Unravelling Disease Presentation Patterns in ALS Using Biclustering for Discriminative Meta-Features Discovery

Matos, Joana M.; Pires, Sofia; Aidos, Helena; Gromicho, Marta; Pinto, Susana; Carvalho, Mamede de; Madeira, Sara C.

doi:10.1007/978-3-030-45385-5_46

Cited by 7 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…16 After discovering the biclusters for a group of subjects, a data matrix can be obtained locating the presence of some bicluster in a subject, and then used for classification tasks. The biclusters (sets of features and corresponding representative values) are used as features (Figure adapted from [ 112 ]) …”

Section: Discussionmentioning

confidence: 99%

“…In these approaches, the biclustering algorithm CCC was used. Matos et al [ 112 ] used the BicPAM biclustering algorithm to analyze non-temporal data, together with the concept of meta-biclusters to characterize amyotrophic lateral sclerosis patients. Recently, Henriques and Madeira [ 114 ] showed that the use of biclustering based classification improves the performance of state-of-the-art classifiers.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Biclustering fMRI time series: a comparative study

2022

Self Cite

View full text Add to dashboard Cite

Background The effectiveness of biclustering, simultaneous clustering of rows and columns in a data matrix, was shown in gene expression data analysis. Several researchers recognize its potentialities in other research areas. Nevertheless, the last two decades have witnessed the development of a significant number of biclustering algorithms targeting gene expression data analysis and a lack of consistent studies exploring the capacities of biclustering outside this traditional application domain. Results This work evaluates the potential use of biclustering in fMRI time series data, targeting the Region × Time dimensions by comparing seven state-in-the-art biclustering and three traditional clustering algorithms on artificial and real data. It further proposes a methodology for biclustering evaluation beyond gene expression data analysis. The results discuss the use of different search strategies in both artificial and real fMRI time series showed the superiority of exhaustive biclustering approaches, obtaining the most homogeneous biclusters. However, their high computational costs are a challenge, and further work is needed for the efficient use of biclustering in fMRI data analysis. Conclusions This work pinpoints avenues for the use of biclustering in spatio-temporal data analysis, in particular neurosciences applications. The proposed evaluation methodology showed evidence of the effectiveness of biclustering in finding local patterns in fMRI time series data. Further work is needed regarding scalability to promote the application in real scenarios.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Biclustering fMRI time series: a comparative study

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…ALS disease presents an inherent complexity, and future work can extend our approach by employing clustering methods to find groups of patients with correlated clinical features and, thus, develop more effective models based on the clusters identified. We can cite FCAN-MOPSO [23] and Biclustering [24] as examples of such methods.…”

Section: Data Preprocessingmentioning

confidence: 99%

Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis

Papaiz,

Dourado,

de Medeiros Valentim

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Prognosticating Amyotrophic Lateral Sclerosis (ALS) presents a formidable challenge due to patients exhibiting different onset sites, progression rates, and survival times. In this study, we have developed and evaluated Machine Learning (ML) algorithms that integrate Ensemble and Imbalance Learning techniques to classify patients into Short and Non-Short survival groups based on data collected during diagnosis. We aimed to identify individuals at high risk of mortality within 24 months of symptom onset through analysis of patient data commonly encountered in daily clinical practice. Our Ensemble-Imbalance approach underwent evaluation employing six ML algorithms as base classifiers. Remarkably, our results outperformed those of individual algorithms, achieving a Balanced Accuracy of 88% and a Sensitivity of 96%. Additionally, we used the Shapley Additive Explanations framework to elucidate the decision-making process of the top-performing model, pinpointing the most important features and their correlations with the target prediction. Furthermore, we presented helpful tools to visualize and compare patient similarities, offering valuable insights. Confirming the obtained results, our approach could aid physicians in devising personalized treatment plans at the time of diagnosis or serve as an inclusion/exclusion criterion in clinical trials.

show abstract

“…Based on this large dataset, several papers were published so far, describing the influence of environment and lifestyle factors on ALS onset and progression (Kuraszkiewicz et al 2018;Korner et al 2019), risk factors for polyneuropathy in ALS (de Carvalho et al 2020), the patterns of disease presentation (Prell et al 2020;Gromicho et al 2020;Gromicho et al 2021;Matos et al 2020), diagnostic pathway of ALS patients (Campos et al 2021(Campos et al , 2023, the rate of disease progression (Prell, 2020;Barc et al 2020), the possible biomarkers (Hertel et al 2022), the impact of comorbidities (Diekmann et al 2020;Pereira et al 2021), the predictive impact of C9Orf72 mutation in respiratory decline (Miltenberger-Miltenyi et al 2019), family history of neurodegenerative diseases (Campos et al, 2020), influence of ALS on fertility (Uysal et al 2021), association of the contact sports with ALS (Henriques et al 2023), as well as potential predictive measures (Kuraszkiewicz et al 2020). METHONTOLOGY (Fernández-López et al 1997) is a method of ontology building that is grounded in software engineering methodologies.…”

Section: Ontology-based Web Database For Understanding Als (Onwebduals)mentioning

confidence: 99%

DALSO: domain ALS ontology

Podsiadły-Marczykowska,

Andersen,

Gromicho

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Amyotrophic lateral sclerosis (ALS) is an incurable, rapidly progressive neurodegenerative disease. During the course of ALS, virtually all skeletal muscles are gradually affected, including the respiratory muscles, and the disease is usually fatal within 2–5 years of symptom onset. Unequivocal and conclusive tests for ALS do not exist, its disease etiology is still unknown, and therapeutic options are limited. This paper presents the ALS domain ontology (DALSO), model containing formalized, semantic descriptions of a wide range of modeled disease related notions such as patient demographics, clinical findings and history, disease clinical features and diagnostic classifications, risk factors, genetics and pathophysiological mechanisms of motor neuron degeneration. The DALSO’s aim and information scope, design assumption, structure and implementation details are also described. DALSO covers the broad range of significant biomedical concepts ranging from clinical to molecular feature of the modeled disease, it represents a comprehensive, structured knowledge source for the ALS disease domain. To the best of authors’ knowledge, the DALSO is the first attempt to develop a formal, computational model representing knowledge of this fatal motor neuron disease. It provides the means for integrating and annotating clinical and research data, not only at the generic domain knowledge level, but also at the level of individual patient case studies. The DALSO is expressed in OWL2 language, contains 910 classes, is consistent and free of logical errors. Its syntactic correctness was validated by the Fact++ reasoner.

show abstract

Unravelling Disease Presentation Patterns in ALS Using Biclustering for Discriminative Meta-Features Discovery

Cited by 7 publications

References 18 publications

Biclustering fMRI time series: a comparative study

Biclustering fMRI time series: a comparative study

Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis

DALSO: domain ALS ontology

Contact Info

Product

Resources

About