Dataset Information

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

ABSTRACT:

Background

Not being well controlled by therapy with inhaled corticosteroids and long-acting β2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response.

Methods

Two novel computational algorithms, machine-learning based Recursive Ensemble Feature Selection (REFS) and rule-based algorithm Logic Explainable Networks (LEN), were used on open accessible mRNA expression data from moderate-to-severe asthma patients to identify genes as predictors of omalizumab response.

Results

With REFS, the number of features was reduced from 28,402 genes to 5 genes while obtaining a cross-validated accuracy of 0.975. The 5 responsiveness predictive genes encode the following proteins: Coiled-coil domain- containing protein 113 (CCDC113), Solute Carrier Family 26 Member 8 (SLC26A), Protein Phosphatase 1 Regulatory Subunit 3D (PPP1R3D), C-Type lectin Domain Family 4 member C (CLEC4C) and LOC100131780 (not annotated). The LEN algorithm found 4 identical genes with REFS: CCDC113, SLC26A8 PPP1R3D and LOC100131780. Literature research showed that the 4 identified responsiveness predicting genes are associated with mucosal immunity, cell metabolism, and airway remodeling.

Conclusion and clinical relevance

Both computational methods show 4 identical genes as predictors of omalizumab response in moderate-to-severe asthma patients. The obtained high accuracy indicates that our approach has potential in clinical settings. Future studies in relevant cohort data should validate our computational approach.

SUBMITTER: Kidwai S

PROVIDER: S-EPMC10655633 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

Kidwai Sarah S Barbiero Pietro P Meijerman Irma I Tonda Alberto A Perez-Pardo Paula P Lio Pietro P van der Maitland-Zee Anke H AH Oberski Daniel L DL Kraneveld Aletta D AD Lopez-Rincon Alejandro A

Clinical and translational allergy 20231101 11

<h4>Background</h4>Not being well controlled by therapy with inhaled corticosteroids and long-acting β2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response.<h4>Methods</ ...[more]

PMID: 38006387

Similar Datasets

Project description:Landslides pose significant threats to ecosystems, lives, and economies, particularly in the geologically fragile Sub-Himalayan region of West Bengal, India. This study enhances landslide susceptibility prediction by developing an ensemble framework integrating Recursive Feature Elimination (RFE) with meta-learning techniques. Seven advanced machine learning models- Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and a Meta Classifier (MC) were applied using Remote Sensing and GIS tools to identify key landslide-conditioning factors and classify susceptibility zones. Model performance was assessed through metrics such as accuracy, precision, recall, F1 score, and AUC of the ROC curve. Among the models, the Meta Classifier (MC) achieved the highest accuracy (0.956) and AUC (0.987), demonstrating superior predictive ability. Gradient Boosting (GB), XGBoost, and RF also performed well, with accuracies of 0.943 and AUC values of 0.987 (GB and XGBoost) and 0.983 (RF). Extremely Randomized Trees (ET) exhibited the highest accuracy (0.946) among individual models and an AUC of 0.985. SVM and LR, while slightly less accurate (0.941 and 0.860, respectively), provided valuable insights, with SVM achieving an AUC of 0.972 and LR achieving 0.935. The models effectively delineated landslide susceptibility into five zones (very low, low, moderate, high, and very high), with high and very high susceptibility zones concentrated in Darjeeling and Kalimpong subdivisions. These zones are influenced by intense rainfall, unstable geological structures, and anthropogenic activities like deforestation and urbanization. Notably, ET, RF, GB, and XGBoost demonstrated efficiency in feature selection, requiring fewer input variables while maintaining high performance. This study establishes a benchmark for landslide susceptibility mapping, providing a scalable and adaptable framework for geospatial hazard prediction. The findings hold significant implications for land-use planning, disaster management, and environmental conservation in vulnerable regions worldwide.

