Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study

Detectable troponin below the 99th percentile predicts survival in patients undergoing coronary angiography

Background

Cardiac troponin I (cTnI) above the 99th percentile is associated with an increased risk of major adverse events. Patients with detectable cTnI below the 99th percentile are a heterogeneous group with a less well-defined risk profile. The purpose of this study is to investigate the prognostic relevance of detectable cTnI below the 99th percentile in patients undergoing coronary angiography.

Methods

The study included 14,776 consecutive patients (mean age of 65.4 ± 12.7 years, 71.3 % male) from the Essen Coronary Artery Disease (ECAD) registry. Patients with cTnI levels above the 99th percentile and patients with ST-segment elevation acute myocardial infarction were excluded. All-cause mortality was defined as the primary endpoint.

Results

Detectable cTnI below the 99th percentile was present in 2811 (19.0 %) patients, while 11,965 (81.0 %) patients were below detection limit of the employed assay. The mean follow-up was 4.25 ± 3.76 years. All-cause mortality was 20.8 % for patients with detectable cTnI below the 99th percentile and 15.0 % for those without detectable cTnI. In a multivariable Cox regression analysis, detectable cTnI was independently associated with all-cause mortality with a hazard ratio of 1.60 (95 % CI 1.45-1.76; p < 0.001). There was a stepwise relationship with increasing all-cause mortality and tertiles of detectable cTnI levels with hazard ratios of 1.63 (95 % CI 1.39-1.90) for the first tertile to 2.02 (95 % CI 1.74-2.35) for the third tertile.

Conclusions

Detectable cTnI below the 99th percentile is an independent predictor of mortality in patients undergoing coronary angiography with the risk of death growing progressively with increasing troponin levels.

Development and validation of a nomogram model for all-cause mortality risk in patients with chronic heart failure and atrial fibrillation

BACKGROUND

As the global aging process continues to accelerate, heart failure (HF) has become an important cause of increased morbidity and mortality in elderly patients. Chronic atrial fibrillation (AF) is a major risk factor for HF. Patients with HF combined with AF are more difficult to treat and have a worse prognosis. The aim of this study was to explore the risk factors for 1-year mortality in patients with HF combined with AF and to develop a risk prediction assessment model.

METHODS

We recruited hospitalized patients with HF and AF who received standardized care in the Department of Cardiology at Shengjing Hospital of China Medical University from January 2013 to December 2018. The patients were randomly divided into modeling and internal validation groups using a random number generator at a 1:1 ratio. Multivariate Cox regression analysis was used to identify risk factors for all-cause mortality during a one-year follow-up period. Then, a nomogram was constructed based on the weights of each index and validated. Receiver operating characteristic curve, the area under the curve (AUC), decision curve, and calibration curve analyses for survival were used to evaluate the model's predictive and clinical validities and calibration.

RESULTS

We included 3,406 patients who met the eligibility criteria; 1,703 cases each were included in the modeling and internal validation groups. Eight statistically significant predictors were identified: age, sex, New York Heart Association cardiac function class III or IV, a history of myocardial infarction, and the albumin, triglycerides, N-terminal pro-b-type natriuretic peptide, and blood urea nitrogen levels. The AUCs were 0.793 (95% confidence interval: 0.763-0.823) and 0.794 (95% confidence interval: 0.763-0.823) in the modeling and validation cohorts, respectively.

CONCLUSIONS

We present a predictive model for all-cause mortality in patients with coexisting HF and AF comprising eight key factors. This model gives clinicians a simple assessment tool that may improve the clinical management of these patients.

Development and Validation of an Explainable Deep Learning Model to Predict In-Hospital Mortality for Patients With Acute Myocardial Infarction: Algorithm Development and Validation Study

BACKGROUND

Acute myocardial infarction (AMI) is one of the most severe cardiovascular diseases and is associated with a high risk of in-hospital mortality. However, the current deep learning models for in-hospital mortality prediction lack interpretability.

OBJECTIVE

This study aims to establish an explainable deep learning model to provide individualized in-hospital mortality prediction and risk factor assessment for patients with AMI.

