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

Frontiers in Immunology, Journal Year: 2024, Volume and Issue: 15

Published: June 10, 2024

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

Language: Английский

---

GradWise: A Novel Application of a Rank-Based Weighted Hybrid Filter and Embedded Feature Selection Method for Glioma Grading with Clinical and Molecular Characteristics

Cancers, Journal Year: 2023, Volume and Issue: 15(18), P. 4628 - 4628

Published: Sept. 19, 2023

Glioma grading plays a pivotal role in guiding treatment decisions, predicting patient outcomes, facilitating clinical trial participation and research, tailoring strategies. Current glioma the clinic is based on tissue acquired at time of resection, with tumor aggressiveness assessed from morphology molecular features. The increased emphasis characteristics as guide for management prognosis estimation underscores driven by need accurate standardized systems that integrate information process carry expectation exposure markers go beyond to increase understanding biology means identifying druggable targets. In this study, we introduce novel application (GradWise) combines rank-based weighted hybrid filter (i.e., mRMR) embedded LASSO) feature selection methods enhance performance machine learning models using both predictors. We utilized publicly available TCGA UCI ML Repository CGGA datasets identify most effective scheme allows minimum number features their names. Two popular weighting procedure were employed conduct comprehensive experiments five supervised models. computational results demonstrate our proposed method achieves an accuracy rate 87.007% 13 80.412% datasets, respectively. also obtained four shared biomarkers emerged can be transferable value other data-based outcome analyses. These findings are significant step toward highlighting effectiveness approach offering pioneering prospects targeting biologic mechanisms progression improve outcomes.

Language: Английский

---

GLIO-Select: Machine Learning-Based Feature Selection and Weighting of Tissue and Serum Proteomic and Metabolomic Data Uncovers Sex Differences in Glioblastoma

International Journal of Molecular Sciences, Journal Year: 2025, Volume and Issue: 26(9), P. 4339 - 4339

Published: May 2, 2025

Glioblastoma (GBM) is a fatal brain cancer known for its rapid and aggressive growth, with some studies indicating that females may have better survival outcomes compared to males. While sex differences in GBM been observed, the underlying biological mechanisms remain poorly understood. Feature selection can lead identification of discriminative key biomarkers by reducing dimensionality from high-dimensional medical datasets improve machine learning model performance, explainability, interpretability. uncover unique sex-specific biomarkers, determinants, molecular profiles patients GBM. We analyzed proteomic metabolomic serum biospecimens obtained 109 pathology-proven glioblastoma on NIH IRB-approved protocols full clinical annotation (local dataset). Serum analysis was performed using Somalogic aptamer-based technology (measuring 7289 proteins) metabolome University Florida’s SECIM (Southeast Center Integrated Metabolomics) platform 6015 metabolites). Machine learning-based feature employed identify proteins metabolites associated male female labels datasets. Results were publicly available (CPTAC TCGA) same methodology TCGA data previously structured glioma grading. Employing hybrid approach, utilizing both LASSO mRMR, conjunction rank-based weighting method (i.e., GLIO-Select), we linked purposes reduction used separate set explore possible linkages between mutations tumor identified several hundred features male/female class label Using local serum-based dataset patients, 17 (100% ACC) 16 (92% datasets, respectively. CPTAC tissue-based (8828 59 features), 5 (99% 13 (80% The or tissue (CPTAC) achieved highest accuracy rates 99%, respectively), followed metabolome. yielded clinically (PSA, PZP, HCG, FSH) which distinct (RPS4Y1 DDX3Y), providing methodological validation, PZP defensins (DEFA3 DEFB4A) representing shared tissue. Metabolomic homocysteine pantothenic acid. Several signals emerged are be but not sex, requiring further research, as well novel either glioma. EGFR, FAT4, BCOR three 64% ACC grading set. GLIO-Select shows remarkable results when different types (e.g., tissue-based) our analyses. proposed approach successfully reduced relevant less than twenty each dataset. appear highly effective identifying biologically These findings suggest noninvasive biospecimen-based analyses provide more accurate detailed insights into variable (SABV) other biospecimens, linking pathology via immune response, amino acid metabolism, hallmark research. Our underscore importance biospecimen choice enhancing interpretation omics understanding sex-based This discovery holds significant potential personalized treatment plans patient outcomes.

