Synthetic Biology and AI DOI

Archana Lakshmaiah,

Chandana Korrapati,

Suresh Challa

et al.

Advances in medical diagnosis, treatment, and care (AMDTC) book series, Journal Year: 2024, Volume and Issue: unknown, P. 265 - 290

Published: Dec. 17, 2024

Synthetic biology and artificial intelligence are ushering in a new era of healthcare. In the specific context bioengineering, organoids, brain-computer interfaces, ethical considerations particularly salient. Challenges such as data inadequacy, unintended bias can undermine reliability fairness decision making. Additionally, cultural barriers concerns related to nonmaleficence, autonomy, justice must be carefully considered. To fully realize benefits this technological synergy, multidisciplinary approach is necessary, involving scientists, engineers, ethicists, policymakers. Transparent accountable AI systems essential mitigate biases, protect privacy, avoid consequences. By proactively addressing developing robust regulatory frameworks, we harness power these technologies for betterment humanity.

Language: Английский

Guiding AI in radiology: ESR’s recommendations for effective implementation of the European AI Act DOI Creative Commons
Elmar Kotter, Tugba Akinci D’Antonoli, Renato Cuocolo

et al.

Insights into Imaging, Journal Year: 2025, Volume and Issue: 16(1)

Published: Feb. 13, 2025

Abstract This statement has been produced within the European Society of Radiology AI Working Group and identifies key policies EU Act as they pertain to medical imaging. It offers specific recommendations policymakers professional community for effective implementation legislation, addressing potential gaps uncertainties. Key areas include literacy, classification rules high-risk systems, data governance, transparency, human oversight, quality management, deployer obligations, regulatory sandboxes, post-market monitoring, information sharing, market surveillance. By proposing actionable solutions, highlights ESR’s readiness in supporting appropriate application field, promoting clarity integration technologies ensure their impactful safe use benefit Europe’s patients. Critical relevance With impending arrival Act, it is critical stakeholders provide timely input on its areas. expert feedback aspects that will affect Points The significantly impact field imaging, shaping how are used regulated. ESR committed develop guidelines best practices, collaborating process. framework Graphical

Language: Английский

Citations

4
Künstliche Intelligenz in der Medizin – Chancen und Risiken aus ethischer Sicht DOI

Saskia Metan,

Florian Bruns

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: April 2, 2025

Imaging disciplines, such as ophthalmology, offer a wide range of opportunities for the beneficial use artificial intelligence (AI). The analysis images and data by trained algorithms has potential to facilitate making diagnosis patient care not just in ophthalmology. If AI brings about advances clinical practice that benefit patients, this is ethically be welcomed; however, respect self-determination patients security must guaranteed. Traceability explainability would strengthen trust automated decision-making enable ultimate medical responsibility. It should noted are only good unbiased used train them. likely lead loss skills on part doctors (deskilling), counteracted, example through improved training. Accompanying ethics research necessary identify those aspects require regulation. In principle, taken ensure serves people adapts their needs, other way round.

Language: Английский

Citations

1
Artificial intelligence tool development: what clinicians need to know? DOI Creative Commons
Boon‐How Chew, Kee Yuan Ngiam

BMC Medicine, Journal Year: 2025, Volume and Issue: 23(1)

Published: April 24, 2025

Digital medicine and smart healthcare will not be realised without the cognizant participation of clinicians. Artificial intelligence (AI) today primarily involves computers or machines designed to simulate aspects human using mathematically neural networks, although early AI systems relied on a variety non-neural network techniques. With increased complexity layers, deep machine learning (ML) can self-learn augment many tasks that require decision-making basis multiple sources data. Clinicians are important stakeholders in use ML tools. The review questions as follows: What is typical process tool development full cycle? concepts technical each step? This synthesises targeted literature reports summarises online structured materials present succinct explanation whole tools series cyclical processes: (1) identifying clinical problems suitable for solutions, (2) forming project teams collaborating with experts, (3) organising curating relevant data, (4) establishing robust physical virtual infrastructure, computer systems' architecture support subsequent stages, (5) exploring networks open access platforms before making new decision, (6) validating AI/ML models, (7) registration, (8) deployment continuous performance monitoring (9) improving ecosystem ensures its adaptability evolving needs. A sound understanding this would help clinicians appreciate engage codesigning, evaluating facilitate broader closer regulation settings.