METHODS

In this retrospective multicenter study, we used data for consecutive patients hospitalized with AMI from the Chongqing University Central Hospital between July 2016 and December 2022 and the Electronic Intensive Care Unit Collaborative Research Database. These patients were randomly divided into training (7668/10,955, 70%) and internal test (3287/10,955, 30%) data sets. In addition, data of patients with AMI from the Medical Information Mart for Intensive Care database were used for external validation. Deep learning models were used to predict in-hospital mortality in patients with AMI, and they were compared with linear and tree-based models. The Shapley Additive Explanations method was used to explain the model with the highest area under the receiver operating characteristic curve in both the internal test and external validation data sets to quantify and visualize the features that drive predictions.

RESULTS

A total of 10,955 patients with AMI who were admitted to Chongqing University Central Hospital or included in the Electronic Intensive Care Unit Collaborative Research Database were randomly divided into a training data set of 7668 (70%) patients and an internal test data set of 3287 (30%) patients. A total of 9355 patients from the Medical Information Mart for Intensive Care database were included for independent external validation. In-hospital mortality occurred in 8.74% (670/7668), 8.73% (287/3287), and 9.12% (853/9355) of the patients in the training, internal test, and external validation cohorts, respectively. The Self-Attention and Intersample Attention Transformer model performed best in both the internal test data set and the external validation data set among the 9 prediction models, with the highest area under the receiver operating characteristic curve of 0.86 (95% CI 0.84-0.88) and 0.85 (95% CI 0.84-0.87), respectively. Older age, high heart rate, and low body temperature were the 3 most important predictors of increased mortality, according to the explanations of the Self-Attention and Intersample Attention Transformer model.

CONCLUSIONS

The explainable deep learning model that we developed could provide estimates of mortality and visual contribution of the features to the prediction for a patient with AMI. The explanations suggested that older age, unstable vital signs, and metabolic disorders may increase the risk of mortality in patients with AMI.

Exploring trends and autonomy levels of adaptive business intelligence in healthcare: A systematic review

OBJECTIVE

In order to comprehensively understand the characteristics of Adaptive Business Intelligence (ABI) in Healthcare, this study is structured to provide insights into the common features and evolving patterns within this domain. Applying the Sheridan's Classification as a framework, we aim to assess the degree of autonomy exhibited by various ABI components. Together, these objectives will contribute to a deeper understanding of ABI implementation and its implications within the Healthcare context.

METHODS

A comprehensive search of academic databases was conducted to identify relevant studies, selecting AIS e-library (AISel), Decision Support Systems Journal (DSSJ), Nature, The Lancet Digital Health (TLDH), PubMed, Expert Systems with Application (ESWA) and npj Digital Medicine as information sources. Studies from 2006 to 2022 were included based on predefined eligibility criteria. PRISMA statements were used to report this study.

RESULTS

The outcomes showed that ABI systems present distinct levels of development, autonomy and practical deployment. The high levels of autonomy were essentially associated with predictive components. However, the possibility of completely autonomous decisions by these systems is totally excluded. Lower levels of autonomy are also observed, particularly in connection with prescriptive components, granting users responsibility in the generation of decisions.

CONCLUSION

The study presented emphasizes the vital connection between desired outcomes and the inherent autonomy of these solutions, highlighting the critical need for additional research on the consequences of ABI systems and their constituent elements. Organizations should deploy these systems in a way consistent with their objectives and values, while also being mindful of potential adverse effects. Providing valuable insights for researchers, practitioners, and policymakers aiming to comprehend the diverse levels of ABI systems implementation, it contributes to well-informed decision-making in this dynamic field.

Forecasting the Risk of Heart Failure Hospitalization After Acute Coronary Syndromes: the CORALYS HF Score

The present study aimed to identify patients at a higher risk of hospitalization for heart failure (HF) in a population of patients with acute coronary syndrome (ACS) treated with percutaneous coronary revascularization without a history of HF or reduced left ventricular (LV) ejection fraction before the index admission. We performed a Cox regression multivariable analysis with competitive risk and machine learning models on the incideNce and predictOrs of heaRt fAiLure After Acute coronarY Syndrome (CORALYS) registry (NCT04895176), an international and multicenter study including consecutive patients admitted for ACS in 16 European Centers from 2015 to 2020. Of 14,699 patients, 593 (4.0%) were admitted for the development of HF up to 1 year after the index ACS presentation. A total of 2 different data sets were randomly created, 1 for the derivative cohort including 11,626 patients (80%) and 1 for the validation cohort including 3,073 patients (20%). On the Cox regression multivariable analysis, several variables were associated with the risk of HF hospitalization, with reduced renal function, complete revascularization, and LV ejection fraction as the most relevant ones. The area under the curve at 1 year was 0.75 (0.72 to 0.78) in the derivative cohort, whereas on validation, it was 0.72 (0.67 to 0.77). The machine learning analysis showed a slightly inferior performance. In conclusion, in a large cohort of patients with ACS without a history of HF or LV dysfunction before the index event, the CORALYS HF score identified patients at a higher risk of hospitalization for HF using variables easily accessible at discharge. Further approaches to tackle HF development in this high-risk subset of patients are needed.

