Advancing precision rheumatology: applications of machine learning for rheumatoid arthritis management.

Rheumatoid arthritis (RA) is an autoimmune disease causing progressive joint damage. Early diagnosis and treatment is critical, but remains challenging due to RA complexity and heterogeneity. Machine learning (ML) techniques may enhance RA management by identifying patterns within multidimensional biomedical data to improve classification, diagnosis, and treatment predictions. In this review, we summarize the applications of ML for RA management. Emerging studies or applications have developed diagnostic and predictive models for RA that utilize a variety of data modalities, including electronic health records, imaging, and multi-omics data. High-performance supervised learning models have demonstrated an Area Under the Curve (AUC) exceeding 0.85, which is used for identifying RA patients and predicting treatment responses. Unsupervised learning has revealed potential RA subtypes. Ongoing research is integrating multimodal data with deep learning to further improve performance. However, key challenges remain regarding model overfitting, generalizability, validation in clinical settings, and interpretability. Small sample sizes and lack of diverse population testing risks overestimating model performance. Prospective studies evaluating real-world clinical utility are lacking. Enhancing model interpretability is critical for clinician acceptance. In summary, while ML shows promise for transforming RA management through earlier diagnosis and optimized treatment, larger scale multisite data, prospective clinical validation of interpretable models, and testing across diverse populations is still needed. As these gaps are addressed, ML may pave the way towards precision medicine in RA.

Targeted siRNA Therapy for Psoriasis: Translating Preclinical Potential into Clinical Treatments.

Psoriasis is a chronic inflammatory skin disease characterized by the excessive proliferation of keratinocytes and heightened immune activation. Targeting pathogenic genes through small interfering RNA (siRNA) therapy represents a promising strategy for the treatment of psoriasis. This mini-review provides a comprehensive summary of siRNA research targeting the pathogenesis of psoriasis, covering aspects such as keratinocyte function, inflammatory cell roles, preclinical animal studies, and siRNA delivery mechanisms. It details recent advancements in RNA interference that modulate key factors including keratinocyte proliferation (Fibroblast Growth Factor Receptor 2, FGFR2), apoptosis (Interferon Alpha Inducible Protein 6, G1P3), differentiation (Grainyhead Like Transcription Factor 2, GRHL2), and angiogenesis (Vascular Endothelial Growth Factor, VEGF); immune cell infiltration and inflammation (Tumor Necrosis Factor-Alpha, TNF-α; Interleukin-17, IL-17); and signaling pathways (JAK-STAT, Nuclear Factor Kappa B, NF-κB) that govern immunopathology. Despite significant advances in siRNA-targeted treatments for psoriasis, several challenges persist. Continued scientific developments promise the creation of more effective and safer siRNA medications, potentially enhancing the quality of life for psoriasis patients and revolutionizing treatments for other diseases. This article focuses on the most recent research advancements in targeting the pathogenesis of psoriasis with siRNA and explores its future therapeutic prospects.

Macrophage polarization in rheumatoid arthritis: signaling pathways, metabolic reprogramming, and crosstalk with synovial fibroblasts.

Rheumatoid arthritis (RA) is a chronic autoimmune disease characterized by persistent synovial inflammation and progressive joint destruction. Macrophages are key effector cells that play a central role in RA pathogenesis through their ability to polarize into distinct functional phenotypes. An imbalance favoring pro-inflammatory M1 macrophages over anti-inflammatory M2 macrophages disrupts immune homeostasis and exacerbates joint inflammation. Multiple signaling pathways, including Notch, JAK/STAT, NF-κb, and MAPK, regulate macrophage polarization towards the M1 phenotype in RA. Metabolic reprogramming also contributes to this process, with M1 macrophages prioritizing glycolysis while M2 macrophages utilize oxidative phosphorylation. Redressing this imbalance by modulating macrophage polarization and metabolic state represents a promising therapeutic strategy. Furthermore, complex bidirectional interactions exist between synovial macrophages and fibroblast-like synoviocytes (FLS), forming a self-perpetuating inflammatory loop. Macrophage-derived factors promote aggressive phenotypes in FLS, while FLS-secreted mediators contribute to aberrant macrophage activation. Elucidating the signaling networks governing macrophage polarization, metabolic adaptations, and crosstalk with FLS is crucial to developing targeted therapies that can restore immune homeostasis and mitigate joint pathology in RA.

Risk factors of systemic lupus erythematosus patients with pulmonary arterial hypertension: A systematic review and meta-analysis.

BACKGROUND: To investigate the risk factors for the development of pulmonary arterial hypertension (PAH) in patients with systemic lupus erythematosus (SLE). METHODS: The literature related to risk factors for the development of PAH in SLE patients was searched by the computer on China national knowledge infrastructure (CNKI), PubMed, and Embase, and the literature search was limited to the period of library construction to October 2022. Two researchers independently performed literature screening and literature information extracting, including first author, publication time, case collection time, sample size, and study factors, and used the Newcastle-Ottawa Scale (NOS) to evaluate the quality of the literature. The relationship between each clinical manifestation and laboratory index and the occurrence of PAH in SLE patients was evaluated based on the ratio (OR value) and its 95% CI. RESULTS: A total of 24 publications were included, including 23 case-control studies and 1 cohort study with NOS ≥ 6, and the overall quality of the literature was high. The risk of PAH was higher in SLE patients who developed Raynaud phenomenon than in those who did not [OR = 2.39, 95% CI (1.91, 2.99), P < .05]; the risk of PAH was higher in SLE patients who were positive for anti-RNP antibodies than in those who were negative for anti-RNP antibodies [OR = 1.77, 95% CI (1.17, 3.2.65), P < .05]; the risk of PAH was higher in SLE patients with interstitial lung lesions than in those without combined interstitial lung lesions [OR = 3.28, 95% CI (2.37, 4.53), P < .05]; the risk of PAH was higher in SLE patients with combined serositis than in those without serositis [OR = 2.28, 95% CI (1.83, 2.84), P < .05]. The risk of PAH was higher in SLE patients with combined pericardial effusion than in those without pericardial effusion [OR = 2.97, 95% CI (2.37, 3.72), P < .05]; the risk of PAH was higher in SLE patients with combined vasculitis than in those without vasculitis [OR = 1.50, 95% CI (1.08, 2.07), P < .05]; rheumatoid factor-positive SLE patients had a higher risk of PAH than those with rheumatoid factor-negative [OR = 1.66, 95% CI (1.24, 2.24), P < .05]. CONCLUSION: Raynaud phenomenon, vasculitis, anti-RNP antibodies, serositis, interstitial lung lesions, rheumatoid factor, and pericardial effusion are risk factors for the development of PAH in patients with SLE.

Event-Triggered Adaptive Optimal Control With Output Feedback: An Adaptive Dynamic Programming Approach.

This article presents an event-triggered output-feedback adaptive optimal control method for continuous-time linear systems. First, it is shown that the unmeasurable states can be reconstructed by using the measured input and output data. An event-based feedback strategy is then proposed to reduce the number of controller updates and save communication resources. The discrete-time algebraic Riccati equation is iteratively solved through event-triggered adaptive dynamic programming based on both policy iteration (PI) and value iteration (VI) methods. The convergence of the proposed algorithm and the closed-loop stability is carried out by using the Lyapunov techniques. Two numerical examples are employed to verify the effectiveness of the design methodology.