Andrew J. Yang

Andrew J. Yang

Auto-generated profile, based on publicly available information

Andrew J. Yang

The Warren Alpert Medical School of Brown University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2026 in Journal of Bone and Joint Surgery
Verified
Journal Article
Closed access
AYAndrew J. Yang
Andrew J. Yang
PRPrem N. Ramkumar
Prem N. Ramkumar
JWJoshua J. Woo
Joshua J. Woo

14 October 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
AYAndrew J. Yang
Andrew J. Yang
CTChichun Tan
Chichun Tan
YMYing Ma
Ying Ma
Spatially resolved transcriptomics (SRT) measures gene expression within tissues. Existing methods that summarize the activity of functionally related genes often ignore relationships between neighboring locations and offer limited statistical testing, gene-level interpretation, or scalability. Here we present GESSO, a method that incorporates spatial information to estimate gene set activity within tissues, quantify how strongly each gene contributes to the resulting activity scores, and perform location-specific statistical tests for elevated pathway activity. In simulations and analyses of 13 datasets from five SRT platforms, GESSO better recovers known spatial patterns, provides well-calibrated statistical tests and interpretable gene-level contributions, and scales more efficiently than existing methods. Applications across tumor, embryonic, and lymphoid tissues reveal localized biological programs, including epithelial-to-mesenchymal transition at tumor-stroma interfaces, developmental signaling gradients, and coordinated immune pathways within germinal centers. Therefore, GESSO enables interpretable and scalable spatial mapping of gene set activity across diverse SRT technologies and biological settings.

2 December 2025 in medRxiv
Verified
Preprint
Open access
PDF file
AYAndrew Yang
Andrew Yang
JWJoshua Woo
Joshua Woo
RZRyan Zhang
Ryan Zhang
AMAlan Mach
Alan Mach
PRPrem Ramkumar
Prem Ramkumar
YMYing Ma
Ying Ma
Advancing evidence-based medicine requires integrating clinical expertise with data analysis. While clinicians contribute essential domain knowledge, applying modern data science methods often requires specialized training, creating a barrier to adoption. To bridge this gap, we developed ChatDA, an artificial intelligence agent enabling large-language-model-mediated conversational analysis of de-identified clinical tabular datasets. ChatDA empowers clinicians to extract meaningful insights efficiently and accurately, making data-driven clinical research more accessible and effective.

1 April 2026 in JBJS Open Access
Verified
Journal Article
Open access
JWJoshua J. Woo
Joshua J. Woo
AYAndrew J. Yang
Andrew J. Yang
YSYash S. Saboo
Yash S. Saboo
AWAndrew J. Wassef
Andrew J. Wassef
ASAlexandra I. Stavrakis
Alexandra I. Stavrakis
PRPrem N. Ramkumar
Prem N. Ramkumar
Background: Large language models (LLMs) are used for clinical information retrieval, yet their performance on highly domain-specific documents such as orthopaedic technique guides or instructions for use (IFU) remains poorly understood. Various financial drivers affecting the orthopaedic medical device industry have generated interest in automated perioperative support during surgery using advanced generative artificial intelligence (AI) techniques leveraging LLMs. We sought to establish whether these complex, manufacturer-specific IFUs for surgical planning and intraoperative execution were clinically amenable to substitution by custom LLM applications. Methods: We evaluated 5 LLM-based information retrieval solutions, including 4 custom retrieval-augmented generation pipelines and ChatGPT5, in their ability to extract clinically relevant information from 3 distal femoral replacement IFUs. Two fellowship-trained orthopaedic surgeons curated 28 questions spanning literal, enumerative, and reasoned query types. Answers were scored against the expert-generated ground truth using a three-tier rubric (incorrect, partially correct, fully correct). Results: All systems demonstrated low overall accuracy (<50%). A custom multimodal pipeline achieved the highest overall score (44.6%), outperforming commercial systems such as ChatGPT (29.2%). Performance varied by document and question type: literal queries were most accurately answered (up to 53.0%), while reasoned questions yielded the lowest scores across all systems (as low as 15.3%). Conclusions: Current LLM-based retrieval systems, including commercially available tools, are unreliable for extracting complex procedural information from orthopaedic implant protocols. Whether IFUs require further clarity for clinical queries or open source LLMs require enhanced image processing, medical device representatives are far from being replaced by generative AI techniques given their poor performance in safe integration with surgical workflows. Improving LLMs with enhanced image processing and domain-specific training will be necessary before considering medical device representatives’ substitution. Level of Evidence: Prognostic, Level IV . See Instructions for Authors for a complete description of levels of evidence.

