immolation cases was 16.6% (p less than 0.001). Trends in the number of cases were cyclic, with the highest and lowest number of burns cases being in March and May. Overall, hot liquids and flammable materials were the two most important causes of unintentional burns. However, flammable materials were the main cause of burns among self-immolation cases. During hospital admission, 168 (51%) self-immolation victims and 43 (0.33%) unintentional burn victims died. CONCLUSIONS: While major preventive measures are not adequately used in developing countries, burns and their burden can be significantly reduced by increasing public awareness and by applying simple preventive measures.