Xiruo Ding
YOU?
Author Swipe
View article: Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking Open
Deep transformer models have been used to detect linguistic anomalies in patient transcripts for early Alzheimer's disease (AD) screening. While pre-trained neural language models (LMs) fine-tuned on AD transcripts perform well, little res…
View article: Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shifts
Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shifts Open
Foundation models are a current focus of attention in both industry and academia. While they have shown their capabilities in a variety of tasks, in-depth research is required to determine their robustness to distribution shift when used a…
View article: Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes
Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes Open
Natural Language Processing (NLP) methods have been broadly applied to clinical tasks. Machine learning and deep learning approaches have been used to improve the performance of clinical NLP. However, these approaches require sufficiently …
View article: From benchmark to bedside: transfer learning from social media to patient-provider text messages for suicide risk prediction
From benchmark to bedside: transfer learning from social media to patient-provider text messages for suicide risk prediction Open
Objective Compared to natural language processing research investigating suicide risk prediction with social media (SM) data, research utilizing data from clinical settings are scarce. However, the utility of models trained on SM data in t…
View article: Effect of Hypokalemia on Screening for Primary Aldosteronism
Effect of Hypokalemia on Screening for Primary Aldosteronism Open
Context Primary aldosteronism (PA) is a common, underdiagnosed, and treatable cause of hypertension. Guidelines recommend testing for hypokalemia, but current practices and their impact are unknown. Objective To estimate the impact of hypo…
View article: Identifying Distorted Thinking in Patient-Therapist Text Message Exchanges by Leveraging Dynamic Multi-Turn Context
Identifying Distorted Thinking in Patient-Therapist Text Message Exchanges by Leveraging Dynamic Multi-Turn Context Open
There is growing evidence that mobile text message exchanges between patients and therapists can augment traditional cognitive behavioral therapy. The automatic characterization of patient thinking patterns in this asynchronous text commun…
View article: Predicting Drug Blood-Brain Barrier Penetration with Adverse Event Report Embeddings.
Predicting Drug Blood-Brain Barrier Penetration with Adverse Event Report Embeddings. Open
Adverse event reports (AER) are widely used for post-market drug safety surveillance and drug repurposing, with the assumption that drugs with similar side-effects may have similar therapeutic effects also. In this study, we used distribut…
View article: Improving Classification of Infrequent Cognitive Distortions: Domain-Specific Model vs. Data Augmentation
Improving Classification of Infrequent Cognitive Distortions: Domain-Specific Model vs. Data Augmentation Open
Xiruo Ding, Kevin Lybarger, Justin Tauscher, Trevor Cohen. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop. 2022.
View article: Distinct roles of glutamine metabolism in benign and malignant cartilage tumors with <i>IDH</i> mutations
Distinct roles of glutamine metabolism in benign and malignant cartilage tumors with <i>IDH</i> mutations Open
Enchondromas and chondrosarcomas are common cartilage neoplasms that are either benign or malignant respectively. The majority of these tumors harbor mutations in either IDH1 or IDH2. Glutamine metabolism has been implicated as a critical …
View article: Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes
Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes Open
Objective Electronic health records (EHRs) can improve patient care by enabling systematic identification of patients for targeted decision support. But, this requires scalable learning of computable phenotypes. To this end, we developed t…
View article: Distinct Roles of Glutamine Metabolism in Benign and Malignant Cartilage Tumors With IDH Mutations
Distinct Roles of Glutamine Metabolism in Benign and Malignant Cartilage Tumors With IDH Mutations Open
Enchondromas and chondrosarcomas are common cartilage neoplasms that are either benign or malignant, respectively. The majority of these tumors harbor mutations in either IDH1 or IDH2. Glutamine metabolism has been implicated as a critical…
View article: Retrofitting Vector Representations of Adverse Event Reporting Data to Structured Knowledge to Improve Pharmacovigilance Signal Detection
Retrofitting Vector Representations of Adverse Event Reporting Data to Structured Knowledge to Improve Pharmacovigilance Signal Detection Open
Adverse drug events (ADE) are prevalent and costly. Clinical trials are constrained in their ability to identify potential ADEs, motivating the development of spontaneous reporting systems for post-market surveillance. Statistical methods …
View article: A maximum likelihood approach to electronic health record phenotyping using positive and unlabeled patients
A maximum likelihood approach to electronic health record phenotyping using positive and unlabeled patients Open
Objective Phenotyping patients using electronic health record (EHR) data conventionally requires labeled cases and controls. Assigning labels requires manual medical chart review and therefore is labor intensive. For some phenotypes, ident…
View article: Electronic Health Record Phenotyping with Internally Assessable Performance (PhIAP) using Anchor-Positive and Unlabeled Patients
Electronic Health Record Phenotyping with Internally Assessable Performance (PhIAP) using Anchor-Positive and Unlabeled Patients Open
Building phenotype models using electronic health record (EHR) data conventionally requires manually labeled cases and controls. Assigning labels is labor intensive and, for some phenotypes, identifying gold-standard controls is prohibitiv…
View article: Designing risk prediction models for ambulatory no-shows across different specialties and clinics
Designing risk prediction models for ambulatory no-shows across different specialties and clinics Open
Objective As available data increases, so does the opportunity to develop risk scores on more refined patient populations. In this paper we assessed the ability to derive a risk score for a patient no-showing to a clinic visit. Methods Usi…