Exploring and validating the prognostic value of pathomics signatures and genomics in patients with cutaneous melanoma based on bioinformatics and deep learning

BACKGROUND

Cutaneous melanoma (CM) is the most common malignant tumor of the skin. Our study aimed to investigate the prognostic value of pathomics signatures for CM by combining pathomics and genomics.

PURPOSE

The purpose of this study was to explore the potential application value of pathomics signatures.

METHODS

Pathology full scans, clinical information, and genomics data for CM patients were downloaded from The Cancer Genome Atlas (TCGA) database. Exploratory data analysis (EDA) was used to visualize patient characteristics. Genes related to a poorer prognosis were screened through differential analysis. Survival analysis was performed to assess the prognostic value of gene and pathomics signatures. Artificial neural network (ANN) models predicted prognosis using signatures and genes. Correlation analysis was used to explore signature-gene links.

RESULTS

The clinical traits for 468 CM samples and the genomic data and pathology images for 471 CM samples were obtained from the TCGA database. The EDA results combined with multiple machine learning (ML) models suggested that the top 5 clinical traits in terms of importance were age, biopsy site, T stage, N stage and overall disease stage, and the eight ML models had a precision lower than 0.56. A total of 60 differentially expressed genes were obtained by comparing sequencing data. A total of 413 available quantitative signatures of each pathomics image were obtained with CellProfile software. The precision of the binary classification model based on pathomics signatures was 0.99, with a loss value of 1.7119e-04. The precision of the binary classification model based on differentially expressed genes was 0.98, with a loss value of 0.1101. The precision of the binary classification model based on pathomics signatures and differentially expressed genes was 0.97, with a loss value of 0.2088. The survival analyses showed that the survival rate of the high-risk group based on gene expression and pathomics signatures was significantly lower than that of the low-risk group. A total of 222 pathomics signatures and 51 differentially expressed genes were analyzed for survival with p-values of less than 0.05. There was a certain correlation between some pathomics signatures and differential gene expression involving ANO2, LINC00158, NDNF, ADAMTS15, and ADGRB3, etc. CONCLUSION: This study evaluated the prognostic significance of pathomics signatures and differentially expressed genes in CM patients. Three ANN models were developed, and all achieved accuracy rates higher than 97%. Specifically, the pathomics signature-based ANN model maintained a remarkable accuracy of 99%. These findings highlight the CellProfile + ANN model as an excellent choice for prognostic prediction in CM patients. Furthermore, our correlation analysis experimentally demonstrated a preliminary link between disease quantification and qualitative changes. Among various features, including M stage and treatments received, special attention should be given to age, biopsy site, T stage, N stage, and overall disease stage in CM patients.

Organ dysfunction and mortality in preterm neonates with late-onset bloodstream infection

BACKGROUND

Organ dysfunction (ODF) in late-onset bloodstream infection (LBSI) is associated with increased risk of adverse outcomes. However, no established definition of ODF exists among preterm neonates. Our objective was to describe an outcome-based ODF definition for preterm infants, and assess factors associated with mortality.

METHODS

This is a six-year retrospective study of neonates <35 weeks gestational age, >72 h of age, with non-CONS bacterial/fungal LBSI. Discriminatory ability of each parameter for mortality was evaluated: base deficit ≤-8 mmol/L (BD8), renal dysfunction (urine output <1 cc/kg/h or creatinine ≥100 μmol/L), hypoxic respiratory failure (HRF, ventilated, FiO2 = 1.0), or vasopressor/inotrope use (V/I). Multivariable logistic regression analysis was performed to derive a mortality score.

