RESUMEN
The issue of left against medical advice (LAMA) patients is common in today's emergency departments (EDs). This issue represents a medico-legal risk and may result in potential readmission, mortality, or revenue loss. Thus, understanding the factors that cause patients to "leave against medical advice" is vital to mitigate and potentially eliminate these adverse outcomes. This paper proposes a framework for studying the factors that affect LAMA in EDs. The framework integrates machine learning, metaheuristic optimization, and model interpretation techniques. Metaheuristic optimization is used for hyperparameter optimization-one of the main challenges of machine learning model development. Adaptive tabu simulated annealing (ATSA) metaheuristic algorithm is utilized for optimizing the parameters of extreme gradient boosting (XGB). The optimized XGB models are used to predict the LAMA outcomes for patients under treatment in ED. The designed algorithms are trained and tested using four data groups which are created using feature selection. The model with the best predictive performance is then interpreted using the SHaply Additive exPlanations (SHAP) method. The results show that best model has an area under the curve (AUC) and sensitivity of 76% and 82%, respectively. The best model was explained using SHAP method.
RESUMEN
How to cite this article: Mani RK. INDICAPS II: A Bird's Eye View of the Indian Intensive Care Landscape. Indian J Crit Care Med 2021; 25(10):1087-1088.
RESUMEN
BACKGROUND: Leaving against medical advice (LAMA) is a common health concern seen worldwide. It has variable incidence and reasons depending upon disease, geographical region and type of health care system. MATERIALS AND METHODS: We approached anesthesiologists and intensivists for their opinion through ISA and ISCCM contact database using Monkey Survey of 22 questions covering geographical area, type of healthcare system, incidence, reasons, type of disease, expected outcome of LAMA patients etc. RESULTS: We received only 1154 responses. Only 584 answered all questions. Out of 1154, only 313 respondents were from government medical colleges or hospitals while remaining responses were from private and corporate sector. Most hospitals had >100 beds. ICUs were semi-closed and supervised by critical-care physicians. LAMA incidence was maximum from ICU (45%) followed by ward (32%) and emergency (25%). Most patients of LAMA had ICU stay for >1 week (60%). Eighty percent of the respondents opined that financial constraints are the most common reason of LAMA. Unsatisfactory care was rarely considered as a factor for LAMA. Approximately 40% patients had advanced malignancy or disease. Nearly 2/3rd strongly believed that insurance cover may reduce the LAMA rate. CONCLUSION: Most patients get LAMA from the ICU after a stay of week. Financial constraints, terminal medical illness, malignancy and sepsis are major causes of LAMA. Remedial methods suggested to decrease the incidence include a good national health policy by the state; improved communication between the patient, caregivers and heathcare team; practice of palliative and end-of-life care support; and lastly, awareness among the people about advance directives. HOW TO CITE THIS ARTICLE: Paul G, Gautam PL et al. Patients Leaving Against Medical Advice-A National Survey. Indian J Crit Care Med 2019;23(3):143-148.
RESUMEN
INTRODUCTION: With an increasing number of sicker patients, limited hospital beds, and an emphasis on day care, the profile of patients hospitalized to medicine wards has undergone a radical re-definition. The increasing share of patients hospitalized through the emergency department for acute care to medicine wards has left little space for hospitalization through the outpatient department (OPD). There are some global data available on the profile of patients presenting to the emergency rooms (ERs) and their subsequent outcome. Data from developing countries, especially India, in this regard are lacking. METHODS: This cross-sectional study included all patients hospitalized to the medicine ward through the medical emergency services, provided by the Department of Medicine, each Wednesday and every sixth Sunday for the entire year (a total of 62 days), from November 2010 through October 2011, and followed their outcome up to seven days after hospitalization. RESULTS: Of the 3,618 cases presenting to medicine emergency on these days, 1,547 (42.3%) were advised admission. Nine hundred sixty-seven reported to the medicine wards. One hundred eleven (7.73%) expired within 24 hours; others absconded, were lost in transit, did not consent to participation, or were discharged. During the next seven days, 452 (46.7%) recovered sufficiently and were discharged to go home. Two hundred thirty (23.8%) left the hospital without informing the medical staff. Fourteen (1.4%) patients were transferred to other departments. One hundred thirty-seven (8.8%) patients died during the next six days of hospitalization. After Multivariate Logistic Regression analysis, abnormal Glasgow Coma Scale (GCS) score, high systolic blood pressure (BP), age, increased total leucocyte count, increased globulin, low bicarbonate in arterial blood, low Mini Mental Status Examination (MMSE) score, and a raised urea >40 mg/dL were found to be associated significantly with mortality. CONCLUSION: Of the 1,547 patients who needed urgent hospitalization, 248 (16%) died within the first week, one-half of them within the first 24 hours. An advanced age, abnormal GCS score, low MMSE score, increased systolic BP, leukocytosis, acidosis, and uremia were found to be associated with a fatal outcome. Therefore, nearly one-half of the patients who would have a fatal short-term outcome were likely to do so within the first 24 hours, making the first day of presentation "the golden day" period.