Osteoporosis Risk Assessment with Well-Calibrated Probabilistic Outputs

Abstract : Osteoporosis is a disease of bones that results in an increased risk of bone fracture. The diagnosis of Osteoporosis is usually performed by measuring the Bone Mineral Density (BMD) using Dual-Energy X-ray Absorptiometry (DEXA) scanning. In this work, we introduce the use of Venn Prediction in order to assess the risk of Osteoporosis before a DEXA scan, based on known risk factors. Unlike other probabilistic methods, Venn Predictors can provide well-calibrated probabilistic outputs under the assumption that the data used are identically and independently distributed (i.i.d.). Our contribution is two-fold: Firstly, we have collected real-world data from various clinic centres in Cyprus which based on their locality can be used for analysis of Osteoporosis risk factors specifically for Cypriot patients. To the best of our knowledge, local data in Cyprus for Osteoporosis risk assessment have not been collected before. Secondary, our results demonstrate that our method can provide probabilistic outputs that may be practical and trustful to physicians.
Type de document :
Communication dans un congrès
Harris Papadopoulos; Andreas S. Andreou; Lazaros Iliadis; Ilias Maglogiannis. 9th Artificial Intelligence Applications and Innovations (AIAI), Sep 2013, Paphos, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-412, pp.432-441, 2013, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-41142-7_44〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01459680
Contributeur : Hal Ifip <>
Soumis le : mardi 7 février 2017 - 13:19:53
Dernière modification le : vendredi 1 décembre 2017 - 01:16:33
Document(s) archivé(s) le : lundi 8 mai 2017 - 14:13:53

Fichier

978-3-642-41142-7_44_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Antonis Lambrou, Harris Papadopoulos, Alexander Gammerman. Osteoporosis Risk Assessment with Well-Calibrated Probabilistic Outputs. Harris Papadopoulos; Andreas S. Andreou; Lazaros Iliadis; Ilias Maglogiannis. 9th Artificial Intelligence Applications and Innovations (AIAI), Sep 2013, Paphos, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-412, pp.432-441, 2013, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-41142-7_44〉. 〈hal-01459680〉

Partager

Métriques

Consultations de la notice

68

Téléchargements de fichiers

93