Dataset Information

Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis.

ABSTRACT:

Background

Osteoporosis is an asymptomatic disease of high prevalence and incidence, leading to bone fractures burdened by high mortality and disability, mainly when several subsequent fractures occur. A fragility fracture predictive model, Artificial Intelligence-based, to identify dual X-ray absorptiometry (DXA) variables able to characterise those patients who are prone to further fractures called Bone Strain Index, was evaluated in this study.

Methods

In a prospective, longitudinal, multicentric study 172 female outpatients with at least one vertebral fracture at the first observation were enrolled. They performed a spine X-ray to calculate spine deformity index (SDI) and a lumbar and femoral DXA scan to assess bone mineral density (BMD) and bone strain index (BSI) at baseline and after a follow-up period of 3 years in average. At the end of the follow-up, 93 women developed a further vertebral fracture. The further vertebral fracture was considered as one unit increase of SDI. We assessed the predictive capacity of supervised Artificial Neural Networks (ANNs) to distinguish women who developed a further fracture from those without it, and to detect those variables providing the maximal amount of relevant information to discriminate the two groups. ANNs choose appropriate input data automatically (TWIST-system, Training With Input Selection and Testing). Moreover, we built a semantic connectivity map usingthe Auto Contractive Map to provide further insights about the convoluted connections between the osteoporotic variables under consideration and the two scenarios (further fracture vs no further fracture).

Results

TWIST system selected 5 out of 13 available variables: age, menopause age, BMI, FTot BMC, FTot BSI. With training testing procedure, ANNs reached predictive accuracy of 79.36%, with a sensitivity of 75% and a specificity of 83.72%. The semantic connectivity map highlighted the role of BSI in predicting the risk of a further fracture.

Conclusions

Artificial Intelligence is a useful method to analyse a complex system like that regarding osteoporosis, able to identify patients prone to a further fragility fracture. BSI appears to be a useful DXA index in identifying those patients who are at risk of further vertebral fractures.

SUBMITTER: Ulivieri FM

PROVIDER: S-EPMC7870050 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis.

Ulivieri Fabio Massimo FM Rinaudo Luca L Piodi Luca Petruccio LP Messina Carmelo C Sconfienza Luca Maria LM Sardanelli Francesco F Guglielmi Giuseppe G Grossi Enzo E

PloS one 20210208 2

<h4>Background</h4>Osteoporosis is an asymptomatic disease of high prevalence and incidence, leading to bone fractures burdened by high mortality and disability, mainly when several subsequent fractures occur. A fragility fracture predictive model, Artificial Intelligence-based, to identify dual X-ray absorptiometry (DXA) variables able to characterise those patients who are prone to further fractures called Bone Strain Index, was evaluated in this study.<h4>Methods</h4>In a prospective, longitu ...[more]

PMID: 33556061

Similar Datasets

Project description:BackgroundFor osteoporotic fractures in men (MrOS) and in women (MsOS) (Hong Kong) baseline (BL) study, Chinese men and women ≥65 years were recruited during 2001 to 2003. This study presents the year-18 follow-up (FU) results. We were particularly interested in whether women with 'minimal' grade osteoporotic-like vertebral fracture (OLVF) of <20% height loss have an increased vertebral fracture (VF) risk than those without BL OLVF.MethodsAt year-18 FU, spine radiography was performed on 144 males (mean: 87.4±3.1 years) and 156 females (mean: 87.0±3.2 years). OLVF classification included no OLVF (grade 0), and OLVFs with <20%, ≥20-25%, ≥25%-1/3, ≥1/3-40%, ≥40%-2/3, ≥2/3 height loss (grades 1-6). With an existing OLVF, a further height loss of ≥15% was an OLVF progression. A new incident OLVF was a change from grade 0 to ≥ grade 2 or to grade 1 with the appearance of endplate and/or cortex fracture (ECF) during FU. Both OLVF progression and incident OLVF were considered incident VF. Acquired short vertebra (aSV) was defined as with decreased vertebral anterior and middle heights, while without anterior wedging and bi-concave changes, and only those with at least two adjacent aSVs were recorded as aSV cases.ResultsFor subjects without BL OLVF, 12.5% of the males and 27.1% of the females had incident VF. For subjects with BL OLVF of ≥20% height loss, males' and females' incident VF rate were 20% and 66.7% respectively. Females subjects with BL minimal OLVF, while all without radiographic ECF, had an incident VF rate of 59.3% during the FU. For males with and without aSV, 11.8% and 15% have incident fracture of other vertebrae. For females with and without aSV, 35.3% and 34.5% have incident fracture of other vertebrae. Recovery from minimal or mild grades OLVF to normal shape was observed in a number of cases.ConclusionsOLVF with less than 20% height loss is associated with increased VF risk in older females, but not in older males. Acquired short vertebra (SV) is not associated with increased incident fracture risk for other vertebrae, both for females and males. OLVF among older subjects can repair and heal.

Dataset Information

Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis.

Background

Methods

Results

Conclusions

Publications

Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets