國立虎尾科技大學 |

An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores).

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores)./
Author:	Dweekat, Odai Y.
Description:	1 online resource (240 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
Subject:	Industrial engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798379733728

An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores).
Dweekat, Odai Y.

An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores). - 1 online resource (240 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--State University of New York at Binghamton, 2023.

Includes bibliographical references

Hospital-Acquired Pressure Injuries (HAPIs), known as bedsores, are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. The injuries develop because of pressure or pressure in combination with shear resulting in tissue deformation or tissue ischemia. HAPIs refer to these injuries that occur while admitted to the healthcare system. The Braden Scale, commonly used to identify HAPIs, is limited by the number of factors that a caregiver can reasonably assess during patient care. Moreover, it identifies a large percentage of hospitalized patients as being at risk for developing HAPIs. In the last decade, Machine Learning (ML) techniques have been used to predict HAPIs by utilizing related risk factors. Nevertheless, none of these studies consider the change in patient status from admission until discharge. Until now, all studies have predicted who will develop HAPI, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop pressure injuries; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop an integrated framework of multifaceted machine learning, metaheuristics, and Braden scale to predict if and when HAPI occurs. Three different types of predictive models are investigated in two phases. Phase 1: an integrated system of Braden, Genetic Algorithm, and Cost-Sensitive Support Vector Machine (Braden-GA-CS-SVM) to predict if a patient will develop HAPI. Braden-GA-CS-SVM considers the changes in patients' status at three points in time during hospitalization. Phase 2: an integrated system of Braden and ML to predict when a patient is likely to develop HAPI. Two predictive models are explored in phase 2: A) an integrated system of Braden and SVM (Braden-SVM) that considers the changes in patients' status at three points in time during hospitalization. The timing of HAPI is measured from admission to HAPI occurrence. B) an integrated system of Braden and Random Forest (Braden-RF) that considers changes in patients' status based on all changes in patients' diagnoses from admission until HAPI occurrence. The timing of HAPI is measured from the day of diagnosis until HAPI occurrence. The performance of Braden-GA-CS-SVM, Braden-SVM, and Braden-RF are compared with the most common algorithms used to predict HAPI. Braden-GA-CS-SVM achieved the best sensitivity (74.29 ± 1.23) to predict if a patient will develop HAPI. Both Braden-SVM and Braden-RF achieved the best sensitivity (75.56 and 89.33 ± 0.49, respectively) to predict when HAPI will occur for at-risk patients. The proposed research framework achieves better performance than Braden and reduces the number of patients identified as at-risk. Furthermore, allocating targeted resources allows for better allocation of resources to high-risk patients. It will result in cost savings, better utilization of resources, and aid with better medical staff planning to provide intervention to those patients. The research outcomes will provide guidance on early target intervention when it is needed most and will help reduce unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379733728Subjects--Topical Terms:

679492
Industrial engineering.
Subjects--Index Terms:

BedsoresIndex Terms--Genre/Form:

554714
Electronic books.

An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores).
LDR:04928ntm a22004217 4500 001 1141752
005 20240414211504.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379733728
035 $a (MiAaPQ)AAI30527103
035 $a AAI30527103
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Dweekat, Odai Y. $3 1465709
245 1 3 $a An Integrated Framework of Multifaceted Machine Learning, Metaheuristics, and Braden Scale to Predict Hospital-Acquired Pressure Injuries (Bedsores).
264 0 $c 2023
300 $a 1 online resource (240 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: Dissertations Abstracts International, Volume: 84-12, Section: B.
500 $a Advisor: Lam, Sarah S.
502 $a Thesis (Ph.D.)--State University of New York at Binghamton, 2023.
504 $a Includes bibliographical references
520 $a Hospital-Acquired Pressure Injuries (HAPIs), known as bedsores, are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. The injuries develop because of pressure or pressure in combination with shear resulting in tissue deformation or tissue ischemia. HAPIs refer to these injuries that occur while admitted to the healthcare system. The Braden Scale, commonly used to identify HAPIs, is limited by the number of factors that a caregiver can reasonably assess during patient care. Moreover, it identifies a large percentage of hospitalized patients as being at risk for developing HAPIs. In the last decade, Machine Learning (ML) techniques have been used to predict HAPIs by utilizing related risk factors. Nevertheless, none of these studies consider the change in patient status from admission until discharge. Until now, all studies have predicted who will develop HAPI, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop pressure injuries; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop an integrated framework of multifaceted machine learning, metaheuristics, and Braden scale to predict if and when HAPI occurs. Three different types of predictive models are investigated in two phases. Phase 1: an integrated system of Braden, Genetic Algorithm, and Cost-Sensitive Support Vector Machine (Braden-GA-CS-SVM) to predict if a patient will develop HAPI. Braden-GA-CS-SVM considers the changes in patients' status at three points in time during hospitalization. Phase 2: an integrated system of Braden and ML to predict when a patient is likely to develop HAPI. Two predictive models are explored in phase 2: A) an integrated system of Braden and SVM (Braden-SVM) that considers the changes in patients' status at three points in time during hospitalization. The timing of HAPI is measured from admission to HAPI occurrence. B) an integrated system of Braden and Random Forest (Braden-RF) that considers changes in patients' status based on all changes in patients' diagnoses from admission until HAPI occurrence. The timing of HAPI is measured from the day of diagnosis until HAPI occurrence. The performance of Braden-GA-CS-SVM, Braden-SVM, and Braden-RF are compared with the most common algorithms used to predict HAPI. Braden-GA-CS-SVM achieved the best sensitivity (74.29 ± 1.23) to predict if a patient will develop HAPI. Both Braden-SVM and Braden-RF achieved the best sensitivity (75.56 and 89.33 ± 0.49, respectively) to predict when HAPI will occur for at-risk patients. The proposed research framework achieves better performance than Braden and reduces the number of patients identified as at-risk. Furthermore, allocating targeted resources allows for better allocation of resources to high-risk patients. It will result in cost savings, better utilization of resources, and aid with better medical staff planning to provide intervention to those patients. The research outcomes will provide guidance on early target intervention when it is needed most and will help reduce unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Industrial engineering. $3 679492
650 4 $a Bioinformatics. $3 583857
653 $a Bedsores
653 $a Braden Scale
653 $a Cost-Sensitive Support Vector Machine
653 $a Genetic algorithm
653 $a Hospital-Acquired Pressure Injuries
653 $a Machine Learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0546
690 $a 0796
690 $a 0800
690 $a 0715
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a State University of New York at Binghamton. $b Systems Science Industrial Engineering. $3 1182293
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30527103 $z click for full text (PQDT)