Applications of artificial intelligence in clinical management, research, and health administration: imaging perspectives with a focus on hemophilia

ABSTRACT

Introduction

Joints of persons with hemophilia are frequently affected by repetitive hemarthrosis. In this paper, concepts, perks, and quirks of the use of artificial intelligence (AI), machine learning (ML), and deep learning are reviewed within clinical and research contexts of hemophilia and other blood-induced disorders’ patient care, targeted to the imaging diagnosis of hemophilic joints, under the perspective of different stakeholders (radiologists, hematologists, nurses, physiotherapists, technologists, researchers, managers, and patients/caregivers).

Areas covered

Rubrics that determine the suitability of the utilization of AI in blood-induced disorders’ patient care, including diagnosis and follow-up of patients are discussed, focusing on features in which AI can replace or augment the role of radiology in the clinical management and in research of patients. Insights on features in the design and conduct of AI projects in which the human intervention remains critical are provided.

Expert opinion

The author discusses research concepts in radiogenomics, and challenges for the utilization of AI in different healthcare fields such as patient safety, data sharing and privacy regulations, workforce education and future jobs’ shortage. Finally, the author proposes alternatives and potential solutions to mitigate challenges in successfully deploying ML algorithms into clinical practice.

KEYWORDS:

• Artificial intelligence
• machine learning
• hemophilia
• joints
• arthropathy
• imaging
• radiogenomics
• augmentation
• regulations

Article highlights

• Brynjolfsson & Mitchell described rubrics that determine the suitability of utilization of artificial intelligence (AI) in our lives, ranging from human tasks with low level of difficulty for replacement by AI, repetitive ones, to human tasks with high level of difficulty for replacement by AI. Examples of clinical applications of AI in the management of hemophilic arthropathy are provided under these rubrics.

• Human tasks with high level of difficulty for replacement by AI relate to datasets that highly rely on human decision-making such as those in which anatomic structures are obscured due to artifacts, those with variable fields-of-view and poor quality of images and those that hold a subtle threshold between physiologic and minimum pathology joint changes, particularly in growing joints.

• Clinical applications of AI in radiology include workflow of patients (administration, consultation, imaging acquisition and interpretation, intervention, communication), education (explanatory discussions, diagnostic hypothesis, data summary, and training), and standardization of policy making strategies.

• Radiogenomics is a science that combines a large volume of quantitative data extracted from medical images with individual genomic phenotypes and constructs prediction models by using simple linear or deep learning models to stratify patients, guide therapeutic strategies, and evaluate clinical outcomes of patients.

• Machine learning (ML) algorithms hold potential to answer specific research questions related to risk stratification and prevention of outcomes in patients with hemophilia and other arthropathies.

• Challenges for the utilization of imaging-related ML algorithms in clinical practice include need for big data, data sharing agreements, data standardization, data integration into clinical-surgical-pathology-imaging workflows, different perspectives for utilization of ML algorithms, moving-target AI perspectives, patient safety, need for education of our workforce, jobs’ shortage, healthcare inequity, and data privacy issues.

Acknowledgments

I would like to thank Dr. Victor Blanchette and Mr Ernest Namdar for reviewing the manuscript under different perspectives.

Declaration of interest

A Doria has had the following relationships unrelated to the conduct of this study: advisory boards of the International Myositis Assessment & Clinical Studies Group (not for profit) and the OMERACT SIG in MRI in JIA and OMERACT Technical Advisory Group (not for profit), and research support from Baxalta-Shire (Research Grant), Novo Nordisk (Research Grant), the Terry Fox Foundation (Research Grant), the PSI Foundation (Research Grant), the Society of Pediatric Radiology (Research Grant), and the Garron Family Cancer Centre (Research Grant). The author has no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

Reviewer Disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Supplementary Material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/17474086.2023.2192474

Additional information

Funding

This paper was not funded.