Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

Development of a Cohort Analytics Tool for Monitoring Progression Patterns in Cardiovascular Diseases: Advanced Stochastic Modeling Approach

BACKGROUND

The World Health Organization (WHO) reported that cardiovascular diseases (CVDs) are the leading cause of death worldwide. CVDs are chronic, with complex progression patterns involving episodes of comorbidities and multimorbidities. When dealing with chronic diseases, physicians often adopt a "watchful waiting" strategy, and actions are postponed until information is available. Population-level transition probabilities and progression patterns can be revealed by applying time-variant stochastic modeling methods to longitudinal patient data from cohort studies. Inputs from CVD practitioners indicate that tools to generate and visualize cohort transition patterns have many impactful clinical applications. The resultant computational model can be embedded in digital decision support tools for clinicians. However, to date, no study has attempted to accomplish this for CVDs.

OBJECTIVE

This study aims to apply advanced stochastic modeling methods to uncover the transition probabilities and progression patterns from longitudinal episodic data of patient cohorts with CVD and thereafter use the computational model to build a digital clinical cohort analytics artifact demonstrating the actionability of such models.

METHODS

Our data were sourced from 9 epidemiological cohort studies by the National Heart Lung and Blood Institute and comprised chronological records of 1274 patients associated with 4839 CVD episodes across 16 years. We then used the continuous-time Markov chain method to develop our model, which offers a robust approach to time-variant transitions between disease states in chronic diseases.

RESULTS

Our study presents time-variant transition probabilities of CVD state changes, revealing patterns of CVD progression against time. We found that the transition from myocardial infarction (MI) to stroke has the fastest transition rate (mean transition time 3, SD 0 days, because only 1 patient had a MI-to-stroke transition in the dataset), and the transition from MI to angina is the slowest (mean transition time 1457, SD 1449 days). Congestive heart failure is the most probable first episode (371/840, 44.2%), followed by stroke (216/840, 25.7%). The resultant artifact is actionable as it can act as an eHealth cohort analytics tool, helping physicians gain insights into treatment and intervention strategies. Through expert panel interviews and surveys, we found 9 application use cases of our model.

CONCLUSIONS

Past research does not provide actionable cohort-level decision support tools based on a comprehensive, 10-state, continuous-time Markov chain model to unveil complex CVD progression patterns from real-world patient data and support clinical decision-making. This paper aims to address this crucial limitation. Our stochastic model-embedded artifact can help clinicians in efficient disease monitoring and intervention decisions, guided by objective data-driven insights from real patient data. Furthermore, the proposed model can unveil progression patterns of any chronic disease of interest by inputting only 3 data elements: a synthetic patient identifier, episode name, and episode time in days from a baseline date.

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.

Unmet needs and future directions in hypertrophic cardiomyopathy

Hypertrophic cardiomyopathy (HCM) is a highly treatable monogenetic disorder affecting nearly 0.2% of the population. The high burden of this disease demands suitable measures for early diagnosis and preventing as well as tackling misdiagnosis. While conventionally available therapies have been efficacious in reducing symptoms, they have not been able to change the natural history of the disease. The landscape of medical treatment is rapidly changing with advent of novel pharmacotherapies such as cardiac myosin inhibitors. Ongoing investigations in gene editing have demonstrated benefits in correcting underlying genetic mutations and this is where the future of treatment lies. Contemporary procedural techniques as alternatives to available septal reduction therapies independent of coronary vascular anatomy are also emerging. This review details the recent developments, unmet needs and future directions in diagnosis, medical and invasive treatment of HCM.

Primer on Machine Learning in Electrophysiology

Artificial intelligence has become ubiquitous. Machine learning, a branch of artificial intelligence, leads the current technological revolution through its remarkable ability to learn and perform on data sets of varying types. Machine learning applications are expected to change contemporary medicine as they are brought into mainstream clinical practice. In the field of cardiac arrhythmia and electrophysiology, machine learning applications have enjoyed rapid growth and popularity. To facilitate clinical acceptance of these methodologies, it is important to promote general knowledge of machine learning in the wider community and continue to highlight the areas of successful application. The authors present a primer to provide an overview of common supervised (least squares, support vector machine, neural networks and random forest) and unsupervised (k-means and principal component analysis) machine learning models. The authors also provide explanations as to how and why the specific machine learning models have been used in arrhythmia and electrophysiology studies.

