Reliability of Postoperative Free Flap Monitoring with a Novel Prediction Model Based on Supervised Machine Learning

Artificial Intelligence and Postoperative Monitoring in Plastic Surgery

Technological innovation has fueled an evolving landscape in plastic surgery. Recently, artificial intelligence (AI) has demonstrated tremendous potential in enhancing our diagnostic ability, automating data acquisition for research purposes, and supplementing our intraoperative decision-making. Over the last two decades, advancements in AI enhanced pre- and intraoperative management of plastic surgery patients. However, the demand to keep plastic surgery patients out of hospital during the COVID-19 pandemic has recently inspired important AI innovations in postoperative care, such as telemedicine and remote patient monitoring. As we transition into the post-COVID era of medicine, these novel technologies will be critical in enhancing patient safety and satisfaction, while reducing rising healthcare costs. Herein, we review the basic principles of AI in plastic surgery and illustrate its significance in remote postoperative monitoring.

"INVOS" WE TRUST. Tissue Oximetry for Free Flap Monitoring in Lower Limb Reconstruction

INTRODUCTION

Free flaps on the lower limb could make the difference between salvage and amputation. Regional tissue oximetry (rSO₂) measured by near-infrared light is a tool that is not yet widely described or recognized, as most published studies focus on its use in breast flap monitoring. However, in the context of lower limb reconstruction, it offers an objective and real-time evaluation of flap tissue perfusion, enabling faster responses for salvage compared to traditional clinical monitoring.

MATERIAL AND METHODS

We conducted a retrospective study comparing lower limb free flap monitoring using two techniques. Group A (June 2016-January 2020) used local real-time rSO2 monitoring with the INVOS-TM 5100C Somatic Oximeter (Medtronic Inc., Minneapolis, MN); each patient had two sensors, one over the flap, another (control) over a nearby non-flap area. Group B (February 2013-May 2016) relied on traditional clinical examination.

RESULTS

A total of 148 free flaps were included (74 in each group). There was a small, non-significant difference in overall flap survival (Group A: 94.6% vs. Group B: 90.5%, p = 0.344). The flap salvage rate, when reoperated within the first 72 h, was higher but not significantly so (66% vs. 43%, p = 0.483) and significantly faster (121 vs. 181 min, p = < 0.001) in Group A. According to our study, INVOS demonstrated 100% sensitivity and negative predictive value (NPV), with 90% specificity.

CONCLUSIONS

Regional tissue oximetry monitoring of lower limb free flaps is a real-time, objective, non-invasive, and reliable method for early detection of complications. This study allows us to affirm that the revisions of the flaps are statistically significantly faster. It also provides valuable information about anastomotic failure, clearly differentiating between arterial and venous issues, as well as identifying local or systemic issues.

Artificial intelligence in maxillofacial and facial plastic and reconstructive surgery

PURPOSE OF REVIEW

To provide a current review of artificial intelligence and its subtypes in maxillofacial and facial plastic surgery including a discussion of implications and ethical concerns.

RECENT FINDINGS

Artificial intelligence has gained popularity in recent years due to technological advancements. The current literature has begun to explore the use of artificial intelligence in various medical fields, but there is limited contribution to maxillofacial and facial plastic surgery due to the wide variance in anatomical facial features as well as subjective influences. In this review article, we found artificial intelligence's roles, so far, are to automatically update patient records, produce 3D models for preoperative planning, perform cephalometric analyses, and provide diagnostic evaluation of oropharyngeal malignancies.

SUMMARY

Artificial intelligence has solidified a role in maxillofacial and facial plastic surgery within the past few years. As high-quality databases expand with more patients, the role for artificial intelligence to assist in more complicated and unique cases becomes apparent. Despite its potential, ethical questions have been raised that should be noted as artificial intelligence continues to thrive. These questions include concerns such as compromise of the physician-patient relationship and healthcare justice.

