Alaa Talaat Youssef

All Publications

• Ethical Considerations in the Design and Conduct of Clinical Trials of Artificial Intelligence. JAMA network open Youssef, A., Nichol, A. A., Martinez-Martin, N., Larson, D. B., Abramoff, M., Wolf, R. M., Char, D. 2024; 7 (9): e2432482

  Abstract

  Importance: Safe integration of artificial intelligence (AI) into clinical settings often requires randomized clinical trials (RCT) to compare AI efficacy with conventional care. Diabetic retinopathy (DR) screening is at the forefront of clinical AI applications, marked by the first US Food and Drug Administration (FDA) De Novo authorization for an autonomous AI for such use.Objective: To determine the generalizability of the 7 ethical research principles for clinical trials endorsed by the National Institute of Health (NIH), and identify ethical concerns unique to clinical trials of AI.Design, Setting, and Participants: This qualitative study included semistructured interviews conducted with 11 investigators engaged in the design and implementation of clinical trials of AI for DR screening from November 11, 2022, to February 20, 2023. The study was a collaboration with the ACCESS (AI for Children's Diabetic Eye Exams) trial, the first clinical trial of autonomous AI in pediatrics. Participant recruitment initially utilized purposeful sampling, and later expanded with snowball sampling. Study methodology for analysis combined a deductive approach to explore investigators' perspectives of the 7 ethical principles for clinical research endorsed by the NIH and an inductive approach to uncover the broader ethical considerations implementing clinical trials of AI within care delivery.Results: A total of 11 participants (mean [SD] age, 47.5 [12.0] years; 7 male [64%], 4 female [36%]; 3 Asian [27%], 8 White [73%]) were included, with diverse expertise in ethics, ophthalmology, translational medicine, biostatistics, and AI development. Key themes revealed several ethical challenges unique to clinical trials of AI. These themes included difficulties in measuring social value, establishing scientific validity, ensuring fair participant selection, evaluating risk-benefit ratios across various patient subgroups, and addressing the complexities inherent in the data use terms of informed consent.Conclusions and Relevance: This qualitative study identified practical ethical challenges that investigators need to consider and negotiate when conducting AI clinical trials, exemplified by the DR screening use-case. These considerations call for further guidance on where to focus empirical and normative ethical efforts to best support conduct clinical trials of AI and minimize unintended harm to trial participants.

  View details for DOI 10.1001/jamanetworkopen.2024.32482

  View details for PubMedID 39240560

• Applied artificial intelligence for global child health: Addressing biases and barriers. PLOS digital health Muralidharan, V., Schamroth, J., Youssef, A., Celi, L. A., Daneshjou, R. 2024; 3 (8): e0000583

  Abstract

  Given the potential benefits of artificial intelligence and machine learning (AI/ML) within healthcare, it is critical to consider how these technologies can be deployed in pediatric research and practice. Currently, healthcare AI/ML has not yet adapted to the specific technical considerations related to pediatric data nor adequately addressed the specific vulnerabilities of children and young people (CYP) in relation to AI. While the greatest burden of disease in CYP is firmly concentrated in lower and middle-income countries (LMICs), existing applied pediatric AI/ML efforts are concentrated in a small number of high-income countries (HICs). In LMICs, use-cases remain primarily in the proof-of-concept stage. This narrative review identifies a number of intersecting challenges that pose barriers to effective AI/ML for CYP globally and explores the shifts needed to make progress across multiple domains. Child-specific technical considerations throughout the AI/ML lifecycle have been largely overlooked thus far, yet these can be critical to model effectiveness. Governance concerns are paramount, with suitable national and international frameworks and guidance required to enable the safe and responsible deployment of advanced technologies impacting the care of CYP and using their data. An ambitious vision for child health demands that the potential benefits of AI/Ml are realized universally through greater international collaboration, capacity building, strong oversight, and ultimately diffusing the AI/ML locus of power to empower researchers and clinicians globally. In order that AI/ML systems that do not exacerbate inequalities in pediatric care, teams researching and developing these technologies in LMICs must ensure that AI/ML research is inclusive of the needs and concerns of CYP and their caregivers. A broad, interdisciplinary, and human-centered approach to AI/ML is essential for developing tools for healthcare workers delivering care, such that the creation and deployment of ML is grounded in local systems, cultures, and clinical practice. Decisions to invest in developing and testing pediatric AI/ML in resource-constrained settings must always be part of a broader evaluation of the overall needs of a healthcare system, considering the critical building blocks underpinning effective, sustainable, and cost-efficient healthcare delivery for CYP.

