Will artificial intelligence help us in predicting outcomes in cardiac surgery?

Artificial Intelligence in Cardiac Surgery: Transforming Outcomes and Shaping the Future

Background: Artificial intelligence (AI) has emerged as a transformative technology in healthcare, with its integration into cardiac surgery offering significant advancements in precision, efficiency, and patient outcomes. However, a comprehensive understanding of AI's applications, benefits, challenges, and future directions in cardiac surgery is needed to inform its safe and effective implementation. Methods: A systematic review was conducted following PRISMA guidelines. Literature searches were performed in PubMed, Scopus, Cochrane Library, Google Scholar, and Web of Science, covering publications from January 2000 to November 2024. Studies focusing on AI applications in cardiac surgery, including risk stratification, surgical planning, intraoperative guidance, and postoperative management, were included. Data extraction and quality assessment were conducted using standardized tools, and findings were synthesized narratively. Results: A total of 121 studies were included in this review. AI demonstrated superior predictive capabilities in risk stratification, with machine learning models outperforming traditional scoring systems in mortality and complication prediction. Robotic-assisted systems enhanced surgical precision and minimized trauma, while computer vision and augmented cognition improved intraoperative guidance. Postoperative AI applications showed potential in predicting complications, supporting patient monitoring, and reducing healthcare costs. However, challenges such as data quality, validation, ethical considerations, and integration into clinical workflows remain significant barriers to widespread adoption. Conclusions: AI has the potential to revolutionize cardiac surgery by enhancing decision making, surgical accuracy, and patient outcomes. Addressing limitations related to data quality, bias, validation, and regulatory frameworks is essential for its safe and effective implementation. Future research should focus on interdisciplinary collaboration, robust testing, and the development of ethical and transparent AI systems to ensure equitable and sustainable advancements in cardiac surgery.

Prediction of coronary artery bypass graft outcomes using a single surgical note: An artificial intelligence-based prediction model study

BACKGROUND

Healthcare providers currently calculate risk of the composite outcome of morbidity or mortality associated with a coronary artery bypass grafting (CABG) surgery through manual input of variables into a logistic regression-based risk calculator. This study indicates that automated artificial intelligence (AI)-based techniques can instead calculate risk. Specifically, we present novel numerical embedding techniques that enable NLP (natural language processing) models to achieve higher performance than the risk calculator using a single preoperative surgical note.

METHODS

The most recent preoperative surgical consult notes of 1,738 patients who received an isolated CABG from July 1, 2014 to November 1, 2022 at a single institution were analyzed. The primary outcome was the Society of Thoracic Surgeons defined composite outcome of morbidity or mortality (MM). We tested three numerical-embedding techniques on the widely used TextCNN classification model: 1a) Basic embedding, treat numbers as word tokens; 1b) Basic embedding with a dataloader that Replaces out-of-context (ROOC) numbers with a tag, where context is defined as within a number of tokens of specified keywords; 2) ScaleNum, an embedding technique that scales in-context numbers via a learned sigmoid-linear-log function; and 3) AttnToNum, a ScaleNum-derivative that updates the ScaleNum embeddings via multi-headed attention applied to local context. Predictive performance was measured via area under the receiver operating characteristic curve (AUC) on holdout sets from 10 random-split experiments. For eXplainable-AI (X-AI), we calculate SHapley Additive exPlanation (SHAP) values at an ngram resolution (SHAP-N). While the analyses focus on TextCNN, we execute an analogous performance pipeline with a long short-term memory (LSTM) model to test if the numerical embedding advantage is robust to model architecture.

RESULTS

A total of 567 (32.6%) patients had MM following CABG. The embedding performances are as follows with the TextCNN architecture: 1a) Basic, mean AUC 0.788 [95% CI (confidence interval): 0.768-0.809]; 1b) ROOC, 0.801 [CI: 0.788-0.815]; 2) ScaleNum, 0.808 [CI: 0.785-0.821]; and 3) AttnToNum, 0.821 [CI: 0.806-0.834]. The LSTM architecture produced a similar trend. Permutation tests indicate that AttnToNum outperforms the other embedding techniques, though not statistically significant verse ScaleNum (p-value of .07). SHAP-N analyses indicate that the model learns to associate low blood urine nitrate (BUN) and creatinine values with survival. A correlation analysis of the attention-updated numerical embeddings indicates that AttnToNum learns to incorporate both number magnitude and local context to derive semantic similarities.

CONCLUSION

This research presents both quantitative and clinical novel contributions. Quantitatively, we contribute two new embedding techniques: AttnToNum and ScaleNum. Both can embed strictly positive and bounded numerical values, and both surpass basic embeddings in predictive performance. The results suggest AttnToNum outperforms ScaleNum. With regards to clinical research, we show that AI methods can predict outcomes after CABG using a single preoperative note at a performance that matches or surpasses the current risk calculator. These findings reveal the potential role of NLP in automated registry reporting and quality improvement.