PMID- 38398304
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240227
IS  - 2077-0383 (Print)
IS  - 2077-0383 (Electronic)
IS  - 2077-0383 (Linking)
VI  - 13
IP  - 4
DP  - 2024 Feb 8
TI  - Integrated Machine Learning Approach for the Early Prediction of Pressure Ulcers 
      in Spinal Cord Injury Patients.
LID - 10.3390/jcm13040990 [doi]
LID - 990
AB  - (1) Background: Pressure ulcers (PUs) substantially impact the quality of life of 
      spinal cord injury (SCI) patients and require prompt intervention. This study 
      used machine learning (ML) techniques to develop advanced predictive models for 
      the occurrence of PUs in patients with SCI. (2) Methods: By analyzing the medical 
      records of 539 patients with SCI, we observed a 35% incidence of PUs during 
      hospitalization. Our analysis included 139 variables, including baseline 
      characteristics, neurological status (International Standards for Neurological 
      Classification of Spinal Cord Injury [ISNCSCI]), functional ability (Korean 
      version of the Modified Barthel Index [K-MBI] and Functional Independence Measure 
      [FIM]), and laboratory data. We used a variety of ML methods-a graph neural 
      network (GNN), a deep neural network (DNN), a linear support vector machine 
      (SVM_linear), a support vector machine with radial basis function kernel 
      (SVM_RBF), K-nearest neighbors (KNN), a random forest (RF), and logistic 
      regression (LR)-focusing on an integrative analysis of laboratory, neurological, 
      and functional data. (3) Results: The SVM_linear algorithm using these composite 
      data showed superior predictive ability (area under the receiver operating 
      characteristic curve (AUC) = 0.904, accuracy = 0.944), as demonstrated by a 
      5-fold cross-validation. The critical discriminators of PU development were 
      identified based on limb functional status and laboratory markers of 
      inflammation. External validation highlighted the challenges of model 
      generalization and provided a direction for future research. (4) Conclusions: Our 
      study highlights the importance of a comprehensive, multidimensional data 
      approach for the effective prediction of PUs in patients with SCI, especially in 
      the acute and subacute phases. The proposed ML models show potential for the 
      early detection and prevention of PUs, thus contributing substantially to 
      improving patient care in clinical settings.
FAU - Kim, Yuna
AU  - Kim Y
AD  - Department of Rehabilitation Medicine, College of Medicine, Dankook University, 
      Cheonan 31116, Republic of Korea.
FAU - Lim, Myungeun
AU  - Lim M
AUID- ORCID: 0000-0003-4409-8890
AD  - Digital Biomedical Research Division, Electronics and Telecommunications Research 
      Institute, Daejeon 34129, Republic of Korea.
FAU - Kim, Seo Young
AU  - Kim SY
AD  - Department of Rehabilitation Medicine, College of Medicine, Dankook University, 
      Cheonan 31116, Republic of Korea.
FAU - Kim, Tae Uk
AU  - Kim TU
AD  - Department of Rehabilitation Medicine, College of Medicine, Dankook University, 
      Cheonan 31116, Republic of Korea.
FAU - Lee, Seong Jae
AU  - Lee SJ
AUID- ORCID: 0000-0001-7867-4695
AD  - Department of Rehabilitation Medicine, College of Medicine, Dankook University, 
      Cheonan 31116, Republic of Korea.
FAU - Bok, Soo-Kyung
AU  - Bok SK
AD  - Department of Rehabilitation Medicine, College of Medicine, Chungnam National 
      University, Daejeon 35015, Republic of Korea.
FAU - Park, Soojun
AU  - Park S
AD  - Digital Biomedical Research Division, Electronics and Telecommunications Research 
      Institute, Daejeon 34129, Republic of Korea.
FAU - Han, Youngwoong
AU  - Han Y
AUID- ORCID: 0000-0001-6418-7730
AD  - Digital Biomedical Research Division, Electronics and Telecommunications Research 
      Institute, Daejeon 34129, Republic of Korea.
FAU - Jung, Ho-Youl
AU  - Jung HY
AUID- ORCID: 0000-0002-4467-6307
AD  - Digital Biomedical Research Division, Electronics and Telecommunications Research 
      Institute, Daejeon 34129, Republic of Korea.
FAU - Hyun, Jung Keun
AU  - Hyun JK
AUID- ORCID: 0000-0001-9254-4424
AD  - Department of Rehabilitation Medicine, College of Medicine, Dankook University, 
      Cheonan 31116, Republic of Korea.
AD  - Department of Nanobiomedical Science and BK21 NBM Global Research Center for 
      Regenerative Medicine, Dankook University, Cheonan 31116, Republic of Korea.
AD  - Institute of Tissue Regeneration Engineering, Dankook University, Cheonan 31116, 
      Republic of Korea.
LA  - eng
GR  - 2019R1A6A1A11034536/National Research Foundation of Korea/
GR  - RS-2023-00208315/National Research Foundation of Korea/
GR  - 21YR2410/Electronics and Telecommunications Research Institute/
PT  - Journal Article
DEP - 20240208
PL  - Switzerland
TA  - J Clin Med
JT  - Journal of clinical medicine
JID - 101606588
PMC - PMC10889422
OTO - NOTNLM
OT  - laboratory test
OT  - machine learning
OT  - prediction model
OT  - pressure ulcer
OT  - spinal cord injury
COIS- The authors declare no conflicts of interest.
EDAT- 2024/02/24 11:44
MHDA- 2024/02/24 11:45
PMCR- 2024/02/08
CRDT- 2024/02/24 01:12
PHST- 2023/12/19 00:00 [received]
PHST- 2024/01/19 00:00 [revised]
PHST- 2024/02/07 00:00 [accepted]
PHST- 2024/02/24 11:45 [medline]
PHST- 2024/02/24 11:44 [pubmed]
PHST- 2024/02/24 01:12 [entrez]
PHST- 2024/02/08 00:00 [pmc-release]
AID - jcm13040990 [pii]
AID - jcm-13-00990 [pii]
AID - 10.3390/jcm13040990 [doi]
PST - epublish
SO  - J Clin Med. 2024 Feb 8;13(4):990. doi: 10.3390/jcm13040990.