Project description:BackgroundBronchial thermoplasty (BT) is a recently developed treatment for patients with moderate-to-severe asthma. A few studies have suggested the clinical efficacy of this intervention. However, no study has evaluated the cost-effectiveness of BT compared to other alternative treatments for moderate-to-severe allergic asthma, which currently include omalizumab and standard therapy.ObjectiveTo evaluate the cost-effectiveness of standard therapy, BT, and omalizumab for moderate-to-severe allergic asthma in the USA.MethodsA probabilistic Markov model with weekly cycles was developed to reflect the course of asthma progression over a 5-year time horizon. The study population was adults with moderate-to-severe allergic asthma whose asthma remained uncontrolled despite using high-dose inhaled corticosteroids (ICS, with or without long-acting beta-agonists [LABA]). A perspective of the health-care system was adopted with asthma-related costs as well as quality-adjusted life years (QALYs) and exacerbations as the outcomes.ResultsFor standard therapy, BT, and omalizumab, the discounted 5-year costs and QALYs were $15,400 and 3.08, $28,100 and 3.24, and $117,000 and 3.26, respectively. The incremental cost-effectiveness ratio (ICER) of BT versus standard therapy and omalizumab versus BT was $78,700/QALY and $3.86 million/QALY, respectively. At the willingness-to-pay (WTP) of $50,000/QALY and $100,000/QALY, the probability of BT being cost-effective was 9%, and 67%, respectively. The corresponding expected value of perfect information (EVPI) was $155 and $1,530 per individual at these thresholds. In sensitivity analyses, increasing the costs of BT from $14,900 to $30,000 increased its ICER relative to standard therapy to $178,000/QALY, and decreased the ICER of omalizumab relative to BT to $3.06 million/QALY. Reducing the costs of omalizumab by 25% decreased its ICER relative to BT by 29%.ConclusionsBased on the available evidence, our study suggests that there is more than 60% chance that BT becomes cost-effective relative to omalizumab and standard therapy at the WTP of $100,000/QALY in patients with moderate-to-severe allergic asthma. However, there is a substantial uncertainty in the underlying evidence, indicating the need for future research towards reducing such uncertainty.

Project description:Omalizumab is licensed as add-on therapy for patients with severe allergic asthma. Response is in most studies scored by the physician's global evaluation of treatment effectiveness (GETE). A good clinical and validated parameter for treatment response is currently missing. Also, there are no established criteria for identifying patients who will respond to omalizumab based on pre-treatment characteristics. The Dutch National Omalizumab in Asthma Registry was developed in 2011 to better evaluate inclusion criteria and measure treatment response after 4 months.This is a "real world" prospectively designed, observational data registry in which the outcomes of patients who received omalizumab between 2012 and 2015 were evaluated. Data were collected from all centers in the Netherlands comprising demographic features, criteria for starting treatment, GETE, FEV1, oral corticosteroid use and ACQ.65.5% of the 403 patients had a good or excellent response to omalizumab after 16 weeks according to the treating physician GETE. 64.5% fulfilled all the criteria for prescribing omalizumab at baseline. The mean ACQ improved from 2.96 at baseline to 1.83 at 16 weeks (p < 0.001). 75.3% of the responders showed more than 0.5 points improvement in the ACQ. The mean FEV1 increased from 71.58 to 79.06 (p < 0.001). There was no relationship between patients with a FEV1 <80 and ≥80% at baseline and response (p = 0.981). Most of the responders had a considerable improvement of FEV1 either/or ACQ or OCS use (88.3%). While 86.7% of the responders had an improvement of either ACQ or FEV1. 75.4% of the responders had an improvement of ACQ, while 50.4% had an improvement of FEV1. Finally 11.7% of the patients with no improvement of FEV1, ACQ or OCS use were considered to have a good response.This registry of 403 inadequately controlled severe allergic asthma patients in the Netherlands showed a good or excellent response of 65.5% to omalizumab after 16 weeks, in accordance with previous studies. The assumption that careful registration would lead to higher response rates could not be supported by the data from this registry. Improvement of ACQ appears to be a useful additional assessment tool to measure response in omalizumab treated patients.

Dataset Information

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

Background

Methods

Results

Conclusion and clinical relevance

Publications

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets