Validation of a one year fracture prediction tool for absolute hip fracture risk in long term care residents

Negm, Ahmed; Ioannidis, George; Jantzi, Micaela; Bucek, Jenn; Giangregorio, Lora; Pickard, Laura; Hirdes, John P.; Adachi, Jonathan D.; Richardson, Julie; Thabane, Lehana; Παπαϊωάννου, Αλεξάνδρα

doi:10.1186/s12877-018-1010-1

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20,21 Other hip fracture prediction models exist, including a Canadian model developed in MDS v2.0 including eight risk factors for fracture (C-index = 0.64-0.67). 32 The discrimination of these models is consistent with other commonly used clinical prediction tools, like Fracture Risk Assessment Tool (FRAX ® ), whose performance varies between C-indices of 0.60 and 0.69, depending on whether bone mineral density is available. 33 Approximately 2/5 of the FRIs in our study were non-hip fractures, yet 13 of the characteristics included in the INJURE-NH model are also included in FRAiL, and eight in the Canadian model.…”

Section: Discussionsupporting

confidence: 74%

“…Discrimination of FRAiL was good in women in the original sample (C‐index = 0.71), but was more modest when the model was used to predict non‐vertebral fractures (C‐index = 0.65) 20,21 . Other hip fracture prediction models exist, including a Canadian model developed in MDS v2.0 including eight risk factors for fracture (C‐index = 0.64–0.67) 32 . The discrimination of these models is consistent with other commonly used clinical prediction tools, like Fracture Risk Assessment Tool (FRAX®), whose performance varies between C‐indices of 0.60 and 0.69, depending on whether bone mineral density is available 33 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of the fall‐related injury risk in nursing homes (INJURE‐NH) prediction tool

Duprey

Zullo

Gouskova

et al. 2023

J American Geriatrics Society

View full text Add to dashboard Cite

Background Existing models to predict fall‐related injuries (FRI) in nursing homes (NH) focus on hip fractures, yet hip fractures comprise less than half of all FRIs. We developed and validated a series of models to predict the absolute risk of FRIs in NH residents. Methods Retrospective cohort study of long‐stay US NH residents (≥100 days in the same facility) between January 1, 2016 and December 31, 2017 (n = 733,427) using Medicare claims and Minimum Data Set v3.0 clinical assessments. Predictors of FRIs were selected through LASSO logistic regression in a 2/3 random derivation sample and tested in a 1/3 validation sample. Sub‐distribution hazard ratios (HR) and 95% confidence intervals (95% CI) were estimated for 6‐month and 2‐year follow‐up. Discrimination was evaluated via C‐statistic, and calibration compared the predicted rate of FRI to the observed rate. To develop a parsimonious clinical tool, we calculated a score using the five strongest predictors in the Fine‐Gray model. Model performance was repeated in the validation sample. Results Mean (Q1, Q3) age was 85.0 (77.5, 90.6) years and 69.6% were women. Within 2 years of follow‐up, 43,976 (6.0%) residents experienced ≥1 FRI. Seventy predictors were included in the model. The discrimination of the 2‐year prediction model was good (C‐index = 0.70), and the calibration was excellent. Calibration and discrimination of the 6‐month model were similar (C‐index = 0.71). In the clinical tool to predict 2‐year risk, the five characteristics included independence in activities of daily living (ADLs) (HR 2.27; 95% CI 2.14–2.41) and a history of non‐hip fracture (HR 2.02; 95% CI 1.94–2.12). Performance results were similar in the validation sample. Conclusions We developed and validated a series of risk prediction models that can identify NH residents at greatest risk for FRI. In NH, these models should help target preventive strategies.

show abstract

Section: Discussionsupporting

confidence: 74%

Section: Discussionmentioning

confidence: 99%

Development and validation of the fall‐related injury risk in nursing homes (INJURE‐NH) prediction tool

Duprey

Zullo

Gouskova

et al. 2023

J American Geriatrics Society

View full text Add to dashboard Cite

show abstract

“…Most baseline factors of geriatric HF patients between live and dead groups were significantly different, so it is possible to use baseline factors at the onset to predict the clinical prognosis of patients. Currently, several risk prediction tools have been constructed to predict the clinical prognosis of geriatric HF patients ( 17 , 19 – 21 ). However, all these prediction tools were constructed by typically performed univariate regression followed by multivariate logistic regression, resulting in reduced prediction accuracy.…”

