Zember Jonathan

Final Pr. ID: Poster #: EDU-048

In 2021, the European Society of Radiology published its whitepaper: “ESR white paper: blockchain and medical imaging”. Blockchain provides trustful information on how, who, and when data was generated. While blockchain has become familiar to the public due to the cryptocurrency markets, there are many applications in health care and medical imaging that blockchain technology can be used. The purpose of this exhibit is to provide radiologists a background to understand blockchain by highlighting the technological aspects, history, and applications in healthcare and radiology.
The exhibit will be divided as follows:
1. Underlying technology of blockchain and what separates it from traditional databases.
2. Historical overview of blockchain.
3. Potential use cases of blockchain in healthcare and deep learning/AI.
4. Specific use cases of blockchain in medical imaging (and pediatric radiology?)
5. Challenges and Limitations. Areas for the radiology community to engage and collaborate in the development and implementation of blockchain technologies in research and patient care. Read More

Authors:  Zember Jonathan

Keywords:  cryptography, Informatics

Lall Neil,  Spaeth-cook Douglas,  Ho Mai Lan,  Zucker Evan

Final Pr. ID: Poster #: EDU-002

Artificial Intelligence (AI) holds great promise in pediatric radiology, but its adoption has been slower compared to adult imaging. Although a 2022 special issue of Pediatric Radiology highlighted potential AI applications, the number of FDA-cleared AI algorithms for pediatric radiology remains limited. As of October 2024, out of 333 FDA-cleared AI Software-as-a-Medical-Device (SaMD) tools, only 26 (8%) are applicable to pediatric imaging, despite children comprising 22% of the U.S. population. More strikingly, only three (<1%) of these SaMD tools are specifically designed for pediatric use, focusing on dental cavity detection, bone age assessment, and hip dysplasia. This educational exhibit showcases the different types of FDA-cleared SaMD AI algorithms designated for use in pediatric radiology and identifies the clinical needs being served as well as those that have yet to be addressed. Additionally, the exhibit will explore the discordance in the development of AI imaging tools for the pediatric population compared to adults, highlighting risks created by this gap and addressing the reasons for such a disparity. Read More

Authors:  Lall Neil , Spaeth-cook Douglas , Ho Mai Lan , Zucker Evan

Keywords:  Artificial Intelligence, Pediatric Radiology, Informatics

Sher Andrew,  Hayatghaibi Shireen,  Kan J.,  Sammer Marla

Final Pr. ID: Paper #: 077

To analyze the effect of point-of-care ACR-clinical decision support (CDS) software embedded in the electronic health records (EHR) on CT ordering patterns in a quaternary care pediatric emergency center (EC). Read More

Authors:  Sher Andrew , Hayatghaibi Shireen , Kan J. , Sammer Marla

Keywords:  decision support, pediatric, informatics

Battle Wilson,  Bala Wasif,  Smith Hayden,  Moon John,  Li Hanzhou,  Weinberg Brent,  Trivedi Hari

Final Pr. ID: Poster #: SCI-003

Pediatric radiology presents unique educational challenges, requiring trainees to master complex imaging patterns across varying patient ages and developmental stages. We developed an innovative learning platform powered by large language models (LLMs) to address these challenges through personalized, adaptive instruction. Our approach aims to bridge the gap between traditional teaching methods and the need for consistent, scalable feedback in pediatric imaging education. Read More

Authors:  Battle Wilson , Bala Wasif , Smith Hayden , Moon John , Li Hanzhou , Weinberg Brent , Trivedi Hari

Keywords:  Adaptive Learning, Educational Informatics

Sher Andrew,  Hayatghaibi Shireen,  Sammer Marla

Final Pr. ID: Paper #: 078

The purpose of this study is to share our experience implementing a clinical decision support (CDS) solution for imaging at a quaternary care pediatric academic hospital. Read More

Authors:  Sher Andrew , Hayatghaibi Shireen , Sammer Marla

Keywords:  decision support, pediatric, informatics

Gupta Amit

Final Pr. ID: Poster #: EDU-002

Artificial intelligence (AI) chatbots powered by large language models (LLMs) are beginning to appear in pediatric radiology workspace: as assistants for reporting, learning, and patient communication. Their fluency, speed, and apparent intelligence have sparked enthusiasm, yet beneath their polished prose lie subtle but consequential pitfalls that can mislead radiologists if unrecognized.

This educational exhibit highlights the cognitive, behavioral, and system-level risks of using AI chatbots in pediatric radiology practice. Key reliability issues include hallucinations, where models fabricate confident but false information, and sycophantic agreement, where they align with a user’s incorrect assumptions (“yes-man” behavior). These errors are often cloaked in convincing medical language, amplifying risk for trainees and non-experts. Bias propagation from skewed or adult-dominant training data may reinforce inequities, while emergent misalignment can produce unpredictable or unsafe outputs following system updates or fine-tuning.

Human-AI interaction adds another layer of concern. The ELIZA effect refers to our instinct to anthropomorphize machines, creating misplaced trust, as users perceive the chatbot as a knowledgeable colleague rather than a probability engine. This illusion of “seeming consciousness” can breed overconfidence and automation bias, where clinicians accept AI outputs uncritically. Over time, over-reliance can contribute to deskilling, as repetitive dependence on automated summaries erodes critical reasoning and vigilance.

Beyond technical flaws, chatbots also lack true creativity and problem-solving ability. Their responses mirror patterns from prior data, limiting originality and leading to formulaic, conventional outputs. In pediatric imaging education, this can hinder the cultivation of innovative clinical thinking.

Educational goals of this poster:
1. Illustrate common and emerging pitfalls of radiology chatbot use, including hallucination, bias, and misalignment.
2. Explain cognitive effects such as the ELIZA effect, automation bias, and deskilling.
3. Present real-world studies and simulated examples, where chatbot errors could influence pediatric imaging decision-making.
4. Offer practical guidelines for safe, critical, and educationally constructive chatbot use. Read More

Authors:  Gupta Amit

Keywords:  Artificial Intelligence, Informatics Workflow, Radiology Education

Sammer Marla,  Hayatghaibi Shireen,  Nguyen Haithuy,  Sher Andrew

Final Pr. ID: Paper #: 170

In our pediatric radiology department, radiographs (XR) are the shared responsibility of body radiologists, expected to be read in addition to daily modality-based or site-specific assignments. Due to concerns that the increasing XR volume was unevenly shared amongst colleagues, a software intervention was developed to improve weekday 7am-5pm workload balance by auto-distributing exams at 10-minute intervals during peak hours to rotation worklists within PACS; a cap of 20 distributed exams to each target worklist was set. Metrics to evaluate the intervention’s effectiveness were assessed. Additionally, as there was concern that assigning exams may result in slower turnaround times (TATs) and increased errors, TATs and error rates were evaluated. Read More

Authors:  Sammer Marla , Hayatghaibi Shireen , Nguyen Haithuy , Sher Andrew

Keywords:  turnaround time, informatics, radiographs

Hogan James,  Frasso Rosemary,  Hailu Tigist,  Tate Alyssa,  Martin Robert,  Sze Raymond

Final Pr. ID: Poster #: SCI-025

To explore the imaging clinical decision support (ICDS) needs of pediatric emergency department physicians (PEDP’s) prior to the implementation of imaging clinical decision support software (ICDSS). Read More

Authors:  Hogan James , Frasso Rosemary , Hailu Tigist , Tate Alyssa , Martin Robert , Sze Raymond

Keywords:  Informatics, Education