Prediction of high and low disease activity in early MS patients using multiple kernel learning identifies importance of lateral ventricle intensity.
Ontology highlight
ABSTRACT: Background
Lack of easy-to-interpret disease activity prediction methods in early MS can lead to worse patient prognosis.Objectives
Using machine learning (multiple kernel learning - MKL) models, we assessed the prognostic value of various clinical and MRI measures for disease activity.Methods
Early MS patients (n = 148) with at least two associated clinical and MRI visits were investigated. T2-weighted MRIs were cropped to contain mainly the lateral ventricles (LV). High disease activity was defined as surpassing NEDA-3 Criteria more than once per year. Clinical demographic, MRI-extracted image-derived phenotypes (IDP), and MRI data were used as inputs for separate kernels to predict future disease activity with MKL. Model performance was compared using bootstrapped effect size analysis of mean differences.Results
A total of 681 visits were included, where 81 (55%) patients had high disease activity in a combined end point measure using all follow-up visits. MKL model discrimination performance was moderate (AUC ≥ 0.62); however, modelling with combined clinical and cropped LV kernels gave the highest prediction performance (AUC = 0.70).Conclusions
MRIs contain valuable information on future disease activity, especially in and around the LV. MKL techniques for combining different data types can be used for the prediction of disease activity in a relatively small MS cohort.
SUBMITTER: Chien C
PROVIDER: S-EPMC9260586 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Attempts to predict prognosis in cancer patients using high-dimensional genomic data such as gene expression in tumor tissue can be made difficult by the large number of features and the potential complexity of the relationship between features and the outcome. Integrating prior biological knowledge into risk prediction with such data by grouping genomic features into pathways and networks reduces the dimensionality of the problem and could improve prediction accuracy. Additionally, such knowledge-based models may be more biologically grounded and interpretable. Prediction could potentially be further improved by allowing for complex nonlinear pathway effects. The kernel machine framework has been proposed as an effective approach for modeling the nonlinear and interactive effects of genes in pathways for both censored and noncensored outcomes. When multiple pathways are under consideration, one may efficiently select informative pathways and aggregate their signals via multiple kernel learning (MKL), which has been proposed for prediction of noncensored outcomes. In this paper, we propose MKL methods for censored survival outcomes. We derive our approach for a general survival modeling framework with a convex objective function and illustrate its application under the Cox proportional hazards and semiparametric accelerated failure time models. Numerical studies demonstrate that the proposed MKL-based prediction methods work well in finite sample and can potentially outperform models constructed assuming linear effects or ignoring the group knowledge. The methods are illustrated with an application to 2 cancer data sets.
| S-EPMC5994931 | biostudies-literature
Project description:BackgroundAdvances in medical technology have allowed for customized prognosis, diagnosis, and treatment regimens that utilize multiple heterogeneous data sources. Multiple kernel learning (MKL) is well suited for the integration of multiple high throughput data sources. MKL remains to be under-utilized by genomic researchers partly due to the lack of unified guidelines for its use, and benchmark genomic datasets.ResultsWe provide three implementations of MKL in R. These methods are applied to simulated data to illustrate that MKL can select appropriate models. We also apply MKL to combine clinical information with miRNA gene expression data of ovarian cancer study into a single analysis. Lastly, we show that MKL can identify gene sets that are known to play a role in the prognostic prediction of 15 cancer types using gene expression data from The Cancer Genome Atlas, as well as, identify new gene sets for the future research.ConclusionMultiple kernel learning coupled with modern optimization techniques provides a promising learning tool for building predictive models based on multi-source genomic data. MKL also provides an automated scheme for kernel prioritization and parameter tuning. The methods used in the paper are implemented as an R package called RMKL package, which is freely available for download through CRAN at https://CRAN.R-project.org/package=RMKL .
| S-EPMC6694479 | biostudies-literature
Project description:BackgroundIdentification of molecular mechanisms that determine tumour progression in cancer patients is a prerequisite for developing new disease treatment guidelines. Even though the predictive performance of current machine learning models is promising, extracting significant and meaningful knowledge from the data simultaneously during the learning process is a difficult task considering the high-dimensional and highly correlated nature of genomic datasets. Thus, there is a need for models that not only predict tumour volume from gene expression data of patients but also use prior information coming from pathway/gene sets during the learning process, to distinguish molecular mechanisms which play crucial role in tumour progression and therefore, disease prognosis.ResultsIn this study, instead of initially choosing several pathways/gene sets from an available set and training a model on this previously chosen subset of genomic features, we built a novel machine learning algorithm, PrognosiT, that accomplishes both tasks together. We tested our algorithm on thyroid carcinoma patients using gene expression profiles and cancer-specific pathways/gene sets. Predictive performance of our novel multiple kernel learning algorithm (PrognosiT) was comparable or even better than random forest (RF) and support vector regression (SVR). It is also notable that, to predict tumour volume, PrognosiT used gene expression features less than one-tenth of what RF and SVR algorithms used.ConclusionsPrognosiT was able to obtain comparable or even better predictive performance than SVR and RF. Moreover, we demonstrated that during the learning process, our algorithm managed to extract relevant and meaningful pathway/gene sets information related to the studied cancer type, which provides insights about its progression and aggressiveness. We also compared gene expressions of the selected genes by our algorithm in tumour and normal tissues, and we then discussed up- and down-regulated genes selected by our algorithm while learning, which could be beneficial for determining new biomarkers.