RESULTS

One hundred and forty-eight infants had LBSI. BD8 had the highest individual predictive ability for mortality (AUROC = 0.78). The combination BD8 + HRF + V/I was used to define ODF (AUROC = 0.84). Fifty-seven (39%) infants developed ODF, among which 28 (49%) died. Mortality increased inversely relative to GA at LBSI-onset (aOR 0.81 [0.67, 0.98]) and directly relative to ODF occurrence (12.15 [4.48, 33.92]). Compared to no-ODF, ODF infants had lower GA and age at illness, and higher frequency of Gram-negative pathogen.

CONCLUSIONS

Among preterm neonates with LBSI, significant metabolic acidosis, HRF, and vasopressor/inotrope use may identify infants high risk for mortality. These criteria could help identify patients for future studies of adjunctive therapies.

IMPACT

Sepsis-related organ dysfunction is associated with increased risk of adverse outcomes. Among preterm neonates, significant metabolic acidosis, use of vasopressors/inotropes, and hypoxic respiratory failure may identify high-risk infants. This can be used to target research and quality improvement efforts toward the most vulnerable infants.

Development and comparison of machine learning-based models for predicting heart failure after acute myocardial infarction

AIMS

Heart failure (HF) is one of the common adverse cardiovascular events after acute myocardial infarction (AMI), but the predictive efficacy of numerous machine learning (ML) built models is unclear. This study aimed to build an optimal model to predict the occurrence of HF in AMI patients by comparing seven ML algorithms.

METHODS

Cohort 1 included AMI patients from 2018 to 2019 divided into HF and control groups. All first routine test data of the study subjects were collected as the features to be selected for the model, and seven ML algorithms with screenable features were evaluated. Cohort 2 contains AMI patients from 2020 to 2021 to establish an early warning model with external validation. ROC curve and DCA curve to analyze the diagnostic efficacy and clinical benefit of the model respectively.

RESULTS

The best performer among the seven ML algorithms was XgBoost, and the features of XgBoost algorithm for troponin I, triglycerides, urine red blood cell count, γ-glutamyl transpeptidase, glucose, urine specific gravity, prothrombin time, prealbumin, and urea were ranked high in importance. The AUC of the HF-Lab9 prediction model built by the XgBoost algorithm was 0.966 and had good clinical benefits.

CONCLUSIONS

This study screened the optimal ML algorithm as XgBoost and developed the model HF-Lab9 will improve the accuracy of clinicians in assessing the occurrence of HF after AMI and provide a reference for the selection of subsequent model-building algorithms.

Artificial Intelligence Technologies in Cardiology

As the world produces exabytes of data, there is a growing need to find new methods that are more suitable for dealing with complex datasets. Artificial intelligence (AI) has significant potential to impact the healthcare industry, which is already on the road to change with the digital transformation of vast quantities of information. The implementation of AI has already achieved success in the domains of molecular chemistry and drug discoveries. The reduction in costs and in the time needed for experiments to predict the pharmacological activities of new molecules is a milestone in science. These successful applications of AI algorithms provide hope for a revolution in healthcare systems. A significant part of artificial intelligence is machine learning (ML), of which there are three main types-supervised learning, unsupervised learning, and reinforcement learning. In this review, the full scope of the AI workflow is presented, with explanations of the most-often-used ML algorithms and descriptions of performance metrics for both regression and classification. A brief introduction to explainable artificial intelligence (XAI) is provided, with examples of technologies that have developed for XAI. We review important AI implementations in cardiology for supervised, unsupervised, and reinforcement learning and natural language processing, emphasizing the used algorithm. Finally, we discuss the need to establish legal, ethical, and methodical requirements for the deployment of AI models in medicine.

A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction

A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.

Patient-oriented risk score for predicting death 1 year after myocardial infarction: the SweDen risk score

OBJECTIVES

Our aim was to derive, based on the SWEDEHEART registry, and validate, using the Western Denmark Heart registry, a patient-oriented risk score, the SweDen score, which could calculate the risk of 1-year mortality following a myocardial infarction (MI).

METHODS

The factors included in the SweDen score were age, sex, smoking, diabetes, heart failure and statin use. These were chosen a priori by the SWEDEHEART steering group based on the premise that the factors were information known by the patients themselves. The score was evaluated using various statistical methods such as time-dependent receiver operating characteristics curves of the linear predictor, area under the curve metrics, Kaplan-Meier survivor curves and the calibration slope.

