Dataset Information

AI in Healthcare: Time-Series Forecasting Using Statistical, Neural, and Ensemble Architectures.

ABSTRACT: Both statistical and neural methods have been proposed in the literature to predict healthcare expenditures. However, less attention has been given to comparing predictions from both these methods as well as ensemble approaches in the healthcare domain. The primary objective of this paper was to evaluate different statistical, neural, and ensemble techniques in their ability to predict patients' weekly average expenditures on certain pain medications. Two statistical models, persistence (baseline) and autoregressive integrated moving average (ARIMA), a multilayer perceptron (MLP) model, a long short-term memory (LSTM) model, and an ensemble model combining predictions of the ARIMA, MLP, and LSTM models were calibrated to predict the expenditures on two different pain medications. In the MLP and LSTM models, we compared the influence of shuffling of training data and dropout of certain nodes in MLPs and nodes and recurrent connections in LSTMs in layers during training. Results revealed that the ensemble model outperformed the persistence, ARIMA, MLP, and LSTM models across both pain medications. In general, not shuffling the training data and adding the dropout helped the MLP models and shuffling the training data and not adding the dropout helped the LSTM models across both medications. We highlight the implications of using statistical, neural, and ensemble methods for time-series forecasting of outcomes in the healthcare domain.

SUBMITTER: Kaushik S

PROVIDER: S-EPMC7931939 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

AI in Healthcare: Time-Series Forecasting Using Statistical, Neural, and Ensemble Architectures.

Kaushik Shruti S Choudhury Abhinav A Sheron Pankaj Kumar PK Dasgupta Nataraj N Natarajan Sayee S Pickett Larry A LA Dutt Varun V

Frontiers in big data 20200319

Both statistical and neural methods have been proposed in the literature to predict healthcare expenditures. However, less attention has been given to comparing predictions from both these methods as well as ensemble approaches in the healthcare domain. The primary objective of this paper was to evaluate different statistical, neural, and ensemble techniques in their ability to predict patients' weekly average expenditures on certain pain medications. Two statistical models, persistence (baselin ...[more]

PMID: 33693379

Similar Datasets

Project description:BackgroundThe COVID-19 pandemic has significantly altered the global health and medical landscape. In response to the outbreak, Chinese hospitals have established 24-hour fever clinics to serve patients with COVID-19. The emergence of these clinics and the impact of successive epidemics have led to a surge in visits, placing pressure on hospital resource allocation and scheduling. Therefore, accurate prediction of outpatient visits is essential for informed decision-making in hospital management.ObjectiveHourly visits to fever clinics can be characterized as a long-sequence time series in high frequency, which also exhibits distinct patterns due to the particularity of pediatric treatment behavior in an epidemic context. This study aimed to build models to forecast fever clinic visit with outstanding prediction accuracy and robust generalization in forecast horizons. In addition, this study hopes to provide a research paradigm for time-series forecasting problems, which involves an exploratory analysis revealing data patterns before model development.MethodsAn exploratory analysis, including graphical analysis, autocorrelation analysis, and seasonal-trend decomposition, was conducted to reveal the seasonality and structural patterns of the retrospective fever clinic visit data. The data were found to exhibit multiseasonality and nonlinearity. On the basis of these results, an ensemble of time-series analysis methods, including individual models and their combinations, was validated on the data set. Root mean square error and mean absolute error were used as accuracy metrics, with the cross-validation of rolling forecasting origin conducted across different forecast horizons.ResultsHybrid models generally outperformed individual models across most forecast horizons. A novel model combination, the hybrid neural network autoregressive (NNAR)-seasonal and trend decomposition using Loess forecasting (STLF), was identified as the optimal model for our forecasting task, with the best performance in all accuracy metrics (root mean square error=20.1, mean absolute error=14.3) for the 15-days-ahead forecasts and an overall advantage for forecast horizons that were 1 to 30 days ahead.ConclusionsAlthough forecast accuracy tends to decline with an increasing forecast horizon, the hybrid NNAR-STLF model is applicable for short-, medium-, and long-term forecasts owing to its ability to fit multiseasonality (captured by the STLF component) and nonlinearity (captured by the NNAR component). The model identified in this study is also applicable to hospitals in other regions with similar epidemic outpatient configurations or forecasting tasks whose data conform to long-sequence time series in high frequency exhibiting multiseasonal and nonlinear patterns. However, as external variables and disruptive events were not accounted for, the model performance declined slightly following changes in the COVID-19 containment policy in China. Future work may seek to improve accuracy by incorporating external variables that characterize moving events or other factors as well as by adding data from different organizations to enhance algorithm generalization.

Project description:In this paper, we introduce a novel model selection approach to time series forecasting. For linear stationary processes, such as AR processes, the direction of time is independent of the model parameters. By combining theoretical principles of time-reversibility in time series with conventional modeling approaches such as information criteria, we construct a criterion that employs the backwards prediction (backcast) as a proxy for the forecast. Hereby, we aim to adopt a theoretically grounded, data-driven approach to model selection. The novel criterion is named the backwards validated information criterion (BVIC). The BVIC identifies suitable models by trading off a measure of goodness-of-fit and a models ability to predict backwards. We test the performance of the BVIC by conducting experiments on synthetic and real data. In each experiment, the BVIC is examined in contrast to conventionally employed criteria. Our experimental results suggest that the BVIC has comparable performance as conventional information criteria. Specifically, in most of the experiments performed, we did not find statistically significant differences between the forecast error of the BVIC under certain parameterizations and that of the different information criteria. Nonetheless, it is worth emphasizing that the BVIC guarantees are established by design where the model order penalization term depends on strong mathematical properties of time-reversible time series forecasting properties and a finite data assessment. In particular, the penalization term is replaced by a weighted trade-off between functional dimensions pertaining to forecasting.That said, we observed that the BVIC recovered more accurately the real order of the underlying process than the other criteria, which rely on a static penalization of the model order. Lastly, leveraging the latter property we perform the assessment of the order model (or, memory) of time series pertaining to epileptic seizures recorded using electrocorticographic data. Our results provide converging evidence that the order of the model increases during the epileptic events.

Dataset Information

AI in Healthcare: Time-Series Forecasting Using Statistical, Neural, and Ensemble Architectures.

Publications

AI in Healthcare: Time-Series Forecasting Using Statistical, Neural, and Ensemble Architectures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets