Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction
IntroductionHereditary transthyretin amyloidosis (ATTRv amyloidosis) is a rare neurological hereditary disease clinically characterized as severe, progressive, and life-threatening while the age of onset represents the moment in time when the first symptoms are felt. In this study, we present and di...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1216214/full |
| _version_ | 1797777902820917248 |
|---|---|
| author | Maria Pedroto Maria Pedroto Maria Pedroto Teresa Coelho Alípio Jorge Alípio Jorge João Mendes-Moreira João Mendes-Moreira |
| author_facet | Maria Pedroto Maria Pedroto Maria Pedroto Teresa Coelho Alípio Jorge Alípio Jorge João Mendes-Moreira João Mendes-Moreira |
| author_sort | Maria Pedroto |
| collection | DOAJ |
| description | IntroductionHereditary transthyretin amyloidosis (ATTRv amyloidosis) is a rare neurological hereditary disease clinically characterized as severe, progressive, and life-threatening while the age of onset represents the moment in time when the first symptoms are felt. In this study, we present and discuss our results on the study, development, and evaluation of an approach that allows for time-to-event prediction of the age of onset, while focusing on genealogical feature construction.Materials and methodsThis research was triggered by the need to answer the medical problem of when will an asymptomatic ATTRv patient show symptoms of the disease. To do so, we defined and studied the impact of 77 features (ranging from demographic and genealogical to familial disease history) we studied and compared a pool of prediction algorithms, namely, linear regression (LR), elastic net (EN), lasso (LA), ridge (RI), support vector machines (SV), decision tree (DT), random forest (RF), and XGboost (XG), both in a classification as well as a regression setting; we assembled a baseline (BL) which corresponds to the current medical knowledge of the disease; we studied the problem of predicting the age of onset of ATTRv patients; we assessed the viability of predicting age of onset on short term horizons, with a classification framing, on localized sets of patients (currently symptomatic and asymptomatic carriers, with and without genealogical information); and we compared the results with an out-of-bag evaluation set and assembled in a different time-frame than the original data in order to account for data leakage.ResultsCurrently, we observe that our approach outperforms the BL model, which follows a set of clinical heuristics and represents current medical practice. Overall, our results show the supremacy of SV and XG for both the prediction tasks although impacted by data characteristics, namely, the existence of missing values, complex data, and small-sized available inputs.DiscussionWith this study, we defined a predictive model approach capable to be well-understood by medical professionals, compared with the current practice, namely, the baseline approach (BL), and successfully showed the improvement achieved to the current medical knowledge. |
| first_indexed | 2024-03-12T23:11:11Z |
| format | Article |
| id | doaj.art-0b5687cc1e2c4792adafab3c5022f292 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-03-12T23:11:11Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-0b5687cc1e2c4792adafab3c5022f2922023-07-18T02:54:59ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-07-011410.3389/fneur.2023.12162141216214Clinical model for Hereditary Transthyretin Amyloidosis age of onset predictionMaria Pedroto0Maria Pedroto1Maria Pedroto2Teresa Coelho3Alípio Jorge4Alípio Jorge5João Mendes-Moreira6João Mendes-Moreira7Laboratory of Artificial Intelligence and Decision Support (LIAAD), Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, PortugalDepartment of Computer Science (DCC), Faculty of Sciences (FCUP), University of Porto, Porto, PortugalDepartment of Informatics Engineering (DEI), Faculty of Engineering (FEUP), University of Porto, Porto, PortugalUnidade Corino de Andrade, Centro Hospitalar Universitário de Santo António, Porto, PortugalLaboratory of Artificial Intelligence and Decision Support (LIAAD), Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, PortugalDepartment of Computer Science (DCC), Faculty of Sciences (FCUP), University of Porto, Porto, PortugalLaboratory of Artificial Intelligence and Decision Support (LIAAD), Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, PortugalDepartment of Informatics Engineering (DEI), Faculty of Engineering (FEUP), University of Porto, Porto, PortugalIntroductionHereditary transthyretin amyloidosis (ATTRv amyloidosis) is a rare neurological hereditary disease clinically characterized as severe, progressive, and life-threatening while the age of onset represents the moment in time when the first symptoms are felt. In this study, we present and discuss our results on the study, development, and evaluation of an approach that allows for time-to-event prediction of the age of onset, while focusing on genealogical feature construction.Materials and methodsThis research was triggered by the need to answer the medical problem of when will an asymptomatic ATTRv patient show symptoms of the disease. To do so, we defined and studied the impact of 77 features (ranging from demographic and genealogical to familial disease history) we studied and compared a pool of prediction algorithms, namely, linear regression (LR), elastic net (EN), lasso (LA), ridge (RI), support vector machines (SV), decision tree (DT), random forest (RF), and XGboost (XG), both in a classification as well as a regression setting; we assembled a baseline (BL) which corresponds to the current medical knowledge of the disease; we studied the problem of predicting the age of onset of ATTRv patients; we assessed the viability of predicting age of onset on short term horizons, with a classification framing, on localized sets of patients (currently symptomatic and asymptomatic carriers, with and without genealogical information); and we compared the results with an out-of-bag evaluation set and assembled in a different time-frame than the original data in order to account for data leakage.ResultsCurrently, we observe that our approach outperforms the BL model, which follows a set of clinical heuristics and represents current medical practice. Overall, our results show the supremacy of SV and XG for both the prediction tasks although impacted by data characteristics, namely, the existence of missing values, complex data, and small-sized available inputs.DiscussionWith this study, we defined a predictive model approach capable to be well-understood by medical professionals, compared with the current practice, namely, the baseline approach (BL), and successfully showed the improvement achieved to the current medical knowledge.https://www.frontiersin.org/articles/10.3389/fneur.2023.1216214/fullATTRv amyloidosisfeature constructiongenealogical featuresonset predictionregression data modeling |
| spellingShingle | Maria Pedroto Maria Pedroto Maria Pedroto Teresa Coelho Alípio Jorge Alípio Jorge João Mendes-Moreira João Mendes-Moreira Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction Frontiers in Neurology ATTRv amyloidosis feature construction genealogical features onset prediction regression data modeling |
| title | Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction |
| title_full | Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction |
| title_fullStr | Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction |
| title_full_unstemmed | Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction |
| title_short | Clinical model for Hereditary Transthyretin Amyloidosis age of onset prediction |
| title_sort | clinical model for hereditary transthyretin amyloidosis age of onset prediction |
| topic | ATTRv amyloidosis feature construction genealogical features onset prediction regression data modeling |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1216214/full |
| work_keys_str_mv | AT mariapedroto clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT mariapedroto clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT mariapedroto clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT teresacoelho clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT alipiojorge clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT alipiojorge clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT joaomendesmoreira clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction AT joaomendesmoreira clinicalmodelforhereditarytransthyretinamyloidosisageofonsetprediction |