Language: Английский

---

STSA‐Based Early‐Stage Detection of Small Brain Tumors Using Neural Network

Engineering Reports, Journal Year: 2025, Volume and Issue: 7(5)

Published: May 1, 2025

ABSTRACT Early‐stage brain tumor detection is critical for improving patient outcomes, optimizing treatment strategies, and enhancing healthcare resource allocation. However, existing state‐of‐the‐art techniques struggle to detect tumors smaller than 5 mm due their minimal dimensions complex electromagnetic interactions. This study introduces a machine learning‐based classification approach early‐stage Astrocytoma (grades I II) using step‐constant tapered slot antenna (STSA) parameters. By leveraging scattering (S), admittance (Y), impedance (Z) parameters as input features, an Artificial Neural Network (ANN) achieved 99.95% accuracy with radii of 3 mm. Among the was identified most significant contributor accuracy, whereas S‐parameter exhibited lowest performance at 84.21% accuracy. The proposed methodology benchmarked against Support Vector Machine (SVM), K‐Nearest Neighbor (KNN), Random Forest Classifier (RFC), Graph Convolutional (GCN), demonstrating superior across different sizes. Additionally, system maintained low Specific Absorption Rate (SAR) 0.30 W/Kg, reinforcing its suitability biomedical antenna‐based applications. An ablation further confirmed that Z 22 14 phase components within matrix were particularly influential, revealed through Local Interpretable Model‐Agnostic Explanations (LIME), explainable AI (XAI) technique. method evaluated publicly available dataset, validating robustness. These findings highlight potential STSA‐based learning models accurate, non‐invasive classification, enabling cost‐effective, scalable diagnostics.

Language: Английский

---

Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach

Diagnostics, Journal Year: 2025, Volume and Issue: 15(10), P. 1292 - 1292

Published: May 21, 2025

Background/Objectives: Glioblastoma (GBM) is a highly aggressive primary central nervous system tumor with median survival of 14 months. MGMT (O6-methylguanine-DNA methyltransferase) promoter methylation status key biomarker as prognostic indicator and predictor chemotherapy response in GBM. Patients methylated disease progress later survive longer (median rate 22 vs. 15 months, respectively) compared to patients unmethylated disease. GBM undergo an MRI the brain prior diagnosis following surgical resection for radiation therapy planning ongoing follow-up. There currently no imaging Studies have attempted connect appearance determine if can be leveraged provide information non-invasively more expeditiously. Methods: Artificial intelligence (AI) identify features that are not distinguishable human eye linked status. We employed UPenn-GBM dataset whom was available (n = 146), employing novel radiomic method grounded hybrid feature selection weighting predict Results: The best classification result obtained resulted mean accuracy value 81.6% utilizing 101 selected five-fold cross-validation. Conclusions: This favorably similar studies literature. Validation external datasets remains critical enhance generalizability propagate robust results while reducing bias. Future directions include multi-channel data integration deep ensemble learning methods improve predictive performance.

Language: Английский

---

MGMT ProFWise: Unlocking a New Application for Combined Feature Selection and the Rank-Based Weighting Method to Link MGMT Methylation Status to Serum Protein Expression in Patients with Glioblastoma