RESULTS

The area under the curve values were 0.81 in the derivation data and 0.76 in the validation data. The Kaplan-Meier curves showed similar patient profiles across datasets. The calibration slope was 1.03 (95% CI 0.99 to 1.08) in the validation data using the linear predictor from the derivation data.

CONCLUSIONS

The SweDen risk score is a novel tool created for patient use. The risk score calculator will be available online and presents mortality risk on a colour scale to simplify interpretation and to avoid exact life span expectancies. It provides a validated patient-oriented risk score predicting the risk of death within 1 year after suffering an MI, which visualises the benefit of statin use and smoking cessation in a simple way.

Applying Artificial Intelligence to Wearable Sensor Data to Diagnose and Predict Cardiovascular Disease: A Review

Cardiovascular disease (CVD) is the world's leading cause of mortality. There is significant interest in using Artificial Intelligence (AI) to analyse data from novel sensors such as wearables to provide an earlier and more accurate prediction and diagnosis of heart disease. Digital health technologies that fuse AI and sensing devices may help disease prevention and reduce the substantial morbidity and mortality caused by CVD worldwide. In this review, we identify and describe recent developments in the application of digital health for CVD, focusing on AI approaches for CVD detection, diagnosis, and prediction through AI models driven by data collected from wearables. We summarise the literature on the use of wearables and AI in cardiovascular disease diagnosis, followed by a detailed description of the dominant AI approaches applied for modelling and prediction using data acquired from sensors such as wearables. We discuss the AI algorithms and models and clinical applications and find that AI and machine-learning-based approaches are superior to traditional or conventional statistical methods for predicting cardiovascular events. However, further studies evaluating the applicability of such algorithms in the real world are needed. In addition, improvements in wearable device data accuracy and better management of their application are required. Lastly, we discuss the challenges that the introduction of such technologies into routine healthcare may face.

An Artificial Intelligence Approach to Guiding the Management of Heart Failure Patients Using Predictive Models: A Systematic Review

Heart failure (HF) is one of the leading causes of mortality and hospitalization worldwide. The accurate prediction of mortality and readmission risk provides crucial information for guiding decision making. Unfortunately, traditional predictive models reached modest accuracy in HF populations. We therefore aimed to present predictive models based on machine learning (ML) techniques in HF patients that were externally validated. We searched four databases and the reference lists of the included papers to identify studies in which HF patient data were used to create a predictive model. Literature screening was conducted in Academic Search Ultimate, ERIC, Health Source Nursing/Academic Edition and MEDLINE. The protocol of the current systematic review was registered in the PROSPERO database with the registration number CRD42022344855. We considered all types of outcomes: mortality, rehospitalization, response to treatment and medication adherence. The area under the receiver operating characteristic curve (AUC) was used as the comparator parameter. The literature search yielded 1649 studies, of which 9 were included in the final analysis. The AUCs for the machine learning models ranged from 0.6494 to 0.913 in independent datasets, whereas the AUCs for statistical predictive scores ranged from 0.622 to 0.806. Our study showed an increasing number of ML predictive models concerning HF populations, although external validation remains infrequent. However, our findings revealed that ML approaches can outperform conventional risk scores and may play important role in HF management.

Application of artificial intelligence techniques for automated detection of myocardial infarction: a review

Myocardial infarction (MI) results in heart muscle injury due to receiving insufficient blood flow. MI is the most common cause of mortality in middle-aged and elderly individuals worldwide. To diagnose MI, clinicians need to interpret electrocardiography (ECG) signals, which requires expertise and is subject to observer bias. Artificial intelligence-based methods can be utilized to screen for or diagnose MI automatically using ECG signals. In this work, we conducted a comprehensive assessment of artificial intelligence-based approaches for MI detection based on ECG and some other biophysical signals, including machine learning (ML) and deep learning (DL) models. The performance of traditional ML methods relies on handcrafted features and manual selection of ECG signals, whereas DL models can automate these tasks. The review observed that deep convolutional neural networks (DCNNs) yielded excellent classification performance for MI diagnosis, which explains why they have become prevalent in recent years. To our knowledge, this is the first comprehensive survey of artificial intelligence techniques employed for MI diagnosis using ECG and some other biophysical signals.