A remote monitoring system based on deep learning for real-time assessment of free flaps

Clinical Snapshot

Key Findings

• P Value: Not reported for diagnostic accuracy measures

• Effect Size: Sensitivity 95.18%, specificity ~97.38% (calculated from false-positive rate 2.62%)

• Primary Outcome: Diagnostic accuracy for venous congestion detection

• Nnt Or Sensitivity: Sensitivity 95.18%, specificity 97.38%, accuracy 92.16%

• Confidence Interval: Not reported

Clinical Application

Requires smartphone technology and technical infrastructure; may face regulatory hurdles Would require TGA approval as medical device software; integration with existing hospital systems needed; cost-effectiveness analysis required for PBS consideration Patients undergoing free flap reconstruction requiring postoperative monitoring

Abstract

PURPOSE: Venous congestion is a major cause of postoperative free flap compromise, and early detection is crucial for improving flap salvage rates and patient outcomes. This study aimed to develop and validate a deep learning (DL)-integrated remote monitoring system with a smartphone application for real-time, quantitative assessment of free flaps, with a specific focus on the early detection of venous congestion. METHODS: This diagnostic study was conducted at our institution. Patients aged 18-60 years who underwent free flap reconstruction between January 2019 and June 2025 were included. The study was divided into three phases: a 5-month model training phase for DL model development and internal validation, a 5-month external validation and clinical application phase, and a 4-month clinical comparison phase. The DL model was developed using TensorFlow Lite and a Flap Segmentation Network (FS-Net). Performance was evaluated through accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and clinical outcomes including time to detection and flap survival. RESULTS: A total of 1649 photographs from 615 patients were analyzed in the development and validation of the DL classification model between January 2019 and February 2025. During model development, the model achieved an accuracy of 86.8%, sensitivity of 92.4%, specificity of 79.7%, and AUC of 0.88. Internal validation improved these metrics to 87.6%, 95.0%, 81.1%, and 0.92, respectively. External validation demonstrated the model's generalizability, with an accuracy of 89.3%, sensitivity of 96.2%, specificity of 84.9%, and AUC of 0.93. The clinical application phase showed that the system had an overall accuracy of 92.16%, sensitivity of 95.18%, false-positive rate of 2.62%, and false-negative rate of 4.82%. A total of 113 patients were included in clinical comparison between March 2025 and June 2025. The remote monitoring group exhibited a trend towards a shorter mean time to congestion detection, higher flap survival rate, and shorter mean time to re-exploration, although these differences were not statistically significant. CONCLUSIONS: The DL-integrated remote monitoring system demonstrated high accuracy and reliability in detecting venous congestion. It provided an objective and real-time tool that may help reduce clinical burden and support timely intervention in free flap management. However, its impact on definitive clinical outcomes required further validation in larger studies.

References

1. 1.Huang, X., Cheng, C., Ren, S., Fang, R., Lu, F., Wu, C., & Jiang, Z. (2026). A remote monitoring system based on deep learning for real-time assessment of free flaps. PLoS One. https://doi.org/10.1371/journal.pone.0347343