Interesting reads ... August 2022

I thought to summarise the most interesting papers I read during the last 4 weeks. I hope you find it useful.

The disconnect between the metrics for algorithm performance and the realities of a clinician’s workflow and decision-making process is a fundamental but often overlooked issue. The inclusion of clinical context in?#AI?performance metrics for optimizing and evaluating clinical algorithms could make AI tools more clinically relevant and readily adopted.

????https://www.dhirubhai.net/posts/janbeger_ai-artificialintelligence-activity-6954308061566005248-qPYU

Digital patient experience is the sum of all interactions affected by a patient’s behavioral determinants, framed by digital technologies, and shaped by organizational culture, that influence patient perceptions across the continuum of care channeling?#DigitalHealth.

????https://www.dhirubhai.net/posts/janbeger_digital-patient-experience-umbrella-systematic-activity-6961906630393241600-RzTE

?

The authors of this paper outline many of the problems that future developers will likely face that contribute to these failures, specifically related to the approach, data, methodology, and operations of #MachineLearning based system developments.

????https://www.dhirubhai.net/posts/janbeger_12-plagues-of-ai-in-healthcare-activity-6964813432994861056-VGZn

One of the key challenges in successful deployment and meaningful adoption of?AI?in?#Healthcare?is health system-level governance of AI applications.

????https://www.dhirubhai.net/posts/janbeger_governance-of-clinical-ai-applications-activity-6972080719766396928-8gwB

To achieve?#Medicine’s new potential, it must be optimized around the wants and priorities of the ultimate stakeholder—the party that has the most at stake in how it all plays out: the patient.

????https://www.dhirubhai.net/posts/janbeger_the-importance-of-including-patients-in-designing-activity-6970956013315203072-5Hk9

The maximum benefits of?#ArtificialIntelligence?technologies in healthcare can be realized when there is a safe and systematic implementation of AI devices. Thus far, several research has documented the power and potential of AI technologies within healthcare institutions. However, the integration of advanced systems such as AI in healthcare mandates a sound understanding of the technology and the human factors responsible for hindering technology acceptance among clinicians.

????https://www.dhirubhai.net/posts/janbeger_factors-influencing-clinicians-willingness-activity-6969527382898524160-K_2P

In this review, the authors discuss the rationale for the use and applications of?#ML?in?heart failure, including disease classification, early diagnosis, early detection of decompensation, risk stratification, optimal titration of medical therapy, effective patient selection for devices, and clinical trial recruitment.

????https://www.dhirubhai.net/posts/janbeger_applications-of-ai-and-ml-in-heart-failure-activity-6962278830744948736-G8ud

?

Data from?Healthcare?systems hold value for improving healthcare delivery and in the development of commercially successful products through private sector collaborations. As well safeguarding privacy, data sharing agreements must ensure fair benefit for health systems and the public. Lack of commercial expertise and transparency risks health systems being disadvantaged in agreements. Health systems and governments must establish terms for sharing data informed by extensive public, professional, and expert consultation.

????https://www.dhirubhai.net/posts/janbeger_healthcare-activity-6953981715182710784-JLM8

Hospitals are highly connected systems in which capacity constraints in one area (for example, lack of ward beds) impede the flow of patients from other locations, such as the emergency department or those ready for discharge from intensive care. This work provides a practical example of a?ML-based modelling approach that is designed and fit for the purpose of informing real-time operational management of emergency admissions. The authors discuss how they surmounted challenges of designing and implementing models for real-time use, including temporal framing, data preparation, and changing operational conditions.

????https://www.dhirubhai.net/posts/janbeger_ml-for-real-time-aggregated-prediction-of-activity-6957905877987139584-RZhO

?

With the increasing number of?FDA-approved?artificial intelligence?systems, the financing of these technologies has become a primary gatekeeper to mass clinical adoption. Reimbursement models adapted for current payment schemes, including per-use rates, are feasible for early?AI?products. Alternative and complementary models may offer future payment options for value-based AI. A successful reimbursement strategy will align interests across stakeholders to guide value-based and cost-effective improvements to care.?

????https://www.dhirubhai.net/posts/janbeger_leveraging-reimbursement-strategies-to-guide-activity-6963724253560983552-TgYx

For more great reads, I recommend to have a look to ...

... an independent place dedicated to free and equal access to reliable knowledge in Digital Health, Healthcare, Technology, and Innovation.

For more, follow me on LinkedIn &?Twitter.

Follow?GE Healthcare?and learn more at?GE Healthcare Insights.?