Reticulated livedoid skin patterns after soft-tissue filler-related vascular adverse events.

BACKGROUND: For the treatment of vascular adverse events caused by filler injections, duplex ultrasound imaging may be used. The findings of duplex ultrasound examination and the clinical features of reticulated livedoid skin patterns were compared with the hemifaces anatomy. OBJECTIVE: The objective of this study was to link the reticulated livedoid skin patterns to the corresponding duplex ultrasound findings and the facial perforasomes. METHODS: Duplex ultrasound imaging was used for the diagnosis and treatment of vascular adverse events. The clinical features and duplex ultrasound findings of 125 patients were investigated. Six cadaver hemifaces were examined to compare the typical livedo skin patterns with the vasculature of the face. RESULTS: Clinically, the affected skin showed a similar reticulated pattern in each facial area corresponding with arterial anatomy and their perforators in the cadaver hemifaces. With duplex ultrasound, a disturbed microvascularization in the superficial fatty layer was visualized. After hyaluronidase injection, clinical improvement of the skin pattern was seen. Normalization of blood flow was noted accompanied by restoration of flow in the corresponding perforator artery. The skin patterns could be linked to the perforators of the superficial fat compartments. CONCLUSION: The livedo skin patterns seen in vascular adverse events may reflect the involvement of the perforators.

Paracrine cross-talk between human adipose tissue-derived endothelial cells and perivascular cells accelerates the endothelialization of an electrospun ionomeric polyurethane scaffold.

The ex vivo endothelialization of small diameter vascular prostheses can prolong their patency. Here, we demonstrate that heterotypic interactions between human adipose tissue-derived endothelial cells and perivascular cells can be exploited to accelerate the endothelialization of an electrospun ionomeric polyurethane scaffold. The scaffold was used to physically separate endothelial cells from perivascular cells to prevent their diffuse neo-intimal hyperplasia and spontaneous tubulogenesis, yet enable their paracrine cross-talk to accelerate the integration of the endothelial cells into a temporally stable endothelial lining of a continuous, elongated, and aligned morphology. Perivascular cells stimulated endothelial basement membrane protein production and suppressed their angiogenic and inflammatory activation to accelerate this biomimetic morphogenesis of the endothelium. These findings demonstrate the feasibility and underscore the value of exploiting heterotypic interactions between endothelial cells and perivascular cells for the fabrication of an endothelial lining intended for small diameter arterial reconstruction. STATEMENT OF SIGNIFICANCE: Adipose tissue is an abundant, accessible, and uniquely dispensable source of endothelial cells and perivascular cells for vascular tissue engineering. While their spontaneous self-assembly into microvascular networks is routinely exploited for the vascularization of engineered tissues, it threatens the temporal stability of an endothelial lining intended for small diameter arterial reconstruction. Here, we demonstrate that an electrospun polyurethane scaffold can be used to physically separate endothelial cells from perivascular cells to prevent their spontaneous capillary morphogenesis, yet enable their cross-talk to promote the formation of a stable endothelium. Our findings demonstrate the feasibility of engineering an endothelial lining from human adipose tissue, poising it for the rapid ex vivo endothelialization of small diameter vascular prostheses in an autologous, patient-specific manner.

Intraoperative vasopressor use does not increase complications in microvascular post-mastectomy breast reconstruction: Experience in 1729 DIEP flaps at a single center.

