Marlies Schijven

This study examines the impact of AI-based Clinical Decision Support Systems (CDSS) on patient-physician trust, focusing on competence, integrity, and benevolence in high-risk and low-risk clinical scenarios. 1️⃣ Cross-sectional vignette study with 398 patients from the University Medical Center Utrecht. 2️⃣ Patients were divided into high-risk and low-risk scenarios, with control and intervention groups for each. 3️⃣ Trust was measured using a questionnaire based on competence, integrity, and benevolence on a 7-point Likert scale. 4️⃣ High-risk scenario: Slight decrease in perceived competence and integrity when CDSS was used, particularly among women. 5️⃣ Low-risk scenario: Trust remained high overall, with increased trust in technology positively influencing perceptions of benevolence and integrity. 6️⃣ While patient-physician trust was generally high, the use of AI applications showed a potential negative impact, especially among women in high-risk situations. Trust in technology plays a crucial role in the acceptance of AI-supported medical decisions. 7️⃣ In low-risk scenarios, patients with higher trust in technology perceived greater physician benevolence and integrity when CDSS was used. 8️⃣ Effective communication about AI's role and patient involvement in the development and use of CDSS are crucial for maintaining trust. ✍🏻 Anna Zondag, Raoul Rozestraten, Stephan Grimmelikhuijsen, Karin Jongsma, Wouter van Solinge, Michiel Bots, Robin Vernooij, Saskia Haitjema. The Effect of Artificial Intelligence on Patient-Physician Trust: Cross-Sectional Vignette Study. J Med Internet Res 2024;26:e50853. DOI: 10.2196/50853 📄 Planning to submit your research to a peer-reviewed, open-access journal? Use the discount code AMJB200 at checkout to save $200 USD on the article processing charge at any JMIR Publications journal. Start your submission here: https://lnkd.in/deuAEN2r. It's important to me that you know this isn't a sponsored post. I'm simply committed to keeping you informed about opportunities to disseminate your research effectively.

134

7 commentaren

🚨 Webinar alert! For further information and registration, check the link below ⬇

4

#3𝐃 𝐩𝐫𝐢𝐧𝐭𝐢𝐧𝐠 𝐩𝐨𝐰𝐞𝐫𝐞𝐝 𝐛𝐲 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞 (𝐀𝐈) #3D printing powered by #AI in healthcare is opening up new possibilities. Let’s explore how it can contribute to healthcare. 👉 𝐖𝐡𝐚𝐭 𝐢𝐬 𝐀𝐈-𝐩𝐨𝐰𝐞𝐫𝐞𝐝 3𝐃 𝐏𝐫𝐢𝐧𝐭𝐢𝐧𝐠? AI-powered 3D printing, or additive manufacturing, is a process that creates a three-dimensional object from a digital model. It does this by adding material layer by layer, allowing for the production of complex shapes with also complex design. The role of AI here is to #optimize the design process, #improve the quality of prints, and even #predict and correct errors in real-time. 𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬 𝐢𝐧 𝐇𝐞𝐚𝐥𝐭𝐡𝐜𝐚𝐫𝐞 🩺 👉 𝐂𝐮𝐬𝐭𝐨𝐦𝐢𝐳𝐞𝐝 𝐈𝐦𝐩𝐥𝐚𝐧𝐭𝐬 𝐚𝐧𝐝 𝐏𝐫𝐨𝐬𝐭𝐡𝐞𝐭𝐢𝐜𝐬 #AI algorithms analyze patient data to design implants that are suitable to the patient’s unique anatomy, improving patient comfort and reducing the risk of complications. 👉 𝐀𝐧𝐚𝐭𝐨𝐦𝐢𝐜𝐚𝐥 𝐌𝐨𝐝𝐞𝐥𝐬 These models can help surgeons prepare for complex procedures, improve outcomes, and reduce costs. For example, surgeons can perform practice sessions on AI-generated duplicate copies of a patient’s organs to improve success rates. 👉 𝐌𝐚𝐧𝐮𝐟𝐚𝐜𝐭𝐮𝐫𝐢𝐧𝐠 𝐌𝐞𝐝𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬, 𝐒𝐤𝐢𝐧 𝐓𝐢𝐬𝐬𝐮𝐞, 𝐚𝐧𝐝 𝐎𝐫𝐠𝐚𝐧𝐬 Research is also going on to use AI-powered 3D printing to manufacture medications, skin tissue, and even organs. The idea of using a person’s cells to 3D print new organs could potentially reduce major rejection rates seen in organ transplants. The future of healthcare with AI-powered 3D printing is bright and full of potential. If we can use this technology effectively it will undoubtedly enhance many aspects of healthcare. #AIinHealthcare #3DPrinting #DigitalHealth #ArtificialIntelligence