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(7), P. 4082 - 4082

Published: April 6, 2024

Glioblastoma (GBM) is a fatal brain tumor with limited treatment options. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status the central molecular biomarker linked to both response temozolomide, standard chemotherapy drug employed for GBM, and patient survival. However, MGMT captured on tissue which, given difficulty in acquisition, limits use of this feature monitoring. protein expression levels may offer additional insights into mechanistic understanding but, currently, they correlate poorly methylation. The acquiring testing drives need non-invasive methods predict status. Feature selection aims identify most informative features build accurate interpretable prediction models. This study explores new application combined (i.e., LASSO mRMR) rank-based weighting method ProFWise) non-invasively link serum patients GBM. Our provides promising results, reducing dimensionality (by more than 95%) when two large-scale proteomic datasets (7k SomaScan® panel CPTAC) all our analyses. computational results indicate that proposed approach 14 shared biomarkers be helpful diagnostic, prognostic, and/or predictive operations GBM-related processes, further validation.

Language: Английский

---

MetaWise: Combined Feature Selection and Weighting Method to Link the Serum Metabolome to Treatment Response and Survival in Glioblastoma

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(20), P. 10965 - 10965

Published: Oct. 11, 2024

Glioblastoma (GBM) is a highly malignant and devastating brain cancer characterized by its ability to rapidly aggressively grow, infiltrating tissue, with nearly universal recurrence after the standard of care (SOC), which comprises maximal safe resection followed chemoirradiation (CRT). The metabolic triggers leading reprogramming tumor behavior resistance are an area increasingly studied in relation molecular features associated outcome. There currently no metabolomic biomarkers for GBM. Studying alterations GBM patients undergoing CRT could uncover biochemical pathways involved response resistance, identification novel optimization treatment response. feature selection process identifies key factors improve model’s accuracy interpretability. This study utilizes combined approach, incorporating both Least Absolute Shrinkage Selection Operator (LASSO) Minimum Redundancy–Maximum Relevance (mRMR), alongside rank-based weighting method (i.e., MetaWise) link 12-month 20-month overall survival (OS) status Our shows promising results, reducing dimensionality when employed on serum-based large-scale datasets (University Florida) all our analyses. proposed successfully identified set eleven serum shared among three datasets. computational results show that utilized achieves 96.711%, 92.093%, 86.910% rates 48, 46, 33 selected CRT, 12-month, OS-based datasets, respectively. discovery has implications developing personalized plans improving patient outcomes.

Language: Английский

---

Advances in the field of developing biomarkers for re-irradiation: a how-to guide to small, powerful data sets and artificial intelligence

Expert Review of Precision Medicine and Drug Development, Journal Year: 2024, Volume and Issue: 9(1), P. 3 - 16

Published: March 11, 2024

Introduction Patient selection remains challenging as the clinical use of re-irradiation (re-RT) increases. Re-RT data are limited to retrospective studies and small prospective single-institution reports, resulting in small, heterogenous sets. Validated prognostic predictive biomarkers derived from large-volume with long-term follow-up. This review aims examine existing re-RT publications available sets discuss strategies using artificial intelligence (AI) approach optimize data.

Language: Английский

---

Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review

Neurology International, Journal Year: 2024, Volume and Issue: 16(6), P. 1285 - 1307

Published: Oct. 29, 2024

In recent years, Artificial Intelligence (AI) methods, specifically Machine Learning (ML) models, have been providing outstanding results in different areas of knowledge, with the health area being one its most impactful fields application. However, to be applied reliably, these models must provide users clear, simple, and transparent explanations about medical decision-making process. This systematic review aims investigate use application explainability ML used brain disease studies. A search was conducted three major bibliographic databases, Web Science, Scopus, PubMed, from January 2014 December 2023. total 133 relevant studies were identified analyzed out a 682 found initial search, which context studied, identifying 11 12 techniques study 20 diseases.

Language: Английский

---

Correction: Tasci et al. RadWise: A Rank-Based Hybrid Feature Weighting and Selection Method for Proteomic Categorization of Chemoirradiation in Patients with Glioblastoma. Cancers 2023, 15, 2672

Cancers, Journal Year: 2024, Volume and Issue: 16(15), P. 2744 - 2744

Published: Aug. 1, 2024

In the original publication [...].

Language: Английский

---