Development and Assessment of Machine Learning Models for Individualized Risk Assessment of Mastectomy Skin Flap Necrosis

Explainable artificial intelligence prediction-based model in laparoscopic liver surgery for segments 7 and 8: an international multicenter study

BACKGROUND

Artificial intelligence (AI) is becoming more useful as a decision-making and outcomes predictor tool. We have developed AI models to predict surgical complexity and the postoperative course in laparoscopic liver surgery for segments 7 and 8.

METHODS

We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open.

RESULTS

Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time."

CONCLUSION

We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8.

Frail but Resilient: Frailty in Autologous Breast Reconstruction is Associated with Worse Surgical Outcomes but Equivalent Long-Term Patient-Reported Outcomes

BACKGROUND

Frailty is associated with higher risk of complications following breast reconstruction, but its impact on long-term surgical and patient-reported outcomes has not been investigated. We examined the association of the five-item modified frailty index (MFI) score with long-term surgical and patient-reported outcomes in autologous breast reconstruction.

PATIENTS AND METHODS

We conducted a retrospective cohort study of consecutive patients who underwent mastectomy and autologous breast reconstruction between January 2016 and April 2022. Primary outcome was any flap-related complication. Secondary outcomes were patient-reported outcomes and predictors of complications in the frail cohort.

RESULTS

We identified 1640 reconstructions (mean follow-up 24.2 ± 19.2 months). In patients with MFI ≥ 2, the odds of surgical [odds ratio (OR) 2.13, p = 0.023] and medical (OR 17.02, p < 0.001) complications were higher than in nonfrail patients. We found no significant difference in satisfaction with the breast (p = 0.287), psychosocial well-being (p = 0.119), or sexual well-being (p = 0.314) according to MFI score. Chronic obstructive pulmonary disease was an independent predictor of infection (OR 3.70, p = 0.002). Tobacco use (OR 7.13, p = 0.002) and contralateral prophylactic mastectomy (OR 2.36, p = 0.014) were independent predictors of wound dehiscence. Dependent functional status (OR 2.36, p = 0.007) and immediate reconstruction (compared with delayed reconstruction; OR 3.16, p = 0.026) were independent predictors of skin flap necrosis. Dependent functional status was also independently associated with higher odds of reoperation (OR 2.64, p = 0.011).

CONCLUSION

Frailty is associated with higher risk of complications in breast reconstruction, but there is no significant difference in long-term patient-reported outcomes. MFI should be considered in breast reconstruction to improve outcomes in high-risk frail patients.

The Skin Necrosis Conundrum: Examining Long-term Outcomes and Risk Factors in Implant-Based Breast Reconstruction

BACKGROUND

Mastectomy skin flap necrosis (MSFN) is a common complication following mastectomy that causes significant distress to patients and physicians and also compromises oncologic, surgical, and quality-of-life outcomes.

OBJECTIVES

We sought to investigate the long-term outcomes of MSFN following implant-based reconstruction (IBR) and determine the rates and predictors of post-MSFN complications.

METHODS

This was a 20-year analysis of consecutive adult (>18 years) patients who developed MSFN following mastectomy and IBR from January 2001 to January 2021. Multivariable analyses were performed to identify factors associated with post-MSFN complications.

RESULTS

We identified 148 reconstructions, with a mean follow-up time of 86.6 ± 52.9 months. The mean time from reconstruction to MSFN was 13.3 ± 10.4 days, and most cases (n = 84, 56.8%) were full-thickness injuries. Most cases (63.5%) were severe, 14.9% were moderate, and 21.6% were mild. Forty-six percent (n = 68) developed a breast-related complication, with infection being the most common (24%). An independent predictor of overall complications was longer time from reconstruction to MSFN (odds ratio [OR], 1.66; P = .040). Aging was an independent predictor of overall complications (OR, 1.86; P = .038); infection (OR, 1.72; P = .005); and dehiscence (OR, 6.18; P = .037). Independent predictors of dehiscence were longer interval from reconstruction to MSFN (OR, 3.23; P = .018) and larger expander/implant size (OR, 1.49; P = .024). Independent predictors of explantation were larger expander/implant size (OR, 1.20; P = .006) and nipple-sparing mastectomy (OR, 5.61; P = .005).

CONCLUSIONS

MSFN is associated with high risk of complications following IBR. Awareness of the timing and severity of MSFN and the predictors of post-MSFN complications is crucial for guiding evidence-based decision-making and improving outcomes.

LEVEL OF EVIDENCE: 4

The Use of Machine Learning for Predicting Complications of Free-Flap Head and Neck Reconstruction

BACKGROUND

Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction.

METHODS

We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss.

RESULTS

We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50).

CONCLUSIONS

ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.

A Surgeon's Guide to Artificial Intelligence-Driven Predictive Models

Artificial intelligence (AI) focuses on processing and interpreting complex information as well as identifying relationships and patterns among complex data. Artificial intelligence- and machine learning (ML)-driven predictions have shown promising potential in influencing real-time decisions and improving surgical outcomes by facilitating screening, diagnosis, risk assessment, preoperative planning, and shared decision-making. Fundamental understanding of the algorithms, as well as their development and interpretation, is essential for the evolution of AI in surgery. In this article, we provide surgeons with a fundamental understanding of AI-driven predictive models through an overview of common ML and deep learning algorithms, model development, performance metrics and interpretation. This would serve as a basis for understanding ML-based research, while fostering new ideas and innovations for furthering the reach of this emerging discipline.

Predicting Patient-Reported Outcomes Following Surgery Using Machine Learning

Patient-reported outcomes (PROs) enable providers to identify differences in treatment effectiveness, postoperative recovery, quality of life, and patient satisfaction. By allowing a shift from disease-specific factors to the patient perspective, PROs provide a tailored patient-centric approach to shared decision-making. Artificial intelligence (AI) and machine learning (ML) techniques can facilitate such shared decision-making and improve patient outcomes by accurate prediction of PROs. This article aims to provide a comprehensive review of the use of AI and ML models in predicting PROs following surgery through an overview of common predictive algorithms and modeling techniques, as well as current applications and limitations in the surgical field.

Artificial Intelligence and Machine Learning in Prediction of Surgical Complications: Current State, Applications, and Implications

Surgical complications pose significant challenges for surgeons, patients, and health care systems as they may result in patient distress, suboptimal outcomes, and higher health care costs. Artificial intelligence (AI)-driven models have revolutionized the field of surgery by accurately identifying patients at high risk of developing surgical complications and by overcoming several limitations associated with traditional statistics-based risk calculators. This article aims to provide an overview of AI in predicting surgical complications using common machine learning and deep learning algorithms and illustrates how this can be utilized to risk stratify patients preoperatively. This can form the basis for discussions on informed consent based on individualized patient factors in the future.