Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis
Abstract 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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-024-02484-5 |
| _version_ | 1797247211187208192 |
|---|---|
| author | Fabiano Papaiz Mario Emílio Teixeira Dourado Ricardo Alexsandro de Medeiros Valentim Rafael Pinto Antônio Higor Freire de Morais Joel Perdiz Arrais |
| author_facet | Fabiano Papaiz Mario Emílio Teixeira Dourado Ricardo Alexsandro de Medeiros Valentim Rafael Pinto Antônio Higor Freire de Morais Joel Perdiz Arrais |
| author_sort | Fabiano Papaiz |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-04-24T19:55:05Z |
| format | Article |
| id | doaj.art-8ad0b42f3a8d474b8aac201739980126 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-24T19:55:05Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-8ad0b42f3a8d474b8aac2017399801262024-03-24T12:22:50ZengBMCBMC Medical Informatics and Decision Making1472-69472024-03-0124111410.1186/s12911-024-02484-5Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosisFabiano Papaiz0Mario Emílio Teixeira Dourado1Ricardo Alexsandro de Medeiros Valentim2Rafael Pinto3Antônio Higor Freire de Morais4Joel Perdiz Arrais5Federal University of Rio Grande Do NorteFederal University of Rio Grande Do NorteFederal University of Rio Grande Do NorteFederal University of Rio Grande Do NorteFederal Institute of Rio Grande Do NorteUniversity of CoimbraAbstract 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.https://doi.org/10.1186/s12911-024-02484-5Amyotrophic lateral sclerosisPrognosisMachine learningHealth informatics |
| spellingShingle | Fabiano Papaiz Mario Emílio Teixeira Dourado Ricardo Alexsandro de Medeiros Valentim Rafael Pinto Antônio Higor Freire de Morais Joel Perdiz Arrais Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis BMC Medical Informatics and Decision Making Amyotrophic lateral sclerosis Prognosis Machine learning Health informatics |
| title | Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis |
| title_full | Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis |
| title_fullStr | Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis |
| title_full_unstemmed | Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis |
| title_short | Ensemble-imbalance-based classification for amyotrophic lateral sclerosis prognostic prediction: identifying short-survival patients at diagnosis |
| title_sort | ensemble imbalance based classification for amyotrophic lateral sclerosis prognostic prediction identifying short survival patients at diagnosis |
| topic | Amyotrophic lateral sclerosis Prognosis Machine learning Health informatics |
| url | https://doi.org/10.1186/s12911-024-02484-5 |
| work_keys_str_mv | AT fabianopapaiz ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis AT marioemilioteixeiradourado ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis AT ricardoalexsandrodemedeirosvalentim ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis AT rafaelpinto ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis AT antoniohigorfreiredemorais ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis AT joelperdizarrais ensembleimbalancebasedclassificationforamyotrophiclateralsclerosisprognosticpredictionidentifyingshortsurvivalpatientsatdiagnosis |