| S-EPMC8561914 | biostudies-literature
Project description:There is significant clinical and prognostic heterogeneity in the neurodegenerative disorder amyotrophic lateral sclerosis (ALS), despite a common immunohistological signature. Consistent extra-motor as well as motor cerebral, spinal anterior horn and distal neuromuscular junction pathology supports the notion of ALS a system failure. Establishing a disease biomarker is a priority but a simplistic, coordinate-based approach to brain dysfunction using MRI is not tenable. Resting-state functional MRI reflects the organization of brain networks at the systems-level, and so changes in of motor functional connectivity were explored to determine their potential as the substrate for a biomarker signature. Intra- as well as inter-motor functional networks in the 0.03-0.06 Hz frequency band were derived from 40 patients and 30 healthy controls of similar age, and used as features for pattern detection, employing multiple kernel learning. This approach enabled an accurate classification of a group of patients that included a range of clinical sub-types. An average of 13 regions-of-interest were needed to reach peak discrimination. Subsequent analysis revealed that the alterations in motor functional connectivity were widespread, including regions not obviously clinically affected such as the cerebellum and basal ganglia. Complex network analysis showed that functional networks in ALS differ markedly in their topology, reflecting the underlying altered functional connectivity pattern seen in patients: 1) reduced connectivity of both the cortical and sub-cortical motor areas with non motor areas 2)reduced subcortical-cortical motor connectivity and 3) increased connectivity observed within sub-cortical motor networks. This type of analysis has potential to non-invasively define a biomarker signature at the systems-level. As the understanding of neurodegenerative disorders moves towards studying pre-symptomatic changes, there is potential for this type of approach to generate biomarkers for the testing of neuroprotective strategies.
| S-EPMC3877396 | biostudies-literature
Project description:MotivationTandem mass spectrometry provides the means to match mass spectrometry signal observations with the chemical entities that generated them. The technology produces signal spectra that contain information about the chemical dissociation pattern of a peptide that was forced to fragment using methods like collision-induced dissociation. The ability to predict these MS(2) signals and to understand this fragmentation process is important for sensitive high-throughput proteomics research.ResultsWe present a new tool called MS(2)PIP for predicting the intensity of the most important fragment ion signal peaks from a peptide sequence. MS(2)PIP pre-processes a large dataset with confident peptide-to-spectrum matches to facilitate data-driven model induction using a random forest regression learning algorithm. The intensity predictions of MS(2)PIP were evaluated on several independent evaluation sets and found to correlate significantly better with the observed fragment-ion intensities as compared with the current state-of-the-art PeptideART tool.AvailabilityMS(2)PIP code is available for both training and predicting at http://compomics.com/.
| S-EPMC5994937 | biostudies-literature
Project description:Reliable identification of molecular biomarkers is essential for accurate patient stratification. While state-of-the-art machine learning approaches for sample classification continue to push boundaries in terms of performance, most of these methods are not able to integrate different data types and lack generalization power, limiting their application in a clinical setting. Furthermore, many methods behave as black boxes, and we have very little understanding about the mechanisms that lead to the prediction. While opaqueness concerning machine behavior might not be a problem in deterministic domains, in health care, providing explanations about the molecular factors and phenotypes that are driving the classification is crucial to build trust in the performance of the predictive system. We propose Pathway-Induced Multiple Kernel Learning (PIMKL), a methodology to reliably classify samples that can also help gain insights into the molecular mechanisms that underlie the classification. PIMKL exploits prior knowledge in the form of a molecular interaction network and annotated gene sets, by optimizing a mixture of pathway-induced kernels using a Multiple Kernel Learning (MKL) algorithm, an approach that has demonstrated excellent performance in different machine learning applications. After optimizing the combination of kernels to predict a specific phenotype, the model provides a stable molecular signature that can be interpreted in the light of the ingested prior knowledge and that can be used in transfer learning tasks.
