Explainable machine-learning predictions for complications after pediatric congenital heart surgery

Using artificial intelligence to predict post-operative outcomes in congenital heart surgeries: a systematic review

INTRODUCTION

Congenital heart disease (CHD) represents the most common group of congenital anomalies, constitutes a significant contributor to the burden of non-communicable diseases, highlighting the critical need for improved risk assessment tools. Artificial intelligence (AI) holds promise in enhancing outcome predictions for congenital cardiac surgery. This study aims to systematically review the utilization of AI in predicting post-operative outcomes in this population.

METHODS

Following PRISMA guidelines, a comprehensive search of Pubmed, Scopus, and Web of Science databases was conducted. Two independent reviewers screened articles based on predefined criteria. Included studies focused on AI models predicting various post-operative outcomes in congenital heart surgery.

RESULTS

The review included 35 articles, primarily published within the last four years, indicating growing interest in AI applications. Models predominantly targeted mortality and survival (n = 16), prolonged length of hospital or ICU stay (n = 7), postoperative complications (n = 6), prolonged mechanical ventilatory support time (n = 4), with additional focus on specific outcomes such as peri-ventricular leucomalacia (n = 2) and malnutrition (n = 1). Performance metrics, such as area under the curve (AUC), ranged from 0.52 to 0.997. Notably, these AI models consistently outperformed traditional risk stratification categories. For instance, in assessing the risk of morbidity and mortality, the AI models demonstrated superior performance compared to conventional methods.

CONCLUSION

AI-driven prediction models show significant promise in improving outcome predictions for congenital heart surgery. They surpass traditional risk prediction tools not only in immediate postoperative risks but also in long-term outcomes such as 1-year survival and malnutrition. Further studies with robust external validation are necessary to assess the practical applicability of these models in clinical settings. The protocol of this review was prospectively registered on PROSPERO (CRD42024550942).

Feature selection integrating Shapley values and mutual information in reinforcement learning: An application in the prediction of post-operative outcomes in patients with end-stage renal disease

BACKGROUND

In predicting post-operative outcomes for patients with end-stage renal disease, our study faced challenges related to class imbalance and a high-dimensional feature space. Therefore, with a focus on overcoming class imbalance and improving interpretability, we propose a novel feature selection approach using multi-agent reinforcement learning.

METHODS

We proposed a multi-agent feature selection model based on a comprehensive reward function that combines classification model performance, Shapley additive explanations values, and the mutual information. The definition of rewards in reinforcement learning is crucial for model convergence and performance improvement. Initially, we set a deterministic reward based on the mutual information between variables and the target class, selecting variables that are highly dependent on the class, thus accelerating convergence. We then prioritized variables that influence the minority class on a sample basis and introduced a dynamic reward distribution strategy using Shapley additive explanations values to improve interpretability and solve the class imbalance problem.

RESULTS

Involving the integration of electronic medical records, anesthesia records, operating room vital signs, and pre-operative anesthesia evaluations, our approach effectively mitigated class imbalance and demonstrated superior performance in ablation analysis. Our model achieved a 16% increase in the minority class F1 score and an 8.2% increase in the overall F1 score compared to the baseline model without feature selection.

CONCLUSION

This study contributes important research findings that show that the multi-agent-based feature selection method can be a promising approach for solving the class imbalance problem.

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.

Magnitude and Risk Factors for Paediatric Congenital Heart Surgery Complication and its association with Patient Outcomes in the Cardiac Center of Ethiopia

Background

Congenital heart disease surgery is related to significant postoperative complications which have been associated with poor patient outcomes. However, the prevalence, predictors, and effect of complications on outcomes have only been evaluated in a few numbers of studies. This study aimed to assess the magnitude of postoperative complications after congenital heart surgery, their predictors, and the associations between complications and patient outcomes.

Methods

A retrospective, single-center cross-sectional study was done at the Cardiac Center of Ethiopia (CCE) on children who had undergone cardiac surgery between 2009 and 2022. All 919 pediatric patients aged below 18 years who had undergone congenital heart surgery were included in the study.