Deep learning and remote photoplethysmography powered advancements in contactless physiological measurement

In recent decades, there has been ongoing development in the application of computer vision (CV) in the medical field. As conventional contact-based physiological measurement techniques often restrict a patient's mobility in the clinical environment, the ability to achieve continuous, comfortable and convenient monitoring is thus a topic of interest to researchers. One type of CV application is remote imaging photoplethysmography (rPPG), which can predict vital signs using a video or image. While contactless physiological measurement techniques have an excellent application prospect, the lack of uniformity or standardization of contactless vital monitoring methods limits their application in remote healthcare/telehealth settings. Several methods have been developed to improve this limitation and solve the heterogeneity of video signals caused by movement, lighting, and equipment. The fundamental algorithms include traditional algorithms with optimization and developing deep learning (DL) algorithms. This article aims to provide an in-depth review of current Artificial Intelligence (AI) methods using CV and DL in contactless physiological measurement and a comprehensive summary of the latest development of contactless measurement techniques for skin perfusion, respiratory rate, blood oxygen saturation, heart rate, heart rate variability, and blood pressure.

Development of an Automated Free Flap Monitoring System Based on Artificial Intelligence

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.

Current Applications of Artificial Intelligence in Billing Practices and Clinical Plastic Surgery

Integration of artificial intelligence (AI), specifically with natural language processing and machine learning, holds tremendous potential to enhance both clinical practices and administrative workflows within plastic surgery. AI has been applied to various aspects of patient care in plastic surgery, including postoperative free flap monitoring, evaluating preoperative risk assessments, and analyzing clinical documentation. Previous studies have demonstrated the ability to interpret current procedural terminology codes from clinical documentation using natural language processing. Various automated medical billing companies have used AI to improve the revenue management cycle at hospitals nationwide. Additionally, AI has been piloted by insurance companies to streamline the prior authorization process. AI implementation holds potential to enhance billing practices and maximize healthcare revenue for practicing physicians.

Evolution and Diversity of Medial Sural Artery Perforator Flap for Hand Reconstruction

The free medial sural artery perforator (MSAP) flap is a recently popularized flap. It has evolved from a composite myocutaneous flap to a pedicled perforator flap for lower limb reconstruction. It is also a versatile free perforator flap for extremity and head and neck reconstruction. The diversity of the flap designs with options for harvest of non-vascularized grafts enhances the versatility for hand and upper limb reconstruction. The adjunctive use of endoscopy and indocyanine green fluorescence imaging studies can assist and demystify the flap anatomy. The authors present their experience using free MSAP flaps for complex mutilated hand and upper extremity reconstruction.

Machine learning application for prediction of surgical site infection after posterior cervical surgery

Surgical site infection (SSI) is one of the most common complications of posterior cervical surgery. It is difficult to diagnose in the early stage and may lead to severe consequences such as wound dehiscence and central nervous system infection. This retrospective study included patients who underwent posterior cervical surgery at The Second Affiliated Hospital and Yuying Childrens Hospital of Wenzhou Medical University from September 2018 to June 2022. We employed several machine learning methods, such as the gradient boosting (GB), random forests (RF), artificial neural network (ANN) and other popular machine learning models. To minimize the variability introduced by random splitting, the results underwent 10-fold cross-validation repeated 10 times. Five measurements were averaged across 10 repetitions with 10-fold cross-validation, the RF model achieved the highest AUROC (0.9916), specificity (0.9890) and precision (0.9759). The GB model achieved the highest sensitivity (0.9535) and the KNN achieved the highest sensitivity (0.9958). The application of machine learning techniques facilitated the development of a precise model for predicting SSI after posterior cervical surgery. This dynamic model can be served as a valuable tool for clinicians and patients to assess SSI risk and prevent it in clinical practice.

Artificial Intelligence in Plastic Surgery: Insights from Plastic Surgeons, Education Integration, ChatGPT's Survey Predictions, and the Path Forward

Background

Artificial intelligence (AI) is emerging as a transformative technology with potential applications in various plastic surgery procedures and plastic surgery education. This article examines the views of plastic surgeons and residents on the role of AI in the field of plastic surgery.

