Impact of selected pre-processing techniques on prediction of risk of early readmission for diabetic patients in India

Duggal, Ritu; Shukla, Suren; Chandra, Sarika; Shukla, Balvinder; Khatri, Sunil Kumar

doi:10.1007/s13410-016-0495-4

Cited by 15 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2016) investigate health policy support under uncertainty with an application to cervical cancer. In the area of predicting hospital readmission, studies have been performed in India (Duggal et al., 2016a, 2016b) and China (Jiang et al., 2018). Bagula et al.…”

Section: Application Areasmentioning

confidence: 99%

Analytics in developing countries: methods, applications, and the impact on the UN Sustainable Development Goals

Orhan

Guajardo

2021

Int Trans Operational Res

View full text Add to dashboard Cite

The growing availability of data coupled with advanced methods and computing power have fostered organizations to adopt business analytics in their decision‐making. Nevertheless, the application of analytics is subject to available resources and capabilities, and, therefore, differs from region to region. Developing countries in particular are exposed to circumstances that can limit the expansion of analytics within their domains. This may prohibit the acceleration of development efforts and, consequently, may result in delays in achieving the United Nations Sustainable Development Goals (UNSDGs) set for 2030. Taking this concern as a starting point, this paper provides the results of a survey on the status of analytics research in developing countries. Through a thorough review and classification of 142 articles published during 2009–2019, we characterize analytics in developing countries along three dimensions. First, we explore the mainstream methodologies appearing in the literature, which range from classic optimization techniques to more recent statistical and machine learning methods. Second, we identify 11 application areas that cover a broad range. Third, we focus on the linkages between the reviewed papers and the 17 UNSDGs. Along this dimension, we establish a connection between the literature and 13 goals, and illustrate how some of these contributions relate to some of the 169 targets set by United Nations. Goals such as gender equality are addressed to either little or no extent by the surveyed literature. Also, the survey reveals no adoption of indicators that are set to track the progress toward the targets.

show abstract

Section: Application Areasmentioning

confidence: 99%

Analytics in developing countries: methods, applications, and the impact on the UN Sustainable Development Goals

Orhan

Guajardo

2021

Int Trans Operational Res

View full text Add to dashboard Cite

show abstract

“…As real-world medical data are often noisy, a particular focus will be led on pre-processing task handling both missing data and inconsistencies but also by reducing the dataset and optimizing it for further model deployment [19]. While some pre-processing steps are based on an understanding of the data and background, this study will combine and implement the most relevant pre-processing identified in the body of literature [11], [14], [15].…”

Section: B Data Pre-processingmentioning

confidence: 99%

Predicting 30-Day Hospital Readmission for Diabetes Patients using Multilayer Perceptron

Goudjerkan¹,

Jayabalan²

2019

ijacsa

View full text Add to dashboard Cite

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%.

show abstract

“…So before building the prediction model, it is essential to pre-process the data efficiently and make it appropriate for predictive modelling. The impact of different preprocessing techniques on the classifier performance of logistic regression, naïve Bayes, and decision tree was assessed on various performance metrics such as area under curve, precision, recall, and accuracy by the authors [20]. Based on this study, it is concluded that selected data pre-processing techniques like feature selection, missing value imputation, and data balancing have a significant effect on hospital readmission predictive accuracy for patients with diabetes, with certain schemes proving inferior to competitive approaches.…”

Section: Data Pre-processingmentioning

confidence: 99%

Predictive risk modelling for early hospital readmission of patients with diabetes in India

Duggal

Shukla²,

Chandra³

et al. 2016

Int J Diabetes Dev Ctries

Self Cite

View full text Add to dashboard Cite

Hospital readmission is an important contributor to total medical expenditure and is an emerging indicator of quality of care. The goal of this study is to analyze key factors using machine learning methods and patients' medical records of a reputed Indian hospital which impact the all-purpose readmission of a patient with diabetes and compare different classification models that predict readmission and evaluate the best model. This study classified the patients into two different risk groups of readmission (Yes or No) within 30 days of discharge based on patients' characteristics using 2-year clinical and administrative data. It proposed an architecture of this prediction model and identified various risk factors using text mining techniques. Also, groups of consistently occurring factors that inference readmission rates were revealed by associative rule mining. It then evaluated the classification accuracy using five different data mining classifiers and conducted cost analysis. Out of total 9381 records, 1211 (12.9 %) encounters were found as readmissions. This study found that risk factors like hospital department where readmission happens, history of recent prior hospitalization and length of stay are strong predictors of readmission. Random forest was found to be the optimal classifier for this task using the evaluation metric area under precision-recall curve (0.296). From the cost analysis, it is observed that a cost of INR 15.92 million can be saved for 9381 instances of diabetic patient encounters. This work, the first such study done from Indian Healthcare perspective, built a model to predict the risk of readmission within 30 days of discharge for diabetes. This study concludes that the model could be incorporated in healthcare institutions to witness its effectiveness. Cost analysis shows huge savings which is significant for any healthcare system especially in developing countries like India.

show abstract

Impact of selected pre-processing techniques on prediction of risk of early readmission for diabetic patients in India

Cited by 15 publications

References 24 publications

Analytics in developing countries: methods, applications, and the impact on the UN Sustainable Development Goals

Analytics in developing countries: methods, applications, and the impact on the UN Sustainable Development Goals

Predicting 30-Day Hospital Readmission for Diabetes Patients using Multilayer Perceptron

Predictive risk modelling for early hospital readmission of patients with diabetes in India

Contact Info

Product

Resources

About