INTRODUCTION: Vasopressors are traditionally avoided in microsurgery due to concerns about their effect on free flap survival. We examine the impact of intraoperative vasopressors on microsurgical outcomes in a large series of DIEP flap breast reconstructions. METHODS: A retrospective chart review was performed of patients who underwent DIEP breast reconstruction between January 2010 and May 2020. Intraoperative and postoperative microsurgical outcomes were compared in patients who received vasopressors and those who did not. RESULTS: The study included 1102 women who underwent 1729 DIEP. 878 patients (79.7%) received intraoperative phenylephrine, ephedrine, or a combination of both. There was no significant difference in overall complications, intraoperative microvascular events, takebacks for microvascular complications, or partial or total flap loss between groups. Outcomes were not affected by vasopressor type, dose, or timing of administration. The vasopressor group received significantly lower intraoperative fluid volumes. Multivariate logistic regression found a significant association between overall complications and excessive fluids (OR 2.03, 99% CI 0.98-5.18, p = 0.03) but not vasopressor use (OR 0.79, 99% CI 0.64-3.16, p = 0.7) CONCLUSION: This study demonstrates that vasopressors do not adversely affect clinical outcomes after DIEP breast reconstruction. Withholding vasopressors results in excessive intravenous fluid administration and increased postoperative complications.

"Spin" in Observational Studies in Deep Inferior Epigastric Perforator Flap Breast Reconstruction: A Systematic Review.

The deep inferior epigastric artery perforator (DIEP) flap is widely used in autologous breast reconstruction. However, the technique relies heavily on nonrandomized observational research, which has been found to have high risk of bias. "Spin" can be used to inappropriately present study findings to exaggerate benefits or minimize harms. The primary objective was to assess the prevalence of spin in nonrandomized observational studies on DIEP reconstruction. The secondary objectives were to determine the prevalence of each spin category and strategy. Methods: MEDLINE and Embase databases were searched from January 1, 2015, to November 15, 2022. Spin was assessed in abstracts and full-texts of included studies according to criteria proposed by Lazarus et al. Results: There were 77 studies included for review. The overall prevalence of spin was 87.0%. Studies used a median of two spin strategies (interquartile range: 1-3). The most common strategies identified were causal language or claims (n = 41/77, 53.2%), inadequate extrapolation to larger population, intervention, or outcome (n = 27/77, 35.1%), inadequate implication for clinical practice (n = 25/77, 32.5%), use of linguistic spin (n = 22/77, 28.6%), and no consideration of the limitations (n = 21/77, 27.3%). There were no significant associations between selected study characteristics and the presence of spin. Conclusions: The prevalence of spin is high in nonrandomized observational studies on DIEP reconstruction. Causal language or claims are the most common strategy. Investigators, reviewers, and readers should familiarize themselves with spin strategies to avoid misinterpretation of research in DIEP reconstruction.

A Size-Based Criteria for Flap Reconstruction After Thigh-Adductor, Soft-Tissue Sarcoma Resection.

BACKGROUND: Resection of soft-tissue sarcomas from the adductor compartment is associated with significant complications. Free/pedicled flaps often are used for wound closure, but their effect on healing is unclear. We compared wound complications, oncologic, and functional outcomes for patients undergoing flap reconstruction or primary closure following resection of adductor sarcomas. METHODS: A total of 177 patients underwent resection of an adductor sarcoma with primary closure (PrC) or free/pedicled flap reconstruction (FR). Patient, tumor, and treatment characteristics were compared, as well as wound complications, oncologic, and functional outcomes (TESS/MSTS87/MSTS93). To examine the relative benefit of flap reconstruction, number needed to treat (NNT) was calculated. RESULTS: In total, 143 patients underwent PrC and 34 had FR, 68% of which were pedicled. There were few differences in demographic, tumor, or treatment characteristics. No significant difference was found in the rate of wound complications. Length of stay was significantly longer in FR (18 days vs. PrC 8 days; p < 0.01). Oncologic and functional outcomes were similar over 5 years follow-up. Uncomplicated wound healing occurred more often in FR compared with PrC for tumors with ≥15 cm (NNT = 8.4) or volumes ≥ 800 ml (NNT = 8.4). Tumors ≤ 336 ml do not benefit from a flap, whereas those > 600 ml are 1.5 times more likely to heal uneventfully after flap closure. CONCLUSIONS: Although flap use prolonged hospitalization, it decreased wound healing complications for larger tumors, and in all sized tumors, it demonstrated similar functional and oncologic outcomes to primary closure. Our size-based treatment criteria can help to identify patients with large adductor sarcomas who could benefit from flap reconstruction. LEVEL OF EVIDENCE III: (Retrospective cohort study).