14

❤️ The effective design of the Cardio Update Europe will summarize complete “up-to-date” information, novel developments, and new data transpiring in cardiology over two compact days. 👩‍⚕️ 👨‍⚕️ Register and get expert, practical and relevant international, peer-reviewed study summaries, without industry bias. 📺 Receive free access to all on-demand content for later reference. 💬 Exchange ideas with the speakers and Scientific Board during breaks and in discussion sections. ❎ Vote on what to do and next steps in real cases. 🏅 Stay on top of all novel developments and new guidelines. ❤️ Trust in the EFPIA, Ethical Medtech compliancy and CME accreditation. https://lnkd.in/eSFmAtk #cardiology #cardioupdate #cardiologia #CMEcredits #Lipids #Atherosclerosis #Glucose #Metabolism #Obesity #CCS #ACS #Hypertension #Cardiomyopathies #PulmonaryHypertension #VentricularArrhythmias #AFib #Endocarditis #Surgery #HF #ValvularHeartDisease #CongenitalDefects Felix Mahfoud, Arian Sultan, Davide Capodanno, Christian Sticherling, Christoph Binder, Victoria Delgado

How to improve EMRs in HMIS by using Clinical Process Improvements tools The new buzz word in the hospital industry is using EHRs (Electronic Health Records) and AI (Artificial Intelligence). The typical HMIS (Hospital Management Information System) is used for digitising to improve a) General Administration and b) Clinical Services, Clinical Quality & Patient Safety In India, the majority of hospitals use HMIS which is mainly used for routine transaction and administrative applications. Most of these HMIS applications lack clinical applications. The flavour or buzzword of the hospital industry and individual Clinicians is EHR & AI. A Clinical module EHR covering one or more specialties typically covers initial clinical assessment of the patient covering complete clinical history and clinical findings and based on these order sets for diagnostic services, medications, interventions, second opinion from other clinical specialities (if required) are used and a typical patient CARE PLAN is made. The indoor patients will require charting of daily medical parameters, medications, adverse events and day to day medical progress in the patient's medical condition till he/she is cured & discharged. Thus, all aspects related to clinical care, clinical quality and patient safety by various hospital teams, specialities, departments are captured digitally. In India, due to nationwide lax definitions and applications of CLINICAL PROTOCOLS by various clinical specialties has resulted in big Physician practice variations. With a few exceptions, most of the hospitals' medical board/administration are also not empowered to implement clinical protocols in their institutions. A typical HMIS vendor, in the absence of detailed clinical protocols pushes low end EMR solutions. The right way is to involve clinical leadership in drawing & documenting clinical workflows (as in use) processes using SOPs (Standard Operating procedures) approach. A good EHR definitely helps in improving clinical efficiencies by application of clinical protocols, tracking & coordinating patient health & safety and tracking Clinical Quality Indicators. These in turn leads to a positive cycle of CQI (Continuous Quality Improvements) of the clinical services, whether in individual clinician practice or in an indoor setting. Artificial Intelligence and speciality wise Clinical Decision Support Software (already commercially available) applications in medicine comes into picture and help healthcare organisations only when there is a good foundation of digital medical / clinical data is available The Clinicians and Clinical Leadership in the healthcare / hosptal industry needs to become proactive by shedding their fears in anything which requires digitisation of their medical records. Dr Brita Hansen, MD, Chief Medical Officer, LogicStream in her article 'Three Pillars of Clinical Process Improvement & Control' in Healthcare IT TODAY has beautifully described her approach