Result

Of the 919 patients who underwent surgery in the cardiac center of Ethiopia, Ventricular septal defect (VSD) was the most common diagnosis (41%) and VSD patch closure (39.4%) was the most common surgical procedure. The presence of at least one complication was identified in 39.5% of patients. Of all patients, 11.3% had cardiac, 23.1% had extra-cardiac complications, and 5.3%% had major complications. Higher age at diagnosis, lower weight at admission, cyanotic congenital heart disease, higher Risk adjustment for congenital heart surgery score (RACH-1 score), higher vasoactive inotropic score, Cardiopulmonary bypass use during surgery, higher cardiopulmonary bypass time, higher aortic cross-clamp time, higher duration of surgery, and the higher number of surgeries were associated with complications. The duration of mechanical ventilation, length of intensive care unit stays, and length of hospital stay was significantly prolonged in patients with complications.

Conclusion

Congenital heart disease surgeries pose a high risk of complications, and these complications are associated with poor patient outcomes in Ethiopia. Therefore, predicting complications based on risk factors and early detection and treatment is crucial to improve the patient's outcome.

The Pediatric Data Science and Analytics Subgroup of the Pediatric Acute Lung Injury and Sepsis Investigators Network: Use of Supervised Machine Learning Applications in Pediatric Critical Care Medicine Research

OBJECTIVE

Perform a scoping review of supervised machine learning in pediatric critical care to identify published applications, methodologies, and implementation frequency to inform best practices for the development, validation, and reporting of predictive models in pediatric critical care.

DESIGN

Scoping review and expert opinion.

SETTING

We queried CINAHL Plus with Full Text (EBSCO), Cochrane Library (Wiley), Embase (Elsevier), Ovid Medline, and PubMed for articles published between 2000 and 2022 related to machine learning concepts and pediatric critical illness. Articles were excluded if the majority of patients were adults or neonates, if unsupervised machine learning was the primary methodology, or if information related to the development, validation, and/or implementation of the model was not reported. Article selection and data extraction were performed using dual review in the Covidence tool, with discrepancies resolved by consensus.

SUBJECTS

Articles reporting on the development, validation, or implementation of supervised machine learning models in the field of pediatric critical care medicine.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Of 5075 identified studies, 141 articles were included. Studies were primarily (57%) performed at a single site. The majority took place in the United States (70%). Most were retrospective observational cohort studies. More than three-quarters of the articles were published between 2018 and 2022. The most common algorithms included logistic regression and random forest. Predicted events were most commonly death, transfer to ICU, and sepsis. Only 14% of articles reported external validation, and only a single model was implemented at publication. Reporting of validation methods, performance assessments, and implementation varied widely. Follow-up with authors suggests that implementation remains uncommon after model publication.

CONCLUSIONS

Publication of supervised machine learning models to address clinical challenges in pediatric critical care medicine has increased dramatically in the last 5 years. While these approaches have the potential to benefit children with critical illness, the literature demonstrates incomplete reporting, absence of external validation, and infrequent clinical implementation.

Echocardiographic artificial intelligence for pulmonary hypertension classification

OBJECTIVE

The classification of pulmonary hypertension (PH) is crucial for determining the appropriate therapeutic strategy. We investigated whether machine learning (ML) algorithms may assist in echocardiographic PH prediction, where current guidelines recommend integrating several different parameters.

METHODS

We obtained physical and echocardiographic data from 885 patients who underwent right heart catheterisation (RHC). Patients were classified into three groups: non-PH, precapillary PH and postcapillary PH, based on values obtained from RHC. Using 24 parameters, we created predictive models employing four different classifiers and selected the one with the highest area under the curve. We then calculated the macro-average classification accuracy for PH on the derivation cohort (n=720) and prospective validation data set (n=165), comparing the results with guideline-based echocardiographic assessment obtained from each cohort.

RESULTS

Logistic regression with elastic net regularisation had the highest classification accuracy, with areas under the curves of 0.789, 0.766 and 0.742 for normal, precapillary PH and postcapillary PH, respectively. The ML model demonstrated significantly better predictive accuracy than the guideline-based echocardiographic assessment in the derivation cohort (59.4% vs 51.6%, p<0.01). In the independent validation data set, the ML model's accuracy was comparable to the guideline-based PH classification (59.4% vs 57.8%, p=0.638).

CONCLUSIONS

This preliminary study suggests promising potential for our ML model in predicting echocardiographic PH. Further research and validation are needed to fully assess its clinical utility in PH diagnosis and treatment decision-making.