The Role of Augmented Reality in the Next Phase of Surgical Education.

Concomitant with such a shift toward competency-based curricula, there has been increasing adoption of surgical simulation coupled with virtual, mixed, and augmented reality. These technologies have become more commonplace across multiple surgical disciplines, in domains such as preoperative planning, surgical education, and intraoperative navigation. However, there is a relative paucity of literature pertaining to the application of this technology to plastic surgery education. This review outlines the advantages of mixed and augmented reality in the pursuit of an ideal simulation environment, their benefits for the education of plastic surgery trainees, and their role in standardized assessments. In addition, we offer practical solutions to commonly encountered problems with this technology. Augmented reality has tremendous untapped potential in the next phase of plastic surgery education, and we outline steps toward broader implementation to enhance the learning environment for our trainees and to improve patient outcomes.

Picosecond Infrared Laser Mass Spectrometry Identifies a Metabolite Array for 10 s Diagnosis of Select Skin Cancer Types: A Proof-of-Concept Feasibility Study.

Currently, a large number of skin biopsies are taken for each true skin cancer case detected, creating a need for a rapid, high sensitivity, and specificity skin cancer detection tool to reduce the number of unnecessary biopsies taken from benign tissue. Picosecond infrared laser mass spectrometry (PIRL-MS) using a hand-held sampling probe is reported to detect and classify melanoma, squamous cell carcinoma, and normal skin with average sensitivity and specificity values of 86-95% and 91-98%, respectively (at a 95% confidence level) solely requiring 10 s or less of total data collection and analysis time. Classifications are not adversely affected by specimen's quantity of melanin pigments and are mediated by a number of metabolic lipids, further identified herein as potential biomarkers for skin cancer-type differentiation, 19 of which were sufficient here (as a fully characterized metabolite array) to provide high specificity and sensitivity classification of skin cancer types. In situ detection was demonstrated in an intradermal melanoma mouse model wherein in vivo sampling did not cause significant discomfort. PIRL-MS sampling is further shown to be compatible with downstream gross histopathologic evaluations despite loss of tissue from the immediate laser sampling site(s) and can be configured using selective laser pulses to avoid thermal damage to normal skin. Therefore, PIRL-MS may be employed as a decision-support tool to reduce both the subjectivity of clinical diagnosis and the number of unnecessary biopsies currently required for skin cancer screening.

The risk of bias of non-randomized observational studies in deep inferior epigastric perforator flap breast reconstruction: A systematic review using ROBINS-I.

INTRODUCTION: The deep inferior epigastric perforator (DIEP) flap is regarded as the gold standard for autologous breast reconstruction. However, due to difficulty designing and conducting randomized controlled trials in surgical interventions, the majority of literature on DIEP flap breast reconstructions are observational studies. As such, it is pivotal that these studies are performed with high internal validity. METHODS: A literature search was performed using MEDLINE, Embase, and CENTRAL from January 1, 2015 to October 23, 2021. Studies identified as observational studies about DIEP breast reconstruction and published in a journal with a Web of Science impact factor above 1.0 were included. Screening and risk of bias (RoB) assessment using the ROBINS-I tool were performed independently and in duplicate by two authors. RESULTS: From 12,371 studies, 66 observational studies were included. The majority were found at RoB, with 11 at moderate, 26 at serious, and 6 at critical RoB. Only two studies had low RoB. The bias most commonly arose due to Domain 1 (confounding variables), Domain 3 (classification of interventions), and Domain 6 (measurement of outcomes). CONCLUSIONS: In this review, we demonstrate the high RoB of observational studies evaluating DIEP breast reconstruction, which may jeopardize the validity of findings. We recommend that authors consult the ROBINS-I tool not only when assessing observational studies for systematic reviews but also when designing or conducting these studies. In our study, we present additional considerations for each domain to provide researchers with guidance on assessing and conducting surgical observational studies.

