Machine Learning for Clinical Decision-Making: Challenges and Opportunities in Cardiovascular Imaging

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.

Incremental value of machine learning for risk prediction in tetralogy of Fallot

OBJECTIVE

Machine learning (ML) can facilitate prediction of major adverse cardiovascular events (MACEs) in repaired tetralogy of Fallot (rTOF). We sought to determine the incremental value of ML above expert clinical judgement for risk prediction in rTOF.

METHODS

Adult congenital heart disease (ACHD) clinicians (≥10 years of experience) participated (one cardiac surgeon and four cardiologists (two paediatric and two adult cardiology trained) with expertise in heart failure (HF), electrophysiology, imaging and intervention). Clinicians identified 10 high-yield variables for 5-year MACE prediction (defined as a composite of mortality, resuscitated sudden death, sustained ventricular tachycardia and HF). Risk for MACE (low, moderate or high) was assigned by clinicians blinded to outcome for adults with rTOF identified from an institutional database (n=25 patient reviews conducted by five independent observers). A validated ML model identified 10 variables for risk prediction in the same population.

RESULTS

Prediction by ML was similar to the aggregate score of all experts (area under the curve (AUC) 0.85 (95% CI 0.58 to 0.96) vs 0.92 (0.72 to 0.98), p=0.315). Experts with ≥20 years of experience had superior discriminative capacity compared with <20 years (AUC 0.98 (95% CI 0.86 to 0.99) vs 0.80 (0.56 to 0.93), p=0.027). In those with <20 years of experience, ML provided incremental value such that the combined (clinical+ML) AUC approached ≥20 years (AUC 0.85 (95% CI 0.61 to 0.95), p=0.055).

CONCLUSIONS

Robust prediction of 5-year MACE in rTOF was achieved using either ML or a multidisciplinary team of ACHD experts. Risk prediction of some clinicians was enhanced by incorporation of ML suggesting that there may be incremental value for ML in select circumstances.

Application of machine learning in measurement of ageing and geriatric diseases: a systematic review

BACKGROUND

As the ageing population continues to grow in many countries, the prevalence of geriatric diseases is on the rise. In response, healthcare providers are exploring novel methods to enhance the quality of life for the elderly. Over the last decade, there has been a remarkable surge in the use of machine learning in geriatric diseases and care. Machine learning has emerged as a promising tool for the diagnosis, treatment, and management of these conditions. Hence, our study aims to find out the present state of research in geriatrics and the application of machine learning methods in this area.

METHODS

This systematic review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and focused on healthy ageing in individuals aged 45 and above, with a specific emphasis on the diseases that commonly occur during this process. The study mainly focused on three areas, that are machine learning, the geriatric population, and diseases. Peer-reviewed articles were searched in the PubMed and Scopus databases with inclusion criteria of population above 45 years, must have used machine learning methods, and availability of full text. To assess the quality of the studies, Joanna Briggs Institute's (JBI) critical appraisal tool was used.

RESULTS

A total of 70 papers were selected from the 120 identified papers after going through title screening, abstract screening, and reference search. Limited research is available on predicting biological or brain age using deep learning and different supervised machine learning methods. Neurodegenerative disorders were found to be the most researched disease, in which Alzheimer's disease was focused the most. Among non-communicable diseases, diabetes mellitus, hypertension, cancer, kidney diseases, and cardiovascular diseases were included, and other rare diseases like oral health-related diseases and bone diseases were also explored in some papers. In terms of the application of machine learning, risk prediction was the most common approach. Half of the studies have used supervised machine learning algorithms, among which logistic regression, random forest, XG Boost were frequently used methods. These machine learning methods were applied to a variety of datasets including population-based surveys, hospital records, and digitally traced data.

CONCLUSION

The review identified a wide range of studies that employed machine learning algorithms to analyse various diseases and datasets. While the application of machine learning in geriatrics and care has been well-explored, there is still room for future development, particularly in validating models across diverse populations and utilizing personalized digital datasets for customized patient-centric care in older populations. Further, we suggest a scope of Machine Learning in generating comparable ageing indices such as successful ageing index.

Mapping the Bibliometrics Landscape of AI in Medicine: Methodological Study

BACKGROUND

Artificial intelligence (AI), conceived in the 1950s, has permeated numerous industries, intensifying in tandem with advancements in computing power. Despite the widespread adoption of AI, its integration into medicine trails other sectors. However, medical AI research has experienced substantial growth, attracting considerable attention from researchers and practitioners.

OBJECTIVE

In the absence of an existing framework, this study aims to outline the current landscape of medical AI research and provide insights into its future developments by examining all AI-related studies within PubMed over the past 2 decades. We also propose potential data acquisition and analysis methods, developed using Python (version 3.11) and to be executed in Spyder IDE (version 5.4.3), for future analogous research.