Methods

A 34-question survey on AI's role in plastic surgery was distributed to 564 plastic surgeons worldwide, and we received responses from 153 (26.77%) with the majority from Latin America. The survey explored various aspects such as current AI experience, attitudes toward AI, data sources, ethical considerations, and future prospects of AI in plastic surgery and education. Predictions from AI using ChatGPT for each question were compared with the actual survey responses.

Results

The study found that most participants had little or no prior AI experience. Although some believed AI could enhance accuracy and visualization, opinions on its impact on surgical time, patient recovery, and satisfaction were mixed. Concerns included patient privacy, data security, costs, and informed consent. Valuable AI training data sources were identified, and there was agreement on the importance of standards and transparency. Respondents expected AI's increasing role in reconstructive and aesthetic surgery, suggesting its integration into residency programs, addressing administrative challenges, and patient complications. Confidence in the enduring importance of human professionals was expressed, with interest in further AI research.

Conclusion

The survey's findings underscore the need to harness AI's potential while preserving human professionals' roles through informed consent, standardization, and AI education in plastic surgery.

From bench to bedside - current clinical and translational challenges in fibula free flap reconstruction

Fibula free flaps (FFF) represent a working horse for different reconstructive scenarios in facial surgery. While FFF were initially established for mandible reconstruction, advancements in planning for microsurgical techniques have paved the way toward a broader spectrum of indications, including maxillary defects. Essential factors to improve patient outcomes following FFF include minimal donor site morbidity, adequate bone length, and dual blood supply. Yet, persisting clinical and translational challenges hamper the effectiveness of FFF. In the preoperative phase, virtual surgical planning and artificial intelligence tools carry untapped potential, while the intraoperative role of individualized surgical templates and bioprinted prostheses remains to be summarized. Further, the integration of novel flap monitoring technologies into postoperative patient management has been subject to translational and clinical research efforts. Overall, there is a paucity of studies condensing the body of knowledge on emerging technologies and techniques in FFF surgery. Herein, we aim to review current challenges and solution possibilities in FFF. This line of research may serve as a pocket guide on cutting-edge developments and facilitate future targeted research in FFF.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Precision and Progress: Machine Learning Advancements in Plastic Surgery

Machine learning has emerged as a powerful tool in various healthcare domains, and its application in plastic surgery has shown significant promise. Plastic surgery aims to enhance and reconstruct physical appearance and function, making it an ideal field for integrating machine learning techniques. This abstract presents an overview of the applications, challenges, and potential benefits of machine learning in plastic surgery. One of the key areas where machine learning has been applied is in the preoperative assessment and surgical planning process. By analyzing large datasets of patient images and clinical data, machine learning algorithms can assist plastic surgeons in predicting surgical outcomes, identifying optimal surgical techniques, and minimizing potential complications. These algorithms can learn from past cases and provide valuable insights to improve surgical decision-making and optimize patient care. Furthermore, machine learning has shown promise in facial recognition and analysis, which is crucial in plastic surgery procedures involving the face. Algorithms can accurately detect facial landmarks, assess facial symmetry, and simulate potential surgical outcomes. This technology gives plastic surgeons a more comprehensive understanding of the patient's facial structure and aids in designing personalized treatment plans. Additionally, machine learning algorithms have been employed to automate the analysis of large-scale clinical databases, assisting in identifying patterns, risk factors, and treatment outcomes. By leveraging these algorithms, plastic surgeons can gain valuable insights into patient populations, surgical trends, and postoperative complications. This information can inform clinical decision-making, improve patient safety, and enhance the overall quality of care. Despite the numerous advantages, several challenges need to be addressed when integrating machine learning into plastic surgery. These include the need for high-quality and diverse datasets, algorithm interpretability, ethical considerations, and regulatory compliance.