  View details for DOI 10.1371/journal.pdig.0000583

  View details for PubMedID 39172772

• Perceptions of Data Set Experts on Important Characteristics of Health Data Sets Ready for Machine Learning: A Qualitative Study. JAMA network open Ng, M. Y., Youssef, A., Miner, A. S., Sarellano, D., Long, J., Larson, D. B., Hernandez-Boussard, T., Langlotz, C. P. 2023; 6 (12): e2345892

  Abstract

  The lack of data quality frameworks to guide the development of artificial intelligence (AI)-ready data sets limits their usefulness for machine learning (ML) research in health care and hinders the diagnostic excellence of developed clinical AI applications for patient care.To discern what constitutes high-quality and useful data sets for health and biomedical ML research purposes according to subject matter experts.This qualitative study interviewed data set experts, particularly those who are creators and ML researchers. Semistructured interviews were conducted in English and remotely through a secure video conferencing platform between August 23, 2022, and January 5, 2023. A total of 93 experts were invited to participate. Twenty experts were enrolled and interviewed. Using purposive sampling, experts were affiliated with a diverse representation of 16 health data sets/databases across organizational sectors. Content analysis was used to evaluate survey information and thematic analysis was used to analyze interview data.Data set experts' perceptions on what makes data sets AI ready.Participants included 20 data set experts (11 [55%] men; mean [SD] age, 42 [11] years), of whom all were health data set creators, and 18 of the 20 were also ML researchers. Themes (3 main and 11 subthemes) were identified and integrated into an AI-readiness framework to show their association within the health data ecosystem. Participants partially determined the AI readiness of data sets using priority appraisal elements of accuracy, completeness, consistency, and fitness. Ethical acquisition and societal impact emerged as appraisal considerations in that participant samples have not been described to date in prior data quality frameworks. Factors that drive creation of high-quality health data sets and mitigate risks associated with data reuse in ML research were also relevant to AI readiness. The state of data availability, data quality standards, documentation, team science, and incentivization were associated with elements of AI readiness and the overall perception of data set usefulness.In this qualitative study of data set experts, participants contributed to the development of a grounded framework for AI data set quality. Data set AI readiness required the concerted appraisal of many elements and the balancing of transparency and ethical reflection against pragmatic constraints. The movement toward more reliable, relevant, and ethical AI and ML applications for patient care will inevitably require strategic updates to data set creation practices.

  View details for DOI 10.1001/jamanetworkopen.2023.45892

  View details for PubMedID 38039004

• Organizational Factors in Clinical Data Sharing for Artificial Intelligence in Health Care. JAMA network open Youssef, A., Ng, M. Y., Long, J., Hernandez-Boussard, T., Shah, N., Miner, A., Larson, D., Langlotz, C. P. 2023; 6 (12): e2348422