METHODS

Our dual-pronged approach involved (1) retrieving publication metadata related to AI from PubMed (spanning 2000-2022) via Python, including titles, abstracts, authors, journals, country, and publishing years, followed by keyword frequency analysis and (2) classifying relevant topics using latent Dirichlet allocation, an unsupervised machine learning approach, and defining the research scope of AI in medicine. In the absence of a universal medical AI taxonomy, we used an AI dictionary based on the European Commission Joint Research Centre AI Watch report, which emphasizes 8 domains: reasoning, planning, learning, perception, communication, integration and interaction, service, and AI ethics and philosophy.

RESULTS

From 2000 to 2022, a comprehensive analysis of 307,701 AI-related publications from PubMed highlighted a 36-fold increase. The United States emerged as a clear frontrunner, producing 68,502 of these articles. Despite its substantial contribution in terms of volume, China lagged in terms of citation impact. Diving into specific AI domains, as the Joint Research Centre AI Watch report categorized, the learning domain emerged dominant. Our classification analysis meticulously traced the nuanced research trajectories across each domain, revealing the multifaceted and evolving nature of AI's application in the realm of medicine.

CONCLUSIONS

The research topics have evolved as the volume of AI studies increases annually. Machine learning remains central to medical AI research, with deep learning expected to maintain its fundamental role. Empowered by predictive algorithms, pattern recognition, and imaging analysis capabilities, the future of AI research in medicine is anticipated to concentrate on medical diagnosis, robotic intervention, and disease management. Our topic modeling outcomes provide a clear insight into the focus of AI research in medicine over the past decades and lay the groundwork for predicting future directions. The domains that have attracted considerable research attention, primarily the learning domain, will continue to shape the trajectory of AI in medicine. Given the observed growing interest, the domain of AI ethics and philosophy also stands out as a prospective area of increased focus.

Machine learning for predicting hepatitis B or C virus infection in diabetic patients

Highly prevalent hepatitis B and hepatitis C virus (HBV and HCV) infections have been reported among individuals with diabetes. Given the frequently asymptomatic nature of hepatitis and the challenges associated with screening in some vulnerable populations such as diabetes patients, we conducted an investigation into the performance of various machine learning models for the identification of hepatitis in diabetic patients while also evaluating the significance of features. Analyzing NHANES data from 2013 to 2018, machine learning models were evaluated; random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and least absolute shrinkage and selection operator (LASSO) along with stacked ensemble model. We performed hyperparameter tuning to improve the performance of the model, and selected important predictors using the best performance model. LASSO showed the highest predictive performance (AUC-ROC = 0.810) rather than other models. Illicit drug use, poverty, and race were highly ranked as predictive factors for developing hepatitis in diabetes patients. Our study demonstrated that a machine-learning-based model performed optimally in the detection of hepatitis among diabetes patients, achieving high performance. Furthermore, models and predictors evaluated from the current study, we expect, could be supportive information for developing screening or treatment methods for hepatitis care in diabetes patients.

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

The increasing access to health data worldwide is driving a resurgence in machine learning research, including data-hungry deep learning algorithms. More computationally efficient algorithms now offer unique opportunities to enhance diagnosis, risk stratification, and individualised approaches to patient management. Such opportunities are particularly relevant for the management of older patients, a group that is characterised by complex multimorbidity patterns and significant interindividual variability in homeostatic capacity, organ function, and response to treatment. Clinical tools that utilise machine learning algorithms to determine the optimal choice of treatment are slowly gaining the necessary approval from governing bodies and being implemented into healthcare, with significant implications for virtually all medical disciplines during the next phase of digital medicine. Beyond obtaining regulatory approval, a crucial element in implementing these tools is the trust and support of the people that use them. In this context, an increased understanding by clinicians of artificial intelligence and machine learning algorithms provides an appreciation of the possible benefits, risks, and uncertainties, and improves the chances for successful adoption. This review provides a broad taxonomy of machine learning algorithms, followed by a more detailed description of each algorithm class, their purpose and capabilities, and examples of their applications, particularly in geriatric medicine. Additional focus is given on the clinical implications and challenges involved in relying on devices with reduced interpretability and the progress made in counteracting the latter via the development of explainable machine learning.

In-hospital fall prediction using machine learning algorithms and the Morse fall scale in patients with acute stroke: a nested case-control study

BACKGROUND

Falls are one of the most common accidents in medical institutions, which can threaten the safety of inpatients and negatively affect their prognosis. Herein, we developed a machine learning (ML) model for fall prediction in patients with acute stroke and compared its accuracy with that of the existing fall risk prediction tool, the Morse Fall Scale (MFS).

METHODS

This is a retrospective nested case-control study. The initial sample size was 8462 admitted to a single cerebrovascular specialty hospital with acute stroke. A total of 156 fall events occurred, and each fall case was randomly matched with six control cases. Six ML algorithms were used, namely, regularized logistic regression, support vector machine, naïve Bayes (NB), k-nearest neighbors, random forest, and extreme-gradient boosting (XGB).