8 July 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
AYAndrew Yang
Andrew Yang
CTChichun Tan
Chichun Tan
YMYing Ma
Ying Ma
Recent advances in spatially resolved transcriptomics (SRT) enabled measurement of sets of pathway genes activity within tissues. However, existing gene set activity scoring methods overlook spatial dependencies among tissue locations, restricting their ability to capture region-specific pathway activities associated with disease pathology or cellular communication. Moreover, these methods lack significance-level inference for activity scores, provide limited interpretability of gene-level contribution to a pathway, and scale poorly to advanced large-size SRT datasets. To address these limitations, we present GESSO (Gene sEt activity Score analysis with Spatial lOcation), a spatially informed gene set scoring method adaptable to diverse SRT platforms. GESSO models gene set activity levels through a graph-regularized matrix decomposition algorithm, jointly inferring spatially coherent gene set activity scores (GASs) and interpretable metagene weights that capture gene-level contributions. It further implements a permutation-based local significance test and a stratified low-resolution approximation that scales to high-resolution SRT datasets such as Visium HD, Stereo-seq, and Xenium Prime. Across 13 datasets from five SRT platforms, GESSO outperformed all existing methods in accuracy, calibration, interpretability, and scalability. Applications revealed novel biological programs, including spatially confined EMT activation within tumor-stroma interfaces, developmental signaling gradients across embryonic tissues, and coordinated B-cell, T-cell, and signaling pathways within germinal centers of human lymph node tissue, revealing the spatial organization of immune function at subregional resolution.

24 February 2026 in Arthroplasty Today
Verified
Journal Article
Open access
AYAndrew J. Yang
Andrew J. Yang
JWJoshua J. Woo
Joshua J. Woo
TPTeja S. Polisetty
Teja S. Polisetty
YSYash S. Saboo
Yash S. Saboo
PRPrem N. Ramkumar
Prem N. Ramkumar
Preoperative planning in total knee arthroplasty (TKA) has relied on local knee landmarks without considering proximal ones. Although balancing requires triplanar (coronal, sagittal, axial) anatomy, the literature emphasizes 2-dimensional imaging that ignores axial-plane rotation clarified by computed tomography scans. This study of broad arthritic knee anatomy aimed to (1) identify the source of greatest rotational variation between hip and knee, and (2) determine if local knee anatomy morphometrically approximates hip rotation or if the hip independently impacts knee morphometry. A computer vision pipeline analyzed 1352 TKA candidate computed tomography scans to extract 5 hip and 10 knee angular measurements; among 422 anatomical outliers, variability was quantified via dispersion metrics and principal component analysis, while regression models assessed if knee morphology predicts hip morphology. Hip-related features showed significantly greater variability than knee-related features among anatomical outliers (P < .05), particularly in the axial plane, suggesting that most lower-limb rotational variability originates from the hip. Knee-based measurements failed to predict hip morphometry, identifying hip rotation as an independent factor in lower-limb presentation of arthritic knee anatomy. Despite the dogma of intraoperatively balancing using local knee landmarks, the hip—a major source of lower-limb anatomical heterogeneity not captured by standard knee imaging—contributes greater rotational variability than the knee and independently influences observed variation in arthritic knee anatomy. While specific clinical protocols are not yet defined, the proximal femur may represent an important area for further investigation to determine if its consideration can improve TKA rotational alignment, flexion balancing, and patellofemoral stability.