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

Enhancing mortality prediction after coronary artery bypass graft: a machine learning approach utilizing EuroScore

Aim: We developed a machine learning model using EuroScore assumptions and preoperative and intraoperative risk factors to predict mortality after coronary artery bypass graft (CABG). Materials & methods: We retrospectively examined data from 108 CABG patients at King Abdullah University Hospital, classifying them into risk groups via EuroScore and predicting mortality through random forest classification. Results: High-risk patients displayed longer surgical times and significant factors such as age and surgery choice. The median EuroScore was 0.95 (0.5-6.4). The model yielded high AUC scores (0.98, 0.95) indicating strong predictive accuracy. Conclusion: Our findings showed that the machine learning models combined with the EuroScore significantly improve post-CABG mortality prediction. For further validation, larger datasets are needed.

Construction and validation of an immune gene-based model for diagnosis and risk prediction of severe asthma

OBJECTIVE

Severe asthma (SA) is a serious disease with limited treatment options, which is closely linked to immune dysfunction. Therefore, immune-associated biomarkers may diagnose SA and offer therapeutic targets for SA.

METHODS

The gene expression profiles of SA patients and matched controls were from the National Center for Biotechnology Information database. Immune genes were downloaded from the ImmPort database. After screening for differentially expressed genes (DEGs) between SA patients and controls, and identifying gene modules highly associated with SA, immune-related DEGs were obtained. Then, protein-protein interaction analysis, Cytoscape software and receiver operating characteristic (ROC) curves were used to identify hub genes. Next, the relationship between hub genes and immune cells was explored, and single-sample gene set enrichment analysis (ssGSEA) was applied to conduct pathway enrichment analyses. Finally, the Least Absolute Shrinkage and Selection Operator (LASSO) combined with ROC analysis were used to confirm the diagnostic value of the hub genes.

RESULTS

Forty immune-related DEGs were obtained, and RNASE3, CAMP and LTF were determined as hub genes. The hub genes were closely associated with immune cells, and ssGSEA showed that lysosome was associated with high expressions of the hub genes, while primary immunodeficiency was related to low expressions of the hub genes. LASSO combined with ROC analysis confirmed the immune gene-based model (RNASE3, CAMP, LTF, and CD79A) could distinguish SA patients from healthy individuals with high sensitivity.

CONCLUSIONS

RNASE3, CAMP, LTF, and CD79A could act as diagnostic markers for SA, providing a theoretical basis for developing diagnostic targets for SA.

Construction and validation of a nomogram prediction model for the risk of new-onset atrial fibrillation following percutaneous coronary intervention in acute myocardial infarction patients

OBJECTIVE

The objective of this study was to investigate risk factors for new-onset atrial fibrillation (NOAF) post-percutaneous coronary intervention (PCI) in patients with acute myocardial infarction (AMI), aiming to develop a predictive nomogram for NOAF risk.

METHODS

A retrospective cohort study involving 397 AMI patients who underwent PCI at a tertiary hospital in Anhui, China, from January 2021 to July 2022 was performed. Patients were divided into NOAF (n = 63) and non-NOAF (n = 334) groups based on post-PCI outcomes. Clinical data were extracted from the hospital information system (HIS) and analyzed using univariate and multivariate logistic regression to identify independent risk factors. A nomogram was generated utilizing R software (version 3.6.1), with its performance evaluated through receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and Bootstrap resampling.

RESULTS

Independent risk factors for NOAF included age, left atrial diameter (LAD), Gensini score, N-terminal pro-B-type natriuretic peptide (NT-proBNP), alanine transaminase (ALT), low-density lipoprotein cholesterol (LDL-C), left ventricular end-systolic diameter (LVESD), and ventricular rate (P < 0.05). The nomogram's ROC curve demonstrated an area under the curve (AUC) of 0.925 (95% CI: 0.887-0.963), supported by a Bootstrap-verified AUC of 0.924 (95% CI: 0.883-0.954), reflecting strong discriminative capability. The calibration curve indicated a mean absolute error (MAE) of 0.031 and 0.017 prior to and following Bootstrap verification, respectively, signifying robust calibration. The DCA curve illustrated that the nomogram offered optimal clinical net benefit for patients with a threshold probability of NOAF ranging from 0.01 to 0.99.

CONCLUSION

The nomogram developed from independent risk factors for NOAF exhibits significant predictive accuracy and clinical relevance for evaluating the risk of NOAF in AMI patients following PCI, thereby enabling the identification of high-risk individuals for targeted interventions.

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.

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.

Predicting post-discharge complications in cardiothoracic surgery: A clinical decision support system to optimize remote patient monitoring resources

Cardiac surgery patients are highly prone to severe complications post-discharge. Close follow-up through remote patient monitoring can help detect adverse outcomes earlier or prevent them, closing the gap between hospital and home care. However, equipment is limited due to economic and human resource constraints. This issue raises the need for efficient risk estimation to provide clinicians with insights into the potential benefit of remote monitoring for each patient. Standard models, such as the EuroSCORE, predict the mortality risk before the surgery. While these are used and validated in real settings, the models lack information collected during or following the surgery, determinant to predict adverse outcomes occurring further in the future. This paper proposes a Clinical Decision Support System based on Machine Learning to estimate the risk of severe complications within 90 days following cardiothoracic surgery discharge, an innovative objective underexplored in the literature. Health records from a cardiothoracic surgery department regarding 5 045 patients (60.8% male) collected throughout ten years were used to train predictive models. Clinicians' insights contributed to improving data preparation and extending traditional pipeline optimization techniques, addressing medical Artificial Intelligence requirements. Two separate test sets were used to evaluate the generalizability, one derived from a patient-grouped 70/30 split and another including all surgeries from the last available year. The achieved Area Under the Receiver Operating Characteristic curve on these test sets was 69.5% and 65.3%, respectively. Also, additional testing was implemented to simulate a real-world use case considering the weekly distribution of remote patient monitoring resources post-discharge. Compared to the random resource allocation, the selection of patients with respect to the outputs of the proposed model was proven beneficial, as it led to a higher number of high-risk patients receiving remote monitoring equipment.