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

Abstract

The use of machine learning (ML) approaches to target clinical problems is called to revolutionize clinical decision-making in cardiology. The success of these tools is dependent on the understanding of the intrinsic processes being used during the conventional pathway by which clinicians make decisions. In a parallelism with this pathway, ML can have an impact at four levels: for data acquisition, predominantly by extracting standardized, high-quality information with the smallest possible learning curve; for feature extraction, by discharging healthcare practitioners from performing tedious measurements on raw data; for interpretation, by digesting complex, heterogeneous data in order to augment the understanding of the patient status; and for decision support, by leveraging the previous steps to predict clinical outcomes, response to treatment or to recommend a specific intervention. This paper discusses the state-of-the-art, as well as the current clinical status and challenges associated with the two later tasks of interpretation and decision support, together with the challenges related to the learning process, the auditability/traceability, the system infrastructure and the integration within clinical processes in cardiovascular imaging.

Attri-VAE: attribute-based, disentangled and interpretable representations of medical images with variational autoencoders

“…The analysis of medical data demands for interpretable methods. However, the majority of deep learning methods do not fulfill the minimum level of interpretability to be used in reasoning medical decisions (Sanchez-Martinez et al, 2022), being difficult to relate clinically and physiologically meaningful attributes with model parameters and outcomes. Fortunately, interpretable and explainable deep learning methods are starting to emerge.…”

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

“…Studies of CDS systems' effectiveness at detecting dementia in primary care identify significant improvements in rates of reported dementia cases [25] as well as physician confidence in differential diagnosis [26], compared to when the CDS was not utilized. Machine learning is also useful in CDS systems for feature selection as well as model development by optimizing model inputs and allowing for complex data relationships in modeling [27]. A review of the contribution of machine learning in classification of MCI and ADRD using the Alzheimer's Disease Neuroimaging dataset reported overall improvement in classification and prediction accuracy, especially in challenges involving MCI patients [28].…”

Machine Learning and Cognitive Robotics: Opportunities and Challenges

“…In cardiovascular medicine, ML is routinely used to perceive an individual by collecting and interpreting his/her clinical data, and clinicians would reason on them to suggest actions to maintain or improve the individual's health. Thus, it mimics the clinicians' approach when examining and treating sick patients [136]. Big data leveraged by ML can provide well-curated information to clinicians so that they can make better informed diagnosis and treatment.…”

“…Several projects involving the use of cognitive robotics have been reported in industrial settings (Industry 4.0), service robots [144], robotic surgery, cardiovascular surgery [136], assistive technology [148] and several other fields. In ref.…”

“…In ref. 136, ML methods are used in perceiving an individual's health by collecting and interpreting his/her clinical data and would reason to suggest actions to maintain or improve the individual's cardiovascular health. ML augmented decisions point to potential to improve the outcome at a lower cost of care and increase satisfaction.…”