Paul Yi, MD

Associate Member, St. Jude Faculty

Director, Intelligent Imaging Informatics (I3)
Director, Image Quantification and Artificial Intelligence (IQAI)

Departments

Department of Radiology

Education

BA – Boston University College of Arts and Sciences (Seven-Year Liberal Arts/Medical Education Program), Boston, MA
MD – Boston University School of Medicine, Boston, MA
Residency (Radiology) – Johns Hopkins University, Baltimore, MD
Fellowship (Musculoskeletal Radiology) – Johns Hopkins University, Baltimore, MD
Fellowship (Imaging Informatics) – University of Maryland, Baltimore, MD

Research Interests

Artificial Intelligence (AI) for pediatric cancer and other catastrophic diseases
Safe and trustworthy AI, including algorithmic fairness
Human-Computer Interaction (HCI) to augment collaboration between AI & humans in medicine
Emerging AI methods for biomedical data, including large language models and multimodal foundation models

Contact Information

Paul Yi, MD Department of Radiology MS 220 St. Jude Children's Research Hospital 262 Danny Thomas Place Memphis, TN 38105-3678

Selected Publications

Chatterjee D*, Kanhere A*, Doo FX, Zhao J, Chan A, Welsh A, Kulkarni P, Trang A, Parekh VS, Yi PH. [*Co-First Authors]. Children Are Not Small Adults: Addressing Limited Generalizability of an Adult Deep Learning CT Organ Segmentation Model to the Pediatric Population. J Imaging Inform Med 2024 (In Press).

Santomartino SM, Zech JR, Hall K, Jeudy J, Parekh V, Yi PH. Evaluating the performance and bias of natural language processing tools in labeling radiology reports. Radiology 2024 (In Press).

Goodman KE, Yi PH, Morgan DJ. AI-Generated Clinical Summaries Require More Than Accuracy. JAMA Jan 29, 2024. Online ahead of print.

Trang A, Putman K, Savani D, Chatterjee D, Zhao J, Kamel P, Jeudy JJ, Parekh V, Yi PH. Sociodemographic Biases in a Commercial AI Model for Intracranial Hemorrhage Detection. Emerg Radiol Jul 22, 2024. Online ahead of print.

Doo FX*, Savani D*, Kanhere A, Carlos R, Joshi A, Yi PH, Parekh VS. [*Co-First Authors]. Optimal Large Language Model Characteristics to Balance Accuracy and Energy Use for Sustainable Medical Applications. Radiology Aug;312(2):e240320, 2024.

Venkatesh K, Mutasa S, Moore F, Sulam J, Yi PH. Gradient-based saliency maps are not trustworthy visual explanations of automated AI musculoskeletal diagnoses. J Imaging Inform Med May 6, 2024.

Bhayana R, Biswas S, Cook TS, Kim W, Kitamura FC, Gichoya J, Yi PH. From Bench to Bedside With Large Language Models: AJR Expert Panel Narrative Review. AJR Am J Roentgenol Apr 10, 2024. doi: 10.2214/AJR.24.30928.

Santomartino SM, Putman K, Beheshtian E, Parekh VS, Yi PH. Evaluating the Robustness of a Deep Learning Bone Age Algorithm to Clinical Image Variation Using Computational Stress Testing. Radiol Artif Intell May;6(3):e230240, 2024.

Kamel P, Kanhere A, Kulkarni P, Khalid M, Steger R, Bodanapally U, Gandhi D, Parekh V, Yi PH. Optimizing Acute Stroke Segmentation on MRI using Deep Learning: Self-configuring Neural Networks Provide High Performance using only DWI Sequences. J Imaging Inform Med Aug 13, 2024. Online ahead of print.

McNamara SL, Yi PH, Lotter W. The clinician-AI interface: intended use and explainability in FDA-cleared AI devices for medical image interpretation. NPJ Digit Med Mar 26, 2024;7(1):80.

Savage CH, Park H, Kwak K, Smith AD, Rothenberg SA, Parekh VS, Doo FX, Yi PH. General-Purpose Large Language Models Versus a Domain-Specific Natural Language Processing Tool for Label Extraction From Chest Radiograph Reports. AJR Am J Roentgenol Jan 17, 2024. Online ahead of print.

Haver H, Gupta AK, Ambinder EB, Bahl M, Oluyemi ET, Jeudy J, Yi PH. Evaluating the Use of ChatGPT to Accurately Simplify Patient-centered Information About Breast Cancer Prevention and Screening. Radiol Imaging Cancer Mar;6(2):e230086, 2024.

Teneggi J, Yi PH, Sulam J. Examination-level Supervision for Deep Learning-Based Intracranial Hemorrhage Detection on Head CT. Radiol Artif Intell Jan;6(1):e230159, 2024.

Bachina P, Garin SP, Kulkarni P, Kanhere A, Sulam J, Parekh VS, Yi PH. Coarse Race/Ethnicity Labels Mask Underdiagnosis Biases in Deep Learning Models for Chest Radiograph Diagnosis. Radiology Nov;309(2):e231693, 2023.

Morcos G, Yi PH, Jeudy J. Applying AI to Pediatric Chest Imaging: Leveraging Adult-Based AI Models and Databases Can Potentially Augment Pediatric AI Research. J Am Coll Radiol. Aug;20(8):742-747, 2023.

Yi PH, Garner HW, Hirschmann A, Jacobson JA, Omoumi P, Oh K, Zech JR, Lee YH. Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft Tissue Ultrasound: AJR Expert Panel Narrative Review. AJR Am J Roentgenol Jul 12, 2023. Online ahead of print.

Haver HL, Ambinder EB, Bahl M, Oluyemi ET, Jeudy J, Yi PH. Appropriateness of breast cancer prevention and screening recommendations provided by ChatGPT. Radiology May;307(4):e230424, 2023.

Garin S, Parekh VS, Sulam J, Yi PH. Medical imaging data science competitions should report dataset demographics and evaluate for bias. Nat Med May;29(5):1038-1039, 2023.

Santomartino SM, Hafezi-Nejad N, Parekh VS, Yi PH. Performance and usability of code-free deep learning for chest radiograph classification, object detection, and segmentation. Radiol Artif Intell Feb 15;5(2):e220062, 2023.

Murphy Z, Venkatesh K, Sulam J, Yi PH. Visual Transformers And Convolutional Neural Networks For Disease Classification In Radiographs: A Comparison of Performance, Sample Efficiency, and Hidden Stratification. Radiol Artif Intell 4(6):e220012, 2022.

Beheshtian E, Putman K, Santmartino SM, Parekh VS, Yi PH. Generalizability and Bias in a Deep Learning Pediatric Bone Age Prediction Model using Hand Radiographs. Radiology Sep 27, 2022:220505.

See full list of publications

Last update: September 2024