Imaging Based Surgical Site Infection Detection Using Artificial Intelligence

Objective: To develop an AI-based pipeline to assess and triage patient-submitted postoperative wound images. Background: 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. Methods: Patients ≥18 years old who underwent surgery at nine affiliated Mayo Clinic hospitals (2019-2022) and were captured by National Surgical Quality Improvement Program (NSQIP) were included. Eligibility required submission of one image via the patient portal within 30-days post-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 two 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. Results: Among 6,060 patients, the median age was 54 years (IQR 40-65), 61.4% were (n=3,805) female, and 92.5% (n=5,731) 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 (AUC 0.98) and an SSI detection accuracy of 0.73 (AUC 0.81). In addition, it demonstrated strong performance in assessing image quality. Sensitivity analysis revealed comparable performance across racial subgroups. Conclusion: This AI pipeline demonstrates promising performance in automating wound images assessment and SSI detection, reducing clinical workload and improving postoperative care.