Immunomagnetic Isolation and Enrichment of Microvascular Endothelial Cells from Human Adipose Tissue.

Human adipose tissue-resident microvascular endothelial cells are not only garnering attention for their emergent role in the pathogenesis of obesity-related metabolic disorders, but are also of considerable interest for vascular tissue engineering due, in part, to the abundant, accessible, and uniquely dispensable nature of the tissue. Here, we delineate a protocol for the acquisition of microvascular endothelial cells from human fat. A cheaper, smaller, and simpler alternative to fluorescence-assisted cell sorting for the immunoselection of cells, our protocol adapts magnet-assisted cell sorting for the isolation of endothelial cells from enzymatically digested adipose tissue and the subsequent enrichment of their primary cultures. Strategies are employed to mitigate the non-specific uptake of immunomagnetic microparticles, enabling the reproducible acquisition of human adipose tissue-resident microvascular endothelial cells with purities ≥98%. They exhibit morphological, molecular, and functional hallmarks of endothelium, yet retain a unique proteomic signature when compared with endothelial cells derived from different vascular beds. Their cultures can be expanded for >10 population doublings and can be maintained at confluence for at least 28 days without being overgrown by residual stromal cells from the cell sorting procedure. The isolation of human adipose tissue-resident microvascular endothelial cells can be completed within 6 hours and their enrichment within 2 hours, following approximately 7 days in culture. Graphical abstract.

Vascular tissue engineering from human adipose tissue: fundamental phenotype of its resident microvascular endothelial cells and stromal/stem cells.

Adipose tissue is an abundant, accessible, and uniquely dispensable source of cells for vascular tissue engineering. Despite its intrinsic endothelial cells, considerable effort is directed at deriving endothelium from its resident stem and progenitor cells. Here, we investigate the composition of human adipose tissue and characterize the phenotypes of its constituent cells in order to help ascertain their potential utility for vascular tissue engineering. Unsupervised clustering based on cell-surface protein signatures failed to detect CD45-CD31-VEGFR2+ endothelial progenitor cells within adipose tissue, but supported further investigation of its resident CD45-CD31+ microvascular endothelial cells (HAMVECs) and CD45-CD31- stromal/stem cells (ASCs). The endothelial differentiation of ASCs altered their proteome, but it remained distinct from that of primary endothelial cell controls - as well as HAMVECs - regardless of their arterial-venous specification or macrovascular-microvascular origin. Rather, ASCs retained a proteome indicative of a perivascular phenotype, which was supported by their ability to facilitate the capillary morphogenesis of HAMVECs. This study supports the use of HAMVECs for the generation of endothelium. It suggests that the utility of ASCs for vascular tissue engineering lies in their capacity to remodel the extracellular matrix and to function as mural cells.

Evaluating Breast Reconstruction Reviews Using A Measurement Tool to Assess Systematic Reviews (AMSTAR).

BACKGROUND: Breast reconstruction is an important aspect in breast cancer treatment. METHODS: A comprehensive search of MEDLINE, Embase, and the Cochrane Library of Systematic Reviews was performed. Systematic reviews and meta-analyses that focused on breast reconstruction and were published between 2000 and 2020 were included. Quality assessment was performed using A Measurement Tool to Assess Systematic Reviews (AMSTAR). Study characteristics were extracted, including journal and impact factor, year of publication, country affiliation, reporting adherence to Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, number of citations, and number of studies included. RESULTS: The average AMSTAR score was moderate (5.32). There was a significant increase in AMSTAR score (P < 0.01) and number of studies (P < 0.01) over time. There were no significant correlations between AMSTAR score and impact factor (P = 0.038), and AMSTAR score and number of citations (P = 0.52), but there was a significant association between AMSTAR score and number of studies (P = 0.013). Studies that adhered to the PRISMA statement had a higher AMSTAR score on average (P < 0.01). CONCLUSIONS: Systematic reviews and meta-analyses about breast reconstruction had, on average, a moderate AMSTAR score. The number of studies and methodological quality have increased over time. Study characteristics including adherence to PRISMA guidelines are associated with improved methodological quality. Further improvements in specific AMSTAR domains would improve the overall methodological quality.

