Predictors of in-hospital mortality following major lower extremity amputations in type 2 diabetic patients using artificial neural networks

Abstract

BackgroundOutcome prediction is important in the clinical decision-making process. Artificial neural networks (ANN) have been used to predict the risk of post-operative events, including survival, and are increasingly being used in complex medical decision making. We aimed to use ANN analysis to estimate predictive factors of in-hospital mortality (IHM) in patients with type 2 diabetes (T2DM) after major lower extremity amputation (LEA) in Spain.MethodsWe design a retrospective, observational study using ANN models. We used the Spanish National Hospital Discharge Database to select all hospital admissions of major LEA procedure in T2DM patients. Main outcome measures: Predictors of IHM using 4 ANN models: i) with all discharge diagnosis included in the database; ii) with all discharge diagnosis included in the database, excluding infectious diseases; iii) comorbidities included in the Charlson Comorbidities Index; iv) comorbidities included in the Elixhauser Comorbidity Index.ResultsFrom 2003 to 2013, 40,857 major LEAs in patients with T2DM were identified with a 10.0% IHM. We found that Elixhauser Comorbidity Index model performed better in terms of sensitivity, specificity and precision than Charlson Comorbidity Index model (0.7634 vs 0.7444; 0.9602 vs 0.9121; 0.9511 vs 0.888, respectively). The area under the ROC curve for Elixhauser comorbidity model was 91.7% (95% CI 90.3–93.0) and for Charlson comorbidity model was 88.9% (95% CI; 87.590.2) p = 0.043. Models including all discharge diagnosis with and without infectious diseases showed worse results. In the Elixhauser Comorbidity Index model the most sensitive parameter was age (variable sensitive ratio [VSR] 1.451) followed by female sex (VSR 1.433), congestive heart failure (VSR 1.341), renal failure (VSR 1.274) and chronic pulmonary disease (VSR 1.266).ConclusionsElixhauser Comorbidity Index is a superior comorbidity risk-adjustment model for major LEA survival prediction in patients with T2DM than Charlson Comorbidity Index model using ANN models. Female sex, congestive heart failure, and renal failure are strong predictors of mortality in these patients.

Epidemiology of Major Lower Extremity Amputations in Individuals With Diabetes in Austria, 2014-2017: A Retrospective Analysis of Health Insurance Database

“…However, previous studies that have utilized it either did not generate it as a summary tool or had small sample sizes to achieve valid results [3,34,35]. Whilst other studies have shown its association with either short-or longterm mortality after major LEA [4,29,36,37]. Adding to the existing evidence, our study has shown ACCI to be a signi cant predictor of both short-term and long-term mortality after major LEA even after adjusting for sex, age, levels of amputations, and type of diabetes.…”

Major amputations in type 2 diabetes between 2001 and 2015 in Spain: regional differences

“…However, the increase in life expectancy of patients diagnosed with T2DM has also increased the associated morbidity [4]. Advanced age, African ethnicity and male sex are associated with an increased risk of amputations in patients with T2DM, while other factors such as female gender, kidney failure and congestive heart failure increase the risk of death during hospitalization [5]. In addition, undergoing a MA is a significant risk factor for long term mortality among T2DM patients [6].…”

“…In-hospital mortality due to amputations remained stable between 2001 and 2012, around 10%, resulting in an economic cost of 33% of the total cost spent in hospital treatment of T2DM complications [8]. Although there are several published works in relation to nontraumatic amputations in Spain [5][6][7][8], they account for the major and minor procedures globally in the analysis, or do not differentiate the type of diabetes. To our knowledge, there are no publications that have compared MA incidence in patients with T2DM in the seventeen Autonomous Communities (AACC) or Regions of Spain, nor analyzed possible regional heterogeneity in MA mortality or days of hospital stay.…”

Major amputations in type 2 diabetes between 2001 and 2015 in Spain: Regional differences.

“…[4] Advanced age, African ethnicity and male sex are associated with an increased risk of amputations in patients with T2DM, while other factors such as female gender, kidney failure and congestive heart failure increase the risk of death during hospitalization. [5] In addition, undergoing a MA is a significant risk factor for long term mortality among T2DM patients. [6] The overall incidence of amputations due to diabetes increased by 4.29% in Spain between 2001 and2004, followed by a downward trend until 2012, around 2%.…”

“…[7] In-hospital mortality due to amputations remained stable between 2001 and 2012, around 10%, resulting in an economic cost of 33% of the total cost spent in hospital treatment of T2DM complications. [8] Although there are several published works in relation to non-traumatic amputations in Spain [5][6][7][8], they account for the major and minor procedures globally in the analysis, or do not differentiate the type of diabetes. To our knowledge, there are no publications that have compared MA incidence in patients with T2DM in the seventeen Autonomous Communities (AACC) or Regions of Spain, nor analyzed possible regional heterogeneity in MA mortality or days of hospital stay.…”