Validation of the Nottingham Hip Fracture Score (NHFS) for the prediction of 30-day mortality in a Swedish cohort of hip fractures

Systematic review of multivariable prognostic models for outcomes at least 30 days after hip fracture finds 18 mortality models but no nonmortality models warranting validation

OBJECTIVES

Prognostic models have the potential to aid clinical decision-making after hip fracture. This systematic review aimed to identify, critically appraise, and summarize multivariable prediction models for mortality or other long-term recovery outcomes occurring at least 30 days after hip fracture.

STUDY DESIGN AND SETTING

MEDLINE, Embase, Scopus, Web of Science, and CINAHL databases were searched up to May 2023. Studies were included that aimed to develop multivariable models to make predictions for individuals at least 30 days after hip fracture. Risk of bias (ROB) was dual-assessed using the Prediction model Risk Of Bias ASsessment Tool. Study and model details were extracted and summarized.

RESULTS

From 5571 records, 80 eligible studies were identified. They predicted mortality in n = 55 studies/81 models and nonmortality outcomes (mobility, function, residence, medical, and surgical complications) in n = 30 studies/45 models. Most (n = 46; 58%) studies were published since 2020. A quarter of studies (n = 19; 24%) reported using 'machine-learning methods', while the remainder used logistic regression (n = 54; 68%) and other statistical methods (n = 11; 14%) to build models. Overall, 15 studies (19%) presented 18 low ROB models, all predicting mortality. Common concerns were sample size, missing data handling, inadequate internal validation, and calibration assessment. Many studies with nonmortality outcomes (n = 11; 37%) had clear data complexities that were not correctly modeled.

CONCLUSION

This review has comprehensively summarized and appraised multivariable prediction models for long-term outcomes after hip fracture. Only 15 studies of 55 predicting mortality were rated as low ROB, warranting further development of their models. All studies predicting nonmortality outcomes were high or unclear ROB. Careful consideration is required for both the methods used and justification for developing further nonmortality prediction models for this clinical population.

Using machine-learning to decode postoperative hip mortality Trends: Actionable insights from an extensive clinical dataset

BACKGROUND

Hip fractures are one of the most common injuries experienced by the general population. Despite advances in surgical techniques, postoperative mortality rates remain high. identifying relevant clinical factors associated with mortality is essential to preoperative risk stratification and tailored post-surgical interventions to improve patient outcomes. The purpose of this study aimed to identify preoperative risk factors and develop predictive models for increased hip fracture-related mortality within 30 days post-surgery, using one of the largest patient cohorts to date.

METHODS

Data from the American College of Surgeons National Surgical Quality Improvement Program database, comprising 107,660 hip fracture patients treated with surgical fixation was used. A penalized regression approach, least absolute shrinkage and selection operator was employed to develop two predictive models: one using preoperative factors and the second incorporating both preoperative and postoperative factors.

RESULTS

The analysis identified 68 preoperative factor outcomes associated with 30-day mortality. The combined model revealed 84 relevant factors, showing strong predictive power for determining postoperative mortality, with an AUC of 0.83.

CONCLUSIONS

The study's comprehensive methodology provides risk assessment tools for clinicians to identify high-risk patients and optimize patient-specific care.

Predictive Value of Machine Learning Models in Postoperative Mortality of Older Adults Patients with Hip Fracture: A Systematic Review and Meta-analysis

BACKGROUND

Some researchers have used machine learning to predict mortality in old patients with hip fracture, but its application value lacks an evidence-based basis. Hence, we conducted this meta-analysis to explore the predictive accuracy of machine learning for mortality in old patients with hip fracture.

METHODS

We systematically retrieved PubMed, Cochrane, Embase, and Web of Science for relevant studies published before July 15, 2022. The PROBAST assessment tool was used to assess the risk of bias in the included studies. A random-effects model was used for the meta-analysis of C-index, whereas a bivariate mixed-effects model was used for the meta-analysis of sensitivity and specificity. The meta-analysis was performed on R and Stata.

