Muaddi Hala, Choudhary Ashok, Lee Frank, Anderson Stephanie S, Habermann Elizabeth, Etzioni David, McLaughlin Sarah, Kendrick Michael, Salehinejad Hojjat, Thiels Cornelius
Division of Hepatobiliary and Pancreas Surgery, Mayo Clinic, Rochester, MN.
Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, MN.
Ann Surg. 2025 Sep 1;282(3):419-428. doi: 10.1097/SLA.0000000000006826. Epub 2025 Jul 3.
To develop an artificial intelligence-based pipeline to assess and triage patient-submitted postoperative wound images.
The rise of outpatient surgeries, remote monitoring, and patient-submitted wound images via online portals has contributed to a growing administrative workload on clinicians. Early identification of surgical site infection (SSI) is essential for reducing postoperative morbidity.
Patients ≥18 years old who underwent surgery at 9 affiliated Mayo Clinic hospitals (2019-2022) and were captured by the National Surgical Quality Improvement Program (NSQIP) were included. Eligibility required submission of one image via the patient portal within 30 days after surgery. Images were independently screened in duplicate to determine the presence of an incision. SSI outcomes were obtained from NSQIP. The developed model consisted of 2 stages: incision detection and SSI detection in images with incisions. Four pretrained architectures were evaluated using 10-fold cross-validation, with upsampling and data augmentation to mitigate class imbalance. An end-to-end pipeline, image quality assessment and sensitivity analysis stratified by race were also performed.
Among 6060 patients, the median age was 54 years (interquartile range: 40-65), 61.4% (n=3805) were female, and 92.5% (n=5731) identified as White. SSIs were confirmed in 6.2% (n=386) images. Vision Transformer outperformed all others, achieving an incision detection accuracy of 0.94 (area under the curve=0.98) and an SSI detection accuracy of 0.73 (area under the curve=0.81). In addition, it demonstrated strong performance in assessing image quality. Sensitivity analysis revealed comparable performance across racial subgroups.
This artificial intelligence pipeline demonstrates promising performance in automating wound image assessment and SSI detection, reducing clinical workload and improving postoperative care.
开发一种基于人工智能的流程，用于评估和分类患者提交的术后伤口图像。
门诊手术、远程监测以及患者通过在线门户提交伤口图像的兴起，增加了临床医生的行政工作量。早期识别手术部位感染（SSI）对于降低术后发病率至关重要。
纳入2019年至2022年在梅奥诊所9家附属医院接受手术且被纳入国家外科质量改进计划（NSQIP）的18岁及以上患者。入选条件要求患者在术后30天内通过患者门户提交一张图像。图像由两人独立重复筛选以确定是否存在切口。SSI结局数据来自NSQIP。所开发的模型包括两个阶段：切口检测以及对有切口的图像进行SSI检测。使用10折交叉验证对四种预训练架构进行评估，并采用上采样和数据增强来减轻类别不平衡问题。还进行了端到端流程、图像质量评估以及按种族分层的敏感性分析。
在6060例患者中，中位年龄为54岁（四分位间距：40 - 65岁），61.4%（n = 3805）为女性，92.5%（n = 5731）为白人。6.2%（n = 386）的图像确诊为SSI。视觉Transformer的表现优于其他所有架构，切口检测准确率达到0.94（曲线下面积 = 0.98），SSI检测准确率为0.73（曲线下面积 = 0.81）。此外，它在评估图像质量方面表现出色。敏感性分析显示不同种族亚组的表现相当。
这种人工智能流程在自动化伤口图像评估和SSI检测方面表现出了良好的性能，可减轻临床工作量并改善术后护理。
