東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Predicting 30-Day Diabetic Patient R...

Tipu, Amina,

FindBook

Google Book

Amazon

博客來

Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection // Amina Tipu.
作者:	Tipu, Amina,
面頁冊數:	1 electronic resource (221 pages)
附註:	Source: Masters Abstracts International, Volume: 84-04.
Contained By:	Masters Abstracts International84-04.
標題:	Systems science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29328102
ISBN:	9798351457024

Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection /
Tipu, Amina,

Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection /Amina Tipu. - 1 electronic resource (221 pages)

Source: Masters Abstracts International, Volume: 84-04.

This research study focuses on predicting 30-day hospital readmissions for diabetic patients via the knowledge discovery process and a heterogeneous ensemble feature selection algorithm. Patient readmissions are a huge financial cost to hospitals and health care systems at large and are linked to poorer patient health outcomes. The Centers for Medicare and Medicaid recent regulation surrounding financial penalizations towards hospitals with considerable amounts of patient readmissions for certain disease states as well as avoidable readmissions has brought readmissions to the forefront of health services research. This study aims to identify factors that are linked to patient readmissions via the heterogeneous ensemble feature selection method as well as predict patients most likely to be readmitted. To examine diabetic patient readmissions a publicly available dataset from the UCI Machine Learning Repository was used. The dataset contains patient information from 130 hospitals across the United States from 1999-2008. The research methodology was carried out via three unique implementations, in the primary no feature selection or tuning is carried out, and in the second three feature selection techniques: recursive feature elimination, random forest, and mutual information are applied with their results averaged. Lastly, the HEFS algorithm was applied to the dataset in the third implementation. Ten prediction algorithms are employed: Logistic Regression, Gaussian Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors Support Vector Machine, Bagging, Adaptive Boosting, Gradient Boosting, and Multi-Layer Perceptron. The performance metric results show an improvement is achieved based on the HEFS algorithm in the case of LR, RF, KNN, SVM, BG, ADA, GB, and MLP in comparison to LR and GNB in differentiating between patients likely to be readmitted and not. The research output will act as a decision support tool for medical health professionals and executives in allocating and assigning resources to relevant patients regarding readmissions.

English

ISBN: 9798351457024Subjects--Topical Terms:

3168411
Systems science.
Subjects--Index Terms:

Heterogeneous ensemble feature selection

Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection /
LDR:03439nmm a22003853i 4500 001 2396136
005 20250522083156.5
006 m o d
007 cr|nu||||||||
008 251215s2022 miu||||||m |||||||eng d
020 $a 9798351457024
035 $a (MiAaPQD)AAI29328102
035 $a AAI29328102
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tipu, Amina, $e author. $3 3765713
245 1 0 $a Predicting 30-Day Diabetic Patient Readmissions via Heterogeneous Ensemble Feature Selection / $c Amina Tipu.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 1 electronic resource (221 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-04.
500 $a Advisors: Wang, Yong Committee members: Khasawneh, Mohammad T.; Shi, Chao.
502 $b M.S. $c State University of New York at Binghamton $d 2022.
520 $a This research study focuses on predicting 30-day hospital readmissions for diabetic patients via the knowledge discovery process and a heterogeneous ensemble feature selection algorithm. Patient readmissions are a huge financial cost to hospitals and health care systems at large and are linked to poorer patient health outcomes. The Centers for Medicare and Medicaid recent regulation surrounding financial penalizations towards hospitals with considerable amounts of patient readmissions for certain disease states as well as avoidable readmissions has brought readmissions to the forefront of health services research. This study aims to identify factors that are linked to patient readmissions via the heterogeneous ensemble feature selection method as well as predict patients most likely to be readmitted. To examine diabetic patient readmissions a publicly available dataset from the UCI Machine Learning Repository was used. The dataset contains patient information from 130 hospitals across the United States from 1999-2008. The research methodology was carried out via three unique implementations, in the primary no feature selection or tuning is carried out, and in the second three feature selection techniques: recursive feature elimination, random forest, and mutual information are applied with their results averaged. Lastly, the HEFS algorithm was applied to the dataset in the third implementation. Ten prediction algorithms are employed: Logistic Regression, Gaussian Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors Support Vector Machine, Bagging, Adaptive Boosting, Gradient Boosting, and Multi-Layer Perceptron. The performance metric results show an improvement is achieved based on the HEFS algorithm in the case of LR, RF, KNN, SVM, BG, ADA, GB, and MLP in comparison to LR and GNB in differentiating between patients likely to be readmitted and not. The research output will act as a decision support tool for medical health professionals and executives in allocating and assigning resources to relevant patients regarding readmissions.
546 $a English
590 $a School code: 0792
650 4 $a Systems science. $3 3168411
653 $a Heterogeneous ensemble feature selection
653 $a Diabetic patient readmissions
653 $a Financial penalizations
690 $a 0790
710 2 $a State University of New York at Binghamton. $b Systems Science Industrial Engineering. $e degree granting institution. $3 3765714
720 1 $a Wang, Yong $e degree supervisor.
773 0 $t Masters Abstracts International $g 84-04.
790 $a 0792
791 $a M.S.
792 $a 2022
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29328102