5

1 commentaar

This paper discusses the pervasive issue of burnout among healthcare workers and proposes strategies for its mitigation. 1️⃣ Burnout is a global issue in healthcare, exacerbated by increasing patient demands, complex conditions, and administrative burdens. 2️⃣ European healthcare systems face challenges in replacing retiring professionals, leading to increased workloads for remaining staff. 3️⃣ Self-reporting studies often underestimate the real-life burnout levels among healthcare professionals, indicating a more severe issue than literature suggests. 4️⃣ Burnout can transfer to the next generation of healthcare workers, as burned-out professionals may pass on negative attitudes and emotional exhaustion to trainees. 5️⃣ Expanding competencies and sharing tasks across healthcare professions can help manage workloads and delay burnout onset. 6️⃣ AI can aid in reducing routine tasks, but its implementation must be carefully managed with quality education and early engagement of healthcare workers. 7️⃣ Mitigating burnout requires a supportive work environment, teamwork, emotional support resources, and resilience training. 8️⃣ Insufficient appreciation and remuneration, coupled with high administrative burdens, contribute significantly to burnout. Delegating administrative tasks to assistants can enhance job satisfaction. 9️⃣ Developing appropriate work-life balance strategies and building personal resilience are crucial for improving job performance and overall well-being of healthcare professionals. ✍🏻 David Sipos, Rahul Goyal, Tomas Zapata. Addressing burnout in the healthcare workforce. The Lancet Regional Health - Europe. 2024. DOI: 10.1016/j.lanepe.2024.100961

105

6 commentaren

🚨Excited to share insights on healthcare innovation and bridging research with clinical practice! ��️ In this upcoming conference in Kuala Lumpur our Inti Zlobec will discuss the intersection of data science, AI, and digital pathology in driving impactful healthcare decisions. 👉🏻 Follow us and don’t miss her panel discussion alongside Malaysia's Minister of Health and General Director of Health. #HealthcareInnovation #ResearchTranslation #DigitalHealth #digitalpathology #AI #itmp #unibern

1

🎯 Evidence-based medicine #EBM will remain a pure theory until #AI is implemented in doctors' decision-making. 🎓 Every day, 5000-1000 research papers are published in the field of #biomedicine and #lifesciences. 📚 It’s a #library that a doctor would need to study daily to stay up to date. It has been impossible so far, but now it is doable due to #AI-driven decision support systems that can access the recent know-how - no matter where it is generated - to help make the right decision for a patient based on facts and data. 🧑‍⚕️ And doctors soon won’t be able to imagine working without #AI as they can’t imagine working without modern medical devices or medicines today. AI as healthcare professionals’ co-pilot is necessary to reduce medical errors (they will soon become more visible when data on patient outcomes becomes available) or meet rising patient expectations. ❤️ Evidence-based medicine will be more human when AI offers a well-crafted diagnosis or prevention-related advice adapted to the patient's lifestyle and needs instead of generalized guidelines. 🪄 Also, patients won’t trust doctors who don’t use AI. We no longer trust those who make notes on paper and claim they do not need stethoscopes or MRIs. The more we get familiar with AI, the less we fear it. The pre-ChatGPT skepticism is now being replaced by wonder of AI’s capabilities. And medicine needs wonders like no other sector. 📈 Already now, according to OECD statistics, healthcare is leading in VC’s investments in artificial intelligence. 🚄 No, AI is not a silver bullet in medicine. Stethoscopes without doctors are of no use. AI without doctors is powerless: even if ChatGPT can diagnose quite well, it can’t guide patients through their emotional challenges. We humans are far too complex to be treated by algorithms that have no idea what it means to suffer, hope, and fight for life. Every human has their story and acts in an irrational - not mathematical - way that only humans can understand. 🧪 But medicine and AI can create perfect synergy, leading to discoveries, improved patient outcomes/safety, and prevention we haven’t dreamed of. I’m 100% sure that the next breakthroughs in treating cancer will be due to AI. 📱 We all are lucky to be Gen T - generation growing up in the digital age, generation Tech, or generation Transformation. And we are responsible for making the best of the AI in medicine. 📚 On the photo: city library in Stuttgart. For the first time in history, everybody can access knowledge without the need to study all the books. Thanks to AI.