| S-EPMC6401099 | biostudies-literature
Project description:BackgroundRecently, as the research of microRNA (miRNA) continues, there are plenty of experimental evidences indicating that miRNA could be associated with various human complex diseases development and progression. Hence, it is necessary and urgent to pay more attentions to the relevant study of predicting diseases associated miRNAs, which may be helpful for effective prevention, diagnosis and treatment of human diseases. Especially, constructing computational methods to predict potential miRNA-disease associations is worthy of more studies because of the feasibility and effectivity.MethodsIn this work, we developed a novel computational model of multiple kernels learning-based Kronecker regularized least squares for MiRNA-disease association prediction (MKRMDA), which could reveal potential miRNA-disease associations by automatically optimizing the combination of multiple kernels for disease and miRNA.ResultsMKRMDA obtained AUCs of 0.9040 and 0.8446 in global and local leave-one-out cross validation, respectively. Meanwhile, MKRMDA achieved average AUCs of 0.8894 ± 0.0015 in fivefold cross validation. Furthermore, we conducted three different kinds of case studies on some important human cancers for further performance evaluation. In the case studies of colonic cancer, esophageal cancer and lymphoma based on known miRNA-disease associations in HMDDv2.0 database, 76, 94 and 88% of the corresponding top 50 predicted miRNAs were confirmed by experimental reports, respectively. In another two kinds of case studies for new diseases without any known associated miRNAs and diseases only with known associations in HMDDv1.0 database, the verified ratios of two different cancers were 88 and 94%, respectively.ConclusionsAll the results mentioned above adequately showed the reliable prediction ability of MKRMDA. We anticipated that MKRMDA could serve to facilitate further developments in the field and the follow-up investigations by biomedical researchers.
| S-EPMC5727873 | biostudies-literature
Project description:MS²PIP is a data-driven tool that accurately predicts peak intensities for a given peptide's fragmentation mass spectrum. Since the release of the MS²PIP web server in 2015, we have brought significant updates to both the tool and the web server. In addition to the original models for CID and HCD fragmentation, we have added specialized models for the TripleTOF 5600+ mass spectrometer, for TMT-labeled peptides, for iTRAQ-labeled peptides, and for iTRAQ-labeled phosphopeptides. Because the fragmentation pattern is heavily altered in each of these cases, these additional models greatly improve the prediction accuracy for their corresponding data types. We have also substantially reduced the computational resources required to run MS²PIP, and have completely rebuilt the web server, which now allows predictions of up to 100 000 peptide sequences in a single request. The MS²PIP web server is freely available at https://iomics.ugent.be/ms2pip/.
| S-EPMC6602496 | biostudies-literature
Project description:Combining information from various image features has become a standard technique in concept recognition tasks. However, the optimal way of fusing the resulting kernel functions is usually unknown in practical applications. Multiple kernel learning (MKL) techniques allow to determine an optimal linear combination of such similarity matrices. Classical approaches to MKL promote sparse mixtures. Unfortunately, 1-norm regularized MKL variants are often observed to be outperformed by an unweighted sum kernel. The main contributions of this paper are the following: we apply a recently developed non-sparse MKL variant to state-of-the-art concept recognition tasks from the application domain of computer vision. We provide insights on benefits and limits of non-sparse MKL and compare it against its direct competitors, the sum-kernel SVM and sparse MKL. We report empirical results for the PASCAL VOC 2009 Classification and ImageCLEF2010 Photo Annotation challenge data sets. Data sets (kernel matrices) as well as further information are available at http://doc.ml.tu-berlin.de/image_mkl/(Accessed 2012 Jun 25).
| S-EPMC3427351 | biostudies-literature
Project description:BackgroundBreast cancer is one of the common kinds of cancer among women, and it ranks second among all cancers in terms of incidence, after lung cancer. Therefore, it is of great necessity to study the detection methods of breast cancer. Recent research has focused on using gene expression data to predict outcomes, and kernel methods have received a lot of attention regarding the cancer outcome evaluation. However, selecting the appropriate kernels and their parameters still needs further investigation.ResultsWe utilized heterogeneous kernels from a specific kernel set including the Hadamard, RBF and linear kernels. The mixed coefficients of the heterogeneous kernel were computed by solving the standard convex quadratic programming problem of the quadratic constraints. The algorithm is named the heterogeneous multiple kernel learning (HMKL). Using the particle swarm optimization (PSO) in HMKL, we selected the kernel parameters, then we employed HMKL to perform the breast cancer outcome evaluation. By testing real-world microarray datasets, the HMKL method outperforms the methods of the random forest, decision tree, GA with Rotation Forest, BFA?+?RF, SVM and MKL.ConclusionsOn one hand, HMKL is effective for the breast cancer evaluation and can be utilized by physicians to better understand the patient's condition. On the other hand, HMKL can choose the function and parameters of the kernel. At the same time, this study proves that the Hadamard kernel is effective in HMKL. We hope that HMKL could be applied as a new method to more actual problems.
| S-EPMC7181520 | biostudies-literature