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.

Management and outcome of post-myocardial infarction ventricular septal rupture-A Low-Middle-Income Country Experience.

BACKGROUND: Ventricular septal rupture (VSR) is a rare complication after acute myocardial infarction (AMI) especially in the reperfusion era but its associated mortality has remained high. This case series evaluated in-hospital and intermediate-term mortality in VSR patients. Additionally, we also analyzed risk factors, clinical presentation, intervention, and predictors of in-hospital mortality in VSR patients. METHODS: Data of 67 patients with echocardiography confirmed diagnosis of VSR from January 2011 to April 2020 was extracted from hospital medical records. Records were also reviewed to document 30 day and 1-year mortality, recurrent heart failure admission, repeat myocardial infarction, and revascularization. In addition, telephonic follow-up was done to assess health-related quality of life(HRQOL) assessed by KCCQ-12. SCAI shock classification was used to categorize severity of cardiogenic shock. Univariate and multivariable logistic regression was used to determine predictors of in-hospital mortality. Survival function was presented using the Kaplan-Meier survival curve. RESULTS: Mean age of patients was 62.7 ± 11.1 years, 62.7% were males. 65.7% of the patients presented more than 24 hours after MI and did not receive reperfusion therapy. Median time from AMI to VSR diagnosis was 2 (1-5) days. VSR closure was attempted in 53.7% patients. In-hospital mortality was 65.7%. At univariate level, predictors of in-hospital mortality were non-surgical management, basal VSR, right ventricular dysfunction, early VSR post-MI, and severe cardiogenic shock at admission (class C, D, or E). Adjusted predictors of in-hospital mortality included non-surgical management, basal VSR and advanced cardiogenic shock. There were 5 deaths during median followup of 44.1 months. HRQOL in patients available on followup was good (54.5%) or excellent (45.5%). CONCLUSION: High in-hospital mortality was seen in VSR patients. VSR closure is the preferred treatment to get long-term survival, however, timing of repair as well as severity of cardiogenic shock plays a significant role in determining prognosis.

Emergency Inguinal Hernia Repair: Comparison Of Desarda's Versus Darning Technique.

BACKGROUND: Emergency inguinal hernia repair remains the commonest operation performed by general surgeons all over the world. The aim of this study was to compare the mean operative time, post-operative pain, wound infection and early recurrence between Desarda's and Darning emergency inguinal hernia repair. METHODS: This is a randomized controlled trial conducted at Jinnah Postgraduate Medical Centre, Karachi. A total of 186 patients of male gender between ages 20-60 years with incarcerated, obstructed and strangulated inguinal hernia were enrolled in the study. Patients with primary and recurrent inguinal hernias were excluded. All patients were randomized to Desarda group (n=93) and Darning group (n=93). RESULTS: Mean operative time in Desarda group was 55.53±6.81 minutes and mean operative time in darning group was 53.06±5.51 minutes (p-value 0.007). Mild to moderate pain was found insignificantly higher in Desarda group 75 (80.6%) as compared to Darning group 66 (71%) (p-value 0.170). Wound infection was found higher in Desarda group 18 (19.4%) as compared to darning group 9 (9.7%) (p-value 0.061). Recurrence was found significantly higher 15 (55.5%) in Darning group as compared to Desarda group 2 (7.4%) (p-value <0.001). CONCLUSIONS: No significant difference was observed in the postoperative pain, wound infection however, significant differences were observed in the mean operative time and recurrence rates.