  Abstract

  Limited sharing of data sets that accurately represent disease and patient diversity limits the generalizability of artificial intelligence (AI) algorithms in health care.To explore the factors associated with organizational motivation to share health data for AI development.This qualitative study investigated organizational readiness for sharing health data across the academic, governmental, nonprofit, and private sectors. Using a multiple case studies approach, 27 semistructured interviews were conducted with leaders in data-sharing roles from August 29, 2022, to January 9, 2023. The interviews were conducted in the English language using a video conferencing platform. Using a purposive and nonprobabilistic sampling strategy, 78 individuals across 52 unique organizations were identified. Of these, 35 participants were enrolled. Participant recruitment concluded after 27 interviews, as theoretical saturation was reached and no additional themes emerged.Concepts defining organizational readiness for data sharing and the association between data-sharing factors and organizational behavior were mapped through iterative qualitative analysis to establish a framework defining organizational readiness for sharing clinical data for AI development.Interviews included 27 leaders from 18 organizations (academia: 10, government: 7, nonprofit: 8, and private: 2). Organizational readiness for data sharing centered around 2 main constructs: motivation and capabilities. Motivation related to the alignment of an organization's values with data-sharing priorities and was associated with its engagement in data-sharing efforts. However, organizational motivation could be modulated by extrinsic incentives for financial or reputational gains. Organizational capabilities comprised infrastructure, people, expertise, and access to data. Cross-sector collaboration was a key strategy to mitigate barriers to access health data.This qualitative study identified sector-specific factors that may affect the data-sharing behaviors of health organizations. External incentives may bolster cross-sector collaborations by helping overcome barriers to accessing health data for AI development. The findings suggest that tailored incentives may boost organizational motivation and facilitate sustainable flow of health data for AI development.

  View details for DOI 10.1001/jamanetworkopen.2023.48422

  View details for PubMedID 38113040

• Inter-institutional data-driven education research: consensus values, principles, and recommendations to guide the ethical sharing of administrative education data in the Canadian medical education research context. Canadian medical education journal Grierson, L., Cavanagh, A., Youssef, A., Lee-Krueger, R., McNeill, K., Button, B., Kulasegaram, K. 2023; 14 (5): 113-120

  Abstract

  Background: Administrative data are generated when educating, licensing, and regulating future physicians but these data are rarely used beyond their pre-specified purposes. The capacity necessary for sensitive and responsive oversight that supports the sharing of administrative medical education data across institutions for research purposes needs to be developed.Method: A pan-Canadian consensus-building project was undertaken to develop agreement on the goals, benefits, risks, values, and principles that should underpin inter-institutional data-driven medical education research in Canada. A survey of key literature, consultations with various stakeholders and five successive knowledge synthesis workshops informed this project. Propositions were developed, driving subsequent discussions until collective agreement was distilled.Results: Consensus coalesced around six key principles: establishing clear purposes, rationale, and methodology for inter-institutional data-driven research a priori; informed consent from data generators in education systems is non-negotiable; multi-institutional data sharing requires special governance; data governance should be guided by data sovereignty; data use should be guided by an identified set of shared values; and best practices in research data-management should be applied.Conclusion: We recommend establishing a representative governance body, engaging trusted data facility, and adherence to extant data management policies when sharing administrative medical education data for research purposes in Canada.

  View details for DOI 10.36834/cmej.75874

  View details for PubMedID 38045068

• The Importance of Understanding Language in Large Language Models. The American journal of bioethics : AJOB Youssef, A., Stein, S., Clapp, J., Magnus, D. 2023; 23 (10): 6-7

  View details for DOI 10.1080/15265161.2023.2256614

  View details for PubMedID 37812091

• Is the Algorithm Good in a Bad World, or Has It Learned to be Bad? The Ethical Challenges of "Locked" Versus "Continuously Learning" and "Autonomous" Versus "Assistive" AI Tools in Healthcare. The American journal of bioethics : AJOB Youssef, A., Abramoff, M., Char, D. 2023; 23 (5): 43-45

  View details for DOI 10.1080/15265161.2023.2191052

  View details for PubMedID 37130390

• Multimodal large language models for women's reproductive mental health. Archives of women's mental health AlSaad, R., Youssef, A., Kashani, S., AlAbdulla, M., Abd-Alrazaq, A., Khaled, S. M., Ahmed, A., Sheikh, J. 2025

