Xiaoqian Jiang
YOU?
Author Swipe
View article: Psychological crisis detection based on behavioral data: a new approach to non-contact measurement
Psychological crisis detection based on behavioral data: a new approach to non-contact measurement Open
The findings suggest that the non-contact method is effective in predicting student psychological crisis. The use of Random Forest algorithm combined with Top-N assessment can effectively identify high-risk individuals and optimize interve…
View article: Injectable cationic dynamic hydrogel with supramolecular drug loading reprograms neutrophil fate to alleviate diabetic periodontitis
Injectable cationic dynamic hydrogel with supramolecular drug loading reprograms neutrophil fate to alleviate diabetic periodontitis Open
The pervasive infiltration of tissue-destructive yet microbicidal-impaired neutrophil extracellular traps (NETs) constitutes a primary mechanistic driver of diabetic periodontitis refractoriness. Apoptosis facilitates nonphlogistic turnove…
View article: THOR: Secure Transformer Inference with Homomorphic Encryption
THOR: Secure Transformer Inference with Homomorphic Encryption Open
View article: Multi agent large language models for biomedical hypothesis generation in drug combination discovery
Multi agent large language models for biomedical hypothesis generation in drug combination discovery Open
View article: FusionDP: Foundation Model-Assisted Differentially Private Learning for Partially Sensitive Features
FusionDP: Foundation Model-Assisted Differentially Private Learning for Partially Sensitive Features Open
Ensuring the privacy of sensitive training data is crucial in privacy-preserving machine learning. However, in practical scenarios, privacy protection may be required for only a subset of features. For instance, in ICU data, demographic at…
View article: A Bayesian deep segmentation framework for glioblastoma tumor segmentation using follow-up MRIs
A Bayesian deep segmentation framework for glioblastoma tumor segmentation using follow-up MRIs Open
Background Glioblastoma (GBM) is the most common malignant brain tumor with an abysmal prognosis. Since complete tumor cell removal is impossible due to the infiltrative nature of GBM, accurate measurement is paramount for GBM assessment. …
View article: Introducing mCODEGPT as a zero-shot information extraction from clinical free text data tool for cancer research
Introducing mCODEGPT as a zero-shot information extraction from clinical free text data tool for cancer research Open
View article: Empowering Clinical Trial Design through AI: A Randomized Evaluation of PowerGPT
Empowering Clinical Trial Design through AI: A Randomized Evaluation of PowerGPT Open
Sample size calculations for power analysis are critical for clinical research and trial design, yet their complexity and reliance on statistical expertise create barriers for many researchers. We introduce PowerGPT, an AI-powered system i…
View article: Ethical sourcing in the context of health data supply chain management: a value sensitive design approach
Ethical sourcing in the context of health data supply chain management: a value sensitive design approach Open
Objective The Bridge2AI program is establishing rules of practice for creating ethically sourced health data repositories to support the effective use of ML/AI in biomedical and behavioral research. Given the initially undefined nature of …
View article: BrainGeneBot: a framework for variant prioritization and generative pretrained transformer-informed interpretation across polygenic risk score studies
BrainGeneBot: a framework for variant prioritization and generative pretrained transformer-informed interpretation across polygenic risk score studies Open
Polygenic risk scores (PRS) are widely used to assess genetic susceptibility in Alzheimer’s disease (AD) research. However, the rapid expansion of PRS studies has led to dataset-specific biases—stemming from factors like population makeup,…
View article: Nicotine and tar-multiple targets synergize to alter the immune micro-environment to induce prostate cancer
Nicotine and tar-multiple targets synergize to alter the immune micro-environment to induce prostate cancer Open
Nicotine and tar may contribute to the development of PC through complex immuno-inflammatory mechanisms, and in-depth study of these mechanisms could help develop more effective prevention and treatment strategies for PC.
