LSTM DSS Automatism and Dataset Optimization for Diabetes Prediction

Abstract

The paper is focused on the application of Long Short-Term Memory (LSTM) neural network enabling patient health status prediction focusing the attention on diabetes. The proposed topic is an upgrade of a Multi-Layer Perceptron (MLP) algorithm that can be fully embedded into an Enterprise Resource Planning (ERP) platform. The LSTM approach is applied for multi-attribute data processing and it is integrated into an information system based on patient management. To validate the proposed model, we have adopted a typical dataset used in the literature for data mining model testing. The study is focused on the procedure to follow for a correct LSTM data analysis by using artificial records (LSTM-AR-), improving the training dataset stability and test accuracy if compared with traditional MLP and LSTM approaches. The increase of the artificial data is important for all cases where only a few data of the training dataset are available, as for more practical cases. The paper represents a practical application about the LSTM approach into the decision support systems (DSSs) suitable for homecare assistance and for de-hospitalization processes. The paper goal is mainly to provide guidelines for the application of LSTM neural network in type I and II diabetes prediction adopting automatic procedures. A percentage improvement of test set accuracy of 6.5% has been observed by applying the LSTM-AR- approach, comparing results with up-to-date MLP works. The LSTM-AR- neural network can be applied as an alternative approach for all homecare platforms where not enough training sequential dataset is available.

Degrees of Shortage and Uncovered Ratios for Long-Term Care in Taiwan’s Regions: Evidence from Dynamic DEA

“…If long-term caregiver numbers, and number of caregivers in temporary care facilities unchanged, then a decline in the elderly population will lead to a sudden increase in long-term care shortage efficiency, presenting a push effect. Because of the lack of medical care resources in the outer islands, telemedicine is available in the outer islands [ 16 ], through telemedicine technology, long-term care patient’s daily health data was collected. When the patient needs emergency medical treatment, such data can provide detailed health information, so that a hospital can immediately receive disease treatment.…”

“…Like novel ensemble learning algorithms, artificial intelligence skills can provide different results and help analyze a model to predict patients’ health risks. The results can be used as future hospital resources for home caregivers, hence providing patients at home with better treatment and reducing the risk of in-hospital infection [ 16 ]. In 2007, the Taiwanese government began to promote a program of setting up long-term care departments and cultivating talent to improve healthcare workers’ needs.…”

Data Mining Applied in Food Trade Network

“…The artificial intelligence (AI) algorithms supporting the DSS have been implemented by means of recurrent neural networks. Different architecture of neural networks such as Long Short Term Memory (LSTM) neural networks [13], [21], standard Recurrent Neural Network (RNN) [22], [23] and Gated Recurrent Units (GRU) [24] have been tested in terms of accuracy. The comparison of results of the LSTM network with the different RNN and GRU architecture has been implemented through a code written in Python language (see appendix A).…”

The Influence of Internet Usage Frequency on Women’s Fertility Intentions—The Mediating Effects of Gender Role Attitudes

“…Thirdly, at present, many scholars use artificial intelligence tools (ANN, LSTM, etc.) to conduct influence factor analyses and predictive analyses [ 32 , 33 , 34 ]. It is also of great significance to analyze the influencing factors of women’s fertility intentions and predict the changing trends surrounding the female fertility rate, which is also the research field we will pay attention to in the future.…”