Predicting Thermal Injury Patient Outcomes in a Tertiary-Care Burn Center, Pakistan

Predicting the Length of Stay of Cardiac Patients Based on Pre-Operative Variables-Bayesian Models vs. Machine Learning Models

Length of stay (LoS) prediction is deemed important for a medical institution's operational and logistical efficiency. Sound estimates of a patient's stay increase clinical preparedness and reduce aberrations. Various statistical methods and techniques are used to quantify and predict the LoS of a patient based on pre-operative clinical features. This study evaluates and compares the results of Bayesian (simple Bayesian regression and hierarchical Bayesian regression) models and machine learning (ML) regression models against multiple evaluation metrics for the problem of LoS prediction of cardiac patients admitted to Tabba Heart Institute, Karachi, Pakistan (THI) between 2015 and 2020. In addition, the study also presents the use of hierarchical Bayesian regression to account for data variability and skewness without homogenizing the data (by removing outliers). LoS estimates from the hierarchical Bayesian regression model resulted in a root mean squared error (RMSE) and mean absolute error (MAE) of 1.49 and 1.16, respectively. Simple Bayesian regression (without hierarchy) achieved an RMSE and MAE of 3.36 and 2.05, respectively. The average RMSE and MAE of ML models remained at 3.36 and 1.98, respectively.

Mortality and survival analysis of burn patients admitted in a critical care burn unit, Saudi Arabia

Background

Burn injury is associated with a high mortality risk. Recent epidemiological data on burn injury and mortality rate from Saudi Arabia is lacking.

Objective:

This study aimed to analyze the survival rates and its predictability using the Baux score in patients with burn injury at a tertiary care hospital in Saudi Arabia.

Materials and Methods:

This retrospective study included all patients admitted to the burn unit at King Fahd Hospital of the University, Al Khobar, between March 2014 and February 2020. Patients' burn characteristics and calculated revised Baux scores were collected. The age, burn wound size, type of burn, burn extension, and Baux score of the survivors and non-survivors were compared.

Results:

A total number of 102 patients were included, and their mean age was 24.2 years (range: 9 months to 78 years). The mean affected total body surface area was 26.4%. Ninety patients (88%) suffered from flame/scald burn. The mortality rate was 17.6% (18 patients); all these patients had flame burns. No patient with a revised Baux score ≥110 survived (n = 14; 77% of the total deaths), while there was no mortality at score <36. Inhalational injuries were reported in 18 patients, of which 13 (72%) died. Patients with patent airway and no inhalation injury were 19 times more likely to survive than those with a compromised airway (P < 0.001). In terms of the depth of burn, partial thickness increased the likeliness of survival by 10 times compared with full thickness (P < 0.003).

Conclusion:

Inhalational injury and burn size were the most prognostic factors of burn injury in this study. As all cases of mortality were from flame burns, regulation on flammable materials and safety measures should be promoted to the public.