AJAndrew R. Jamieson

Andrew R. Jamieson

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrew R. Jamieson has a total of 182 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    How recording inputs affect multimodal AI agreement with reference scores in OSCE physical examinations: a retrospective ablation study

    by Shinyoung Kang, Michael J. Holcomb, Ameer H. Shakur, David Hein, Huong-Tra Ngo, Hunter Schuler, Philip C. Jarrett, Thomas O. Dalton, Andrew R. Jamieson

  • Open Access

    Prospective deployment of multimodal AI grading for medical student OSCEs

    by Huong-Tra Ngo, Ameer Hamza Shakur, Michael Holcomb, Shinyoung Kang, David Hein, Judah Gruen, Hunter Schuler, Philip Jarrett, Thomas Dalton, Krystle Campbell, et al.

  • Open Access

    Outcome-grounded effect of clinically stigmatizing information on large language model emergency triage prioritization

    by Philip Jarrett, Peter Yun, Emmanuel Ohuabunwa, Doreen Agboh, D. Mark Courtney, Andrew Jamieson

  • Open Access

    Frontier Language Models and OCR Preprocessing Mitigate Invisible Text Injection in AI Peer Review

    by Philip Jarrett, Peter Yun, Andrew Jamieson, Deborah Diercks, Daniel Courtney, Dazhe Cao

    Background: As journals explore artificial intelligence (AI)-assisted peer review, the integrity of AI-generated evaluations has emerged as a critical concern. Invisible text injection (ITI), in which adversarial instructions are hidden from human readers via techniques such as white-on-white text or zero-point font size, has been shown to inflate quality scores assigned by earlier large language models (LLMs). Whether current frontier models remain vulnerable, and whether optical character recognition (OCR) preprocessing can neutralize ITI, has not been established. Methods: Using a published open-access clinical trial as a base manuscript, we created six variants: one unaltered control and five containing a single injected flaw each. Each variant was rendered under four ITI conditions and processed via two text extraction paths: direct PDF extraction (which preserves hidden text) and OCR-based extraction (which does not). Six LLMs served as reviewers: three models utilized in prior ITI research (Claude 3 Haiku, GPT-4o-mini, Gemini 2.0 Flash Lite) and three 2026 frontier models (Claude Sonnet 4.5, GPT-5.2, Gemini 3 Pro), yielding 2,880 total reviews analyzed using a linear mixed-effects model. Results: ITI inflated quality scores for earlier models by 0.82 points on direct extraction (Cohen's d = 1.11; P < .001). Frontier models not only resisted ITI but penalized manuscripts containing it (−0.15 points; d = −0.39; P < .001). OCR preprocessing eliminated the ITI effect entirely across all models and generations. Conclusions: Frontier LLMs and OCR preprocessing represent complementary, implementable defenses against ITI in AI-assisted peer review. Journals adopting AI-augmented review should consider both model selection and preprocessing pipeline as components of editorial integrity.

  • Open Access

    Context-Aware Emergency Department Triage Using Pairwise Comparisons and Bradley-Terry Aggregation

    by Philip Jarrett, Jonathan Reeder, Samuel McDonald, Deborah Diercks, Andrew Jamieson

    STRUCTURED Objective: To evaluate a ranking approach for emergency department (ED) waiting room prioritization that uses pairwise clinical comparisons aggregated via a Bradley-Terry model, and to assess its cross-site stability without site-specific training. Materials and Methods: Using the Multimodal Clinical Monitoring in the Emergency Department (MC-MED) dataset (118,385 ED visits, Site A), we defined a composite deterioration outcome (intensive care unit [ICU] admission, intubation, vasopressor, ventilation, or death within 6 hours) and evaluated 7 queue-ordering policies across 1,000 simulated shifts. The primary endpoint was Recall@5 for deteriorators; secondary endpoints included area under the receiver operating characteristic curve (AUROC) and simulated time-to-provider (TTP) metrics. External validation used MIMIC-IV-ED (425,087 visits, Site B) with 500 shifts. Methods reported per TRIPOD-LLM. Results: On MC-MED, BT-LLM-Enriched (Bradley-Terry ranking with a large language model [LLM] judge, GPT-4.1, using full diagnoses and medications) exceeded the Emergency Severity Index (ESI) on the primary endpoint: Recall@5 0.587 vs. 0.491 (p<0.001). XGBoost achieved Recall@5 0.648 but required large site-specific labeled training data. On external validation, supervised model performance attenuated (XGBoost AUROC 0.892 to 0.807) while BT-LLM-Enriched remained stable (0.826 to 0.831); the two were statistically indistinguishable on external data. Discussion: Under external validation, supervised model performance attenuated while zero-shot LLM ranking remained stable, suggesting cross-site stability without requiring site-specific training data. Conclusion: Pairwise ranking with an LLM judge significantly outperforms ESI-based ordering and remains stable across sites without local training, matching supervised models on external data.