Mitigating the non-specific uptake of immunomagnetic microparticles enables the extraction of endothelium from human fat.

Endothelial cells are among the fundamental building blocks for vascular tissue engineering. However, a clinically viable source of endothelium has continued to elude the field. Here, we demonstrate the feasibility of sourcing autologous endothelium from human fat - an abundant and uniquely dispensable tissue that can be readily harvested with minimally invasive procedures. We investigate the challenges underlying the overgrowth of human adipose tissue-derived microvascular endothelial cells by stromal cells to facilitate the development of a reliable method for their acquisition. Magnet-assisted cell sorting strategies are established to mitigate the non-specific uptake of immunomagnetic microparticles, enabling the enrichment of endothelial cells to purities that prevent their overgrowth by stromal cells. This work delineates a reliable method for acquiring human adipose tissue-derived microvascular endothelial cells in large quantities with high purities that can be readily applied in future vascular tissue engineering applications.

Longitudinal Study of Psychosocial Outcomes Following Surgery in Women with Unilateral Nonhereditary Breast Cancer.

INTRODUCTION: Rates of bilateral mastectomy are rising in women with unilateral, nonhereditary breast cancer. We aim to characterize how psychosocial outcomes evolve after breast cancer surgery. PATIENTS AND METHODS: We performed a prospective cohort study of women with unilateral, sporadic stage 0-III breast cancer at University Health Network in Toronto, Canada between 2014 and 2017. Women completed validated psychosocial questionnaires (BREAST-Q, Impact of Event Scale, Hospital Anxiety & Depression Scale) preoperatively, and at 6 and 12 months following surgery. Change in psychosocial scores was assessed between surgical groups using linear mixed models, controlling for age, stage, and adjuvant treatments. P < .05 were significant. RESULTS: A total of 475 women underwent unilateral lumpectomy (42.5%), unilateral mastectomy (38.3%), and bilateral mastectomy (19.2%). There was a significant interaction (P < .0001) between procedure and time for breast satisfaction, psychosocial and physical well-being. Women having unilateral lumpectomy had higher breast satisfaction and psychosocial well-being scores at 6 and 12 months after surgery compared with either unilateral or bilateral mastectomy, with no difference between the latter two groups. Physical well-being declined in all groups over time; scores were not better in women having bilateral mastectomy. While sexual well-being scores remained stable in the unilateral lumpectomy group, scores declined similarly in both unilateral and bilateral mastectomy groups over time. Cancer-related distress, anxiety, and depression scores declined significantly after surgery, regardless of surgical procedure (P < .001). CONCLUSIONS: Psychosocial outcomes are not improved with contralateral prophylactic mastectomy in women with unilateral breast cancer. Our data may inform women considering contralateral prophylactic mastectomy.

The Toronto Sarcoma Flap Score: A Validated Wound Complication Classification System for Extremity Soft Tissue Sarcoma Flap Reconstruction.

