Search for: All records

Measuring parathyroid hormone-related peptide (PTHrP) helps diagnose the humoral hypercalcemia of malignancy, but is often ordered for patients with low pretest probability, resulting in poor test utilization. Manual review of results to identify inappropriate PTHrP orders is a cumbersome process.

Using a dataset of 1330 patients from a single institute, we developed a machine learning (ML) model to predict abnormal PTHrP results. We then evaluated the performance of the model on two external datasets. Different strategies (model transporting, retraining, rebuilding, and fine-tuning) were investigated to improve model generalizability. Maximum mean discrepancy (MMD) was adopted to quantify the shift of data distributions across different datasets.

The model achieved an area under the receiver operating characteristic curve (AUROC) of 0.936, and a specificity of 0.842 at 0.900 sensitivity in the development cohort. Directly transporting this model to two external datasets resulted in a deterioration of AUROC to 0.838 and 0.737, with the latter having a larger MMD corresponding to a greater data shift compared to the original dataset. Model rebuilding using site-specific data improved AUROC to 0.891 and 0.837 on the two sites, respectively. When external data is insufficient for retraining, a fine-tuning strategy also improved model utility.

ML offers promise to improve PTHrP test utilization while relieving the burden of manual review. Transporting a ready-made model to external datasets may lead to performance deterioration due to data distribution shift. Model retraining or rebuilding could improve generalizability when there are enough data, and model fine-tuning may be favorable when site-specific data is limited.

 

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.

 

It has been presumed that rheumatoid arthritis (RA) joint pain is related to inflammation in the synovium; however, recent studies reveal that pain scores in patients do not correlate with synovial inflammation. We developed a machine-learning approach (graph-based gene expression module identification or GbGMI) to identify an 815-gene expression module associated with pain in synovial biopsy samples from patients with established RA who had limited synovial inflammation at arthroplasty. We then validated this finding in an independent cohort of synovial biopsy samples from patients who had early untreated RA with little inflammation. Single-cell RNA sequencing analyses indicated that most of these 815 genes were most robustly expressed by lining layer synovial fibroblasts. Receptor-ligand interaction analysis predicted cross-talk between human lining layer fibroblasts and human dorsal root ganglion neurons expressing calcitonin gene–related peptide (CGRP⁺). Both RA synovial fibroblast culture supernatant and netrin-4, which is abundantly expressed by lining fibroblasts and was within the GbGMI-identified pain-associated gene module, increased the branching of pain-sensitive murine CGRP⁺dorsal root ganglion neurons in vitro. Imaging of solvent-cleared synovial tissue with little inflammation from humans with RA revealed CGRP⁺pain-sensing neurons encasing blood vessels growing into synovial hypertrophic papilla. Together, these findings support a model whereby synovial lining fibroblasts express genes associated with pain that enhance the growth of pain-sensing neurons into regions of synovial hypertrophy in RA.

 

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named structure fairness. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose Structural Fair Graph Neural Network (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.