Machine Learning Outperforms Existing Clinical Scoring Tools in the Prediction of Postoperative Atrial Fibrillation During Intensive Care Unit Admission After Cardiac Surgery

Preoperative ECG-assisted feature engineering enhances prediction of new-onset atrial fibrillation after cardiac surgery

BACKGROUND

New-onset postoperative atrial fibrillation (POAF) is the most common complication following cardiac surgery, associated with adverse outcomes. However, the predictive accuracy of existing models remains unsatisfactory, primarily due to insufficient utilization of electrocardiogram (ECG) data and limitations in model development methodologies. This study aims to develop an accurate prediction model for POAF by comprehensively analyzing the predictive power of various preoperative ECG features.

METHODS

This study enrolled 92 cardiac surgery patients with no prior history of atrial fibrillation (AF). One-minute ECG segments, extracted from preoperative long-term ECG recordings, were analyzed for P-wave and short-term heart rate variability (HRV) characteristics. A total of 39 HRV indices and 9 P-wave indices were calculated as ECG features. Additionally, clinical baseline characteristics were incorporated into a multi-modal risk assessment model. Using various feature combinations, six machine learning classifiers were applied to assess the predictive efficacy of various models. Finally, an ensemble strategy was implemented to enhance the model's prediction performance for POAF.

RESULTS

Statistical analysis revealed significant differences (p < 0.05) in 15 ECG features between patients with POAF and those without, including RR interval unpredictability and the cardiac sympathetic index. The predictive model based solely on clinical baseline characteristics demonstrated high accuracy (78.26 %), sensitivity (78.57 %), and specificity (78.13 %), with superior sensitivity in identifying patients at high risk for POAF compared to existing models. Furthermore, the multi-modal model, which integrated preoperative ECG features and an ensemble machine learning (EML) strategy, demonstrated a significant improvement in prediction performance, with an average accuracy of 81.52 %, sensitivity of 82.14 %, and specificity of 81.25 %.

CONCLUSION

The integration of P-wave and short-term HRV features holds promise for improving the prediction of new-onset POAF. ECG-assisted analysis is a valuable tool for elucidating the underlying mechanisms of POAF and advancing clinical strategies for its prevention and management.

The Emerging and Important Role of Artificial Intelligence in Cardiac Surgery

Artificial Intelligence (AI) has greatly affected our everyday lives and holds great promise to change the landscape of medicine. AI is particularly positioned to improve care for the increasingly complex patients undergoing cardiac surgery using the immense amount of data generated in the course of their care. When deployed, AI can be used to analyze this information at the patient's bedside more expediently and accurately, all while providing new insights. This review summarizes the current applications of AI in cardiac surgery from the vantage point of a patient's journey. Applications of AI include preoperative risk assessment, intraoperative planning, postoperative patient care, and outpatient telemonitoring, encompassing the spectrum of cardiac surgical care. Offloading of administrative processes and enhanced experience with information gathering also represent a unique and under-represented avenue for future use of AI. As clinicians, understanding the nomenclature and applications of AI is important to contextualize issues, to ensure problem-driven solutions, and for clinical benefit. Precision medicine, and thus clinically relevant AI, remains dependent on data curation and warehousing to gather insights from large multicentre repositories while treating privacy with the utmost importance. AI tasks should not be siloed but rather holistically integrated into clinical workflow to retain context and relevance. As cardiac surgeons, AI allows us to look forward to a bright future of more efficient use of our clinical expertise toward high-level decision making and technical prowess.

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.

Postoperative Atrial Fibrillation: A Review

Atrial fibrillation (AF) in the postoperative phase is a manifestation of numerous factors, including surgical stress, anesthetic effects, and underlying cardiovascular conditions. The resultant cardiac hyperactivity can induce new onset or exacerbate existing AF. A common phenomenon, postoperative atrial fibrillation (POAF) affects nearly 40% of patients and is associated with longer hospitalization stays, and increased mortality, heart failure, stroke, and healthcare costs. Areas of controversy in POAF include whether to anticoagulate patients who have short-lived POAF, especially given their higher bleeding risk in the postoperative period, and the identification of patients who would benefit the most from preventive drug therapy for POAF. This review discusses the pathophysiology and management of POAF, and strategies to reduce its occurrence.

A review of evaluation approaches for explainable AI with applications in cardiology

Explainable artificial intelligence (XAI) elucidates the decision-making process of complex AI models and is important in building trust in model predictions. XAI explanations themselves require evaluation as to accuracy and reasonableness and in the context of use of the underlying AI model. This review details the evaluation of XAI in cardiac AI applications and has found that, of the studies examined, 37% evaluated XAI quality using literature results, 11% used clinicians as domain-experts, 11% used proxies or statistical analysis, with the remaining 43% not assessing the XAI used at all. We aim to inspire additional studies within healthcare, urging researchers not only to apply XAI methods but to systematically assess the resulting explanations, as a step towards developing trustworthy and safe models.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10462-024-10852-w.