Machine learning prediction model of major adverse outcomes after pediatric congenital heart surgery-a retrospective cohort study

BACKGROUND

Major adverse postoperative outcomes (APOs) can greatly affect mortality, hospital stay, care management and planning, and quality of life. This study aimed to evaluate the performance of five machine learning (ML) algorithms for predicting four major APOs after pediatric congenital heart surgery and their clinically meaningful model interpretations.

METHODS

Between August 2014 and December 2021, 23,000 consecutive pediatric patients receiving congenital heart surgery were enrolled. Based on the split date of 1 January 2019, we selected 13,927 participants for the training cohort, and 9,073 participants for the testing cohort. Four predefined major APOs including low cardiac output syndrome (LCOS), pneumonia, renal failure, and deep venous thrombosis (DVT) were investigated. 39 clinical and laboratory features were inputted in five ML models: light gradient boosting machine (LightGBM), logistic regression (LR), support vector machine, random forest, and CatBoost. The performance and interpretations of ML models were evaluated using the area under the receiver operating characteristic curve (AUC) and Shapley Additive Explanations (SHAP).

RESULTS

In the training cohort, CatBoost algorithms outperformed others with the mean AUCs of 0.908 for LCOS and 0.957 for renal failure, while LightGBM and LR achieved the best mean AUCs of 0.886 for pneumonia and 0.942 for DVT, respectively. In the testing cohort, the best-performing ML model for each major APOs with the following mean AUCs: LCOS (LightGBM), 0.893 (95% confidence interval (CI), 0.884-0.895); pneumonia (LR), 0.929 (95% CI, 0.926-0.931); renal failure (LightGBM), 0.963 (95% CI, 0.947-0.979), and DVT (LightGBM), 0.970 (95% CI, 0.953-0.982). The performance of ML models using only clinical variables was slightly lower than those using combined data, with the mean AUCs of 0.873 for LCOS, 0.894 for pneumonia, 0.953 for renal failure, and 0.933 for DVT. The SHAP showed that mechanical ventilation time was the most important contributor of four major APOs.

CONCLUSIONS

In pediatric congenital heart surgery, the established ML model can accurately predict the risk of four major APOs, providing reliable interpretations for high-risk contributor identification and informed clinical decisions making.

A Patient Similarity Network (CHDmap) to Predict Outcomes After Congenital Heart Surgery: Development and Validation Study

Background

Although evidence-based medicine proposes personalized care that considers the best evidence, it still fails to address personal treatment in many real clinical scenarios where the complexity of the situation makes none of the available evidence applicable. "Medicine-based evidence" (MBE), in which big data and machine learning techniques are embraced to derive treatment responses from appropriately matched patients in real-world clinical practice, was proposed. However, many challenges remain in translating this conceptual framework into practice.

Objective

This study aimed to technically translate the MBE conceptual framework into practice and evaluate its performance in providing general decision support services for outcomes after congenital heart disease (CHD) surgery.

Methods

Data from 4774 CHD surgeries were collected. A total of 66 indicators and all diagnoses were extracted from each echocardiographic report using natural language processing technology. Combined with some basic clinical and surgical information, the distances between each patient were measured by a series of calculation formulas. Inspired by structure-mapping theory, the fusion of distances between different dimensions can be modulated by clinical experts. In addition to supporting direct analogical reasoning, a machine learning model can be constructed based on similar patients to provide personalized prediction. A user-operable patient similarity network (PSN) of CHD called CHDmap was proposed and developed to provide general decision support services based on the MBE approach.

Results

Using 256 CHD cases, CHDmap was evaluated on 2 different types of postoperative prognostic prediction tasks: a binary classification task to predict postoperative complications and a multiple classification task to predict mechanical ventilation duration. A simple poll of the k-most similar patients provided by the PSN can achieve better prediction results than the average performance of 3 clinicians. Constructing logistic regression models for prediction using similar patients obtained from the PSN can further improve the performance of the 2 tasks (best area under the receiver operating characteristic curve=0.810 and 0.926, respectively). With the support of CHDmap, clinicians substantially improved their predictive capabilities.

Conclusions

Without individual optimization, CHDmap demonstrates competitive performance compared to clinical experts. In addition, CHDmap has the advantage of enabling clinicians to use their superior cognitive abilities in conjunction with it to make decisions that are sometimes even superior to those made using artificial intelligence models. The MBE approach can be embraced in clinical practice, and its full potential can be realized.

