Weatherall Teagan, Avsar Pinar, Nugent Linda, Moore Zena, McDermott John H, Sreenan Seamus, Wilson Hannah, McEvoy Natalie L, Derwin Rosemarie, Chadwick Paul, Patton Declan
Skin Wounds and Trauma (SWaT) Research Centre, RCSI University of Medicine and Health Sciences, Dublin, Ireland; School of Nursing and Midwifery, RCSI University of Medicine and Health Sciences, Dublin, Ireland.
Skin Wounds and Trauma (SWaT) Research Centre, RCSI University of Medicine and Health Sciences, Dublin, Ireland; School of Nursing and Midwifery, RCSI University of Medicine and Health Sciences, Dublin, Ireland; Fakeeh College of Medical Sciences, Jeddah, Saudi Arabia.
J Tissue Viability. 2024 Nov;33(4):853-863. doi: 10.1016/j.jtv.2024.07.004. Epub 2024 Jul 11.
Globally, diabetes mellitus poses a significant health challenge as well as the associated complications of diabetes, such as diabetic foot ulcers (DFUs). The early detection of DFUs is important in the healing process and machine learning may be able to help inform clinical staff during the treatment process.
A PRISMA-informed search of the literature was completed via the Cochrane Library and MEDLINE (OVID), EMBASE, CINAHL Plus and Scopus databases for reports published in English and in the last ten years. The primary outcome of interest was the impact of machine learning on the prediction of DFUs. The secondary outcome was the statistical performance measures reported. Data were extracted using a predesigned data extraction tool. Quality appraisal was undertaken using the evidence-based librarianship critical appraisal tool.
A total of 18 reports met the inclusion criteria. Nine reports proposed models to identify two classes, either healthy skin or a DFU. Nine reports proposed models to predict the progress of DFUs, for example, classing infection versus non-infection, or using wound characteristics to predict healing. A variety of machine learning techniques were proposed. Where reported, sensitivity = 74.53-98 %, accuracy = 64.6-99.32 %, precision = 62.9-99 %, and the F-measure = 52.05-99.0 %.
A variety of machine learning models were suggested to successfully classify DFUs from healthy skin, or to inform the prediction of DFUs. The proposed machine learning models may have the potential to inform the clinical practice of managing DFUs and may help to improve outcomes for individuals with DFUs. Future research may benefit from the development of a standard device and algorithm that detects, diagnoses and predicts the progress of DFUs.
在全球范围内，糖尿病及其相关并发症（如糖尿病足溃疡，DFUs）对健康构成了重大挑战。DFUs的早期检测对愈合过程很重要，机器学习或许能够在治疗过程中为临床工作人员提供帮助。
通过Cochrane图书馆、MEDLINE（OVID）、EMBASE、CINAHL Plus和Scopus数据库，对过去十年以英文发表的报告进行了基于PRISMA的文献检索。感兴趣的主要结果是机器学习对DFUs预测的影响。次要结果是报告的统计性能指标。使用预先设计的数据提取工具提取数据。使用循证图书馆学批判性评价工具进行质量评估。
共有18份报告符合纳入标准。9份报告提出了用于识别两类情况的模型，即健康皮肤或DFU。9份报告提出了用于预测DFUs进展的模型，例如，区分感染与非感染，或利用伤口特征预测愈合情况。提出了多种机器学习技术。在有报告的情况下，敏感性为74.53%-98%，准确性为64.6%-99.32%，精确性为62.9%-99%，F值为52.05%-99.0%。
提出了多种机器学习模型，以成功地将DFUs与健康皮肤进行分类，或为DFUs的预测提供信息。所提出的机器学习模型可能有潜力为DFUs的临床管理实践提供信息，并可能有助于改善DFUs患者的治疗结果。未来的研究可能会受益于开发一种能够检测、诊断和预测DFUs进展的标准设备和算法。
