Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data
<italic>Goal</italic>: Impulse control disorders (ICDs) are frequent non-motor symptoms occurring during the course of Parkinson’s disease (PD). The objective of this study was to estimate the predictability of the future occurrence of these disorders using longitudinal data,...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9783181/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849707644577644544 |
|---|---|
| author | Johann Faouzi Samir Bekadar Fanny Artaud Alexis Elbaz Graziella Mangone Olivier Colliot Jean-Christophe Corvol |
| author_facet | Johann Faouzi Samir Bekadar Fanny Artaud Alexis Elbaz Graziella Mangone Olivier Colliot Jean-Christophe Corvol |
| author_sort | Johann Faouzi |
| collection | DOAJ |
| description | <italic>Goal</italic>: Impulse control disorders (ICDs) are frequent non-motor symptoms occurring during the course of Parkinson’s disease (PD). The objective of this study was to estimate the predictability of the future occurrence of these disorders using longitudinal data, the first study using cross-validation and replication in an independent cohort. <italic>Methods:</italic> We used data from two longitudinal PD cohorts (training set: PPMI, Parkinson’s Progression Markers Initiative; test set: DIGPD, Drug Interaction With Genes in Parkinson’s Disease). We included 380 PD subjects from PPMI and 388 PD subjects from DIGPD, with at least two visits and with clinical and genetic data available, in our analyses. We trained three logistic regressions and a recurrent neural network to predict ICDs at the next visit using clinical risk factors and genetic variants previously associated with ICDs. We quantified performance using the area under the receiver operating characteristic curve (ROC AUC) and average precision. We compared these models to a trivial model predicting ICDs at the next visit with the status at the most recent visit. <italic>Results:</italic> The recurrent neural network (PPMI: 0.85 [0.80 – 0.90], DIGPD: 0.802 [0.78 – 0.83]) was the only model to be significantly better than the trivial model (PPMI: ROC AUC = 0.75 [0.69 – 0.81]; DIGPD: 0.78 [0.75 – 0.80]) on both cohorts. We showed that ICDs in PD can be predicted with better accuracy with a recurrent neural network model than a trivial model. The improvement in terms of ROC AUC was higher on PPMI than on DIGPD data, but not clinically relevant in both cohorts. <italic>Conclusions:</italic> Our results indicate that machine learning methods are potentially useful for predicting ICDs, but further works are required to reach clinical relevance. |
| format | Article |
| id | doaj-art-7cf12ec92d2848dab7e7da1815a3706e |
| institution | DOAJ |
| issn | 2644-1276 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-7cf12ec92d2848dab7e7da1815a3706e2025-08-20T03:15:51ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762022-01-0139610710.1109/OJEMB.2022.31782959783181Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic DataJohann Faouzi0https://orcid.org/0000-0003-0542-9968Samir Bekadar1Fanny Artaud2https://orcid.org/0000-0003-1899-8502Alexis Elbaz3https://orcid.org/0000-0001-9724-5490Graziella Mangone4Olivier Colliot5https://orcid.org/0000-0002-9836-654XJean-Christophe Corvol6https://orcid.org/0000-0001-7325-0199Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtriére, Paris, FranceDepartment of Neurology, Paris Brain Institute, Inserm, CNRS, Sorbonne Université, Assistance Publique Hôpitaux de Paris, Centre d’Investigation Clinique Neurosciences, Hôpital Pitié-Salpêtrière, Paris, FranceUniversité Paris-Saclay, UVSQ, Université Paris-Sud, Inserm, Gustave Roussy, Équipe “Exposome et Hérédité”, CESP, Villejuif, FranceUniversité Paris-Saclay, UVSQ, Université Paris-Sud, Inserm, Gustave Roussy, Équipe “Exposome et Hérédité”, CESP, Villejuif, FranceDepartment of Neurology, Paris Brain Institute, Inserm, CNRS, Sorbonne Université, Assistance Publique Hôpitaux de Paris, Centre d’Investigation Clinique Neurosciences, Hôpital Pitié-Salpêtrière, Paris, FranceSorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtriére, Paris, FranceDepartment of Neurology, Paris Brain Institute, Inserm, CNRS, Sorbonne Université, Assistance Publique Hôpitaux de Paris, Centre d’Investigation Clinique Neurosciences, Hôpital Pitié-Salpêtrière, Paris, France<italic>Goal</italic>: Impulse control disorders (ICDs) are frequent non-motor symptoms occurring during the course of Parkinson’s disease (PD). The objective of this study was to estimate the predictability of the future occurrence of these disorders using longitudinal data, the first study using cross-validation and replication in an independent cohort. <italic>Methods:</italic> We used data from two longitudinal PD cohorts (training set: PPMI, Parkinson’s Progression Markers Initiative; test set: DIGPD, Drug Interaction With Genes in Parkinson’s Disease). We included 380 PD subjects from PPMI and 388 PD subjects from DIGPD, with at least two visits and with clinical and genetic data available, in our analyses. We trained three logistic regressions and a recurrent neural network to predict ICDs at the next visit using clinical risk factors and genetic variants previously associated with ICDs. We quantified performance using the area under the receiver operating characteristic curve (ROC AUC) and average precision. We compared these models to a trivial model predicting ICDs at the next visit with the status at the most recent visit. <italic>Results:</italic> The recurrent neural network (PPMI: 0.85 [0.80 – 0.90], DIGPD: 0.802 [0.78 – 0.83]) was the only model to be significantly better than the trivial model (PPMI: ROC AUC = 0.75 [0.69 – 0.81]; DIGPD: 0.78 [0.75 – 0.80]) on both cohorts. We showed that ICDs in PD can be predicted with better accuracy with a recurrent neural network model than a trivial model. The improvement in terms of ROC AUC was higher on PPMI than on DIGPD data, but not clinically relevant in both cohorts. <italic>Conclusions:</italic> Our results indicate that machine learning methods are potentially useful for predicting ICDs, but further works are required to reach clinical relevance.https://ieeexplore.ieee.org/document/9783181/Impulse control disordersmachine learningParkinson’s diseaseprecision medicine |
| spellingShingle | Johann Faouzi Samir Bekadar Fanny Artaud Alexis Elbaz Graziella Mangone Olivier Colliot Jean-Christophe Corvol Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data IEEE Open Journal of Engineering in Medicine and Biology Impulse control disorders machine learning Parkinson’s disease precision medicine |
| title | Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data |
| title_full | Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data |
| title_fullStr | Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data |
| title_full_unstemmed | Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data |
| title_short | Machine Learning-Based Prediction of Impulse Control Disorders in Parkinson’s Disease From Clinical and Genetic Data |
| title_sort | machine learning based prediction of impulse control disorders in parkinson x2019 s disease from clinical and genetic data |
| topic | Impulse control disorders machine learning Parkinson’s disease precision medicine |
| url | https://ieeexplore.ieee.org/document/9783181/ |
| work_keys_str_mv | AT johannfaouzi machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT samirbekadar machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT fannyartaud machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT alexiselbaz machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT graziellamangone machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT oliviercolliot machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata AT jeanchristophecorvol machinelearningbasedpredictionofimpulsecontroldisordersinparkinsonx2019sdiseasefromclinicalandgeneticdata |