BACKGROUND: Flap reconstruction plays an important role in limb preservation after wide resection of extremity soft tissue sarcoma (ESTS), but can be associated with high rates of postoperative wound complications. Currently, no standardized system exists for the classification of these complications. This study aimed to develop a standardized classification system for wound complications after ESTS flap reconstruction. METHODS: Outcomes of ESTS flap reconstructions were analyzed in a retrospective cohort of 300 patients. All wound- and flap-related complications were identified and categorized. Based on these data, a scoring system was developed and validated with a prospective cohort of 100 patients who underwent ESTS flap reconstruction. RESULTS: A 10-point scoring system was developed based on the level of intervention required to treat each complication observed in the retrospective cohort. Raters applied the scoring system to the prospective patient cohort. Validation studies demonstrated excellent inter-rater and intra-rater reliability (weighted Cohen's kappa range, 0.82 [95% CI, 0.5-1.0] to 0.99 [95% CI, 0.98-1.0] and 0.95 [95% CI, 0.84-1.0] to 0.97 [95% CI, 0.92-1.0], respectively). The majority of the raters reported the score to be simple, objective, and reproducible (respective mean scores, 4.76 ± 0.43, 4.53 ± 0.62, and 4.56 ± 0.56 on 5-point Likert scales). CONCLUSION: The Toronto Sarcoma Flap Score (TSFS) is a simple and objective classification system with excellent inter- and intra-rater reliability. Universal adoption of the TSFS could standardize outcome reporting in future studies and aid in the establishment of clinical benchmarks to improve the quality of care in sarcoma reconstruction.

Preconsultation Educational Group Intervention Can Address the Knowledge Gap in Postmastectomy Breast Reconstruction.

BACKGROUND: Whether to undergo postmastectomy breast reconstruction (PMBR) is a challenging, preference-sensitive decision. It is therefore paramount to optimize decision quality through ensuring patients' knowledge and aligning treatments with their personal preferences. This study assessed the effects of a preconsultation educational group intervention (PEGI) on patient knowledge, state-trait anxiety, and decisional conflict (patient uncertainty in decision making) during the decision-making process. METHODS: This phase 3 randomized controlled trial assessed effects of a PEGI in women without active breast cancer undergoing delayed PMBR, or prophylactic mastectomy with immediate PMBR. Both groups underwent routine education before consultation. In addition, the intervention group underwent a PEGI composed of presentations from a plastic surgeon and nurse, a value clarification exercise, and shared experiences from PMBR patients before the consultation with the plastic surgeon. Before and 1-week after consultation, outcome measures were assessed using the Decisional Conflict Scale, State-Trait Anxiety Inventory, and the BREAST-Q. RESULTS: Of the 219 women deemed eligible, a total of 156 women were recruited and randomized. Treatment fidelity was 96% and retention was 88%. At baseline, there were no significant differences in terms of demographic or clinical status, knowledge, state-trait anxiety, and decisional conflict. Patient knowledge about PMBR improved in both groups; however, the degree of knowledge attainment was significantly greater in the PEGI group (24.5% improvement in the intervention group compared with 13.5% in the routine education group, P < 0.001). The reduction in decisional conflict from baseline to follow-up was greater in the intervention group compared with the routine education; however, the difference only approached significance (P = 0.09). CONCLUSIONS: The provision of a preconsultation educational group intervention has been shown to significantly close the knowledge gap on PMBR in patients seeking delayed breast reconstruction or prophylactic mastectomy with immediate breast reconstruction compared with routine education alone.

Early Postoperative Complications From National Surgical Quality Improvement Program: A Closer Examination of Timing and Technique of Breast Reconstruction.

BACKGROUND: Despite the recent surge in rates of immediate breast reconstruction, there is a paucity of large multicenter studies to compare differences in morbidity after immediate versus delayed breast reconstruction. This study used the National Surgical Quality Improvement Program (NSQIP) to study the association between timing of breast reconstruction and complication rates, stratified by reconstructive modality. STUDY DESIGN: The NSQIP database was used to identify breast reconstructions from 2005 to 2012. Rates of major complications were compared by timing within each reconstructive modality (implant vs autologous). Cohort differences in baseline characteristics and variables associated with increased complication rates were identified in bivariate analyses. A multivariable model was created to compare the association between the timing of reconstruction and major complications. RESULTS: Of 24,506 postmastectomy reconstructions, 85.8% were immediate, 14.2% were delayed, 84% were implant, and 16% were autologous reconstructions. Overall, 10.0% of patients suffered a major complication. After stratification, only implant reconstructions showed a statistically higher complication rate with immediate (8.8%) reconstruction compared with delayed (5.3%) (odds ratio, 1.7, P < 0.01). There was no significant difference in complication rates between autologous immediate (18.4%) or delayed (19.0%) reconstructions. After controlling for baseline cohort differences and other risk factors, immediate reconstruction remained as an independent significant predictor of major complications in implant reconstructions (odds ratio, 1.8, P < 0.01). CONCLUSIONS: Immediate rather than delayed breast reconstruction is associated with a significantly higher rate of major complications in implant reconstruction but not in autologous reconstruction. It is important to include these findings in the routine preoperative surgeon-patient discussion of reconstructive options.

