Artificial intelligence-based analysis of body composition predicts outcome in patients receiving long-term mechanical circulatory support

The Role of Frailty and Myosteatosis in Predicting All-Cause Mortality in Older Adults with Cancer

Frailty and myosteatosis are each prognostic of all-cause mortality (ACM) in patients with cancer. However, it is unclear whether myosteatosis adds value to frailty for predicting ACM. We assessed whether myosteatosis improves the predictive ability of frailty for ACM in older adults undergoing chemotherapy. This was a retrospective study of older adults (≥65 years) initiating chemotherapy between June 2015 and June 2022. Frailty was assessed using a 24-item frailty index (FI). Myosteatosis was evaluated via computed tomography scans at the third lumbar vertebra (L3).. Multivariable Cox regression and Uno's c-statistic determined the predictive performance of the FI and myosteatosis. In total, 115 participants (mean age: 77.1 years) were included. Frailty alone (adjusted hazards ratio (aHR) = 1.68, 95% confidence intervals (CIs) = 1.03-2.72, p = 0.037) and myosteatosis alone (aHR = 2.14, 95%CI = 1.07-4.30, p = 0.032) exhibited similar performance (c-statistic = 0.66) in predicting ACM in multivariable analyses adjusted for age, sex, body mass index, and treatment intent. However, the highest predictive performance for ACM was observed after inclusion of both myosteatosis and frailty in the multivariable model (c-statistic = 0.70). Myosteatosis improves the performance of frailty for predicting ACM in older adults with cancer. Prospective studies to assess the effect of exercise on myosteatosis in older patients are warranted.

Artificial intelligence in cardiac surgery: A systematic review

BACKGROUND

Artificial intelligence (AI) has emerged as a tool to potentially increase the efficiency and efficacy of cardiovascular care and improve clinical outcomes. This study aims to provide an overview of applications of AI in cardiac surgery.

METHODS

A systematic literature search on AI applications in cardiac surgery from inception to February 2024 was conducted. Articles were then filtered based on the inclusion and exclusion criteria and the risk of bias was assessed. Key findings were then summarized.

RESULTS

A total of 81 studies were found that reported on AI applications in cardiac surgery. There is a rapid rise in studies since 2020. The most popular machine learning technique was random forest (n = 48), followed by support vector machine (n = 33), logistic regression (n = 32), and eXtreme Gradient Boosting (n = 31). Most of the studies were on adult patients, conducted in China, and involved procedures such as valvular surgery (24.7%), heart transplant (9.4%), coronary revascularization (11.8%), congenital heart disease surgery (3.5%), and aortic dissection repair (2.4%). Regarding evaluation outcomes, 35 studies examined the performance, 26 studies examined clinician outcomes, and 20 studies examined patient outcomes.

CONCLUSION

AI was mainly used to predict complications following cardiac surgeries and improve clinicians' decision-making by providing better preoperative risk assessment, stratification, and prognostication. While the application of AI in cardiac surgery has greatly progressed in the last decade, further studies need to be conducted to verify accuracy and ensure safety before use in clinical practice.

The Role of Artificial Intelligence and Machine Learning in the Prediction of Right Heart Failure after Left Ventricular Assist Device Implantation: A Comprehensive Review

One of the most challenging and prevalent side effects of LVAD implantation is that of right heart failure (RHF) that may develop afterwards. The purpose of this study is to review and highlight recent advances in the uses of AI in evaluating RHF after LVAD implantation. The available literature was scanned using certain key words (artificial intelligence, machine learning, left ventricular assist device, prediction of right heart failure after LVAD) was scanned within Pubmed, Web of Science, and Google Scholar databases. Conventional risk scoring systems were also summarized, with their pros and cons being included in the results section of this study in order to provide a useful contrast with AI-based models. There are certain interesting and innovative ML approaches towards RHF prediction among the studies reviewed as well as more straightforward approaches that identified certain important predictive clinical parameters. Despite their accomplishments, the resulting AUC scores were far from ideal for these methods to be considered fully sufficient. The reasons for this include the low number of studies, standardized data availability, and lack of prospective studies. Another topic briefly discussed in this study is that relating to the ethical and legal considerations of using AI-based systems in healthcare. In the end, we believe that it would be beneficial for clinicians to not ignore these developments despite the current research indicating more time is needed for AI-based prediction models to achieve a better performance.