  • Open Access

    Automated Assessment of OSCE Physical Exams using Multimodal AI

    by Shinyoung Kang, Michael J. Holcomb, Ameer H. Shakur, David Hein, Huong-Tra Ngo, Hunter Schuler, Philip C. Jarrett, Thomas O. Dalton, Andrew R. Jamieson

    Background: The assessment of physical examination skills in medical education is resource-intensive and prone to inter-rater variability. While artificial intelligence (AI) has successfully automated the grading of clinical notes and transcripts, evaluating the physical techniques themselves—what students do rather than what they say—remains an unsolved challenge. We evaluated whether a multimodal AI system could assess physical examination skills with expert-level reliability. Methods: In this retrospective ablation study, we analyzed 300 video-recorded encounters from six Objective Structured Clinical Examination (OSCE) stations (cardiovascular, respiratory, gastrointestinal, musculoskeletal, and neurological). We compared the performance of a multimodal AI model (Gemini 2.5 Pro) across single- and multi-camera configurations and isolated input modalities (video, audio-only, transcript-only, visual-only) against standard human grading. The primary outcome was agreement with a physician-adjudicated ground-truth reference standard, measured by quadratic weighted Cohen’s kappa (κ). Results: The AI system using a synchronized 3-camera native video configuration achieved significantly higher reliability (κ = 0.830; 95% CI, 0.773–0.880) than the standard human evaluators (κ = 0.732; 95% CI, 0.687–0.776). Performance followed a strict hierarchy: native video > audio-only > transcript-only > visual-only. Notably, visual-only models failed (κ ≈ 0.20) despite high detection accuracy, revealing a “visual paradox” where models could identify when an action occurred but not how well it was performed without audio cues. Conclusions: A properly configured multimodal AI system can grade physical examination skills with reliability exceeding that of trained human evaluators. Success requires native processing of synchronized audio-visual streams; transcript-based or visual-only approaches are insufficient for high-stakes assessment. These findings suggest that AI can provide scalable, objective, and valid assessment of clinical skills, overcoming the limitations of traditional human grading. Abstract Figure:


  • Open Access

    Physical Examination Identification in Medical Education Videos: Zero-Shot Multimodal AI With Temporal Sequence Optimization Study

    by Shinyoung Kang, Michael Holcomb, David Hein, Ameer Hamza Shakur, Thomas Dalton, Andrew Jamieson

    Background: Objective structured clinical examinations (OSCEs) are widely used for assessing medical student competency, but their evaluation is resource-intensive, requiring trained evaluators to review 15-minute videos. The physical examination (PE) component typically constitutes only a small portion of these recordings; yet, current automated approaches struggle with processing long medical videos due to computational constraints and difficulties maintaining temporal context. Objective: This study aims to determine whether multimodal large language models (MM-LLMs) can effectively segment PE periods within OSCE videos without previous training, potentially reducing the evaluation burden on both human graders and automated assessment systems. Methods: We analyzed 500 videos from 5 OSCE stations at University of Texas Southwestern Simulation Center, each 15 minutes long, by using hand-labeled PE periods as ground truth. Frames were sampled at 1, 2, or 3 seconds. A pose detection preprocessing step filtered frames without people. Six MM-LLMs performed frame-level classification into encounter states by using a standardized prompt. To enforce temporal consistency, we used a hidden Markov model with Viterbi decoding, merging states into 3 primary activities (consulting/notes, physical examination, and no doctor) and adding a brief edge buffer to avoid truncating true PE segments. Performance was computed per video and averaged across the dataset by using recall, precision, intersection over union (IOU), and predicted PE length with 95% CIs. Results: At 1-second sampling, GPT-4o achieved recall of 0.998 (95% CI 0.994-1.000), IOU of 0.784 (95% CI 0.765-0.803), and precision of 0.792 (95% CI 0.774-0.811), identifying a mean of 175 (SD 83) seconds of content per video as PE versus a mean labeled PE of 126 (SD 61) seconds, yielding an 81% reduction in video needing review (from 900 to 175 seconds). Across stations, recall remained high, with expected IOU variability linked to examination format and camera geometry. Increasing the sampling interval modestly decreased recall while slightly improving IOU and precision. Comparative baselines (eg, Gemini 2.0 Flash, Gemma 3, and Qwen2.5-VL variants) demonstrated trade-offs between recall and overselection; GPT-4o offered the best balance among high-recall models. Error analysis highlighted false negatives during occluded or verbally guided maneuvers and false positives during preparatory actions, suggesting opportunities for camera placement optimization and multimodal fusion (eg, audio cues). Conclusions: Integrating zero-shot MM-LLMs with minimal-supervision temporal modeling effectively segments PE periods in OSCE videos without requiring extensive training data. This approach significantly reduces review time while maintaining clinical assessment integrity, demonstrating that artificial intelligence methods combining zero-shot capabilities and light supervision can be optimized for medical education’s specific requirements. This technique establishes a foundation for more efficient and scalable clinical skill assessment across diverse medical education settings.


  • Open Access

    Universal consensus 3D segmentation of cells from 2D segmented stacks

    by Felix Y. Zhou, Zach Marin, Clarence Yapp, Qiongjing Zou, Benjamin A. Nanes, Stephan Daetwyler, Andrew R. Jamieson, Torikul Islam, Edward Jenkins, Gabriel M. Gihana, et al.