Machine learning in the prediction and detection of new-onset atrial fibrillation in ICU: a systematic review

Atrial fibrillation (AF) stands as the predominant arrhythmia observed in ICU patients. Nevertheless, the absence of a swift and precise method for prediction and detection poses a challenge. This study aims to provide a comprehensive literature review on the application of machine learning (ML) algorithms for predicting and detecting new-onset atrial fibrillation (NOAF) in ICU-treated patients. Following the PRISMA recommendations, this systematic review outlines ML models employed in the prediction and detection of NOAF in ICU patients and compares the ML-based approach with clinical-based methods. Inclusion criteria comprised randomized controlled trials (RCTs), observational studies, cohort studies, and case-control studies. A total of five articles published between November 2020 and April 2023 were identified and reviewed to extract the algorithms and performance metrics. Reviewed studies sourced 108,724 ICU admission records form databases, e.g., MIMIC. Eight prediction and detection methods were examined. Notably, CatBoost exhibited superior performance in NOAF prediction, while the support vector machine excelled in NOAF detection. Machine learning algorithms emerge as promising tools for predicting and detecting NOAF in ICU patients. The incorporation of these algorithms in clinical practice has the potential to enhance decision-making and the overall management of NOAF in ICU settings.

Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Machine Learning for Predicting Postoperative Atrial Fibrillation After Cardiac Surgery: A Scoping Review of Current Literature

Postoperative atrial fibrillation (POAF) occurs in up to 20% to 55% of patients who underwent cardiac surgery. Machine learning (ML) has been increasingly employed in monitoring, screening, and identifying different cardiovascular clinical conditions. It was proposed that ML may be a useful tool for predicting POAF after cardiac surgery. An electronic database search was conducted on Medline, EMBASE, Cochrane, Google Scholar, and ClinicalTrials.gov to identify primary studies that investigated the role of ML in predicting POAF after cardiac surgery. A total of 5,955 citations were subjected to title and abstract screening, and ultimately 5 studies were included. The reported incidence of POAF ranged from 21.5% to 37.1%. The studied ML models included: deep learning, decision trees, logistic regression, support vector machines, gradient boosting decision tree, gradient-boosted machine, K-nearest neighbors, neural network, and random forest models. The sensitivity of the reported ML models ranged from 0.22 to 0.91, the specificity from 0.64 to 0.84, and the area under the receiver operating characteristic curve from 0.67 to 0.94. Age, gender, left atrial diameter, glomerular filtration rate, and duration of mechanical ventilation were significant clinical risk factors for POAF. Limited evidence suggest that machine learning models may play a role in predicting atrial fibrillation after cardiac surgery because of their ability to detect different patterns of correlations and the incorporation of several demographic and clinical variables. However, the heterogeneity of the included studies and the lack of external validation are the most important limitations against the routine incorporation of these models in routine practice. Artificial intelligence, cardiac surgery, decision tree, deep learning, gradient-boosted machine, gradient boosting decision tree, k-nearest neighbors, logistic regression, machine learning, neural network, postoperative atrial fibrillation, postoperative complications, random forest, risk scores, scoping review, support vector machine.

Incidence, Risk Score Performance, and In-Hospital Outcomes of Postoperative Atrial Fibrillation After Cardiac Surgery

BACKGROUND

Postoperative atrial fibrillation (POAF) frequently complicates cardiac surgery. Predicting POAF can guide interventions to prevent its onset. This study assessed the incidence, risk factors, and related adverse outcomes of POAF after cardiac surgery.

METHODS

A cohort of 1,606 patients undergoing cardiac surgery at a tertiary referral center was analyzed. Postoperative AF was defined based on the Society of Thoracic Surgeons' criteria: AF/atrial flutter after operating room exit that either lasted longer than 1 hour or required medical or procedural intervention. Risk factors for POAF were evaluated, and the performance of established risk scores (POAF, HATCH, COM-AF, CHA2DS2-VASc, and Society of Thoracic Surgeons risk scores) in predicting POAF was assessed using discrimination (area under the receiver operator characteristics curve) analysis. The association of POAF with secondary outcomes, including length of hospital stay, ventilator time, and discharge to rehabilitation facilities, was evaluated using adjusted linear and logistic regression models.

RESULTS

The incidence of POAF was 32.2% (n = 517). Patients who developed POAF were older, had traditional cardiovascular risk factors and higher Society of Thoracic Surgeons risk scores, and often underwent valve surgery. The POAF risk score demonstrated the highest area under the receiver operator characteristics curve (0.65), but risk scores generally underperformed. Postoperative AF was associated with extended hospital stays, longer ventilator use, and higher likelihood of discharge to rehabilitation facilities (odds ratio, 2.30; 95% CI, 1.73-3.08).

CONCLUSION

This study observed a high incidence of POAF following cardiac surgery and its association with increased morbidity and resource utilization. Accurate POAF prediction remains elusive, emphasizing the need for better risk-prediction methods and tailored interventions to diminish the effect of POAF on patient outcomes.