RESULTS

Eighteen studies were included, involving 8 machine learning models and 398,422 old patients undergoing hip joint surgery, of whom 60,457 died. According to the meta-analysis, the pooled C-index for machine learning models was 0.762 (95% CI: 0.691 ∼ 0.833) in the training set and 0.838 (95% CI: 0.783 ∼ 0.892) in the validation set, which is better than the C-index of the main clinical scale (Nottingham Hip Fracture Score), that is, 0.702 (95% CI: 0.681 ∼ 0.723). Among different machine learning models, ANN and Bayesian belief network had the best predictive performance.

CONCLUSION

Machine learning models are more accurate in predicting mortality in old patients after hip joint surgery than current mainstream clinical scoring systems. Subsequent research could focus on updating clinical scoring systems and improving their predictive performance by relying on machine learning models.

Risk scoring models for patients with proximal femur fractures: Qualitative systematic review assessing 30-day mortality and ease of use

BACKGROUND

Hip fractures are a common orthopaedic injury affecting a particularly frail and vulnerable patient cohort. They are at risk of many complications, including prolonged length of stay and mortality. Efforts to identify those at high risk may be beneficial. Over 25 risk prediction models are published for patients with hip fractures.

AIM

The primary aim of this study was to assess the performance of predictor scores in predicting 30-day mortality. The secondary aim was to assess the ease of use of these systems.

METHODS

A qualitative systematic review was performed. A search was conducted on online databases, including PubMed, CINAHL, Clinical Trials.gov, Cochrane, DARE, EMBASE, SCOPUS, and Web of Science.. The terms fragility hip fractures and risk prediction models were utilised while performing the search. These were then expanded using Boolean operators and similar terms. Search results were imported to Covidence. Primary observational studies using one or more hip fracture mortality prediction models and 30-day mortality as an outcome were included. Systematic reviews and studies on specific patient groups defined other medical conditions (e.g. COVID positive or dialysis patients) were excluded.

RESULTS

3,101 studies were screened following duplicate removal. 34 papers were included in the review, in which 23 scoring systems were reported. Six of these were pre-operative and reported in multiple studies. Most demonstrated appropriate fit and fair discrimination. Five of the six pre-operative scoring systems examined, displayed appropriate ease of use, allowing risk calculation at the time of admission.

CONCLUSION

Nottingham Hip Fracture Score remains the most extensive reported scoring system and performs fair overall with AUROCs of 0.64-0.80 and good fit in calibration across all studies. However, new systems utilise many similar predictors. There is a need for the standardisation of publications on scoring systems to allow further systematic review and meta-analyses.

Validation and updating of the Older Person's Emergency Risk Assessment (OPERA) score to predict outcomes for hip fracture patients

INTRODUCTION

Hip fractures are associated with significant morbidity and mortality in older people. Accurate risk stratification is important for planning of care, informed decision-making and communication with patients and relatives. The Older Persons' Emergency Risk Assessment (OPERA) score is a risk stratification score for older people admitted to hospital. Our aims were to validate OPERA in hip fracture patients, update the score and compare performance with the Nottingham Hip Fracture Score (NHFS).

METHODS

This dual-centre 3-year observational study (2016-2018) included acutely admitted hip fracture patients managed surgically aged ⩾65 years. The primary outcome was 30-day mortality. Secondary outcomes included residence at 120 days and 1-year mortality. Model performance was assessed using area under the curve (AUC) analysis and Brier scores (discrimination) and calibration curves. The OPERA score was updated using regression analysis with additional independent predictors and validated using bootstrap analysis.

RESULTS

2142 patients (median age 86 [80-91] years) were included with a 30-day mortality of 5.2% and a 1-year mortality of 31.4%. 30-day mortality AUC for OPERA was 0.75 (95% CI, 0.73-0.77) and for NHFS 0.68 (0.65-0.70). For 1-year mortality AUC for OPERA was 0.74 (0.73-0.75) and for NHFS 0.70 (0.69-0.71). The OPERA Score was updated to Hip-OPERA, including ASA grade. Hip-OPERA demonstrated an AUC for 30-day mortality of 0.77 (0.73-0.81) and an AUC for 1-year mortality of 0.76 (0.75-0.77). AUC for new residential care status at 120 days was 0.79 (0.78-0.80).

