No abstract

Background: Despite of much advancement in modern diagnostic technology, decision making in patients with acute appendicitis is still a challenge worldwide. Many diagnostic scoring systems have been developed. Of them modified Alvarado scoring system (MASS) has been reported to be a cheap and quick diagnostic tool which minimizes negative appendectomy rate. The present study was aimed to evaluate the efficacy of MASS in diagnosing acute appendicitis and correlating the same with histopathological results.Methods: This prospective cohort study conducted from November 2012 to April 2014, over a period of 18 months at Vydehi Institute of Medical Sciences and Research Centre, Bangalore. 100 patients with symptoms of acute appendicitis were enrolled in the study. They were diagnosed using MASS. Patients with a score of 7 to 10 were taken up for surgery. Patients with a score below 7, but with high suspicion of acute appendicitis by the surgeon were taken up for surgery. Following surgery all appendix specimens were sent for histopathologic examination.Results: A total number of 100 patients were participated in the study. Of them patients under the age group of 21-30 years were more affected with acute appendicitis (51%). Male predominance was observed in the study (74%). The common symptom observed in all patients (100%) was tenderness in right Iliac fossa (RIF). Out of 100 patients, 79% of the patients were presented with a modified Alvarado score of ≥7 and 21% presented with a score of <7. The sensitivity and specificity of the MASS in this study was 89.66% and 92.31% in both males and females respectively. The positive predictive value was 98.73%, negative predictive value was 57.41% and the NAR was 6.75% and 30.76% in male and female patients respectively.Conclusions: The observations of the study confirm that use of MASS in patients suspected to have acute appendicitis provides a high degree of diagnostic accuracy and subsequently reduces the negative appendicectomy and complication rates.

No abstract

No abstract

INTRODUCTION:Intracranial hemorrhage (ICH) has high morbidity and mortality, disproportionately affecting rural patients despite adjusting for comorbidities. Inter-hospital transfers for rural patients cause delays in access to specialized care and are associated with adverse outcomes. Published prognostic tools lack distance as factor hence we explored training of three machine learning models to predict 30-day mortality, modified Rankin scale on discharge and discharge disposition in ICH patients using distance from home to tertiary care. METHODS:Preprocessing functions and ML models were imported from the Python 3.8 library scikit-learn. All categorical variables were one-hot-encoded; ordinal variables were integer encoded. Three machine learning models were trained to predict three labels: 30 Day Mortality (Alive, Dead/ Hospice), modified Rankin Score upon discharge (7 classes), and Discharge Disposition (Home/Inpatient Rehabilitation Facility, Hospice/Acute Care Facility Skilled Nursing Facility/ Other Health Care Facility/Expired /Long Term Care Hospital). Data was split 60/40 for training and testing sets respectively. Mean and standard deviation of F1 score, recall, and precision were calculated over 10 trials. Feature importance was determined using permutation feature importance. RESULTS:The dataset contained 138 patients admitted in calendar year 2019 with 13 useable features: 8 categorical features, 4 numeric features, and 1 ordinal feature. For all of these models, the five most important features were GCS on Admission, ICH Score, age, smoking status, and maximum distance travelled to tertiary care facility. The Multinomial Naive Bayes model showed F1 score of 0.8129 for 30-day mortality. Random forest performed lower but better than chance for mRS at discharge, F1 score 0.68 and discharge disposition 0.34. Varying classification of discharge disposition did not improve. CONCLUSIONS:Distance travelled by an ICH patient from home to tertiary medical center was shown to be indeterminant in patient's outcome in our predictive model. Ongoing study including rural urban status, time traveled to specialized care from point of origin as well as payer status are being evaluated in a larger sample to create a prognostic model accounting for social determinants affecting ICH outcomes.