Ethical Considerations for Artificial Intelligence in Medical Imaging: Deployment and Governance

Herington, Jonathan; McCradden, Melissa D.; Creel, Kathleen; Boellaard, Ronald; Jones, Elizabeth C.; Jha, Abhinav K.; Rahmim, Arman; Scott, Peter J.H.; Sunderland, John J.; Wahl, Richard L.; Zuehlsdorff, Sven; Saboury, Babak

doi:10.2967/jnumed.123.266110

Cited by 15 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The opaque nature of AI decision-making processes (’black box’) raises concerns about the transparency and trustworthiness of these models in clinical settings (79). Finally, ethical considerations around potential biases in training data and algorithmic outputs underscore the necessity for careful implementation to ensure fairness and equity in healthcare delivery (80).…”

Section: Discussionmentioning

confidence: 99%

Emerging Applications of NLP and Large Language Models in Gastroenterology and Hepatology: A Systematic Review

Omar,

SharIf,

Glicksberg

et al. 2024

Preprint

View full text Add to dashboard Cite

Background and AimIn the last two years, natural language processing (NLP) has transformed significantly with the introduction of large language models (LLM). This review updates on NLP and LLM applications and challenges in gastroenterology and hepatology.MethodsRegistered with PROSPERO (CRD42024542275) and adhering to PRISMA guidelines, we searched six databases for relevant studies published from 2003 to 2024, ultimately including 57 studies.ResultsOur review notes an increase in relevant publications in 2023-2024 compared to previous years, reflecting growing interest in newer models such as GPT-3 and GPT-4. The results demonstrate that NLP models have enhanced data extraction from electronic health records and other unstructured medical data sources. Key findings include high precision in identifying disease characteristics from unstructured reports and ongoing improvement in clinical decision-making. Risk of bias assessments using ROBINS-I, QUADAS-2, and PROBAST tools confirmed the methodological robustness of the included studies.ConclusionNLP and LLMs can enhance diagnosis and treatment in gastroenterology and hepatology. They enable extraction of data from unstructured medical records, such as endoscopy reports and patient notes, and for enhancing clinical decision-making. Despite these advancements, integrating these tools into routine practice is still challenging. Future work should prospectively demonstrate real-world value.

show abstract

Section: Discussionmentioning

confidence: 99%

Emerging Applications of NLP and Large Language Models in Gastroenterology and Hepatology: A Systematic Review

Omar,

SharIf,

Glicksberg

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The study highlights the need for future development to be guided by these ethical principles, emphasizing the importance of addressing novel questions raised by AI to lead to properly regulated implementations. Herington et al (2023) discuss the ethical risks associated with the deployment of AI in medical imaging, emphasizing the need for trustworthiness in AI medical devices (AIMDs). They identify four major ethical risks: autonomy of patients and clinicians, transparency of clinical performance and limitations, fairness toward marginalized populations, and accountability of physicians and developers.…”

Section: Ethical Considerations In Ai Health Modelingmentioning

confidence: 99%

Ai-Driven Environmental Health Disease Modeling: A Review of Techniques and Their Impact on Public Health in the Usa and African Contexts

Nzubechukwu Chukwudum Ohalete,

Oluwatoyin Ayo-Farai,

Tolulope O Olorunsogo

et al. 2024

imsrj

View full text Add to dashboard Cite

This scholarly paper embarks on an exploratory journey into the realm of AI-driven environmental health disease modeling, with a keen focus on its implications in the diverse healthcare landscapes of the USA and Africa. The study's background delves into the historical evolution of disease modeling techniques, emphasizing the revolutionary role of AI in modern public health strategies. It meticulously examines the comparative effectiveness of AI models in these distinct regions, addressing the challenges and opportunities inherent in AI-driven health models. Aiming to unravel the multifaceted impact of AI in disease prediction and public health policy, the paper navigates through various thematic corridors. It critically analyzes the significance of data sources and quality, ethical considerations in AI health modeling, and the integration of AI models into public health policies. The scope of the paper encompasses a comprehensive review of AI's efficacy in predicting environmental diseases, its role in enhancing disease surveillance systems, and the geographic and socioeconomic variations affecting model accuracy. The main findings reveal that AI models, while effective in disease prediction and surveillance, encounter challenges related to data integrity and ethical complexities. The study concludes that the integration of AI in healthcare necessitates a balanced approach, advocating for policies that support the development of context-specific AI models and address ethical concerns. Recommendations include fostering interdisciplinary collaboration and continuous evaluation of AI models to align them with evolving healthcare needs and ethical standards. This paper serves as a beacon for understanding AI's transformative potential in environmental health disease modeling, offering insights that are crucial for shaping future public health strategies and interventions. Keywords: AI in Healthcare, Disease Modeling, Public Health Policy, Data Quality, Ethical Considerations, Geographic Variations.

show abstract

“…AI-based triage systems that only trigger radiologist intervention when a critical predicted abnormality threshold is reached have been tested with successful results [81]. Although this strategy offers quick turnaround times, potential cost savings, and improved consistency, it may lack adaptability in nonstandard scenarios and, most importantly, raises ethical questions concerning explainability and accountability [159].…”

Section: Ai Integration Strategiesmentioning

confidence: 99%

Deep Learning in Breast Cancer Imaging: State of the Art and Recent Advancements in Early 2024

Carriero,

Groenhoff,

Vologina

et al. 2024

Diagnostics

View full text Add to dashboard Cite

The rapid advancement of artificial intelligence (AI) has significantly impacted various aspects of healthcare, particularly in the medical imaging field. This review focuses on recent developments in the application of deep learning (DL) techniques to breast cancer imaging. DL models, a subset of AI algorithms inspired by human brain architecture, have demonstrated remarkable success in analyzing complex medical images, enhancing diagnostic precision, and streamlining workflows. DL models have been applied to breast cancer diagnosis via mammography, ultrasonography, and magnetic resonance imaging. Furthermore, DL-based radiomic approaches may play a role in breast cancer risk assessment, prognosis prediction, and therapeutic response monitoring. Nevertheless, several challenges have limited the widespread adoption of AI techniques in clinical practice, emphasizing the importance of rigorous validation, interpretability, and technical considerations when implementing DL solutions. By examining fundamental concepts in DL techniques applied to medical imaging and synthesizing the latest advancements and trends, this narrative review aims to provide valuable and up-to-date insights for radiologists seeking to harness the power of AI in breast cancer care.

show abstract

Ethical Considerations for Artificial Intelligence in Medical Imaging: Deployment and Governance

Cited by 15 publications

References 45 publications

Emerging Applications of NLP and Large Language Models in Gastroenterology and Hepatology: A Systematic Review

Emerging Applications of NLP and Large Language Models in Gastroenterology and Hepatology: A Systematic Review

Ai-Driven Environmental Health Disease Modeling: A Review of Techniques and Their Impact on Public Health in the Usa and African Contexts

Deep Learning in Breast Cancer Imaging: State of the Art and Recent Advancements in Early 2024

Contact Info

Product

Resources

About