ABSTRACT
Background and Objective: Machine learning (ML) is increasingly being utilized to provide data driven solutions to challenges in medicine. Within the field of cardiac surgery, ML methods have been employed as risk stratification tools to predict a variety of operative outcomes. However, the clinical utility of ML in this domain is unclear. The aim of this review is to provide an overview of ML in cardiac surgery, particularly with regards to its utility in predictive analytics and implications for use in clinical decision support. Methods: We performed a narrative review of relevant articles indexed in PubMed since 2000 using the MeSH terms "Machine Learning", "Supervised Machine Learning", "Deep Learning", or "Artificial Intelligence" and "Cardiovascular Surgery" or "Thoracic Surgery". Key Content and Findings: ML methods have been widely used to generate pre-operative risk profiles, consistently resulting in the accurate prediction of clinical outcomes in cardiac surgery. However, improvement in predictive performance over traditional risk metrics has proven modest and current applications in the clinical setting remain limited. Conclusions: Studies utilizing high volume, multidimensional data such as that derived from electronic health record (EHR) data appear to best demonstrate the advantages of ML methods. Models trained on post cardiac surgery intensive care unit data demonstrate excellent predictive performance and may provide greater clinical utility if incorporated as clinical decision support tools. Further development of ML models and their integration into EHR's may result in dynamic clinical decision support strategies capable of informing clinical care and improving outcomes in cardiac surgery.
ABSTRACT
BACKGROUND: Increasing access and better allocation of organs in the field of transplantation is a critical problem in clinical care. Limitations exist in accurately predicting allograft discard. Potential exists for machine learning to provide a balanced assessment of the potential for an organ to be used in a transplantation procedure. METHODS: We accessed and utilized all available deceased donor United Network for Organ Sharing data from 1987 to 2020. With these data, we evaluated the performance of multiple machine learning methods for predicting organ use. The machine learning methods trialed included XGBoost, random forest, Naïve Bayes (NB), logistic regression, and fully connected feedforward neural network classifier methods. The top two methods, XGBoost and random forest, were fully developed using 10-fold cross-validation and Bayesian optimization of hyperparameters. RESULTS: The top performing model at predicting liver organ use was an XGBoost model which achieved an AUC-ROC of .925, an AUC-PR of .868, and an F1 statistic of .756. The top performing model for predicting kidney organ use classification was an XGBoost model which achieved an AUC-ROC of .952, and AUC-PR of .883, and an F1 statistic of .786. CONCLUSIONS: The XGBoost method demonstrated a significant improvement in predicting donor allograft discard for both kidney and livers in solid organ transplantation procedures. Machine learning methods are well suited to be incorporated into the clinical workflow; they can provide robust quantitative predictions and meaningful data insights for clinician consideration and transplantation decision-making.
Subject(s)
Machine Learning , Tissue Donors , Humans , Bayes Theorem , Logistic ModelsABSTRACT
BACKGROUND: The short-term outcomes of concussions within Major League Baseball (MLB) warrant further consideration beyond a medical standpoint given that performance, career, and financial data remain unknown. The perception of this injury directly affects decision making from the perspective of both player and franchise. PURPOSE: To evaluate the effect of concussion on MLB players by (1) establishing return-to-play (RTP) time after concussion; (2) comparing the career length and performance of players with concussion versus those who took nonmedical leave; and (3) analyzing player financial impact after concussion. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: Contracts, transactions, injury reports, and performance statistics from 2005 to 2017 were analyzed by comparing matched players who sustained a concussion versus those who took nonmedical leave. Of the 4186 eligible MLB players, 145 sustained concussions resulting in the activation of concussion protocol and 538 took nonmedical leave. RTP time was recorded. Career length was analyzed in reference to an experience-based stratification of full seasons remaining after the concussion. Changes in player performance and salary before and after concussion were compared with the same parameters for players who took nonmedical leave. RESULTS: The mean RTP time was 26 days (95% CI, 20-32 days) for athletes with concussion and 8 days (95% CI, 6-10 days) for those who took nonmedical leave. Athletes with concussion had a mean of 2.8 full seasons remaining, whereas athletes who took nonmedical leave had 3.1 seasons remaining (P = .493). The probability of playing in the MLB after concussion compared with the nonmedical leave pool was not significantly lower (P = .534, log-rank test; hazard ratio, 1.108). Postconcussion performance decreased significantly in position players, including a lower batting average and decreased on-base percentage in the players with concussion compared with those returning from nonmedical leave. Players who sustained a concussion lost a mean of US$654,990 annually compared with players who took nonmedical leave. CONCLUSION: This study of the short-term outcomes after concussion in limited-contact MLB athletes demonstrates that concussions may not decrease career spans but may result in decreased performance in addition to financial loss when compared with matched controls who took nonmedical leave. In sports such as baseball that are not subject to repetitive head trauma, career spans may not decrease after a single concussive event. However, sentinel concussions have deleterious short-term effects on performance and compensation among MLB players.
