RESUMO
INTRODUCTION: Mortality risk prediction for Intermediate Respiratory Care Unit's (IRCU) patients can facilitate optimal treatment in high-risk patients. While Intensive Care Units (ICUs) have a long term experience in using algorithms for this purpose, due to the special features of the IRCUs, the same strategics are not applicable. The aim of this study is to develop an IRCU specific mortality predictor tool using machine learning methods. METHODS: Vital signs of patients were recorded from 1966 patients admitted from 2007 to 2017 in the Jiménez Díaz Foundation University Hospital's IRCU. A neural network was used to select the variables that better predict mortality status. Multivariate logistic regression provided us cut-off points that best discriminated the mortality status for each of the parameters. A new guideline for risk assessment was applied and mortality was recorded during one year. RESULTS: Our algorithm shows that thrombocytopenia, metabolic acidosis, anemia, tachypnea, age, sodium levels, hypoxemia, leukocytopenia and hyperkalemia are the most relevant parameters associated with mortality. First year with this decision scene showed a decrease in failure rate of a 50%. CONCLUSIONS: We have generated a neural network model capable of identifying and classifying mortality predictors in the IRCU of a general hospital. Combined with multivariate regression analysis, it has provided us with an useful tool for the real-time monitoring of patients to detect specific mortality risks. The overall algorithm can be scaled to any type of unit offering personalized results and will increase accuracy over time when more patients are included to the cohorts.
RESUMO
INTRODUCTION: Historically, it has been assumed that Intermediate Respiratory Care Units (IRCU) were efficient, because they saved costs by reducing the number of admissions to intensive care units (ICU), and effective, because they specialized in respiratory diseases. METHODS: The number of IRCU admissions and mortality rate, historically and in 2016, were evaluated. For 2016, the grouped Related Diagnostic Groups (DRGs) were also described, and the savings achieved under all budgetary headings by avoiding UCI stays were calculated. A multivariate analysis was performed to associate costs with mean weights and complexity, and multiple logistic regression was performed on all patients admitted from 2004 to 2017 to describe the variables associated with mortality in our unit. RESULTS: An IRCU generates savings of 500,000/year by reducing length of ICU stay. Analysis of the 2016 cohort shows that costs correlate with mean weight and mortality, and consequently complexity. The multivariate logistic regression analysis of the 2004-2017 cohort found respiratory frequency, leukopenia, anemia, hyperkalemia, and acidosis to be the variables best associated with mortality. The area under the curve for the logistic model was 0.75. CONCLUSION: The IRCU analyzed in our study was efficient in terms of 'avoided costs' and savings associated with complexity. Our results suggest that IRCUs have a lower mortality rate than other similar units, and are therefore a safe environment for patients.