RESULTS

We included 156 in the fall group and 934 in the non-fall group. The mean ages of the fall and non-fall groups were 68.3 (± 12.2) and 65.3 (± 12.9) years old, respectively. The MFS total score was significantly higher in the fall group (54.3 ± 18.3) than in the non-fall group (37.7 ± 14.7). The area under the receiver operating curve (AUROC) of the MFS in predicting falls was 0.76 (0.73-0.79). XGB had the highest AUROC of 0.85 (0.78-0.92), and XGB and NB had the highest F1 score of 0.44.

CONCLUSIONS

The AUROC values of all of ML algorithms were similar to those of the MFS in predicting fall risk in patients with acute stroke, allowing for accurate and efficient fall screening.

Cost-effectiveness of cardiovascular magnetic resonance imaging compared to common strategies in the diagnosis of coronary artery disease: a systematic review

Cardiovascular magnetic resonance imaging (CMR) has established exceptional diagnostic utility and prognostic value in coronary artery disease (CAD). An assessment of the current evidence on the cost-effectiveness of CMR in patients referred for the investigation of CAD is essential for developing an economic model to evaluate the cost-effectiveness of CMR in CAD. We conducted a comprehensive search of multiple electronic databases, including PubMed, Scopus, Web of Science core collection, Embase, National Health Service Economic Evaluation Database (NHS EED), and health technology assessment, to identify relevant literature. After removing duplicates and screening the title/abstract, a total of 13 articles were deemed eligible for full-text assessment. We included studies that reported one or more of the following outcomes: incremental cost-effectiveness ratio (ICER), cost per quality-adjusted life year (QALYs), cost per life year gained, sensitivity and specificity rate as the primary outcome, and health utility measures or health-related quality of life as the secondary outcome. The quality of the included studies was assessed using the CHEERS 2022 guidelines. The findings of this study demonstrate that in patients undergoing urgent percutaneous coronary intervention, CMR over a one-year and lifetime horizon leads to higher quality-adjusted life years (QALYs) compared to current strategies in cases of multivessel disease. The systematic review indicates that the CMR-based strategy is more cost-effective when compared to standard methods such as single-photon emission computed tomography (SPECT), coronary computed tomography angiography (CCTA), and coronary angiography (CA) (CMR = $19,273, SPECT = $19,578, CCTA = $19,886, and immediate CA = $20,929). The results also suggest that the CMR strategy can serve as a cost-effective gatekeeping tool for patients at risk of obstructive CAD. A CMR-based strategy for managing patients with suspected CAD is more cost-effective compared to both invasive and non-invasive strategies, particularly in real-world patient populations with a low to intermediate prevalence of the disease.

The NeoRoo mobile app: Initial design and prototyping of an Android-based digital health tool to support Kangaroo Mother Care in low/middle-income countries (LMICs)

Premature birth and neonatal mortality are significant global health challenges, with 15 million premature births annually and an estimated 2.5 million neonatal deaths. Approximately 90% of preterm births occur in low/middle income countries, particularly within the global regions of sub-Saharan Africa and South Asia. Neonatal hypothermia is a common and significant cause of morbidity and mortality among premature and low birth weight infants, particularly in low/middle-income countries where rates of premature delivery are high, and access to health workers, medical commodities, and other resources is limited. Kangaroo Mother Care/Skin-to-Skin care has been shown to significantly reduce the incidence of neonatal hypothermia and improve survival rates among premature infants, but there are significant barriers to its implementation, especially in low/middle-income countries (LMICs). The paper proposes the use of a multidisciplinary approach to develop an integrated mHealth solution to overcome the barriers and challenges to the implementation of Kangaroo Mother Care/Skin-to-skin care (KMC/STS) in LMICs. The innovation is an integrated mHealth platform that features a wearable biomedical device (NeoWarm) and an Android-based mobile application (NeoRoo) with customized user interfaces that are targeted specifically to parents/family stakeholders and healthcare providers, respectively. This publication describes the iterative, human-centered design and participatory development of a high-fidelity prototype of the NeoRoo mobile application. The aim of this study was to design and develop an initial ("A") version of the Android-based NeoRoo mobile app specifically to support the use case of KMC/STS in health facilities in Kenya. Key functions and features are highlighted. The proposed solution leverages the promise of digital health to overcome identified barriers and challenges to the implementation of KMC/STS in LMICs and aims to equip parents and healthcare providers of prematurely born infants with the tools and resources needed to improve the care provided to premature and low birthweight babies. It is hoped that, when implemented and scaled as part of a thoughtful, strategic, cross-disciplinary approach to reduction of global rates of neonatal mortality, NeoRoo will prove to be a useful tool within the toolkit of parents, health workers, and program implementors.

