Implementation of a Machine Learning Approach Evaluating Risk Factors for Complications after Single-Stage Augmentation Mastopexy.

BACKGROUND: Single-stage mastopexy augmentation is a much-debated intervention due to its complexity and the associated relatively high complication rates. This study aimed to reevaluate the risk factors for these complications using a novel approach based on artificial intelligence and to demonstrate its possible limitations. PATIENTS AND METHODS: Complete datasets of patients who underwent single-staged augmentation mastopexy during 2014-2023 at one institution by a single surgeon were collected retrospectively. These were subsequently processed and analyzed by CART, RF and XGBoost algorithms. RESULTS: A total of 342 patients were included in the study, of which 43 (12.57%) reported surgery-associated complications, whereby capsular contracture (n = 19) was the most common. BMI represented the most important variable for the development of complications (FIS = 0.44 in CART). 2.9% of the patients expressed the desire for implant change in the course, with absence of any complications. A statistically significant correlation between smoking and the desire for implant change (p < 0.001) was revealed. CONCLUSION: The importance of implementing artificial intelligence into clinical research could be underpinned by this study, as risk variables can be reclassified based on factors previously considered less or even irrelevant. Thereby we encountered limitations using ML approaches. Further studies will be needed to investigate the association between smoking, BMI and the current implant size with the desire for implant change without any complications. Moreover, we could show that the procedure can be performed safely without high risk of developing major complications. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

Risk Stratification with Sarculator and MSKCC in Patients with Primary and Secondary Angiosarcoma.

BACKGROUND: Sarculator and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms are freely available risk prediction scores for surgically treated patients with primary sarcomas. Due to the rarity of angiosarcomas, these scores have only been tested on small cohorts of angiosarcoma patients. In neither the original patient cohort upon which the Sarculator is based nor in subsequent studies was a distinction made between primary and secondary angiosarcomas, as the app is intended to be applied to primary sarcomas. Therefore, the objective of our investigation was to assess whether the Sarculator reveals a difference in prognosis and whether such differentiation aligns with actual clinical data. PATIENTS AND METHODS: Thirty-one patients with primary or secondary soft tissue angiosarcoma, treated at our Sarcoma Center from 2001 to 2023, were included in the study. Actual survival rates were compared with nomogram-derived data for predicted 5-year survival (Sarculator), as well as 4-, 8- and 12-year sarcoma-specific death probabilities (MSKCC). Harrell's c-index was utilized to assess predictive validity. RESULTS: In total, 31 patients were analyzed. The actual overall 5-year survival was 22.57% with a predicted 5-year survival rate of 25.97%, and the concordance index was 0.726 for the entire cohort. The concordance index results from MSKCC for angiosarcoma patients were below 0.7 indicating limited predictive accuracy in this cohort, particularly when compared to Sarculator. SUMMARY: Nomogram-based predictive models are valuable tools in clinical practice for rapidly assessing prognosis. They can streamline the decision-making process for adjuvant treatments and improve patient counselling especially in the treatment of rare and complicated tumor entities such as angiosarcomas.

Digital Media Play a Key Role in Influencing Female Breast Perception.

The female breast is a symbol of femininity and plays a key role in the female body image. However, factors influencing the preferences for different breast shapes and sizes are still not elucidated. In particular, the role of the emerging social media in breast perception has not been analyzed yet. A representative cohort of 1,049 adults completed a web-based questionnaire containing hyperrealistic 3D models of the female breast in the United States. A machine-learning algorithm (Classification and Regression Tree [CART]) was implemented to identify the most influential factors. The study was able to identify the frequency of pornographic and social media consumption as the most influencing factor for altered breast preferences. Although digital media exposure did not alter satisfaction with the own breast among female participants, the tendency to undergo or history of conducted aesthetic surgery correlated with higher access frequency to digital media. Taken together, the overpowering impact of social media and pornographic consumption on the own body image was shown in preference alterations for different anatomical aspects of the breast in the whole population and distorted self-perception about the breast in female participants.