Pressure injuries are a significant concern in clinical settings, requiring accurate assessment to prevent complications. Traditional assessment methods are often subjective and time-consuming.
Objective
This study aimed to develop and evaluate an AI-based intelligent system for assessing pressure injuries, focusing on improving accuracy and efficiency compared to traditional methods.
Methods
The study involved 108 ICU patients, divided into control and experimental groups. The control group used traditional assessment methods, while the experimental group used an AI-based system with deep learning algorithms which is built upon a convolutional neural network (CNN). The accuracy, efficiency, and integration of the AI system with electronic medical records were analyzed.
Results
The AI system achieved an accuracy of 90%, outperforming traditional methods which had an accuracy of 81.2%. The system also significantly reduced the assessment time, improving the overall efficiency of pressure injury evaluation.
Conclusion
The AI-based system demonstrated superior accuracy and efficiency in pressure injury assessment, offering a valuable tool for clinical use. Further research is needed to expand the system's application to other types of wounds.
KottnerJCuddiganJCarvilleK, et al.Prevention and treatment of pressure ulcers/injuries: the protocol for the second update of the international Clinical Practice Guideline 2019. J Tissue Viability2019; 28: 51–58.
2.
WasselCLDelhougneGGayleJA, et al.Risk of readmissions, mortality, and hospital-acquired conditions across hospital-acquired pressure injury (HAPI) stages in a US National Hospital Discharge database. Int Wound J2020; 17: 1924–1934.
3.
LinFWuZSongB, et al.The effectiveness of multicomponent pressure injury prevention programs in adult intensive care patients: a systematic review. Int J Nurs Stud2020; 102: 103483.
4.
LiZLinFThalibL,et al.Global prevalence and incidence of pressure injuries in hospitalised adult patients: a systematic review and meta-analysis. Int J Nurs Stud2020; 105: 103546.
5.
SiotosCBonettAMDamoulakisG, et al.Burden of pressure injuries: findings from the global burden of disease study. Eplasty2022; 22: e19.
6.
HajhosseiniBLongakerMTGurtnerGC. Pressure injury. Ann Surg2020; 271: 671–679.
7.
BatesDWLevineDSyrowatkaA, et al.The potential of artificial intelligence to improve patient safety: a scoping review. NPJ Digit Med2021; 4: 54.
8.
AnNDingHYangJ, et al.Deep ensemble learning for Alzheimer's disease classification. J Biomed Inform2020; 105: 103411.
9.
ZahiaSZapirainMBGSevillanoX, et al.Pressure injury image analysis with machine learning techniques: a systematic review on previous and possible future methods. Artif Intell Med2020; 102: 101742.
10.
AnisuzzamanDWangCRostamiB, et al.Image-based artificial intelligence in wound assessment: a systematic review. Adv Wound Care2022; 11: 687–709.
11.
GhiasiMMZendehboudiS. Application of decision tree-based ensemble learning in the classification of breast cancer. Comput Biol Med2021; 128: 104089.
12.
EstevaARobicquetARamsundarB, et al.A guide to deep learning in healthcare. Nat Med2019; 25: 24–29.
13.
ZhouZSiddiqueeMMRTajbakhshN,et al.Unet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging2019; 39: 1856–1867.
14.
ChiccoDJurmanG. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics2020; 21: 1–13.
15.
TangHHuZ. Research on medical image classification based on machine learning. IEEE Access2020; 8: 93145–93154.
16.
LiJOLiuHTingDSJ, et al.Digital technology, tele-medicine and artificial intelligence in ophthalmology: a global perspective. Prog Retin Eye Res2021; 82: 100900.
17.
RêgoADSFurtadoGEBernardesRA, et al.Development of Smart Clothing to Prevent Pressure Injuries in Bedridden Persons and/or with Severely Impaired Mobility: 4NoPressure Research Protocol. Healthcare (Basel)2023; 11: 1361.
18.
LinYTLinCSTsaiCS, et al.Comprehensive clinical application analysis of artificial intelligence-enabled electrocardiograms for screening multiple valvular heart diseases. Aging (Albany NY)2024; 16: 8717–8731.