  Abstract

  BACKGROUND: Women's risk of mental health conditions fluctuates across the lifespan with hormone-mediated reproductive transitions. Reproductive psychiatry, a relatively new subspecialty, focuses on preventing and treating these conditions throughout various reproductive stages. Multimodal large language models (MLLMs) are advanced artificial intelligence (AI) systems that can process and integrate information across multiple modalities, including text, images, audio, and video. Although MLLMs have shown broad utility in healthcare, their potential in reproductive psychiatry remains largely unexplored.OBJECTIVE: To explore how MLLMs could advance research and clinical care in women's reproductive mental health and to outline opportunities, requirements, and barriers for safe, equitable deployment.METHODS: This perspective synthesizes the literature and domain expertise using a consistent analytical framework applied to each application domain in women's reproductive mental health: (1) define gaps in current clinical knowledge and practice; (2) explain why prevailing AI methods are insufficient; and (3) specify the distinctive advantages of MLLMs, including example data modalities and use cases relevant to reproductive psychiatry.FINDINGS: We identify seven application domains: (1) menstruation, (2) pregnancy, (3) abortion, miscarriage and recurrent pregnancy loss, (4) the postpartum period, (5) menopause, (6) psychiatric comorbidities in infertility, and (7) gynecologic conditions (e.g., endometriosis, polycystic ovary syndrome). Across these domains, MLLMs could enable multimodal risk stratification, longitudinal symptom trajectory modelling, clinical decision support, and patient-tailored education and self-management resources that adapt to evolving reproductive stages. Realizing these benefits requires addressing bias in training corpora; safeguarding privacy and consent for sensitive reproductive data; ensuring consistent, high-quality longitudinal data collection across life stages; and establishing standardized, well-governed multimodal repositories specific to women's health.CONCLUSIONS: MLLMs hold promise to foster more personalized and precise care in reproductive psychiatry. By mapping opportunities and constraints and proposing a structured evaluation lens, this perspective aims to inform clinicians and researchers, stimulate cross-disciplinary dialogue, and guide responsible development and integration of MLLMs in women's mental health.

  View details for DOI 10.1007/s00737-025-01633-7

  View details for PubMedID 41148324

• Clinician Perspectives on Compassionate Deactivation of Pediatric Ventricular Assist Devices. ASAIO journal (American Society for Artificial Internal Organs : 1992) Pyke-Grimm, K. A., Brown, M., Youssef, A., Spengler, M., Hollander, S. A., Feudtner, C., Char, D. 2025

  Abstract

  Following ventricular assist device (VAD) placement, families and clinicians often have differing perspectives. When adverse events reduce patients' quality of life, families and clinicians question the desirability of continuing VAD support. Given the increasing use of VAD in pediatrics, pediatric-specific guidelines for the process of compassionate deactivation (CD) of VAD are needed, based in part on the perspectives of pediatric heart failure clinicians. In this qualitative study, we used a semi-structured interview guide focused on CD. Twenty-one clinicians participated. The central theme characterizing the process of CD-VAD is Making the Decision to CD-VAD. Five categories emerged: 1) communication strategies, 2) relationships and trust, 3) importance of time, 4) emotional toll, and 5) redirecting care. Consensus in decision-making was achieved through collective discussions among staff and care team meetings, including families. Clinicians reported experiencing moral and emotional distress, primarily due to witnessing patient suffering, triggered by close relationships with patients and families, and discord around CD decisions. This study clarifies challenges posed by CD-VAD. Understanding these challenges is a necessary first step in the development of guidance to provide cardiac care integrated with pediatric palliative care (PPC) for children with implanted VAD, and to respond appropriately to circumstances where CD may be warranted.

  View details for DOI 10.1097/MAT.0000000000002530

  View details for PubMedID 40844162

• Educational Competencies for Artificial Intelligence in Radiology: A Scoping Review. Academic radiology Jassar, S., Zhou, Z., Leonard, S., Youssef, A., Probyn, L., Kulasegaram, K., Adams, S. J. 2025

  Abstract

  The integration of artificial intelligence (AI) in radiology may necessitate refinement of the competencies expected of radiologists. There is currently a lack of understanding on what competencies radiology residency programs should ensure their graduates attain related to AI. This study aimed to identify what knowledge, skills, and attitudes are important for radiologists to use AI safely and effectively in clinical practice.Following Arksey and O'Malley's methodology, a scoping review was conducted by searching electronic databases (PubMed, Embase, Scopus, and ERIC) for articles published between 2010 and 2024. Two reviewers independently screened articles based on the title and abstract and subsequently by full-text review. Data were extracted using a standardized form to identify the knowledge, skills, and attitudes surrounding AI that may be important for its safe and effective use.Of 5920 articles screened, 49 articles met inclusion criteria. Core competencies were related to AI model development, evaluation, clinical implementation, algorithm bias and handling discrepancies, regulation, ethics, medicolegal issues, and economics of AI. While some papers proposed competencies for radiologists focused on technical development of AI algorithms, other papers centered competencies around clinical implementation and use of AI.Current AI educational programming in radiology demonstrates substantial heterogeneity with a lack of consensus on the knowledge, skills, and attitudes for the safe and effective use of AI in radiology. Further research is needed to develop consensus on the core competencies for radiologists to safely and effectively use AI to support the integration of AI training and assessment into residency programs.

