Precision medicine and machine learning towards the prediction of the outcome of potential celiac disease
Abstract Potential Celiac Patients (PCD) bear the Celiac Disease (CD) genetic predisposition, a significant production of antihuman transglutaminase antibodies, but no morphological changes in the small bowel mucosa. A minority of patients (17%) showed clinical symptoms and need a gluten free diet a...
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/9c2e7dea48714cbaaf31114059d1a640 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Abstract Potential Celiac Patients (PCD) bear the Celiac Disease (CD) genetic predisposition, a significant production of antihuman transglutaminase antibodies, but no morphological changes in the small bowel mucosa. A minority of patients (17%) showed clinical symptoms and need a gluten free diet at time of diagnosis, while the majority progress over several years (up to a decade) without any clinical problem neither a progression of the small intestine mucosal damage even when they continued to assume gluten in their diet. Recently we developed a traditional multivariate approach to predict the natural history, on the base of the information at enrolment (time 0) by a discriminant analysis model. Still, the traditional multivariate model requires stringent assumptions that may not be answered in the clinical setting. Starting from a follow-up dataset available for PCD, we propose the application of Machine Learning (ML) methodologies to extend the analysis on available clinical data and to detect most influent features predicting the outcome. These features, collected at time of diagnosis, should be capable to classify patients who will develop duodenal atrophy from those who will remain potential. Four ML methods were adopted to select features predictive of the outcome; the feature selection procedure was indeed capable to reduce the number of overall features from 85 to 19. ML methodologies (Random Forests, Extremely Randomized Trees, and Boosted Trees, Logistic Regression) were adopted, obtaining high values of accuracy: all report an accuracy above 75%. The specificity score was always more than 75% also, with two of the considered methods over 98%, while the best performance of sensitivity was 60%. The best model, optimized Boosted Trees, was able to classify PCD starting from the selected 19 features with an accuracy of 0.80, sensitivity of 0.58 and specificity of 0.84. Finally, with this work, we are able to categorize PCD patients that can more likely develop overt CD using ML. ML techniques appear to be an innovative approach to predict the outcome of PCD, since they provide a step forward in the direction of precision medicine aimed to customize healthcare, medical therapies, decisions, and practices tailoring the clinical management of PCD children. |
|---|