View article: D3MI: an efficient and powerful federated imputation method for bias reduction in the analysis of distributed incomplete data by accounting for within-site correlation and between-site heterogeneity
D3MI: an efficient and powerful federated imputation method for bias reduction in the analysis of distributed incomplete data by accounting for within-site correlation and between-site heterogeneity Open
Objective Electronic health records (EHRs) collected from diverse healthcare institutions offer a rich and representative data source for clinical research. Federated learning enables analysis of these distributed data without sharing sens…
View article: Computerized diagnostic decision support systems—Isabel Pro versus ChatGPT-4 part II
Computerized diagnostic decision support systems—Isabel Pro versus ChatGPT-4 part II Open
Objective Does a Tree-of-Thought prompt and reconsideration of Isabel Pro’s differential improve ChatGPT-4’s accuracy; does increasing expert panel size improve ChatGPT-4’s accuracy; does ChatGPT-4 produce consistent outputs in sequential …
View article: Cross-institutional dental electronic health record entity extraction via generative artificial intelligence and synthetic notes
Cross-institutional dental electronic health record entity extraction via generative artificial intelligence and synthetic notes Open
Background While most health-care providers now use electronic health records (EHRs) to document clinical care, many still treat them as digital versions of paper records. As a result, documentation often remains unstructured, with free-te…
View article: iGTP: learning interpretable cellular embedding for inferring biological mechanisms underlying single-cell transcriptomics
iGTP: learning interpretable cellular embedding for inferring biological mechanisms underlying single-cell transcriptomics Open
Deep-learning models like Variational AutoEncoder have enabled low dimensional cellular embedding representation for large-scale single-cell transcriptomes and shown great flexibility in downstream tasks. However, biologically meaningful l…
View article: A pioneering artificial intelligence tool to predict treatment outcomes in ovarian cancer via diagnostic laparoscopy
A pioneering artificial intelligence tool to predict treatment outcomes in ovarian cancer via diagnostic laparoscopy Open
Ovarian cancer is associated with high rates of patient mortality and morbidity. Laparoscopic assessment of tumor localization can be used for treatment planning in newly diagnosed high-grade serous ovarian carcinoma (HGSOC). While spread …
View article: CDEMapper: enhancing National Institutes of Health common data element use with large language models
CDEMapper: enhancing National Institutes of Health common data element use with large language models Open
Objective Common Data Elements (CDEs) standardize data collection and sharing across studies, enhancing data interoperability and improving research reproducibility. However, implementing CDEs presents challenges due to the broad range and…
View article: FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training
FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training Open
Fairness has been a significant challenge in graph neural networks (GNNs) since degree biases often result in un-equal prediction performance among nodes with varying degrees. Existing GNN models focus on prediction accuracy, frequently ov…
View article: Synoptic reporting by summarizing cancer pathology reports using large language models
Synoptic reporting by summarizing cancer pathology reports using large language models Open
Synoptic reporting, the documenting of clinical information in a structured manner, enhances patient care by improving accuracy, readability, and report completeness, but imposes significant administrative burdens on physicians. The potent…
View article: Robust privacy amidst innovation with large language models through a critical assessment of the risks
Robust privacy amidst innovation with large language models through a critical assessment of the risks Open
Objective This study evaluates the integration of electronic health records (EHRs) and natural language processing (NLP) with large language models (LLMs) to enhance healthcare data management and patient care, focusing on using advanced l…
View article: Privacy-Preserving Model and Preprocessing Verification for Machine Learning
Privacy-Preserving Model and Preprocessing Verification for Machine Learning Open
This paper presents a framework for privacy-preserving verification of machine learning models, focusing on models trained on sensitive data. Integrating Local Differential Privacy (LDP) with model explanations from LIME and SHAP, our fram…
View article: Effect of straw retention and mineral fertilization on P speciation and P-transformation microorganisms in water- extractable colloids of a Vertisol
Effect of straw retention and mineral fertilization on P speciation and P-transformation microorganisms in water- extractable colloids of a Vertisol Open
Water-extractable colloids (WECs) serve as crucial micro-particulate components in soils, playing a vital role in the cycling and potential bioavailability of soil phosphorus (P). Yet, the underlying information regarding soil P species an…
View article: Proxy panels enable privacy-aware outsourcing of genotype imputation
Proxy panels enable privacy-aware outsourcing of genotype imputation Open
One of the major challenges in genomic data sharing is protecting participants’ privacy in collaborative studies and in cases when genomic data are outsourced to perform analysis tasks, for example, genotype imputation services and federat…
View article: Unraveling Complex Temporal Patterns in EHRs via Robust Irregular Tensor Factorization.
Unraveling Complex Temporal Patterns in EHRs via Robust Irregular Tensor Factorization. Open
Electronic health records (EHRs) contain diverse patient data with varying visit frequencies. While irregular tensor factorization techniques such as PARAFAC2 have been used for extracting meaningful medical concepts from EHRs, existing…
View article: Not Fully Synthetic: LLM-based Hybrid Approaches Towards Privacy-Preserving Clinical Note Sharing.
Not Fully Synthetic: LLM-based Hybrid Approaches Towards Privacy-Preserving Clinical Note Sharing. Open
The publication and sharing of clinical notes are crucial for healthcare research and innovation. However, privacy regulations such as HIPAA and GDPR pose significant challenges. While de-identification techniques aim to remove protected h…
View article: Simulate Scientific Reasoning with Multiple Large Language Models: An Application to Alzheimer’s Disease Combinatorial Therapy
Simulate Scientific Reasoning with Multiple Large Language Models: An Application to Alzheimer’s Disease Combinatorial Therapy Open
Motivation This study aims to develop an AI-driven framework that leverages large language models (LLMs) to simulate scientific reasoning and peer review to predict efficacious combinatorial therapy when data-driven prediction is infeasibl…
View article: Local Haplotype Classifiers enable Efficient, Flexible, and Secure Genotype Imputation and Downstream Analyses
Local Haplotype Classifiers enable Efficient, Flexible, and Secure Genotype Imputation and Downstream Analyses Open
The decreasing cost of genotyping technologies led to abundant availability and usage of genetic data. Although it offers many potentials for improving health and curing diseases, genetic data is highly intrusive in many aspects of individ…
View article: Development of a Multi‐task Graph Neural Network for Alzheimer’s Disease Drug Repurposing
Development of a Multi‐task Graph Neural Network for Alzheimer’s Disease Drug Repurposing Open
Background Developing drugs for treating Alzheimer’s disease (AD) has been extremely challenging and costly due to limited knowledge on underlying biological mechanisms and therapeutic targets. Repurposing drugs or their combination has sh…
View article: De-identification is not enough: a comparison between de-identified and synthetic clinical notes
De-identification is not enough: a comparison between de-identified and synthetic clinical notes Open
View article: Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?
Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models? Open
Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigat…