Predicting 30-Day Hospital Readmission for Diabetes Patients using Multilayer Perceptron
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 2
Abstract
Hospital readmission is considered a key metric in order to assess health center performances. Indeed, readmissions involve different consequences such as the patient’s health condition, hospital operational efficiency but also cost burden from a wider perspective. Prediction of 30-day readmission for diabetes patients is therefore of prime importance. The existing models are characterized by their limited prediction power, generalizability and pre-processing. For instance, the benchmarked LACE (Length of stay, Acuity of admission, Charlson comorbidity index and Emergency visits) index traded prediction performance against ease of use for the end user. As such, this study propose a comprehensive pre-processing framework in order to improve the model’s performance while exploring and selecting a prominent feature for 30-day unplanned readmission among diabetes patients. In order to deal with readmission prediction, this study will also propose a Multilayer Perceptron (MLP) model on data collected from 130 US hospitals. More specifically, the pre-processing technique includes comprehensive data cleaning, data reduction, and transformation. Random Forest algorithm for feature selection and SMOTE algorithm for data balancing are some example of methods used in the proposed pre-processing framework. The proposed combination of data engineering and MLP abilities was found to outperform existing research when implemented and tested on health center data. The performance of the designed model was found, in this regard, particularly balanced across different metrics of interest with accuracy and Area under the Curve (AUC) of 95% and close to the optimal recall of 99%.
Authors and Affiliations
Ti’jay Goudjerkan, Manoj Jayabalan
Keywords
Related Articles
- EP ID EP468359
- DOI 10.14569/IJACSA.2019.0100236
- Views 71
- Downloads 0
A Proposed Architectural Model for an Automatic Adaptive E-Learning System Based on Users Learning Style
It has been established through literature that, if an e-learning system could adapt to learning characteristics of learners, it will increase learning performance and content knowledge acquisition of learners. This pape...
New Deep Kernel Learning based Models for Image Classification
Deep learning system is used for solving many problems in different domains but it gives an over-fitting risk when richer representations are increased. In this paper, three different models with different deep multiple...
Mobile Sensing for Data-Driven Mobility Modeling
The use of mobile sensed location data for realistic human track generation is privacy sensitive. People are unlikely to share their private mobile phone data if their tracks were to be simulated. However, the ability to...
Implementation of ADS Linked List Via Smart Pointers
Students traditionally have difficulties in implementing abstract data structures (ADS) in C++. To a large extent, these difficulties are due to language complexity in terms of memory management with raw pointers – the p...
A Hybrid Method to Predict Success of Dental Implants
Background/Objectives: The market demand for dental implants is growing at a significant pace. Results obtained from real cases shows that some dental implants do not lead to success. Hence, the main problem is whether m...