1
|
Kim J, Lee SM, Kim DE, Kim S, Chung MJ, Kim Z, Kim T, Lee KT. Development of an Automated Free Flap Monitoring System Based on Artificial Intelligence. JAMA Netw Open 2024; 7:e2424299. [PMID: 39058486 DOI: 10.1001/jamanetworkopen.2024.24299] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/28/2024] Open
Abstract
Importance Meticulous postoperative flap monitoring is essential for preventing flap failure and achieving optimal results in free flap operations, for which physical examination has remained the criterion standard. Despite the high reliability of physical examination, the requirement of excessive use of clinician time has been considered a main drawback. Objective To develop an automated free flap monitoring system using artificial intelligence (AI), minimizing human involvement while maintaining efficiency. Design, Setting, and Participants In this prognostic study, the designed system involves a smartphone camera installed in a location with optimal flap visibility to capture photographs at regular intervals. The automated program identifies the flap area, checks for notable abnormalities in its appearance, and notifies medical staff if abnormalities are detected. Implementation requires 2 AI-based models: a segmentation model for automatic flap recognition in photographs and a grading model for evaluating the perfusion status of the identified flap. To develop this system, flap photographs captured for monitoring were collected from patients who underwent free flap-based reconstruction from March 1, 2020, to August 31, 2023. After the 2 models were developed, they were integrated to construct the system, which was applied in a clinical setting in November 2023. Exposure Conducting the developed automated AI-based flap monitoring system. Main Outcomes and Measures Accuracy of the developed models and feasibility of clinical application of the system. Results Photographs were obtained from 305 patients (median age, 62 years [range, 8-86 years]; 178 [58.4%] were male). Based on 2068 photographs, the FS-net program (a customized model) was developed for flap segmentation, demonstrating a mean (SD) Dice similarity coefficient of 0.970 (0.001) with 5-fold cross-validation. For the flap grading system, 11 112 photographs from the 305 patients were used, encompassing 10 115 photographs with normal features and 997 with abnormal features. Tested on 5506 photographs, the DenseNet121 model demonstrated the highest performance with an area under the receiver operating characteristic curve of 0.960 (95% CI, 0.951-0.969). The sensitivity for detecting venous insufficiency was 97.5% and for arterial insufficiency was 92.8%. When applied to 10 patients, the system successfully conducted 143 automated monitoring sessions without significant issues. Conclusions and Relevance The findings of this study suggest that a novel automated system may enable efficient flap monitoring with minimal use of clinician time. It may be anticipated to serve as an effective surveillance tool for postoperative free flap monitoring. Further studies are required to verify its reliability.
Collapse
Affiliation(s)
- Jisu Kim
- Department of Plastic Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Sang Mee Lee
- Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, South Korea
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, South Korea
| | - Da Eun Kim
- Department of Plastic Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Sungjin Kim
- Banobagi Plastic Surgery Clinic, Seoul, South Korea
| | - Myung Jin Chung
- Department of Data Convergence and Future Medicine, Sungkyunkwan University School of Medicine, Seoul, South Korea
- Department of Radiology and Medical AI Research Center, Samsung Medical Center, Seoul, South Korea
| | - Zero Kim
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, South Korea
- Department of Data Convergence and Future Medicine, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Taeyoung Kim
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, South Korea
| | - Kyeong-Tae Lee
- Department of Plastic Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| |
Collapse
|
2
|
Muacevic A, Adler JR, Osaki T, Sakakibara S. Simple and Easily Interpretable Flap Monitoring Method Using a Commercial Pulse Oximeter and a Widely Used Bedside Patient Monitor. Cureus 2022; 14:e32549. [PMID: 36654599 PMCID: PMC9840461 DOI: 10.7759/cureus.32549] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 12/14/2022] [Indexed: 12/23/2022] Open
Abstract
Background Various methods for monitoring after free flap surgery have been reported in the literature. Among them, pulse oximetry shows a sensitive reaction to vascular issues, and it is easy to interpret visually. However, previous reports used special equipment that was less commonly used and difficult to generalize. In this study, we used a commercial pulse oximeter and a widely used bedside patient monitor to monitor transplanted free tissue and lower extremities of healthy subjects with impaired circulation. Methods A reflectance pulse oximeter sensor was attached on the flap after free tissue transplantation. The sensor was connected to a bedside patient monitor, and the flap oxygen saturation (SpO2) levels and arterial waveforms were continuously monitored. Additionally, blood circulation disorder was induced in the lower limbs of healthy volunteers using pressure cuff inflation on the thigh, and the waveform and SpO2 levels on the pulse oximeter attached to the lower leg were monitored. Results Twenty-two patients were included in this study. No postoperative vascular issues were observed in any case. Pulse oximeters showed normal rhythmic wavelengths, and the flap SpO2 level ranged approximately >90%. The pulse oximeter waveform rapidly disappeared during arterial occlusion in the thigh pressure cuff inflation test, and the waveform flattened and the SpO2 level decreased slightly during venous congestion. Conclusion Flap monitoring using a commercially available pulse oximeter and a bedside patient monitor is a versatile, easy-to-interpret, and useful method. Changes in waveform and SpO2 levels appear during arterial and venous circulation disorders, and these changes can be differentiated.
