Search

The development and commercialisation of medical decision systems based on artificial intelligence (AI) far outpaces our understanding of their value for clinicians. Although applicable across many forms of medicine, we focus on characterising the diagnostic decisions of radiologists through the concept of ecologically bounded reasoning, review the differences between clinician decision making and medical AI model decision making, and reveal how these differences pose fundamental challenges for integrating AI into radiology. We argue that clinicians are contextually motivated, mentally resourceful decision makers, whereas AI models are contextually stripped, correlational decision makers, and discuss misconceptions about clinician-AI interaction stemming from this misalignment of capabilities. We outline how future research on clinician-AI interaction could better address the cognitive considerations of decision making and be used to enhance the safety and usability of AI models in high-risk medical decision-making contexts., Competing Interests: Declaration of interests MG declares grants or contracts from Quanta Computing, Janssen, Moore Foundation, Volkswagen Foundation, and Takeda to MG's institution; and payment or honoraria to MG's institution for a Teir Lecture and to MG for a Harvard Psychiatry Conference. Although held at the time of writing, MG's funding did not contribute to this project. All other authors declare no competing interests., (Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

Background and Objectives: Machine Learning offers opportunities to improve patient outcomes, team performance, and reduce healthcare costs. Yet only a small fraction of all Machine Learning models for health care have been successfully integrated into the clinical space. There are no current guidelines for clinical model integration, leading to waste, unnecessary costs, patient harm, and decreases in efficiency when improperly implemented. Systems engineering is widely used in industry to achieve an integrated system of systems through an interprofessional collaborative approach to system design, development, and integration. We propose a framework based on systems engineering to guide the development and integration of Machine Learning models in healthcare., Methods: Applied systems engineering, software engineering and health care Machine Learning software development practices were reviewed and critically appraised to establish an understanding of limitations and challenges within these domains. Principles of systems engineering were used to develop solutions to address the identified problems. The framework was then harmonized with the Machine Learning software development process to create a systems engineering-based Machine Learning software development approach in the healthcare domain., Results: We present an integration framework for healthcare Artificial Intelligence that considers the entirety of this system of systems . Our proposed framework utilizes a combined software and integration engineering approach and consists of four phases: (1) Inception, (2) Preparation, (3) Development, and (4) Integration. During each phase, we present specific elements for consideration in each of the three domains of integration: The Human, The Technical System, and The Environment. There are also elements that are considered in the interactions between these domains., Conclusion: Clinical models are technical systems that need to be integrated into the existing system of systems in health care. A systems engineering approach to integration ensures appropriate elements are considered at each stage of model design to facilitate model integration. Our proposed framework is based on principles of systems engineering and can serve as a guide for model development, increasing the likelihood of successful Machine Learning translation and integration., Competing Interests: MMcCradden is the John and Melinda Thompson Chair of Artificial Intelligence in Medicine and acknowledges funding from the SickKids Foundation relating to this role. All other authors have no conflicts of interest pertaining to this work to disclose., (© 2022 Assadi, Laussen, Goodwin, Goodfellow, Dixon, Greer, Jegatheeswaran, Singh, McCradden, Gallant, Goldenberg, Eytan and Mazwi.)

Background: The COVID-19 pandemic has strained health systems world wide. In our region, surging numbers of critically ill adult patients demanded urgent system-wide responses. During the peak of the pandemic, our Pediatric Intensive Care Unit (PICU) team redesigned the existing educational resources and processes of care to ensure for adult patients for the first time in the hospital's history., Aim: Describe the experiences and impacts of the rapidly initiated Adult COVID-19 Program on health care providers (HCP) and family members. Havelock's Theory of Change framed the examination of Adult COVID-19 Program participant experiences and surfaced lessons learned., Materials and Methods: A quality improvement review was employed to collect feedback about the program experience from the health care team and patient's family members. HCP completed a questionnaire 10 months following the implementation of the program and feedback from family members was provided during the program was obtained. Havelock's Theory of Change was used to explore trends and frame participants' experiences., Results: Pediatric Intensive Care Unit bedside team members and clinical leaders ( n = 17), adult hospital partners ( n = 3), and family members ( n = 8) participated. HCP describe; motivation and readiness; concern for personal safety and uncertainty experienced in the early program phases; the importance of supports and resources; use of relationships and collaboration to facilitate change; the emotional impacts of this unique experience; and opportunities for individual and team growth. An overarching theme of 'doing our part to help' emerged. Family members described the positive impacts of family-centered interventions offered, individualized care, and shock at their family member's illness., Conclusion: The PICU team rapidly adapted to provide care for adults at the peak of the pandemic. Family members expressed feeling grateful for the care their loved ones received in the pediatric setting. The experience of caring for adult patients with COVID-19 was a source of tension, personal growth, and meaning for the pediatric intensive care team., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Pereira, Akinkugbe, Buckley, Gilfoyle, Ibrahim, McCradden, Somerton and Dryden-Palmer.)