19.
GuRXuG. A meta-analysis looking at the effects of continuous management for complications related to intraoperative pressure wound ulcers in women with breast cancer. Int J Clin Med Res2024; 2: 31. doi:https://doi.org/10.61466/ijcmr2040001
20.
GuoY. Effect of resident participation in ophthalmic surgery on wound dehiscence: A meta-analysis. Int J Clin Med Res2024; 2: 22. doi:https://doi.org/10.61466/ijcmr2020002
21.
JianyLXiuW. A meta-analysis evaluated the effectiveness of Chinese herbal medicine as a supplement to conventional care for patients with diabetic foot ulcers. Int J Clin Med Res2024; 2: 118–126. doi:https://doi.org/10.61466/ijcmr2040003
22.
KoangY. A meta-analysis on the use of photobiomodulation to regulate gingival wound healing in addition to periodontal therapies. Int J Clin Med Res2024; 2: 32. doi:https://doi.org/10.61466/ijcmr2040002
23.
OsamaHSaeedHNicolaM,et al.Neuraxial anesthesia compared to general anesthesia in subjects with hip fracture surgery: a meta-analysis. Int J Clin Med Res2023; 1: 66–76.
24.
ShaabanMEAMohamedAIM. Determining the efficacy of N-acetyl cysteine in treatment of pneumonia in COVID-19 hospitalized patients: a meta-analysis. Int J Clin Med Res2023; 1: 36–42.
25.
SinghRK. A meta-analysis of the impact on gastrectomy versus endoscopic submucosal dissection for early stomach cancer. Int J Clin Med Res2023; 1: 88–99.
26.
SundaresanA. Wound complications frequency in minor technique gastrectomy compared to open gastrectomy for gastric cancer: a meta-analysis. Int J Clin Med Res2023; 1: 100–107.
27.
WeangZ. A meta-analysis examining the impact of antibiotic prophylaxis on surgical site wound infection during third molar surgery. Int J Clin Med Res2024; 2: 34. doi:https://doi.org/10.61466/ijcmr2040004
28.
JiangMMaYGuoS, et al.Using machine learning technologies in pressure injury management: systematic review. JMIR Med Inform2021; 9: e25704.
29.
PierreKGuptaMRaviprasadA, et al.Medical imaging and multimodal artificial intelligence models for streamlining and enhancing cancer care: opportunities and challenges. Expert Rev Anticancer Ther2023; 23: 1265–1279.
30.
RibeiroFFidalgoFSilvaA, et al.Literature review of machine-learning algorithms for pressure ulcer prevention: Challenges and opportunities. Informatics; 2021: MDPI.
31.
ChangYKimJHShinHW, et al.Diagnosis of pressure ulcer stage using on-device AI. Appl Sci2024; 14: 7124.
32.
ElgendyMOHassanAHSaeedH, et al.Asthmatic children and MDI verbal inhalation technique counseling. Pulm Pharmacol Ther2020; 61: 101900.
33.
HarbHSElberryAARabeaH, et al.Performance of large spacer versus nebulizer T-piece in single-limb noninvasive ventilation. Respir Care2018; 63: 1360–1369.
34.
AbdelrahimME. Aerodynamic characteristics of nebulized terbutaline sulphate using the Andersen Cascade Impactor compared to the Next Generation Impactor. Pharm Dev Technol2011; 16: 137–145.
35.
ToffahaKMSimseklerMCEOmarMA. Leveraging artificial intelligence and decision support systems in hospital-acquired pressure injuries prediction: a comprehensive review. Artif Intell Med2023; 141: 102560.
36.
LauCHYuKH-OYipTF, et al.An artificial intelligence-enabled smartphone app for real-time pressure injury assessment. Front Med Technol2022; 4: 905074.
37.
SalehZSAl-NeamiAQRaadHK. Smart monitoring pad for prediction of pressure ulcers with an automatically activated integrated electro-therapy system. Designs2021; 5: 47.