Collapse
|
3
|
Molitor M, Mestak O, Pink R, Foltan R, Sukop A, Lucchina S. The use of sentinel skin islands for monitoring buried and semi-buried micro-vascular flaps. Part I: Summary and brief description of monitoring methods. Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub 2021; 165:113-130. [PMID: 33821844 DOI: 10.5507/bp.2021.016] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2020] [Accepted: 02/26/2021] [Indexed: 11/23/2022] Open
Abstract
Micro-vascular flaps have been used for the repair of challenging defects for over 45 years. The risk of failure is reported to be around 5-10% which despite medical and technical advances in recent years remains essentially unchanged. Precise, continuous, sensitive and specific monitoring together with prompt notification of vascular compromise is crucial for the success of the procedure. In this review, we provide a classification and brief description of the reported methods for monitoring the micro-vascular flap and a summary of the benefits over direct visual monitoring. Over 40 different monitoring techniques have been reported but their comparative merits are not always obvious. One looks for early detection of a flap's compromise, improved flap salvage rate and a minimal false-positive or false-negative rate. The cost-effectiveness of any method should also be considered. Direct visualisation of the flap is the method most generally used and still seems to be the simplest, cheapest and most reliable method for flap monitoring. Considering the alternatives, only implantable Doppler ultrasound probes, near infrared spectroscopy and laser Doppler flowmetry have shown any evidence of improved flap salvage rates over direct visual monitoring.
Collapse
Affiliation(s)
- Martin Molitor
- Department of Plastic Surgery, First Faculty of Medicine Charles University and Na Bulovce Hospital, Prague, Czech Republic
| | - Ondrej Mestak
- Department of Plastic Surgery, First Faculty of Medicine Charles University and Na Bulovce Hospital, Prague, Czech Republic
| | - Richard Pink
- Department of Maxillofacial Surgery, University Hospital Olomouc and Faculty of Medicine and Dentistry, Palacky University Olomouc, Czech Republic
| | - Rene Foltan
- Department of Maxillofacial Surgery, General University Hospital and 1st Faculty of Medicine, Charles University, Prague, Czech Republic
| | - Andrej Sukop
- Department of Plastic Surgery, University Hospital Kralovske Vinohrady and 3rd Faculty of Medicine, Charles University, Prague, Czech Republic
| | - Stefano Lucchina
- Hand Unit, General Surgery Department, Locarno's Regional Hospital, Via Ospedale 1, 6600 Locarno, Switzerland
| |
Collapse
|
4
|
Jones VM, Suarez-Martinez AD, Hodges NA, Murfee WL, Llull R, Katz AJ. A clinical perspective on adipose-derived cell therapy for enhancing microvascular health and function: Implications and applications for reconstructive surgery. Microcirculation 2020; 28:e12672. [PMID: 33174272 DOI: 10.1111/micc.12672] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2020] [Revised: 09/18/2020] [Accepted: 11/04/2020] [Indexed: 12/21/2022]
Abstract
Restoration of form and function requires apposition of tissues in the form of flaps to reconstitute local perfusion. Successful reconstruction relies on flap survival and its integration with the recipient bed. The flap's precariously perfused hypoxic areas undergo adaptive microvascular changes both internally and in connection with the recipient bed. A cell-mediated, coordinated response to hypoxia drives these adaptive processes, restoring a tissue's normoxic homeostasis via de novo vasculogenesis, sprouting angiogenesis, and stabilizing arterialization. As cells exert prolonged and coordinated effects on site, their use as biological agents merit translational consideration of sourcing angio-competent cells and delivering them to territories enduring microcirculatory acclimatization. Angio-competent cells abound in adipose tissue: a reliable, accessible, and expendable source of adipose-derived cells (ADC). When subject to enzymatic digestion and centrifugation, adipose