39

6 commentaren

Like he said. European Health Data Space (#EHDS) regulation voted by the European Parliament today. "Aligned with the goals of the Digital Decade policy programme 2030: 100 % [European Union] citizens having access to their electronic health records." "electronic health data follows patients when they seek care from different healthcare providers within their own Member State *or across the EU*." "electronic health record systems will be certified to guarantee their compliance with #interoperability requirements." "Two key infrastructures, 1. MyHealth@EU [primary use of health data in health services delivery] and 2. HealthData@EU [secondary use of health data for research], will be established to support the implementation of the #EHDS. " "The main components of MyHealth@EU are already operational, and pilots are ongoing in HealthData@EU." #DigitalHealth #EHR #HealthData #EuropeanHealthDataSpace #DigitalDecade

4

This paper by Steven Schalekamp, Kicky van Leeuwen and colleagues highlights the most likely avenue where AI software could do the bulk of the work, rather than a human, in reporting/reading the entire chest imaging study (CXR in this case). Current prominent examples of AI in thoracic radiology are most commonly only identifying selected abnormal findings (nodules, PE, pneumothorax etc) rather than sorting out entire studies. The software (LUNIT CXR) can identify normal CXRs reliably - AUC was 0.92. We may be now approaching the point where AI accurately reads and reports an entire study (CXR in this case) when normal and the principal, if not only role, of the staff radiologist is to 'sign off'. Whether this augments, displaces, or replaces human readers, is to be seen (I know what I think ...). This all may seem far-fetched but then I am reminded that essentially all CBCs (complete blood counts) are repoted in an automated fashion, and not the normals! https://lnkd.in/gx2KWXp4

13

#GenAI won't be soon applied in #medicine due to #bias, #hallucination and #privacy concerns? According to an analysis of 120 articles published by March 2024 on PubMed, there are ways to mitigate these challenges. 🔴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗺𝗼𝗱𝗲𝗹𝘀 𝗮𝗿𝗲 𝗯𝗶𝗮𝘀𝗲𝗱 ❎ Solution: multidimensional fairness evaluations; cross-disciplinary collaboration with ethicists, social scientists, and domain experts; reinforcement learning from expert feedback 🔴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗰𝗮𝗻 𝗰𝗼𝗺𝗽𝗿𝗼𝗺𝗶𝘀𝗲 𝗱𝗮𝘁𝗮 𝗽𝗿𝗶𝘃𝗮𝗰𝘆 ❎ Solution:  localized architecture, federated learning methods, privacy-aware model training and deployment. 🔴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗺𝗶𝘀𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝘀 𝗽𝗿𝗼𝗺𝗽𝘁𝘀 ❎ Solution: understanding some heuristics for crafting effective prompts and algorithms to reduce adversarial attacks and ensure the responses align with human values 🔴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗵𝗮𝗹𝗹𝘂𝗰𝗶𝗻𝗮𝘁𝗲𝘀 ❎ Solution: external review by experts, modifying model parameters, adjusting "temperature parameter" in GPT-4, adversarial testing or out-of-distribution evaluation 🔴 𝗠𝗼𝘀𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗶𝘀 𝗳𝗼𝗰𝘂𝘀𝗲𝗱 𝗼𝗻 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 ❎ Solution: generative AI with nontext data, multimodal foundations models 🔴 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗮𝗿𝗲 𝗱𝘆𝗻𝗮𝗺𝗶𝗰 ❎ Solution: increased attention to HIPAA and GDPR compliance, greater regulation; using private health information to train models and, instead, using synthetic data sets Link to the full paper: https://lnkd.in/eyRpU9zT

40

1 commentaar

Since we launched the Trustworthy & Responsible AI Network (#TRAIN) in March 2024 https://lnkd.in/ePe97EV4, we’ve heard from healthcare organizations across the globe that have expressed interest in and excitement for the initiative.    I’m pleased to share that TRAIN is expanding to Europe (#EuroTRAIN) to help healthcare organizations in the region operationalize responsible AI through technology-based guardrails.    As the technology enabling partner, Microsoft will work with European TRAIN members, including Erasmus MC, HUS Helsingin yliopistollinen sairaala (Helsinki University Hospital), Sahlgrenska University Hospital, Skånes universitetssjukhus (Skåne University Hospital), Libera Università Vita-Salute San Raffaele, UMC Utrecht, and Foundation 29 to improve the quality, safety and trustworthiness of AI tools in healthcare.    Learn more about European TRAIN: https://lnkd.in/e9K-UrZa    #HLTHEurope #HealthcareAI  #TrustworthyAI #ResponsibleAI

218

2 commentaren

The key question is always...what then? Early detection is great is we can intervene. Why live with the knowledge if we can do nothing about it? I would love some insights on the progress of gene therapy in this arena...