  View details for DOI 10.1016/j.acra.2025.06.044

  View details for PubMedID 40695718

• Building health systems capable of leveraging AI: applying Paul Farmer's 5S framework for equitable global health. BMC global and public health McCoy, L. G., Bihorac, A., Celi, L. A., Elmore, M., Kewalramani, D., Kwaga, T., Martinez-Martin, N., Proa, R., Schamroth, J., Shaffer, J. D., Youssef, A., Fiske, A. 2025; 3 (1): 39

  Abstract

  The development of artificial intelligence (AI) applications in healthcare is often positioned as a solution to the greatest challenges facing global health. Advocates propose that AI can bridge gaps in care delivery and access, improving healthcare quality and reducing inequity, including in resource-constrained settings. A broad base of critical scholarship has highlighted important issues with healthcare AI, including algorithmic bias and inequitable and inaccurate model outputs. While such criticisms are valid, there exists a much more fundamental challenge that is often overlooked in global health policy debates: the dangerous mismatch between AI's imagined benefits and the material realities of healthcare systems globally. AI cannot be deployed effectively or ethically in contexts lacking sufficient social and material infrastructure and resources to provide effective healthcare services. Continued investments in AI within unprepared, under-resourced contexts risk misallocating resources and potentially causing more harm than good. The article concludes by providing concrete questions to assess AI systemic capacity and socio-technical readiness in global health.

  View details for DOI 10.1186/s44263-025-00158-6

  View details for PubMedID 40312417

• Foundation Models in Radiology: What, How, Why, and Why Not. Radiology Paschali, M., Chen, Z., Blankemeier, L., Varma, M., Youssef, A., Bluethgen, C., Langlotz, C., Gatidis, S., Chaudhari, A. 2025; 314 (2): e240597

  Abstract

  Recent advances in artificial intelligence have witnessed the emergence of large-scale deep learning models capable of interpreting and generating both textual and imaging data. Such models, typically referred to as foundation models (FMs), are trained on extensive corpora of unlabeled data and demonstrate high performance across various tasks. FMs have recently received extensive attention from academic, industry, and regulatory bodies. Given the potentially transformative impact that FMs can have on the field of radiology, radiologists must be aware of potential pathways to train these radiology-specific FMs, including understanding both the benefits and challenges. Thus, this review aims to explain the fundamental concepts and terms of FMs in radiology, with a specific focus on the requirements of training data, model training paradigms, model capabilities, and evaluation strategies. Overall, the goal of this review is to unify technical advances and clinical needs for safe and responsible training of FMs in radiology to ultimately benefit patients, providers, and radiologists.

  View details for DOI 10.1148/radiol.240597

  View details for PubMedID 39903075

• Standing on FURM Ground: A Framework for Evaluating Fair, Useful, and Reliable AI Models in Health Care Systems NEJM CATALYST INNOVATIONS IN CARE DELIVERY Callahan, A., McElfresh, D., Banda, J. M., Bunney, G., Char, D., Chen, J., Corbin, C. K., Dash, D., Downing, N. L., Jain, S. S., Kotecha, N., Masterson, J., Mello, M. M., Morse, K., Nallan, S., Pandya, A., Revri, A., Sharma, A., Sharp, C., Thapa, R., Wornow, M., Youssef, A., Pfeffer, M. A., Shah, N. H. 2024; 5 (10)

  View details for DOI 10.1056/CAT.24.0131

  View details for Web of Science ID 001422126900001