Applying unsupervised machine learning approaches to characterize autologous breast reconstruction patient subgroups: an NSQIP analysis of 14,274 patients

BACKGROUND

Autologous breast reconstruction is composed of diverse techniques and results in a variety of outcome trajectories. We propose employing an unsupervised machine learning method to characterize such heterogeneous patterns in large-scale datasets.

METHODS

A retrospective cohort study of autologous breast reconstruction patients was conducted through the National Surgical Quality Improvement Program database. Patient characteristics, intraoperative variables, and occurrences of acute postoperative complications were collected. The cohort was classified into patient subgroups via the K-means clustering algorithm, a similarity-based unsupervised learning approach. The characteristics of each cluster were compared for differences from the complementary sample (p < 2 ×10-4) and validated with a test set.

RESULTS

A total of 14,274 female patients were included in the final study cohort. Clustering identified seven optimal subgroups, ordered by increasing rate of postoperative complication. Cluster 1 (2027 patients) featured breast reconstruction with free flaps (50%) and latissimus dorsi flaps (40%). In addition to its low rate of complications (14%, p < 2 ×10-4), its patient population was younger and with lower comorbidities when compared with the whole cohort. In the other extreme, cluster 7 (1112 patients) almost exclusively featured breast reconstruction with free flaps (94%) and possessed the highest rates of unplanned reoperations, readmissions, and dehiscence (p < 2 ×10-4). The reoperation profile of cluster 3 was also significantly different from the general cohort and featured lower proportions of vascular repair procedures (p < 8 ×10-4).

CONCLUSIONS

This study presents a novel, generalizable application of an unsupervised learning model to organize patient subgroups with associations between comorbidities, modality of breast reconstruction, and postoperative outcomes.

Emerging infectious disease surveillance using a hierarchical diagnosis model and the Knox algorithm

Emerging infectious diseases are a critical public health challenge in the twenty-first century. The recent proliferation of such diseases has raised major social and economic concerns. Therefore, early detection of emerging infectious diseases is essential. Subjects from five medical institutions in Beijing, China, which met the spatial-specific requirements, were analyzed. A quality control process was used to select 37,422 medical records of infectious diseases and 56,133 cases of non-infectious diseases. An emerging infectious disease detection model (EIDDM), a two-layer model that divides the problem into two sub-problems, i.e., whether a case is an infectious disease, and if so, whether it is a known infectious disease, was proposed. The first layer model adopts the binary classification model TextCNN-Attention. The second layer is a multi-classification model of LightGBM based on the one-vs-rest strategy. Based on the experimental results, a threshold of 0.5 is selected. The model results were compared with those of other models such as XGBoost and Random Forest using the following evaluation indicators: accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The prediction performance of the first-layer TextCNN is better than that of other comparison models. Its average specificity for non-infectious diseases is 97.57%, with an average negative predictive value of 82.63%, indicating a low risk of misdiagnosing non-infectious diseases as infectious (i.e., a low false positive rate). Its average positive predictive value for eight selected infectious diseases is 95.07%, demonstrating the model's ability to avoid misdiagnoses. The overall average accuracy of the model is 86.11%. The average prediction accuracy of the second-layer LightGBM model for emerging infectious diseases reaches 90.44%. Furthermore, the response time of a single online reasoning using the LightGBM model is approximately 27 ms, which makes it suitable for analyzing clinical records in real time. Using the Knox method, we found that all the infectious diseases were within 2000 m in our case, and a clustering feature of spatiotemporal interactions (P < 0.05) was observed as well. Performance testing and model comparison results indicated that the EIDDM is fast and accurate and can be used to monitor the onset/outbreak of emerging infectious diseases in real-world hospitals.

Model-driven survival prediction after congenital heart surgery

OBJECTIVES

The objective of the study was to improve postoperative risk assessment in congenital heart surgery by developing a machine-learning model based on readily available peri- and postoperative parameters.

METHODS

Our bicentric retrospective data analysis from January 2014 to December 2019 of established risk parameters for dismal outcome was used to train and test a model to predict postoperative survival within the first 30 days. The Freiburg training data consisted of 780 procedures; the Heidelberg test data comprised 985 procedures. STAT mortality score, age, aortic cross-clamp time and postoperative lactate values over 24 h were considered.