Attri-VAE: Attribute-based interpretable representations of medical images with variational autoencoders

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.

Recognized and Unrecognized Value of Echocardiography in Guideline and Consensus Documents Regarding Patients With Chest Pain

Guideline and consensus documents have recently been published on the important topic of the noninvasive evaluation of patients presenting with chest pain (CP) or patients with known acute or chronic coronary syndromes. Authors for these documents have included members representing multispecialty imaging societies, yet the process of generating consensus and the need to produce concise written documents have led to a situation where the particular advantages of echocardiography are overlooked. Broad guidelines such as these can be helpful when it comes to "when to do" noninvasive cardiac testing, but they do not pretend to offer nuances on "how to do" noninvasive cardiac testing. This report details the particular value of echocardiography and potential explanations for its understated role in recent guidelines. This report is categorized into the following sections: (1) impact of the level of evidence on guideline creation; (2) versatility of echocardiography in the assessment of CP and the inimitable role for echo Doppler echocardiography in the assessment of dyspnea; (3) value of point-of-care ultrasound in assessing CP and dyspnea; and (4) the future role of echocardiography in ischemic heart disease.

MITEA: A dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging

Segmentation of the left ventricle (LV) in echocardiography is an important task for the quantification of volume and mass in heart disease. Continuing advances in echocardiography have extended imaging capabilities into the 3D domain, subsequently overcoming the geometric assumptions associated with conventional 2D acquisitions. Nevertheless, the analysis of 3D echocardiography (3DE) poses several challenges associated with limited spatial resolution, poor contrast-to-noise ratio, complex noise characteristics, and image anisotropy. To develop automated methods for 3DE analysis, a sufficiently large, labeled dataset is typically required. However, ground truth segmentations have historically been difficult to obtain due to the high inter-observer variability associated with manual analysis. We address this lack of expert consensus by registering labels derived from higher-resolution subject-specific cardiac magnetic resonance (CMR) images, producing 536 annotated 3DE images from 143 human subjects (10 of which were excluded). This heterogeneous population consists of healthy controls and patients with cardiac disease, across a range of demographics. To demonstrate the utility of such a dataset, a state-of-the-art, self-configuring deep learning network for semantic segmentation was employed for automated 3DE analysis. Using the proposed dataset for training, the network produced measurement biases of -9 ± 16 ml, -1 ± 10 ml, -2 ± 5 %, and 5 ± 23 g, for end-diastolic volume, end-systolic volume, ejection fraction, and mass, respectively, outperforming an expert human observer in terms of accuracy as well as scan-rescan reproducibility. As part of the Cardiac Atlas Project, we present here a large, publicly available 3DE dataset with ground truth labels that leverage the higher resolution and contrast of CMR, to provide a new benchmark for automated 3DE analysis. Such an approach not only reduces the effect of observer-specific bias present in manual 3DE annotations, but also enables the development of analysis techniques which exhibit better agreement with CMR compared to conventional methods. This represents an important step for enabling more efficient and accurate diagnostic and prognostic information to be obtained from echocardiography.

Hierarchical Two-Stage Cost-Sensitive Clinical Decision Support System for Screening Prodromal Alzheimer's Disease and Related Dementias

BACKGROUND

The detection of subtle cognitive impairment in a clinical setting is difficult. Because time is a key factor in small clinics and research sites, the brief cognitive assessments that are relied upon often misclassify patients with very mild impairment as normal.

OBJECTIVE

In this study, we seek to identify a parsimonious screening tool in one stage, followed by additional assessments in an optional second stage if additional specificity is desired, tested using a machine learning algorithm capable of being integrated into a clinical decision support system.

METHODS

The best primary stage incorporated measures of short-term memory, executive and visuospatial functioning, and self-reported memory and daily living questions, with a total time of 5 minutes. The best secondary stage incorporated a measure of neurobiology as well as additional cognitive assessment and brief informant report questionnaires, totaling 30 minutes including delayed recall. Combined performance was evaluated using 25 sets of models, trained on 1,181 ADNI participants and tested on 127 patients from a memory clinic.

RESULTS

The 5-minute primary stage was highly sensitive (96.5%) but lacked specificity (34.1%), with an AUC of 87.5% and diagnostic odds ratio of 14.3. The optional secondary stage increased specificity to 58.6%, resulting in an overall AUC of 89.7% using the best model combination of logistic regression and gradient-boosted machine.

CONCLUSION

The primary stage is brief and effective at screening, with the optional two-stage technique further increasing specificity. The hierarchical two-stage technique exhibited similar accuracy but with reduced costs compared to the more common single-stage paradigm.

Data processing pipeline for cardiogenic shock prediction using machine learning

Introduction

Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS.

Methods

We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction.

Results

We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization.

Conclusion

We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.