Project

Back to overview

Towards semi-personalized (cluster) medicine with the optimal osteoporotic fracture prediction: artificial intelligence- or current human- based models? The OsteoLaus Project

English title Towards semi-personalized (cluster) medicine with the optimal osteoporotic fracture prediction: artificial intelligence- or current human- based models? The OsteoLaus Project
Applicant Didier Hans
Number 188886
Funding scheme Project funding (Div. I-III)
Research institution Département de l'Appareil Locomoteur - DAL Centre Hospital Universitaire Vaudois - CHUV
Institution of higher education University of Lausanne - LA
Main discipline Methods of Epidemiology and Preventive Medicine
Start/End 01.10.2019 - 30.09.2023
Approved amount 904'000.00
Show all

All Disciplines (4)

Discipline
Methods of Epidemiology and Preventive Medicine
Diseases of Bones and Joints
Metabolic Disorders
Biomedical Engineering

Keywords (10)

Cost effectiveness; Body composition; Fracture prediction; Bone microarchitecture; Frailty; Osteoporosis; Bone density; Artificial intelligence; Sarcopenia; Machine learning

Lay Summary (French)

Lead
L’ostéoporose est un problème majeur de santé publique qui deviendra encore plus important dans les prochaines décennies avec le vieillissement de la population, ce qui est particulièrement vrai pour la Suisse. Les conséquences cliniques de l`ostéoporose sont les fractures de fragilité, associées à une augmentation significative des décès et des placements en établissement médico-social. Malgré les efforts continus déployés pour améliorer l’évaluation du risque de fracture, les outils actuels ne permettent pas de prédire plus de 30-50% d’entre elles.
Lay summary

Notre objectif est (i) de réaliser le suivi à 10 ans d’OsteoLaus qui est la seule étude prospective Suisse de femmes ménopausées de cette durée et avec autant de données; (ii) d’étudier la gestion actuelle de l’ostéoporose par les médecins en Suisse, l’incidence des fractures et leurs associations avec des paramètres cliniques, biologiques, issus de l’imagerie par DXA (ex. densité osseuse, micro- and macro-architecture, composition corporelle totale et segmentaire), et de la génétique; (iii) d’explorer des paramètres qui pourraient représenter de bons et nouveaux prédicateurs de la fracture en utilisant des approches par l’intelligence artificielle (IA – supervisée, non supervisée,…); (iv) de comparer le rapport coût-efficacité de la gestion actuelle avec celles suggérées par les approches avec l’IA ; (v) de définir des groupes de patientes qui devraient être gérées différemment selon leurs profils de risque. Par exemple, contrairement à ce qui se fait aujourd’hui, deux femmes présentant un risque fracturaire identique ne devraient pas être traitées de la même manière ; en effet, le choix du traitement devrait dépendre des causes. Traiter les patientes en fonction des causes des risques accrus de fracture permettrait une approche plus personnalisée de la prise en charge de l’ostéoporose.

Ce projet, à notre connaissance le premier du genre dans le domaine de l’ostéoporose, permettra une forte collaboration interdisciplinaire entre médecins, physiciens, mathématicien-informaticiens et économistes pour offrir des solutions à un problème de santé publique majeur. Il permettra de développer une approche novatrice de l’évaluation du risque de fracture et d’améliorer la gestion de l’ostéoporose en intégrant une approche plus personnalisée.

Direct link to Lay Summary Last update: 07.10.2019

Responsible applicant and co-applicants

Employees

Name Institute

Project partner

Associated projects

Number Title Start Funding scheme
156978 Development of an adjustment factor of the ten year probability of fracture (FRAX®) based on an independent bone texture parameter (Trabecular Bone Score) to enhance the detection of patient at risk of fracture: The FRAXOS study 01.11.2014 Project funding (special)
122661 Cardiovascular diseases and psychiatric disorders in the general population: a prospective follow-up study 01.01.2009 Cohort Studies Large

Abstract

Osteoporosis is a major public health issue expected to become even more important in the next decades with population aging, which is specifically truer for Switzerland. Clinical consequences of osteoporosis are fragility fractures. Hip fractures are the most serious, associated with a significant increase in death and institutionalization. Although much effort has been made in recent years to improve fracture risk detection and patient management, we are still missing about 30-50% of atraumatic fractures, and are lacking a more precise individual information to better manage patients.OsteoLaus, a population-based cohort of Swiss postmenopausal women, is by far the only Swiss study with comprehensive data on bone health. Its continuation up to a follow-up period of ten years is of major importance for the validation of the calibration (predicted versus observed) of the current used fracture prediction tool, FRAX, in the Swiss clinics. Moreover, the extension of the follow-up period enables us to study occurrences and associations with a greater power.Using two large population based cohort followed prospectively (OsteoLaus and Rotterdam cohorts totalizing more than 8,300 individuals), we aim at developing a new fracture model based on artificial intelligence (Machine learning - ML) for fracture prediction. This model will include the best fracture predicting variables (chosen from more than 600 parameters available in both studies) with the hypothesis that it will upgrade fracture prediction to a more specific and complex-but-sophisticated level. The ML approach we are suggesting to use will `teach` us which individual`s risk factors profile corresponds to a certain risk profile. In this way, individuals will be clustered based on their risk profile as defined by their risk factors; and therefore be managed/treated based on their profile. Given the economic and social burden of fractures and their incidence, it is a need in the field to provide information on the cost effectiveness (CE) of any suggestive method/tool to be included in the osteoporosis management. Therefore, we will compare the newest AI approach with the most currently used fracture model (FRAX) in terms of clinical costs, personal costs and cost effectiveness performance. In this way, we can provide a full information and decision-making strategy for the actual implementation of our results in clinical practice. Finally, hypothesizing that the ML derived model would be the most cost effective approach, we will categorize individuals in different clusters based on their risk profile as defined by their risk factors. For instance, we claim that two women with an apparent equal level of fracture risk may not be treated similarly as their treatment should depend on the causes of their risk (e.g. normal bone quantity but an impaired bone structure and unhealthy lifestyle or impaired bone parameters but with a healthy lifestyle - both give the same risk of fracture). Treating our patients based on where the causes for their increased fracture risk lie, would bring osteoporosis management a step closer to a more personalized approach in its management.This project, the first of its kind in the osteoporosis field, will enable a strong interdisciplinary collaboration between doctors, physicists, and statisticians directed towards a major public health problem. It will elaborate on an advanced direction of fracture risk assessment and holds promise to improve the management of osteoporosis in general.
-