Machine learning to predict adverse outcomes after cardiac surgery: A systematic review and meta-analysis

BACKGROUND

Machine learning (ML) models are promising tools for predicting adverse postoperative outcomes in cardiac surgery, yet have not translated to routine clinical use. We conducted a systematic review and meta-analysis to assess the predictive performance of ML approaches.

METHODS

We conducted an electronic search to find studies assessing ML and traditional statistical models to predict postoperative outcomes. Our primary outcome was the concordance (C-) index of discriminative performance. Using a Bayesian meta-analytic approach we pooled the C-indices with the 95% credible interval (CrI) across multiple outcomes comparing ML methods to logistic regression (LR) and clinical scoring tools. Additionally, we performed critical difference and sensitivity analysis.

RESULTS

We identified 2792 references from the search of which 51 met inclusion criteria. Two postoperative outcomes were amenable for meta-analysis: 30-day mortality and in-hospital mortality. For 30-day mortality, the pooled C-index and 95% CrI were 0.82 (0.79-0.85), 0.80 (0.77-0.84), 0.78 (0.74-0.82) for ML models, LR, and scoring tools respectively. For in-hospital mortality, the pooled C-index was 0.81 (0.78-0.84) and 0.79 (0.73-0.84) for ML models and LR, respectively. There were no statistically significant results indicating ML superiority over LR.

CONCLUSION

In cardiac surgery patients, for the prediction of mortality, current ML methods do not have greater discriminative power over LR as measured by the C-index.

Long-term single-lead electrocardiogram monitoring to detect new-onset postoperative atrial fibrillation in patients after cardiac surgery

Background

Postoperative atrial fibrillation (POAF) is often associated with serious complications. In this study, we collected long-term single-lead electrocardiograms (ECGs) of patients with preoperative sinus rhythm to build statistical models and machine learning models to predict POAF.

Methods

All patients with preoperative sinus rhythm who underwent cardiac surgery were enrolled and we collected long-term ECG data 24 h before surgery and 7 days after surgery by single-lead ECG. The patients were divided into a POAF group a no-POAF group. A clinical model and a clinical + ECG model were constructed. The ECG parameters were designed and support vector machine (SVM) was selected to build a machine learning model and evaluate its prediction efficiency.

Results

A total of 100 patients were included. The detection rate of POAF in long-term ECG monitoring was 31% and that in conventional monitoring was 19%. We calculated 7 P-wave parameters, Pmax (167 ± 31 ms vs. 184 ± 37 ms, P = 0.018), Pstd (15 ± 7 vs. 19 ± 11, P = 0.031), and PWd (62 ± 28 ms vs. 80 ± 35 ms, P = 0.008) were significantly different. The AUC of the clinical model (sex, age, LA diameter, GFR, mechanical ventilation time) was 0.86. Clinical + ECG model (sex, age, LA diameter, GFR, mechanical ventilation time, Pmax, Pstd, PWd), AUC was 0.89. In the machine learning model, the accuracy (Ac) of the train set and test set was above 80 and 60%, respectively.

Conclusion

Long-term ECG monitoring could significantly improve the detection rate of POAF. The clinical + ECG model and the machine learning model based on P-wave parameters can predict POAF.

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Development of machine learning models for mortality risk prediction after cardiac surgery

BACKGROUND

We developed machine learning models that combine preoperative and intraoperative risk factors to predict mortality after cardiac surgery.

METHODS

Machine learning involving random forest, neural network, support vector machine, and gradient boosting machine was developed and compared with the risk scores of EuroSCORE I and II, Society of Thoracic Surgeons (STS), as well as a logistic regression model. Clinical data were collected from patients undergoing adult cardiac surgery at the First Medical Centre of Chinese PLA General Hospital between December 2008 and December 2017. The primary outcome was post-operative mortality. Model performance was estimated using several metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). The visualization algorithm was implemented using Shapley's additive explanations.

RESULTS

A total of 5,443 patients were enrolled during the study period. The mean EuroSCORE II score was 3.7%, and the actual in-hospital mortality rate was 2.7%. For predicting operative mortality after cardiac surgery, the AUC scores were 0.87, 0.79, 0.81, and 0.82 for random forest, neural network, support vector machine, and gradient boosting machine, compared with 0.70, 0.73, 0.71, and 0.74 for EuroSCORE I and II, STS, and logistic regression model. Shapley's additive explanations analysis of random forest yielded the top-20 predictors and individual-level explanations for each prediction.

CONCLUSIONS

Machine learning models based on available clinical data may be superior to clinical scoring tools in predicting postoperative mortality in patients following cardiac surgery. Explanatory models show the potential to provide personalized risk profiles for individuals by accounting for the contribution of influencing factors. Additional prospective multicenter studies are warranted to confirm the clinical benefit of these machine learning-driven models.