Accurate Machine Learning Model to Diagnose Chronic Autoimmune Diseases Utilizing Information From B Cells and Monocytes

Abstract

Heterogeneity and limited comprehension of chronic autoimmune disease pathophysiology cause accurate diagnosis a challenging process. With the increasing resources of single-cell sequencing data, a reasonable way could be found to address this issue. In our study, with the use of large-scale public single-cell RNA sequencing (scRNA-seq) data, analysis of dataset integration (3.1 × 105 PBMCs from fifteen SLE patients and eight healthy donors) and cellular cross talking (3.8 × 105 PBMCs from twenty-eight SLE patients and eight healthy donors) were performed to identify the most crucial information characterizing SLE. Our findings revealed that the interactions among the PBMC subpopulations of SLE patients may be weakened under the inflammatory microenvironment, which could result in abnormal emergences or variations in signaling patterns within PBMCs. In particular, the alterations of B cells and monocytes may be the most significant findings. Utilizing this powerful information, an efficient mathematical model of unbiased random forest machine learning was established to distinguish SLE patients from healthy donors via not only scRNA-seq data but also bulk RNA-seq data. Surprisingly, our mathematical model could also accurately identify patients with rheumatoid arthritis and multiple sclerosis, not just SLE, via bulk RNA-seq data (derived from 688 samples). Since the variations in PBMCs should predate the clinical manifestations of these diseases, our machine learning model may be feasible to develop into an efficient tool for accurate diagnosis of chronic autoimmune diseases.

Exploring machine learning methods for predicting systemic lupus erythematosus with herpes

“…Similarly, the random forest model used for a European SLE population based on the Gene Expression Omnibus (GEO) database showed an AUC of 0.776, which may be able to distinguish SLE patients from healthy individuals. Indeed, a study in another external cohort confirmed accuracy of the model in diagnosing SLE patients from healthy individuals with 100% sensitivity and 92.7% specificity 21 . Our prediction model for SLE patients with herpes obtained a higher AUC of 0.942, suggesting that the random forest model may be more valuable for clinicians to identify SLE patients with herpes.…”

Identification and Verification of Novel Biomarkers Involving Rheumatoid Arthritis with Multimachine Learning Algorithms: An In Silicon and In Vivo Study

“…Applying machine learning algorithms to biomedicine largely promotes a better understanding and deconvolution of high-sequence information. Several studies have tried to decipher the heterogeneity of RA to some extent and have made limited advances in better understanding RA [ 33 , 36 ]. While the obsolete algorithm limited the reliability of clinical practice, a comprehensive understanding of RA in multiple cohorts with advanced machine learning algorithms is extremely urgent.…”

Systemic lupus in the era of machine learning medicine

“… 127 128 Proteomics using cerebrospinal fluid demonstrated that CST6, L-selectin, Trappin-2, KLK5 and TCN2 could distinguish NPSLE from SLE controls (non-NPSLE). 124 Other reports using single-cell RNA sequencing data compared biomarkers for NPSLE to multiple sclerosis 103 and vascular dementia. 83 To differentiate cutaneous LE from other dermatological disorders such as psoriasis, eczema, atopic dermatitis and systemic sclerosis (RF model, AUC 0.774–0.990), interferon gene signature, tumour necrosis factor, interleukin-23 (IL-23), interferon (IFN), IL-12, and immune cell-related genetic signatures were selected as important biomarkers.…”