Zhanliang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhanliang Wang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Kai Wang
University of Pennsylvania
3 shared publications Da Wu
2 shared publications- Bojian Hou
University of Pennsylvania, Philadelphia, PA, USA
1 shared publication - Boning Tong
University of Pennsylvania, Philadelphia, PA, USA
1 shared publication - Duy Duong-Tran
University of Pennsylvania
1 shared publication - Jingxuan Bao
Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA
1 shared publication
Latest Publications
- Open Access
- 10 March 2026
- Published by Wiley in Medicine Bulletin
- Vol. 2 (2) , 167-183
Integrating Chain‐of‐Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis From Clinical Notes
Background: Several studies show that large language models (LLMs) struggle with phenotype‐driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models such as GPT and LLaMA to predict candidate genes. However, in real‐world settings, foundation models are not optimized for domain‐specific tasks such as clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major challenge. Methods: We introduce RAG‐driven CoT and CoT‐driven RAG, two methods that combine Chain‐of‐Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes. A five‐question CoT protocol mimics expert reasoning, whereas RAG retrieves data from sources such as HPO and OMIM (Online Mendelian Inheritance in Man). We evaluated these approaches on rare disease datasets, including 5980 Phenopacket‐derived notes, 255 literature‐based narratives, and two cohorts of 1088 noisy clinical notes from a children's hospital. Results: We found that recent foundation models, including Llama 3.3–70B‐Instruct and DeepSeek‐R1‐Distill‐Llama‐70B, outperformed earlier versions such as Llama 2 and GPT‐3.5. We also showed that RAG‐driven CoT and CoT‐driven RAG both outperform foundation models in candidate gene prioritization from clinical notes; in particular, both methods with DeepSeek backbone resulted in a top‐10 gene accuracy of over 40% on Phenopacket‐derived clinical notes, although performance was lower on noisier hospital clinical notes. RAG‐driven CoT works better for high‐quality notes, where early retrieval can anchor the subsequent reasoning steps in domain‐specific evidence, whereas CoT‐driven RAG has advantage when processing lengthy and noisy notes. Conclusions: Integrating CoT and RAG enhances LLMs' understanding of clinical notes in the context of rare disease diagnosis, and can facilitate various downstream medical tasks.
- 10 March 2026
- Published by Wiley in Medicine Bulletin
- Vol. 2 (2) , 167-183
Open AccessIntegrating Chain‐of‐Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis From Clinical Notes
Background: Several studies show that large language models (LLMs) struggle with phenotype‐driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models such as GPT and LLaMA to predict candidate genes. However, in real‐world settings, foundation models are not optimized for domain‐specific tasks such as clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major challenge. Methods: We introduce RAG‐driven CoT and CoT‐driven RAG, two methods that combine Chain‐of‐Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes. A five‐question CoT protocol mimics expert reasoning, whereas RAG retrieves data from sources such as HPO and OMIM (Online Mendelian Inheritance in Man). We evaluated these approaches on rare disease datasets, including 5980 Phenopacket‐derived notes, 255 literature‐based narratives, and two cohorts of 1088 noisy clinical notes from a children's hospital. Results: We found that recent foundation models, including Llama 3.3–70B‐Instruct and DeepSeek‐R1‐Distill‐Llama‐70B, outperformed earlier versions such as Llama 2 and GPT‐3.5. We also showed that RAG‐driven CoT and CoT‐driven RAG both outperform foundation models in candidate gene prioritization from clinical notes; in particular, both methods with DeepSeek backbone resulted in a top‐10 gene accuracy of over 40% on Phenopacket‐derived clinical notes, although performance was lower on noisier hospital clinical notes. RAG‐driven CoT works better for high‐quality notes, where early retrieval can anchor the subsequent reasoning steps in domain‐specific evidence, whereas CoT‐driven RAG has advantage when processing lengthy and noisy notes. Conclusions: Integrating CoT and RAG enhances LLMs' understanding of clinical notes in the context of rare disease diagnosis, and can facilitate various downstream medical tasks.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
PhenoGPT2: A Multimodal Fine-tuned Large Language Models for Phenotype Extraction and Normalization from Clinical Text and Facial Images
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessPhenoGPT2: A Multimodal Fine-tuned Large Language Models for Phenotype Extraction and Normalization from Clinical Text and Facial Images
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 1-10
Fair CCA for Fair Representation Learning: An ADNI Study
Canonical correlation analysis (CCA) is a technique for finding correlations between different data modalities and learning low-dimensional representations. As fairness becomes crucial in machine learning, fair CCA has gained attention. However, previous approaches often overlook the impact on downstream classification tasks, limiting applicability. We propose a novel fair CCA method for fair representation learning, ensuring the projected features are independent of sensitive attributes, thus enhancing fairness without compromising accuracy. We validate our method on synthetic data and real-world data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), demonstrating its ability to maintain high correlation analysis performance while improving fairness in classification tasks. Our work enables fair machine learning in neuroimaging studies where unbiased analysis is essential. Code is available in https://github.com/ZhanliangAaronWang/FR-CCA-ADNI.
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 1-10
Open AccessFair CCA for Fair Representation Learning: An ADNI Study
Canonical correlation analysis (CCA) is a technique for finding correlations between different data modalities and learning low-dimensional representations. As fairness becomes crucial in machine learning, fair CCA has gained attention. However, previous approaches often overlook the impact on downstream classification tasks, limiting applicability. We propose a novel fair CCA method for fair representation learning, ensuring the projected features are independent of sensitive attributes, thus enhancing fairness without compromising accuracy. We validate our method on synthetic data and real-world data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), demonstrating its ability to maintain high correlation analysis performance while improving fairness in classification tasks. Our work enables fair machine learning in neuroimaging studies where unbiased analysis is essential. Code is available in https://github.com/ZhanliangAaronWang/FR-CCA-ADNI.