Prediction Model of Hip Fragility Fracture Realistic Data From a Traumatology Department and Orthogeriatric Ward.

Prediction Model of Hip Fragility Fracture Using Explainable Artificial Intelligence and Realistic Data From a Traumatology Department and Orthogeriatric Ward

The aim of the project is to build a prediction model of hip fragility fracture using hospital data routinely collected in the traumatology department from the last 12 years and up to date Explainable Artificial Intelligence (XAI) tools. This model should be adapted to the "real world" conditions of the region and predict clinical data such as risk of fracture and refracture, mortality risk, fracture type classification and the generation of a specific comorbidity index.

Study Overview

• Status: Completed
• Conditions: Osteoporosis Risk; Fragility; Fracture of Femur
• Intervention / Treatment: Other: BLOOD SAMPLE

Detailed Description

Osteoporosis and associated fragility fractures remain an increasing worldwide burden for both health systems and families, in the context of ageing populations. Hip fractures are particularly severe due to the hospital stay, operations, arduous recovery and risk of subsequent fractures.

Thus, it is of significant importance to detect patients at high risk of femoral fragility fractures and to anticipate their recovery capacities in order to take appropriate medical decisions. Early detection of bone deterioration would be ideal for better prevention and bone reconstruction.

The current gold standard for osteoporosis remains the Dual-energy X-ray absorptiometry (DXA),however one the one hand, a majority of fractured patients are not classified as osteoporotic using the WMO definition and on the other hand, DXA is not widely available in numerous places.

Different alternative devices, such as 3D X-Rays, MRI or ultrasound, with different costs and availability, have been proposed. Moreover, online forms, such as FRAX, Garvan or Qfracture, propose to calculate the fracture risk from a limited number of clinical factors.

Nowadays, growing accessibility to clinical data, processing methods and computing power, opened the way to novel data driven prediction models using a large number of biomarkers or parameters, opening perspective towards personalised precision medicine. However a few challenges arise:

1. the data availability and quality to build the models,
2. the ability to collect realistic data from new patients in agreement with the cost and possibilities of each country and
3. the determination of the most important parameters in order to help medical decisions in an interpretable way.

The aim of the project is to build a prediction model of hip fragility fracture using available hospital data, routinely collected in the traumatology department and orthogeriatric ward from the last 12 years, data to be acquired of a control group (without fragility fracture) and up to date Explainable Artificial Intelligence (XAI) tools. This model should be adapted to the "real world" conditions of the region and predict clinical data such as risk of fracture and refracture, mortality risk, fracture type classification and the generation of a specific comorbidity index. Special attention will be given to potential early detectors of bone fragility.

Moreover, this model would later include alternative DXA measurements such as ultrasound, using a specific device successfully tested by the same team. It could also be afterwards compared to other countries or regions with similar available data, thanks to international colleagues currently collaborating with the team. In case of success, database format and prediction models could be shared with other hospitals with perspectives of progressive national and international scaling. In the near future this information could be translated into an informatics tool that could help the physician in his clinical following of the older patients.

• Study Type: Observational
• Enrollment (Actual): 50

Contacts and Locations

Study Locations

• Chile
  • Valparaíso, Chile
    • Universidad de Valparaiso

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Elderly population over 60 years old

Description

Inclusion Criteria:

• minimum 60 years

Exclusion Criteria:

• Hip fractures
• unable to walk from point of examination

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
CONTROL	Other: BLOOD SAMPLE; BLOOD ANALYTICS IN SEVERAL PARAMETERS
FRACTURA	Other: BLOOD SAMPLE; BLOOD ANALYTICS IN SEVERAL PARAMETERS

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Comparison between parameters intra-groups	Analysis of data extracted from blood samples comparing data in control and fractured group separatedly	2023-2024
Comparison between parameters inter-groups	Analysis of data extracted from blood samples comparing data in control and fractured groups	2023-2024

Collaborators and Investigators

• Sponsor: Universidad de Valparaiso
• Collaborators: HOSPITAL DOCTOR GUSTAVO FRICKE; Centro Interdisciplinario para el Desarrollo del Adulto Mayor Gerópolis

Study record dates

Study Major Dates

• Study Start (Actual): March 5, 2024
• Primary Completion (Actual): April 9, 2024
• Study Completion (Actual): April 9, 2024

Study Registration Dates

• First Submitted: August 5, 2024
• First Submitted That Met QC Criteria: August 7, 2024
• First Posted (Actual): August 9, 2024

Study Record Updates

• Last Update Posted (Actual): August 9, 2024
• Last Update Submitted That Met QC Criteria: August 7, 2024
• Last Verified: August 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Metabolic Diseases; Wounds and Injuries; Leg Injuries; Musculoskeletal Diseases; Bone Diseases; Bone Diseases, Metabolic; Femoral Fractures; Fractures, Bone; Osteoporosis
• Other Study ID Numbers: NAM23|0059

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No