Section: Discussionmentioning

confidence: 99%

A New Random Forest Algorithm-Based Prediction Model of Post-operative Mortality in Geriatric Patients With Hip Fractures

et al. 2022

View full text Add to dashboard Cite

BackgroundPost-operative mortality risk assessment for geriatric patients with hip fractures (HF) is a challenge for clinicians. Early identification of geriatric HF patients with a high risk of post-operative death is helpful for early intervention and improving clinical prognosis. However, a single significant risk factor of post-operative death cannot accurately predict the prognosis of geriatric HF patients. Therefore, our study aims to utilize a machine learning approach, random forest algorithm, to fabricate a prediction model for post-operative death of geriatric HF patients.MethodsThis retrospective study enrolled consecutive geriatric HF patients who underwent treatment for surgery. The study cohort was divided into training and testing datasets at a 70:30 ratio. The random forest algorithm selected or excluded variables according to the feature importance. Least absolute shrinkage and selection operator (Lasso) was utilized to compare feature selection results of random forest. The confirmed variables were used to create a simplified model instead of a full model with all variables. The prediction model was then verified in the training dataset and testing dataset. Additionally, a prediction model constructed by logistic regression was used as a control to evaluate the efficiency of the new prediction model.ResultsFeature selection by random forest algorithm and Lasso regression demonstrated that seven variables, including age, time from injury to surgery, chronic obstructive pulmonary disease (COPD), albumin, hemoglobin, history of malignancy, and perioperative blood transfusion, could be used to predict the 1-year post-operative mortality. The area under the curve (AUC) of the random forest algorithm-based prediction model in training and testing datasets were 1.000, and 0.813, respectively. While the prediction tool constructed by logistic regression in training and testing datasets were 0.895, and 0.797, respectively.ConclusionsCompared with logistic regression, the random forest algorithm-based prediction model exhibits better predictive ability for geriatric HF patients with a high risk of death within post-operative 1 year.

show abstract

“…It uses data readily available in the Resident Assessment Instrument Minimum Data Set (RAI-MDS 2.0), which is a comprehensive, standardized assessment that gathers a wide range of socio-demographic and clinical characteristics on admission and a quarterly basis thereafter. The FRS was developed using Ontario residents’ data from the RAI-MDS 2.0, the Discharge Abstract Database (DAD) and the National Ambulatory Care Reporting System (NACRS) and has been externally validated across several Canadian provinces [ 14 ]. The FRS can be easily implemented in LTC as it can be obtained from the interRAI-Long Term Care Facility assessment.…”

Section: Introductionmentioning

confidence: 99%

Hip fracture rate and osteoporosis treatment in Ontario: A population-based retrospective cohort study

AbuAlrob,

Ioannidis,

Jaglal

et al. 2024

Arch Osteoporos

Self Cite

View full text Add to dashboard Cite

Summary This population-based study analyzes hip fracture and osteoporosis treatment rates among older adults, stratified by place of residence prior to fracture. Hip fracture rates were higher among older adults living in the community and discharged to long-term care (LTC) after fracture, compared to LTC residents and older adults living in the community. Only 23% of LTC residents at high fracture risk received osteoporosis treatment. Purpose This population-based study examines hip fracture rate and osteoporosis management among long-term care (LTC) residents > 65 years of age compared to community-dwelling older adults at the time of fracture and admitted to LTC after fracture, in Ontario, Canada. Methods Healthcare utilization and administrative databases were linked using unique, encoded identifiers from the ICES Data Repository to estimate hip fractures (identified using the Public Health Agency of Canada algorithm and International Classification of Diseases (ICD)-10 codes) and osteoporosis management (pharmacotherapy) among adults > 66 years from April 1, 2014 to March 31, 2018. Sex-specific and age-standardized rates were compared by pre-fracture residency and discharge location (i.e., LTC to LTC, community to LTC, or community to community). Fracture risk was determined using the Fracture Risk Scale (FRS). Results At baseline (2014/15), the overall age-standardized hip fracture rate among LTC residents was 223 per 10,000 person-years (173 per 10,000 females and 157 per 10,000 males), 509 per 10,000 person-years (468 per 10,000 females and 320 per 10,000 males) among the community to LTC cohort, and 31.5 per 10,000 person-years (43.1 per 10,000 females and 25.6 per 10,000 males). During the 5-year observation period, the overall annual average percent change (APC) for hip fracture increased significantly in LTC (AAPC = + 8.6 (95% CI 5.0 to 12.3; p = 0.004) compared to the community to LTC group (AAPC = + 2.5 (95% CI − 3.0 to 8.2; p = 0.248)) and the community-to-community cohort (AAPC − 3.8 (95% CI − 6.7 to − 0.7; p = 030)). However, hip fracture rate remained higher in the community to LTC group over the study period. There were 33,594 LTC residents identified as high risk of fracture (FRS score 4 +), of which 7777 were on treatment (23.3%). Conclusion Overall, hip fracture rates have increased in LTC and among community-dwelling adults admitted to LTC after fracture. However, hip fracture rates among community-dwelling adults have decreased over time. A non-significant increase in osteoporosis treatment rates was observed among LTC residents at high risk of fracture (FRS4 +). Residents in LTC are at very high risk for fracture and require individualized based on goals of care and life expectancy.

show abstract

Validation of a one year fracture prediction tool for absolute hip fracture risk in long term care residents

Cited by 12 publications

References 34 publications

Development and validation of the fall‐related injury risk in nursing homes (INJURE‐NH) prediction tool

Development and validation of the fall‐related injury risk in nursing homes (INJURE‐NH) prediction tool

A New Random Forest Algorithm-Based Prediction Model of Post-operative Mortality in Geriatric Patients With Hip Fractures

Hip fracture rate and osteoporosis treatment in Ontario: A population-based retrospective cohort study

Contact Info

Product

Resources

About