RESULTS

Our model showed an area under the curve (AUC) of 94.86%, specificity of 89.48% and sensitivity of 85.00%, resulting in 3 false negatives and 99 false positives.The STAT mortality score and the aortic cross-clamp time each showed a statistically highly significant impact on postoperative mortality. Interestingly, a child's age was barely statistically significant. Postoperative lactate values indicated an increased mortality risk if they were either constantly at a high level or low during the first 8 h postoperatively with an increase afterwards.When considering parameters available before, at the end of and 24 h after surgery, the predictive power of the complete model achieved the highest AUC. This, compared to the already high predictive power alone (AUC 88.9%) of the STAT mortality score, translates to an error reduction of 53.5%.

CONCLUSIONS

Our model predicts postoperative survival after congenital heart surgery with great accuracy. Compared with preoperative risk assessments, our postoperative risk assessment reduces prediction error by half. Heightened awareness of high-risk patients should improve preventive measures and thus patient safety.

Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy

When children are discharged from the hospital after surgery, their caregivers often rely on subjective assessments (e.g., appetite, fatigue) to monitor postoperative recovery as objective assessment tools are scarce at home. Such imprecise and one-dimensional evaluations can result in unwarranted emergency department visits or delayed care. To address this gap in postoperative monitoring, we evaluated the ability of a consumer-grade wearable device, Fitbit, which records multimodal data about daily physical activity, heart rate, and sleep, in detecting abnormal recovery early in children recovering after appendectomy. One hundred and sixty-two children, ages 3-17 years old, who underwent an appendectomy (86 complicated and 76 simple cases of appendicitis) wore a Fitbit device on their wrist for 21 days postoperatively. Abnormal recovery events (i.e., abnormal symptoms or confirmed postoperative complications) that arose during this period were gathered from medical records and patient reports. Fitbit-derived measures, as well as demographic and clinical characteristics, were used to train machine learning models to retrospectively detect abnormal recovery in the two days leading up to the event for patients with complicated and simple appendicitis. A balanced random forest classifier accurately detected 83% of these abnormal recovery days in complicated appendicitis and 70% of abnormal recovery days in simple appendicitis prior to the true report of a symptom/complication. These results support the development of machine learning algorithms to predict onset of abnormal symptoms and complications in children undergoing surgery, and the use of consumer wearables as monitoring tools for early detection of postoperative events.

Clinical assistant decision-making model of tuberculosis based on electronic health records

BACKGROUND

Tuberculosis is a dangerous infectious disease with the largest number of reported cases in China every year. Preventing missed diagnosis has an important impact on the prevention, treatment, and recovery of tuberculosis. The earliest pulmonary tuberculosis prediction models mainly used traditional image data combined with neural network models. However, a single data source tends to miss important information, such as primary symptoms and laboratory test results, that is available in multi-source data like medical records and tests. In this study, we propose a multi-stream integrated pulmonary tuberculosis diagnosis model based on structured and unstructured multi-source data from electronic health records. With the limited number of lung specialists and the high prevalence of tuberculosis, the application of this auxiliary diagnosis model can make substantial contributions to clinical settings.

METHODS

The subjects were patients at the respiratory department and infectious cases department of a large comprehensive hospital in China between 2015 to 2020. A total of 95,294 medical records were selected through a quality control process. Each record contains structured and unstructured data. First, numerical expressions of features for structured data were created. Then, feature engineering was performed through decision tree model, random forest, and GBDT. Features were included in the feature exclusion set as per their weights in descending order. When the importance of the set was higher than 0.7, this process was concluded. Finally, the contained features were used for model training. In addition, the unstructured free-text data was segmented at the character level and input into the model after indexing. Tuberculosis prediction was conducted through a multi-stream integration tuberculosis diagnosis model (MSI-PTDM), and the evaluation indices of accuracy, AUC, sensitivity, and specificity were compared against the prediction results of XGBoost, Text-CNN, Random Forest, SVM, and so on.