Contralateral prophylactic mastectomy at the time of delayed microvascular breast reconstruction adversely affects patient-reported outcomes: A retrospective cohort study.

PURPOSE: An increasing number of women with unilateral breast cancer are seeking bilateral mastectomies and reconstruction. At our centre, many women who have undergone previous unilateral therapeutic mastectomy request contralateral prophylactic mastectomy (CPM) at the time of delayed reconstruction. These mixed timing reconstructions are particularly challenging as patients have an immediate reconstruction on one side and delayed reconstruction on the other, which may result in asymmetry. This retrospective cohort study evaluates patient-reported satisfaction following mixed timing breast reconstruction and compares them to unilateral delayed reconstruction. METHODS: One hundred and forty-one patients who underwent successful deep inferior epigastric artery perforator (DIEP) flap breast reconstruction and completed baseline and 12-month BREAST-Qs were included in the study. Patient-reported outcomes following bilateral mixed timing reconstruction (n = 56) were compared to those of unilateral delayed reconstruction (UDR) without CPM (n = 85). RESULTS: Women who sought CPM were significantly younger and had lower annual incomes when compared with those who underwent unilateral reconstruction. Mixed timing reconstruction was associated with significantly lower levels of breast satisfaction and psychosocial function as compared to UDR at 12 months post-operatively. BREAST-Q scores (18 months) were available for 75 patients in the cohort and indicated that this decreased breast satisfaction and psychosocial impairment was sustained in the longer-term. CONCLUSIONS: Patients who seek CPM at the time of delayed reconstruction should be advised that this is associated with lower levels of breast satisfaction and psychosocial well-being as compared to unilateral delayed breast reconstruction.

Development and Evaluation of a Machine Learning Prediction Model for Flap Failure in Microvascular Breast Reconstruction.

BACKGROUND: Despite high success rates, flap failure remains an inherent risk in microvascular breast reconstruction. Identifying patients who are at high risk for flap failure would enable us to recommend alternative reconstructive techniques. However, as flap failure is a rare event, identification of risk factors is statistically challenging. Machine learning is a form of artificial intelligence that automates analytical model building. It has been proposed that machine learning can build superior prediction models when the outcome of interest is rare. METHODS: In this study we evaluate machine learning resampling and decision-tree classification models for the prediction of flap failure in a large retrospective cohort of microvascular breast reconstructions. RESULTS: A total of 1012 patients were included in the study. Twelve patients (1.1%) experienced flap failure. The ROSE informed oversampling technique and decision-tree classification resulted in a strong prediction model (AUC 0.95) with high sensitivity and specificity. In the testing cohort, the model maintained acceptable specificity and predictive power (AUC 0.67), but sensitivity was reduced. The model identified four high-risk patient groups. Obesity, comorbidities and smoking were found to contribute to flap loss. The flap failure rate in high-risk patients was 7.8% compared with 0.44% in the low-risk cohort (p = 0.001). CONCLUSIONS: This machine-learning risk prediction model suggests that flap failure may not be a random event. The algorithm indicates that flap failure is multifactorial and identifies a number of potential contributing factors that warrant further investigation.