tissue separates its various ADC: A subset of buoyant oil-dense adipocytes (the tissue's parenchymal component) accumulates on a supra-natant layer, whereas the mesenchymal component remains in the infra-natant sediment, containing the tissue's stromal vascular fraction (SVF), where angio-component cells abound. The SVF can be further manipulated, selected, or culture expanded into more specific stromal subsets (herein defined as adipose stromal cells, ASC). While promising clinical applications for ADC await clinical proof and regulatory authorization, basic science investigation is needed to elucidate the specific ADC mechanisms that influence microvascular growth, remodeling, and function following flap surgery. The objective of this article is to share the clinical perspectives of reconstructive plastic surgeons regarding the use of ADC-based therapies to help with flap tissue integration, revascularization, and wound healing. Specifically, the focus will be on considering the potential for ADC as therapeutic agents and how their clinical application motivates basic science opportunities.
Collapse
Affiliation(s)
- V Morgan Jones
- Department of Surgery, Wake Forest School of Medicine, Winston-Salem, NC, USA
| | - Ariana D Suarez-Martinez
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Nicholas A Hodges
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Walter L Murfee
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Ramon Llull
- Department of Plastic Surgery, Hospital Quiron Salud PalmaPlanas, Palma, Spain
| | - Adam J Katz
- Department of Plastic and Reconstructive Surgery, Wake Forest School of Medicine, Winston-Salem, NC, USA
| |
Collapse
|
5
|
The use of venous anastomotic flow couplers to monitor buried free DIEP flap reconstructions following nipple-sparing mastectomy. JPRAS Open 2019; 23:50-54. [PMID: 32158905 DOI: 10.1016/j.jpra.2019.09.002] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2019] [Accepted: 09/25/2019] [Indexed: 11/24/2022] Open
Abstract
Nipple sparing mastectomy with free tissue transfer for breast reconstruction offers excellent aesthetic outcomes but poses a challenge in monitoring the buried flap. Venous anastomotic flow couplers directly monitor buried flaps without the need for monitoring skin paddles. In a two year period we used the Synovis GEM™ flow coupler on 24 DIEP flaps. In our practice, flow couplers are effective in monitoring buried free flaps for breast reconstruction. The avoidance of a second procedure to remove a skin paddle improves patient experience and nullifies the additional flow coupler cost. One patient needed return to theatre when a Doppler wire became dislodged early in the series. There were no other issues with flap monitoring and no flap failures. We offer our tips to optimise flow coupler use.
Collapse
|
6
|
Spiers E. Managing vascular compromise of hand and digit replantation following traumatic amputation. ACTA ACUST UNITED AC 2018; 27:S50-S56. [PMID: 30418845 DOI: 10.12968/bjon.2018.27.sup20.s50] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Hands are anatomically complex and have great social, physical and emotional importance. Hand or digit replantation following traumatic partial or complete amputation is a complex injury for nursing staff to understand and manage. The absence of clear guidance, combined with a lack of consensus in the literature gives rise to ambiguity and insufficient understanding of appropriate and effective management. This article aims to outline nursing care of the patient in the first few days following hand or digit reattachment, particularly focusing on the recognition and management of arterial and venous compromise. Complications must be recognised and acted on quickly to give the best chance of survival so it is essential for nurses to have an accurate understanding of the signs, symptoms and management options of vascular compromise. Leech therapy, also discussed, has long been used as a nonsurgical option in the management of venous congestion and is a simple and minimally invasive method of managing congestion.
