Interesting reads ... January 2023
Topics: #AI, #Medicine, #Healthcare, #CardiovascularDisease, #DigitalHealth, #Cardiology, #Innovation, #MachineLearning, #ArtificialIntelligence
Most of the current applications of?AI?in?medicine?have addressed narrowly defined tasks using one data modality, such as a computed tomography scan or retinal photograph. In contrast, clinicians process data from multiple sources and modalities when diagnosing, making prognostic evaluations and deciding on treatment plans. Multimodal medical AI unlocks key applications in healthcare and many other opportunities exist beyond those described here.
Most AI in medicine today uses single types of inputs (i.e. only images, only text, only numbers) to run predictions. This is not how a doctor evaluates patient information when making a determination, who consciously (or often unconsciously) uses multiple sources of inputs to make decisions... from the patient record, to notes and even direct observations in front of the patient.
World Heart Federation roadmaps aim to identify essential roadblocks on the pathway to effective prevention, detection, and treatment of cardiovascular disease. Further, they aim to provide actionable solutions and implementation frameworks for local adaptation. This WHF Roadmap for digital health in cardiology identifies barriers to implementing digital health technologies for CVD and provides recommendations for overcoming them.
When designing new health systems, products, and services, involving members of the healthcare community and the public with personal healthcare experience can help to make sure that improvements will be useful and relevant to others like them. Together with healthcare workers and family members with healthcare experience, the authors of this paper developed and applied a step-by-step guide to involving those with personal experience in the design of health system improvements.
This paper explains some of the fundamental methodological points that should be considered when designing and appraising the clinical evaluation of AI algorithms for medical diagnosis.
The actual impact of various AI applications on healthcare professionals’ jobs has not been studied yet. Bringing together a framework to analyse AI applications in health-care and the job design model, the authors analysed 80 publications.
领英推荐
A twelve item checklist for clinicians to critically evaluate and design better clinical machine learning studies.
Disruptive innovation should lead to every clinical site being a research site, with all necessary quality checks and research as part of the standard of care. The healthcare system should be integrated into an intuitive RWE-generation system, with clinical research and clinical care going hand in hand.
The impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice’s quality, and judge their own confidence.
Inefficient workflows affect many health care stakeholders including patients, caregivers, clinicians, and staff.?In this article, the authors describe considerations for advancing workflow automation in healthcare and discuss a set of six priorities and related strategies and highlight the role the informatics and research communities have in advancing each priority and the strategies.
Senior Partner at Worldpronet
2 年Hi Jan, It's very interesting! I will be happy to connect.
Domain Consultant and Head Medico-marketing Services at Tata Consultancy Services
2 年Great approach Jan. Love it. Thanks for sharing
CTIO at Grupo Ráscal
2 年Thanks for sharing Jan Beger! Added to my list of readings.
Director Innovation & Living Lab , TransMedTech Institute
2 年Thanks for sharing Jan Beger
Program Manager at GE Healthcare
2 年Thank you for sharing.