RESULTS

Through a variety of characteristic engineering methods, 20 characteristic factors, such as main complaint hemoptysis, cough, and test erythrocyte sedimentation rate, were selected, and the influencing factors were analyzed using the Chinese diagnostic standard of pulmonary tuberculosis. The area under the curve values for MSI-PTDM, XGBoost, Text-CNN, RF, and SVM were 0.9858, 0.9571, 0.9486, 0.9428, and 0.9429, respectively. The sensitivity, specificity, and accuracy of MSI-PTDM were 93.18%, 96.96%, and 96.96%, respectively. The MSI-PTDM prediction model was installed at a doctor workstation and operated in a real clinic environment for 4 months. A total of 692,949 patients were monitored, including 484 patients with confirmed pulmonary tuberculosis. The model predicted 440 cases of pulmonary tuberculosis. The positive sample recognition rate was 90.91%, the false-positive rate was 9.09%, the negative sample recognition rate was 96.17%, and the false-negative rate was 3.83%.

CONCLUSIONS

MSI-PTDM can process sparse data, dense data, and unstructured text data concurrently. The model adds a feature domain vector embedding the medical sparse features, and the single-valued sparse vectors are represented by multi-dimensional dense hidden vectors, which not only enhances the feature expression but also alleviates the side effects of sparsity on the model training. However, there may be information loss when features are extracted from text, and adding the processing of original unstructured text makes up for the error within the above process to a certain extent, so that the model can learn data more comprehensively and effectively. In addition, MSI-PTDM also allows interaction between features, considers the combination effect between patient features, adds more complex nonlinear calculation considerations, and improves the learning ability of the model. It has been verified using a test set and via deployment within an actual outpatient environment.

Artificial Intelligence in Congenital Heart Disease: Current State and Prospects

The current era of big data offers a wealth of new opportunities for clinicians to leverage artificial intelligence to optimize care for pediatric and adult patients with a congenital heart disease. At present, there is a significant underutilization of artificial intelligence in the clinical setting for the diagnosis, prognosis, and management of congenital heart disease patients. This document is a call to action and will describe the current state of artificial intelligence in congenital heart disease, review challenges, discuss opportunities, and focus on the top priorities of artificial intelligence-based deployment in congenital heart disease.

Artificial Intelligence in Pediatric Cardiology: A Scoping Review

The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.

Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022)

BACKGROUND AND OBJECTIVES

Artificial intelligence (AI) has branched out to various applications in healthcare, such as health services management, predictive medicine, clinical decision-making, and patient data and diagnostics. Although AI models have achieved human-like performance, their use is still limited because they are seen as a black box. This lack of trust remains the main reason for their low use in practice, especially in healthcare. Hence, explainable artificial intelligence (XAI) has been introduced as a technique that can provide confidence in the model's prediction by explaining how the prediction is derived, thereby encouraging the use of AI systems in healthcare. The primary goal of this review is to provide areas of healthcare that require more attention from the XAI research community.

METHODS

Multiple journal databases were thoroughly searched using PRISMA guidelines 2020. Studies that do not appear in Q1 journals, which are highly credible, were excluded.

RESULTS

In this review, we surveyed 99 Q1 articles covering the following XAI techniques: SHAP, LIME, GradCAM, LRP, Fuzzy classifier, EBM, CBR, rule-based systems, and others.

CONCLUSION

We discovered that detecting abnormalities in 1D biosignals and identifying key text in clinical notes are areas that require more attention from the XAI research community. We hope this is review will encourage the development of a holistic cloud system for a smart city.

Severe Complications after General Anesthesia versus Sedation during Pediatric Diagnostic Cardiac Catheterization for Ventricular Septal Defect

Pediatric cardiac catheterization requires unconsciousness and immobilization through general anesthesia or sedation. This study aimed to compare the occurrence of severe complications in pediatric diagnostic cardiac catheterization for ventricular septal defect between general anesthesia and sedation performed under similar institutional environments. Using the Japanese Diagnosis Procedure Combination database, we retrospectively identified pediatric patients (aged <2 years) who underwent diagnostic cardiac catheterization for ventricular septal defect between July 2010 and March 2019. The composite outcome was the occurrence of severe complications, including catecholamine use and intensive care unit admission, within seven days after catheterization. Overlap weighting based on propensity scores was used to adjust for patient- and hospital-level confounding factors. We identified 3159 patients from 87 hospitals, including 930 under general anesthesia and 2229 under sedation. The patient- and hospital-level baseline characteristics differed between the groups. After adjustment, the proportion of patients with severe complications was significantly higher in the general anesthesia group than in the sedation group (2.4% vs. 0.6%; risk difference, 1.8% [95% confidence interval, 0.93−2.6%]). Severe complications occurred more frequently in the general anesthesia group than in the sedation group. Further research on anesthetic methods is necessary to assess the safety and accuracy of pediatric diagnostic cardiac catheterization.