CONCLUSIONS

Hip-OPERA demonstrated superior discrimination to the NHFS and OPERA for 30-day mortality, 1-year mortality and residence at 120 days following hip fracture. External validation is desirable.

Utilizing a nomogram to predict the one-year postoperative mortality risk for geriatric patients with a hip fracture

Despite the abundance of research on the risk factors for mortality following hip fracture surgery, there has been a dearth of studies on prediction models in this population. The objective of this research was to explore the influencing factors and construct a clinical nomogram to predict one-year postoperative mortality in patients with hip fracture surgeries. Using the Ditmanson Research Database (DRD), we included 2333 subjects, aged ≥ 50 years who underwent hip fracture surgery between October, 2008 and August, 2021. The endpoint was all-cause mortality. A least absolute shrinkage and selection operator (LASSO) derived Cox regression was performed to select the independent predictors of one-year postoperative mortality. A nomogram was built for predicting one-year postoperative mortality. The prognostic performance of nomogram was evaluated. On the basis of tertiary points in a nomogram, the patients were divided into low, middle and high risk groups, and compared by the Kaplan-Meier analysis. Within 1 year after hip fracture surgery, 274 patients (11.74%) died. Variables retained in the final model comprised age, sex, length of stay, RBC transfusions, hemoglobin, platelet, and eGFR. The AUC for one-year mortality predictions were 0.717 (95% CI = 0.685-0.749). The Kaplan-Meier curves were significantly different among the three risk groups (p < 0.001). The nomogram showed good calibration. In summary, we explored the one-year postoperative mortality risk in geriatric patients with a hip fracture and developed a prediction model that could help clinicians identify patients at high risk of postoperative mortality.

Risk prediction models incorporating institutional case volume for mortality after hip fracture surgery in the elderly

INTRODUCTION

While higher institutional case volume is associated with better postoperative outcomes in various types of surgery, institutional case volume has been rarely included in risk prediction models for surgical patients. This study aimed to develop and validate the predictive models incorporating institutional case volume for predicting in-hospital mortality and 1-year mortality after hip fracture surgery in the elderly.

MATERIALS AND METHODS

Data for all patients (≥ 60 years) who underwent surgery for femur neck fracture, pertrochanteric fracture, or subtrochanteric fracture between January 2008 and December 2016 were extracted from the Korean National Health Insurance Service database. Patients were randomly assigned into the derivation cohort or the validation cohort in a 1:1 ratio. Risk prediction models for in-hospital mortality and 1-year mortality were developed in the derivation cohort using the logistic regression model. Covariates included age, sex, type of fracture, type of anaesthesia, transfusion, and comorbidities such as hypertension, diabetes, coronary artery disease, chronic kidney disease, cerebrovascular disease, and dementia. Two separate models, one with and the other without institutional case volume as a covariate, were constructed, evaluated, and compared using the likelihood ratio test. Based on the models, scoring systems for predicting in-hospital mortality and 1-year mortality were developed.

RESULTS

Analysis of 196,842 patients showed 3.6% in-hospital mortality (7084/196,842) and 15.42% 1-year mortality (30,345/196,842). The model for predicting in-hospital mortality incorporating the institutional case volume demonstrated better discrimination (c-statistics 0.692) compared to the model without the institutional case volume (c-statistics 0.688; likelihood ratio test p value < 0.001). The performance of the model for predicting 1-year mortality was also better when incorporating institutional case volume (c-statistics 0.675 vs. 0.674; likelihood ratio test p value < 0.001).

CONCLUSIONS

The new institutional case volume incorporated scoring system may help to predict in-hospital mortality and 1-year mortality after hip fracture surgery in the elderly population.