Computational Modeling on Drugs Effects for Left Ventricle in Cardiomyopathy Disease

Cardiomyopathy is associated with structural and functional abnormalities of the ventricular myocardium and can be classified in two major groups: hypertrophic (HCM) and dilated (DCM) cardiomyopathy. Computational modeling and drug design approaches can speed up the drug discovery and significantly reduce expenses aiming to improve the treatment of cardiomyopathy. In the SILICOFCM project, a multiscale platform is developed using coupled macro- and microsimulation through finite element (FE) modeling of fluid-structure interactions (FSI) and molecular drug interactions with the cardiac cells. FSI was used for modeling the left ventricle (LV) with a nonlinear material model of the heart wall. Simulations of the drugs' influence on the electro-mechanics LV coupling were separated in two scenarios, defined by the principal action of specific drugs. We examined the effects of Disopyramide and Dygoxin which modulate Ca2+ transients (first scenario), and Mavacamten and 2-deoxy adenosine triphosphate (dATP) which affect changes of kinetic parameters (second scenario). Changes of pressures, displacements, and velocity distributions, as well as pressure-volume (P-V) loops in the LV models of HCM and DCM patients were presented. Additionally, the results obtained from the SILICOFCM Risk Stratification Tool and PAK software for high-risk HCM patients closely followed the clinical observations. This approach can give much more information on risk prediction of cardiac disease to specific patients and better insight into estimated effects of drug therapy, leading to improved patient monitoring and treatment.

Machine Learning for Online Automatic Prediction of Common Disease Attributes Using Never-Ending Image Learner

The rapid increase in Internet technology and machine-learning devices has opened up new avenues for online healthcare systems. Sometimes, getting medical assistance or healthcare advice online is easier to understand than getting it in person. For mild symptoms, people frequently feel reluctant to visit the hospital or a doctor; instead, they express their questions on numerous healthcare forums. However, predictions may not always be accurate, and there is no assurance that users will always receive a reply to their posts. In addition, some posts are made up, which can misdirect the patient. To address these issues, automatic online prediction (OAP) is proposed. OAP clarifies the idea of employing machine learning to predict the common attributes of disease using Never-Ending Image Learner with an intelligent analysis of disease factors. Never-Ending Image Learner predicts disease factors by selecting from finite data images with minimum structural risk and efficiently predicting efficient real-time images via machine-learning-enabled M-theory. The proposed multi-access edge computing platform works with the machine-learning-assisted automatic prediction from multiple images using multiple-instance learning. Using a Never-Ending Image Learner based on Machine Learning, common disease attributes may be predicted online automatically. This method has deeper storage of images, and their data are stored per the isotropic positioning. The proposed method was compared with existing approaches, such as Multiple-Instance Learning for automated image indexing and hyper-spectrum image classification. Regarding the machine learning of multiple images with the application of isotropic positioning, the operating efficiency is improved, and the results are predicted with better accuracy. In this paper, machine-learning performance metrics for online automatic prediction tools are compiled and compared, and through this survey, the proposed method is shown to achieve higher accuracy, proving its efficiency compared to the existing methods.

Performance evaluation of machine learning and Computer Coded Verbal Autopsy (CCVA) algorithms for cause of death determination: A comparative analysis of data from rural South Africa

Computer Coded Verbal Autopsy (CCVA) algorithms are commonly used to determine the cause of death (CoD) from questionnaire responses extracted from verbal autopsies (VAs). However, they can only operate on structured data and cannot effectively harness information from unstructured VA narratives. Machine Learning (ML) algorithms have also been applied successfully in determining the CoD from VA narratives, allowing the use of auxiliary information that CCVA algorithms cannot directly utilize. However, most ML-based studies only use responses from the structured questionnaire, and the results lack generalisability and comparability across studies. We present a comparative performance evaluation of ML methods and CCVA algorithms on South African VA narratives data, using data from Agincourt Health and Demographic Surveillance Site (HDSS) with physicians' classifications as the gold standard. The data were collected from 1993 to 2015 and have 16,338 cases. The random forest and extreme gradient boosting classifiers outperformed the other classifiers on the combined dataset, attaining accuracy of 96% respectively, with significant statistical differences in algorithmic performance (p < 0.0001). All our models attained Area Under Receiver Operating Characteristics (AUROC) of greater than 0.884. The InterVA CCVA attained 83% Cause Specific Mortality Fraction accuracy and an Overall Chance-Corrected Concordance of 0.36. We demonstrate that ML models could accurately determine the cause of death from VA narratives. Additionally, through mortality trends and pattern analysis, we discovered that in the first decade of the civil registration system in South Africa, the average life expectancy was approximately 50 years. However, in the second decade, life expectancy significantly dropped, and the population was dying at a much younger average age of 40 years, mostly from the leading HIV related causes. Interestingly, in the third decade, we see a gradual improvement in life expectancy, possibly attributed to effective health intervention programmes. Through a structure and semantic analysis of narratives where experts disagree, we also demonstrate the most frequent terms of traditional healer consultations and visits. The comparative approach also makes this study a baseline that can be used for future research enforcing generalization and comparability. Future study will entail exploring deep learning models for CoD classification.