Language: Английский

Citations

1
Charting a new course in healthcare: early-stage AI algorithm registration to enhance trust and transparency DOI Creative Commons
Michel E. van Genderen, Davy van de Sande, Lotty Hooft

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: May 8, 2024

AI holds the potential to transform healthcare, promising improvements in patient care. Yet, realizing this is hampered by over-reliance on limited datasets and a lack of transparency validation processes. To overcome these obstacles, we advocate creation detailed registry for algorithms. This would document development, training, models, ensuring scientific integrity transparency. Additionally, it serve as platform peer review ethical oversight. By bridging gap between regulatory approval, such FDA, aim enhance trustworthiness applications healthcare.

Language: Английский

Citations

8
Digital health technologies enabling the transition from pregnancy to early parenthood: A scoping review DOI
Alexander Hochmuth,

Alexander Hochmuth,

Christoph Dockweiler

et al.

Zeitschrift für Evidenz Fortbildung und Qualität im Gesundheitswesen, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Citations

0
The fundamentals of AI ethics in medical imaging DOI
Julia Amann,

Valerie Burger,

Michelle Livne

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 7 - 33

Published: Jan. 1, 2025

Language: Английский

Citations

0
Artificial intelligence and natural language processing for improved telemedicine: Before, during and after remote consultation DOI
Tiago Cunha Reis

Atención Primaria, Journal Year: 2025, Volume and Issue: 57(8), P. 103228 - 103228

Published: Feb. 16, 2025

Language: Английский

Citations

0
The scientific evidence of commercial AI products for MRI acceleration: a systematic review DOI Creative Commons
Stefan J. Fransen, Christian Roest, Frank F.J. Simonis

et al.

European Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 19, 2025

Abstract Objectives This study explores the methods employed by commercially available AI products to accelerate MRI protocols and investigates strength of their diagnostic image quality assessment. Materials All commercial for acceleration were identified from exhibitors presented at RSNA 2023 ECR 2024 annual meetings. Peer-reviewed scientific articles describing validation clinical performance searched each product. Information was extracted regarding technique, achieved acceleration, metrics, test cohort, hallucinatory artifacts. The assessed using evidence levels ranging “product’s technical feasibility purposes” economic impact on society”. Results Out 1046 companies, 14 companies included. No found four (29%). For remaining ten (71%), 21 retrieved. Four identified: noise reduction, raw data reconstruction, personalized scanning protocols, synthetic generation. Only a limited number prospectively demonstrated patient outcomes ( n = 4, 19%), no discussed an evaluation in prospective cohort > 100 patients or performed analysis. None analysis Conclusion Currently, can be categorized into main methods. lack large cohorts analysis, which would help get better insight enable safe effective implementation. Key Points Question There is growing interest that reduce scan time, but overview these missing . Findings (n 19%) software accelerating metrics Clinical relevance Although various shorten acquisition more studies are needed AI-constructed

Language: Английский

Citations

0
Cultivating Patient-Centered Healthcare Artificial Intelligence Transparency: Considerations for AI Documentation DOI
Austin M. Stroud, Jennifer Miller, Barbara Barry

et al.

The American Journal of Bioethics, Journal Year: 2025, Volume and Issue: 25(3), P. 129 - 131

Published: Feb. 24, 2025

Language: Английский

Citations

0
Artificial intelligence as a medical device for ophthalmic image analysis: a scoping review of regulated devices DOI
Ariel Yuhan Ong, Priyal Taribagil,

Mertcan Sevgi

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

Abstract This scoping review aims to identify regulator-approved ophthalmic image analysis AIaMDs in three jurisdictions, examine their characteristics and regulatory approvals, evaluate the available evidence underpinning them, as a step towards identifying best practice areas for improvement. 36 from 28 manufacturers were identified − 97% (35/36) approved EU, 22% (8/36) Australia, 8% (3/36) USA. Most targeted diabetic retinopathy detection. 19% (7/36) did not have published describing performance. For remainder, 131 clinical evaluation studies (range 1–22/AIaMD) 192 datasets/cohorts identified. Demographics poorly reported (age recorded 52%, sex 51%, ethnicity 21%). On study-level, few included head-to-head comparisons against other (8%,10/131) or humans (22%, 29/131), 37% (49/131) conducted independently of manufacturer. Only 11 (8%) interventional. There is scope expanding AIaMD applications imaging modalities, conditions, use cases. Facilitating greater transparency manufacturers, better dataset reporting, validation across diverse populations, high-quality interventional with implementation-focused outcomes are key steps building user confidence supporting integration.

Language: Английский

Citations

0