Collapse
Affiliation(s)
- Emma Spiers
- Military Burns and Plastics Nurse, The Queen Elizabeth Hospital, Birmingham
| |
Collapse
|
7
|
Zoccali G, Molina A, Farhadi J. Is long-term post-operative monitoring of microsurgical flaps still necessary? J Plast Reconstr Aesthet Surg 2017. [PMID: 28648581 DOI: 10.1016/j.bjps.2017.05.041] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Autologous microsurgical flap reconstruction has become commonplace in most plastic surgery units, and the success rates of this procedure have markedly increased over recent years. However, the possibility of flap failure still needs to be considered. A review of the literature reveals that the critical period for flap-threatening complications is the first 24-48 post-operative hours; however, the window for the onset of these complications remains open for up to 7 days post-operatively. In this study, we focus on the timing of flap complications, aiming to elucidate the time period over which meticulous flap monitoring can positively contribute to flap salvage rates. The relevant literature on the study topic was collated and reviewed in conjunction with the senior author's case series, which consisted of a total of 335 free flaps used during a 2-year period for breast and head and neck reconstruction or limb trauma. Patients' series were then divided into groups according to the complications timing. The correlation between the timing of complications and the flap salvage rate was investigated among the groups. Overall analysis of both the literature and our own data on 335 free flaps showed a progressive reduction in flap salvage rate during post-operative days; the correlations between the times of complication onset and the flap salvage rates in all groups were significant up to the third post-operative day. The correlations between salvage rates and later complications were not significant. Our results suggest that hourly flap monitoring should be compulsory during the first 48 post-operative hours, but clinical monitoring four times daily should be sufficient thereafter.
Collapse
Affiliation(s)
- Giovanni Zoccali
- Department of Plastic & Reconstructive Surgery, Guy's and St. Thomas' Hospital NHS Foundation Trust, London, UK.
| | - Alexandra Molina
- Department of Plastic & Reconstructive Surgery, Guy's and St. Thomas' Hospital NHS Foundation Trust, London, UK
| | - Jian Farhadi
- Department of Plastic & Reconstructive Surgery, Guy's and St. Thomas' Hospital NHS Foundation Trust, London, UK; Plastic and Reconstructive Surgery, Basel University, Basel, CH, Switzerland
| |
Collapse
|
8
|
Alemi AS, Seth R, Heaton C, Wang SJ, Knott PD. Comparison of Video and In-person Free Flap Assessment following Head and Neck Free Tissue Transfer. Otolaryngol Head Neck Surg 2017; 156:1035-1040. [DOI: 10.1177/0194599816688620] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Objective Compare the efficiency of remote telehealth flap assessments with traditional in-person flap assessments. Study Design Observational study with retrospective review. Setting Tertiary academic medical center. Subjects and Methods All patients undergoing head and neck free tissue transfer were included in the study. All patients whose surgery was performed at hospital A underwent an in-person flap check overnight. Those at hospital B received a remote flap assessment. The primary outcome was total time spent performing the midnight flap assessment, including travel time. Data were gathered prospectively using an online survey. Results Sixty consecutive patients met inclusion criteria. On the night of the surgery, 31 had an in-person flap check while 29 had a video telehealth flap check. There were no partial or total flap losses or take-backs resulting from the flap checks. Mean (SD) times for in-person and remote assessments were 34 (16) minutes (range, 10-60 minutes) and 13 (8) minutes (range, 5-35 minutes), respectively ( P < .001). House staff unanimously felt the remote telehealth system improved their quality of life without affecting their perception of the quality of the flap assessment ( P = .001). Conclusion Compared with in-person flap assessments in this cohort, telehealth assessments allowed more efficient examination of free tissue reconstructions while yielding seemingly equivalent information. Therefore, remote telehealth flap checks may provide useful information supporting the use of high-fidelity remote data-streaming technology in the delivery of complex care to patients distant from their care provider.
Collapse
Affiliation(s)
- A. Sean Alemi
- Department of Otolaryngology, Head & Neck Surgery, University of California San Francisco, San Francisco, California, USA
| | - Rahul Seth
- Department of Otolaryngology, Head & Neck Surgery, University of California San Francisco, San Francisco, California, USA
| | - Chase Heaton
- Department of Otolaryngology, Head & Neck Surgery, University of California San Francisco, San Francisco, California, USA
| | - Steven J. Wang
- Department of Otolaryngology, Head & Neck Surgery, University of California San Francisco, San Francisco, California, USA
| | - P. Daniel Knott
- Department of Otolaryngology, Head & Neck Surgery, University of California San Francisco, San Francisco, California, USA
| |
Collapse
|