2

Patient input can improve #AI models in #healthcare - this second article in the two-part series offers considerations such as getting patients who are representative of the population and avoiding patient bias #healthIT https://wp.me/p4DF3H-aaMQ

1

Why would you share your wearable data with your healthcare professional? 🎬 Discover the answers in this series of 20+ videos. This one is about the ANNUAL CHECK-UP.

9

1 commentaar

We were just flagging these in recent AI forums! Governance is marked as a solution but what that solution needs , is a globally agreed guideline or charter of practice which is abscent! #geekygynaecologist

2

👀 𝗔𝗜 𝗕𝗿𝗲𝗮𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵: 𝗬𝗼𝘂𝗿 𝗿𝗲𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘁𝗼 𝗰𝗲𝗿𝘁𝗮𝗶𝗻 𝗽𝗵𝗼𝘁𝗼𝘀 𝗰𝗮𝗻 𝗿𝗲𝘃𝗲𝗮𝗹 𝘆𝗼𝘂𝗿 𝗺𝗲𝗻𝘁𝗮𝗹 𝗵𝗲𝗮𝗹𝘁𝗵 Researchers have developed #CompCog AI, an #AI system that can predict anxiety levels up to 81% accurately using just a few images and questions. Here’s why this is important: 1️⃣ 𝗘𝗮𝗿𝗹𝘆 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻: Identify potential mental illness before it becomes serious 2️⃣ 𝗔𝗰𝗰𝗲𝘀𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝘆: Makes quick shows less intimidating and more accessible 3️⃣ 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 𝗰𝗮𝗿𝗲: Paving the way for appropriate mental health services But it comes with some challenges like - 1️⃣ 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗰𝗼𝗻𝗰𝗲𝗿𝗻𝘀 2️⃣ 𝗘𝘁𝗵𝗶𝗰𝗮𝗹 𝗶𝗺𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗼𝗳 𝗔𝗜 𝗶𝗻 𝗵𝗲𝗮𝗹𝘁𝗵 𝗰𝗮𝗿𝗲 3️⃣ 𝗧𝗵𝗲 𝗻𝗲𝗲𝗱 𝗳𝗼𝗿 𝗵𝘂𝗺𝗮𝗻 𝗼𝗯𝘀𝗲𝗿𝘃𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝘁𝗶𝗼𝗻 Let’s discuss: How can we use AI responsibly to support mental health without compromising individual privacy? #AIinHealthcare #MentalHealthInnovation #TechForGood #FutureOfWellness #ArtificialIntelligence https://lnkd.in/grckW8fc

14

3 commentaren

"...Standards play a crucial role in bridging the gap between the high-level principles outlined in regulations that cover all sectors and the concrete technical specifications needed for AI-enabled systems to achieve compliance in specific sectors. To build trust in these systems, regulations and legislation may require third-party audits to provide assurance that entities comply with the established standards. As regulations and standards evolve, the role of ongoing research also becomes increasingly critical. Research on Trustworthy AI is essential not only for shaping these emerging regulations but also for providing the vital insights and empirical data needed to inform and refine both regulations and the corresponding standards. Collaboration between academia and industry is crucial in this endeavor. Each brings to the table a wealth of knowledge and experience that is both distinct and complementary. Industry provides practical insights from deploying and implementing AI systems, while academia contributes through rigorous research and theoretical frameworks. This synergy can accelerate the adoption of AI systems that are not only innovative but also reliable and understandable..." Oleg Agafonov Sharmini Alagaratnam Aleksandar Babic DNV Sónia Sousa Tallinn University https://lnkd.in/g5xG3PqF

14