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

Pediatric congenital heart disease (CHD) patients are at higher risk of postoperative complications and clinical deterioration either due to their underlying pathology or due to the cardiac surgery, contributing significantly to mortality, morbidity, hospital and family costs, and poor quality of life. In current clinical practice, clinical deterioration is detected, in most of the cases, when it has already occurred. Several early warning scores (EWS) have been proposed to assess children at risk of clinical deterioration using vital signs and risk indicators, in order to intervene in a timely manner to reduce the impact of deterioration and risk of death among children. However, EWS are based on measurements performed at a single time point without incorporating trends nor providing information about patient's risk trajectory. Moreover, some of these measurements rely on subjective assessment making them susceptible to different interpretations. All these limitations could explain why the implementation of EWS in high-resource settings failed to show a significant decrease in hospital mortality. By means of machine learning (ML) based algorithms we could integrate heterogeneous and complex data to predict patient's risk of deterioration. In this perspective article, we provide a brief overview of the potential of ML technologies to improve the identification of pediatric CHD patients at high-risk for clinical deterioration after cardiac surgery, and present the CORTEX traffic light, a ML-based predictive system that Sant Joan de Déu Barcelona Children's Hospital is implementing, as an illustration of the application of an ML-based risk stratification system in a relevant hospital setting.

A time-incorporated SOFA score-based machine learning model for predicting mortality in critically ill patients: A multicenter, real-world study

BACKGROUND

Organ dysfunction (OD) assessment is essential in intensive care units (ICUs). However, current OD assessment scores merely describe the number and the severity of each OD, without evaluating the duration of organ injury. The objective of this study is to develop and validate a machine learning model based on the Sequential Organ Failure Assessment (SOFA) score for the prediction of mortality in critically ill patients.

MATERIAL AND METHODS

Data from the eICU Collaborative Research Database and Medical Information Mart for Intensive Care (MIMIC) -III were mixed for model development. The MIMIC-IV and Nanjing Jinling Hospital Surgical ICU database were used as external test set A and set B, respectively. The outcome of interest was in-ICU mortality. A modified SOFA model incorporating time-dimension (T-SOFA) was stepwise developed to predict ICU mortality using extreme gradient boosting (XGBoost), support vector machine, random forest and logistic regression algorithms. Time-dimensional features were calculated based on six consecutive SOFA scores collected every 12 h within the first three days of admission. The predictive performance was assessed with the area under the receiver operating characteristic curves (AUROC) and calibration plot.

RESULTS

A total of 82,132 patients from the real-world datasets were included in this study, and 7,494 patients (9.12%) died during their ICU stay. The T-SOFA M3 that incorporated the time-dimension features and age, using the XGBoost algorithm, significantly outperformed the original SOFA score in the validation set (AUROC 0.800 95% CI [0.787-0.813] vs. 0.693 95% CI [0.678-0.709], p < 0.01). Good discrimination and calibration were maintained in the test set A and B, with AUROC of 0.803, 95% CI [0.791-0.815] and 0.830, 95% CI [0.789-0.870], respectively.

CONCLUSIONS

The time-incorporated T-SOFA model could significantly improve the prediction performance of the original SOFA score and is of potential for identifying high-risk patients in future clinical application.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Medical Professional Enhancement Using Explainable Artificial Intelligence in Fetal Cardiac Ultrasound Screening

Diagnostic support tools based on artificial intelligence (AI) have exhibited high performance in various medical fields. However, their clinical application remains challenging because of the lack of explanatory power in AI decisions (black box problem), making it difficult to build trust with medical professionals. Nevertheless, visualizing the internal representation of deep neural networks will increase explanatory power and improve the confidence of medical professionals in AI decisions. We propose a novel deep learning-based explainable representation "graph chart diagram" to support fetal cardiac ultrasound screening, which has low detection rates of congenital heart diseases due to the difficulty in mastering the technique. Screening performance improves using this representation from 0.966 to 0.975 for experts, 0.829 to 0.890 for fellows, and 0.616 to 0.748 for residents in the arithmetic mean of area under the curve of a receiver operating characteristic curve. This is the first demonstration wherein examiners used deep learning-based explainable representation to improve the performance of fetal cardiac ultrasound screening, highlighting the potential of explainable AI to augment examiner capabilities.