    Cell segmentation is the foundation of a wide range of microscopy-based biological studies. Deep learning has revolutionized two-dimensional (2D) cell segmentation, enabling generalized solutions across cell types and imaging modalities. This has been driven by the ease of scaling up image acquisition, annotation and computation. However, three-dimensional (3D) cell segmentation, requiring dense annotation of 2D slices, still poses substantial challenges. Manual labeling of 3D cells to train broadly applicable segmentation models is prohibitive. Even in high-contrast images annotation is ambiguous and time-consuming. Here we develop a theory and toolbox, u-Segment3D, for 2D-to-3D segmentation, compatible with any 2D method generating pixel-based instance cell masks. u-Segment3D translates and enhances 2D instance segmentations to a 3D consensus instance segmentation without training data, as demonstrated on 11 real-life datasets, comprising >70,000 cells, spanning single cells, cell aggregates and tissue. Moreover, u-Segment3D is competitive with native 3D segmentation, even exceeding when cells are crowded and have complex morphologies.


  • Open Access

    Biomechanical Phenotyping Reveals Unique Mechanobiological Signatures of Early-Onset Colorectal Cancer

    by Nicole C. Huning, Munir H. Buhaya, Victor V. Nguyen, Afeefah Khazi-Syed, Haider A. Ali, Adil Khan, Angela Fan, Robert C. Fisher, Zhikai Chi, Indu Raman, et al.

    While both incidence and mortality of sporadic average-onset colorectal cancer (AO CRC, above 50 years of age) are in constant decline, sporadic early-onset colorectal cancer (EO CRC, under 50 years of age) is rising rapidly. Yet, the causes behind this rise remain poorly understood. Epidemiological studies indicate that lifestyle and environmental exposures may result in chronic inflammation, which is known to trigger tissue fibrosis. This study tests the hypothesis that fibrotic remodeling and biomechanical stiffening of colorectal tissues represent measurable hallmarks and potential drivers of EO CRC. Using primary human tissues, this work shows that EO CRC is associated with changes in collagen microstructure, increased stiffness and elevated viscosity of primary tumors. Spatial transcriptional profiling and immunostaining reveal pro-fibrotic signatures in stromal cells, alongside enhanced Yes-associated protein (YAP) mechanotransduction and proliferation in epithelial cells of EO CRC tissues. Mechanistically, increasing matrix stiffness in vitro promotes proliferation of epithelial cells in 2D and 3D colorectal cancer models. Together, these findings establish EO CRC as a disease marked by early and widespread biomechanical remodeling, suggesting that a fibrotic and stiffened tissue microenvironment may orchestrate EO CRC tumor initiation.


  • Open Access

    Temperature-Driven Variability in Emergency Diagnostic Accuracy by a Leading Language Model

    by Philip C. Jarrett, Jared Hill, Marshall Howell, Kristen Grabow Moore, Joby J. Thoppil, Laura Vargas Ortiz, Samuel T. Parnell, Daniel Mark Courtney, Samuel A. McDonald, Deborah B. Diercks, et al.

    Objective: To determine the impact of the temperature parameter on GPT-4o’s diagnostic accuracy when evaluating emergency medicine cases and assess the effect on diagnostic divergence across iterations. Methods: We conducted a simulation-based diagnostic accuracy study using four challenging emergency medicine cases adapted from the Foundations of Emergency Medicine curriculum. Each case was submitted to GPT-4o 250 times at five temperature settings (0.0, 0.25, 0.50, 0.75, 1.0), both with and without physical examination findings, yielding 10,000 total outputs. Each output contained exactly three differential diagnoses with one leading diagnosis. Diagnostic accuracy was assessed by comparing outputs against predetermined gold-standard diagnoses. Results: At temperature 0.0, GPT-4o achieved 100% leading diagnosis accuracy across all cases with physical exam data. As temperature increased, accuracy declined systematically to 89.4% at temperature 1.0. Diagnostic divergence increased dramatically from an average of 4.5 unique diagnoses at temperature 0.0 to 26.25 at temperature 1.0 (583% increase). Case sensitivity varied significantly, with ascending cholangitis showing the greatest temperature sensitivity (accuracy dropping from 100% to 70.4%) while carbon monoxide poisoning maintained 100% accuracy across all settings. Discussion: Higher temperatures introduced concerning diagnostic inconsistency rather than beneficial exploration, with substantial accuracy degradation in temperature-sensitive cases. Conclusions: Lower temperature settings promote diagnostic accuracy and consistency, making them preferable for clinical applications requiring high reliability. Transparent reporting of temperature settings is essential for reproducible clinical artificial intelligence research. KEY MESSAGES: What is already known on this topic: Large language models demonstrate promising diagnostic capabilities in medical reasoning tasks, but their non-deterministic nature and sensitivity to parameter settings remain poorly understood in clinical contexts. What this study adds: The temperature parameter significantly affects both diagnostic accuracy and consistency, with higher settings causing dramatic increases in diagnostic divergence. How this study might affect research, practice or policy: These findings mandate transparent reporting of temperature settings in clinical AI research and suggest that low-temperature configurations should be prioritized for high-reliability medical applications.