开发用于系统性硬化症相关指端溃疡的测量应用程序(SALVE:硬皮病病灶验证应用程序)
本研究开发了一款智能手机应用程序,用于系统性硬化症(SSc)患者每日拍摄指端病灶照片并填写患者报告结局指标。25例患者入组,19例完成30天研究,共分析506张图像;手动与自动测量面积在30天内的平均变化梯度高度相关(r=0.81),但手动测量值平均比自动测量值低40%,一致性界限较宽。
要点
- 即使存在显著手部残疾的SSc患者也能使用该应用程序每日拍摄病灶照片。
- 手动与自动测量面积在30天内的平均变化梯度高度相关(r=0.81)。
- 手动测量值平均比自动测量值低40%,一致性界限较宽。
核心结论
- 即使存在显著手部残疾的SSc患者也能使用该应用程序。
- 手指病灶的自动测量作为临床试验中的结局指标可能有价值。
研究设计与样本
- 开发了一款收集图像和患者报告结局指标(包括疼痛评分和HDISS-DU问卷)的应用程序;参与者每日拍摄病灶照片并上传至安全存储库,持续30天。
- 25例SSc相关指端病灶患者签署知情同意,其中19例完成30天研究,获得27个病灶的可评估数据。
- 病灶采用手动和基于机器学习方法的自动两种方式进行分析。
主要发现
- 基线疼痛评分均值(标准差)为5.7(2.4),HDISS-DU为2.2(0.9),提示病灶相关和疾病相关的高疾病负担。
- 共506张图像用于分析,每个病灶平均使用图像数为18.7(标准差8.3)。
- 第1天手动和自动病灶面积均值(标准差)分别为11.6(16.0)mm²和13.9(16.7)mm²。
- 手动面积每日减少0.08 mm²(30天共减少2.4 mm²),自动面积每日减少0.1 mm²(30天共减少3.0 mm²)。
- 手动与自动测量在30天内的平均变化梯度高度相关(r=0.81)。
局限性
- 25例签署知情同意的患者中仅19例完成30天研究。
- 手动测量与自动测量的一致性界限较宽。
- 手动测量值平均比自动测量值低40%。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: To test the hypothesis that photographs (in addition to self-reported data) can be collected daily by patients with SSc using a smartphone app designed specifically for digital lesions, and could provide an objective outcome measure for use in clinical trials. METHODS: An app was developed to collect images and patient-reported outcome measures including Pain score and the Hand Disability in Systemic Sclerosis-Digital Ulcers (HDISS-DU) questionnaire. Participants photographed their lesion(s) each day for 30 days and uploaded images to a secure repository. Lesions were analysed both manually and automatically, using a machine learning approach. RESULTS: Twenty-five patients with SSc-related digital lesions consented, of whom 19 completed the 30-day study, with evaluable data from 27 lesions. Mean (s.d.) baseline Pain score was 5.7 (2.4) and HDISS-DU 2.2 (0.9), indicating high lesion- and disease-related morbidity. A total of 506 images were used in the analysis [mean number of used images per lesion 18.7 (s.d. 8.3)]. Mean (s.d.) manual and automated lesion areas at day 1 were 11.6 (16.0) and 13.9 (16.7) mm2, respectively. Manual area decreased by 0.08 mm2 per day (2.4 mm2 over 30 days) and automated area by 0.1 mm2 (3.0 mm2 over 30 days). Average gradients of manual and automated measurements over 30 days correlated strongly (r = 0.81). Manual measurements were on average 40% lower than automated ones, with wide limits of agreement. CONCLUSION: Even patients with significant hand disability were able to use the app. Automated measurement of finger lesions could be valuable as an outcome measure in clinical trials.
引用
- Davison AK, Krishan A, New RP, et al. Development of a measuring app for systemic sclerosis-related digital ulceration (SALVE: Scleroderma App for Lesion VErification). Rheumatology (Oxford). 2024. PMID: 39029921. doi:10.1093/rheumatology/keae371
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。