Artificial neural network models for predicting 1-year mortality in elderly patients with intertrochanteric fractures in China

Abstract

The mortality rate of older patients with intertrochanteric fractures has been increasing with the aging of populations in China. The purpose of this study was: 1) to develop an artificial neural network (ANN) using clinical information to predict the 1-year mortality of elderly patients with intertrochanteric fractures, and 2) to compare the ANN's predictive ability with that of logistic regression models. The ANN model was tested against actual outcomes of an intertrochanteric femoral fracture database in China. The ANN model was generated with eight clinical inputs and a single output. ANN's performance was compared with a logistic regression model created with the same inputs in terms of accuracy, sensitivity, specificity, and discriminability. The study population was composed of 2150 patients (679 males and 1471 females): 1432 in the training group and 718 new patients in the testing group. The ANN model that had eight neurons in the hidden layer had the highest accuracies among the four ANN models: 92.46 and 85.79% in both training and testing datasets, respectively. The areas under the receiver operating characteristic curves of the automatically selected ANN model for both datasets were 0.901 (95%CI=0.814-0.988) and 0.869 (95%CI=0.748-0.990), higher than the 0.745 (95%CI=0.612-0.879) and 0.728 (95%CI=0.595-0.862) of the logistic regression model. The ANN model can be used for predicting 1-year mortality in elderly patients with intertrochanteric fractures. It outperformed a logistic regression on multiple performance measures when given the same variables.

Predictive Values of Preoperative Characteristics for 30-Day Mortality in Traumatic Hip Fracture Patients

“…This result is consistent with a previous systematic review that found no benefit of machine learning, including neural networks, over logistic regression for clinical prediction models [ 34 ]. Nevertheless, several smaller studies have found different results when comparing regression models to neural networks to predict 1-year mortality after hip fracture surgery [ 35 , 36 , 37 , 38 ]. Two of the studies compared logistic regression with a neural network and found that the neural network outperformed the alternative [ 35 , 36 ].…”

“…These studies were, however, limited by small datasets comprising 286 and 434 cases, respectively [ 35 , 36 ]. Another study investigated the same question using a larger dataset with 2150 patients and also found that a neural network was better than a logistic regression model for predicting mortality [ 37 ]. Finally, the largest of these studies, containing 10,534 patients, found that a neural network outperforms a Cox proportional hazards model [ 38 ].…”

“…Finally, the largest of these studies, containing 10,534 patients, found that a neural network outperforms a Cox proportional hazards model [ 38 ]. While the small sample size might limit the generalizability of the neural networks produced in the first two studies [ 39 ], the fact remains that all the studies calculated significantly larger AUCs for their neural networks compared to our CNN, with most having an AUC > 0.9 [ 35 , 36 , 37 , 38 ]. Despite all of our efforts, such as using different split partitions in the training and test datasets, introducing dropout layers, and including only variables with relative higher importance, to improve the performance of the CNN model, the AUC did not reflect the same high values as previous studies.…”

Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

“…The argument is that, it is challenging for researchers to choose appropriate time series modeling techniques that can detect non-linear patterns of mortality rates [3][4][5]. However, some authors have proposed artificial intelligence such as deep learning techniques (e.g., artificial neural networks (ANN), convolution neural networks (CNN), recurrent neural networks (RNN)) [5][6][7][8] and machine learning techniques (e.g., support vector machine, random regression forest) [9][10][11] to improve accuracy of predictive models, while other studies have failed to demonstrate their suitability [12][13][14].…”

“…The argument is that, it is challenging for researchers to choose appropriate time series modeling techniques that can detect non-linear patterns of mortality rates [ 3 – 5 ]. However, some authors have proposed artificial intelligence such as deep learning techniques (e.g., artificial neural networks (ANN), convolution neural networks (CNN), recurrent neural networks (RNN)) [ 5 – 8 ] and machine learning techniques (e.g., support vector machine, random regression forest) [ 9 – 11 ] to improve accuracy of predictive models, while other studies have failed to demonstrate their suitability [ 12 – 14 ]. Unlike the conventional statistical/mathematical techniques such as Box-Jenkins approach of autoregressive integrated moving average (ARIMA) and Holt-Winters exponential smoothing method, ANN combines both linear and non-linear modeling properties [ 4 , 5 ].…”