Predicting Prolonged Hospital Stays in Elderly Patients With Hip Fractures Managed During the COVID-19 Pandemic in Chile: An Artificial Neural Networks Study

Abstract

Background: Prolonged length of stay (LOS) after a hip fracture is associated with increased mortality. Purpose: We sought to create a model to predict prolonged LOS in elderly Chilean patients with hip fractures managed during the COVID-19 pandemic. Methods: Employing an official database, we created an artificial neural network (ANN), a computational model corresponding to a subset of machine learning, to predict prolonged LOS (≥14 days) among 2686 hip fracture patients managed in 43 Chilean public hospitals during 2020. We identified 18 clinically relevant variables as potential predictors; 80% of the sample was used to train the ANN and 20% was used to test it. The performance of the ANN was evaluated via measuring its discrimination power through the area under the curve of the receiver operating characteristic curve (AUC-ROC). Results: Of the 2686 patients, 820 (30.2%) had prolonged LOS. In the training sample (2,125 cases), the ANN correctly classified 1,532 cases (72.09%; AUC-ROC: 0.745). In the test sample (561 cases), the ANN correctly classified 401 cases (71.48%; AUC-ROC: 0.742). The most relevant variables to predict prolonged LOS were the patient’s admitting hospital (relative importance [RI]: 0.11), the patient’s geographical health service providing health care (RI: 0.11), and the patient’s surgery being conducted within 2 days of admission (RI: 0.10). Conclusions: Using national-level big data, we developed an ANN that predicted with fair accuracy prolonged LOS in elderly Chilean patients with hip fractures during the COVID-19 pandemic. The main predictors of a prolonged LOS were unrelated to the patient’s individual health and concerned administrative and organizational factors.

Fractura de cadera durante el primer año de pandemia en Chile

“…Diaz-Ledezma et al usando redes neuronales establecieron que factores relacionados a la geografía donde vive el pacientes y el tipo de establecimiento -público o privadoson los más importantes para predecir la estadía hospitalaria, estos mismos factores podrían explicar la heterogeneidad de la incidencia por no hospitalizar. 23 Otras causas para explicar la disminución de la incidencia propiamente tal, sería una disminución en la accidentabilidad y en que los pacientes adultos mayores frágiles estaban más expuestos a enfermarse por covid-19 y a presentar enfermedad grave. De hecho, en el registro DEIS se ve una mortalidad en mayores de 60 años por COVID confirmado de 7.946 hombres y 6.264 mujeres durante el año 2020, es decir, ambas patologías son de alto riesgo para este grupo etario.…”

“…These same factors could explain the heterogeneity in the incidence of non-hospitalization. 23 Other causes to explain the decrease in the incidence itself would be a decrease in the accident rate and the fact that frail older adult patients were more exposed to getting sick from Covid-19 and presenting with serious illness. In fact, the DEIS registry shows a mortality rate in people over 60 years of age due to confirmed COVID of 7,946 men and 6,264 women during 2020, that is, both pathologies are high risk for this age group.…”

“…Diaz-Ledezma et al usando redes neuronales establecieron que factores relacionados a la geografía donde vive el pacientes y el tipo de establecimiento -público o privado – son los más importantes para predecir la estadía hospitalaria, estos mismos factores podrían explicar la heterogeneidad de la incidencia por no hospitalizar. 23…”

Machine learning applications for the prediction of extended length of stay in geriatric hip fracture patients

“…Long-term LOS not only results in inefficient use of medical resources but also increases the risk of complications among hip fracture patients[ 19 ]. In addition, the length of hospital stay varies greatly among healthcare systems[ 17 , 18 , 20 ]. The identification of risk factors associated with the eLOS may be helpful in cost forecasting and patient management[ 21 ].…”