Fragility fractures: A complex interaction of the health care system- the patient and the bone: Can we do better?

Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates

This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. For objective labeling, we collected a dataset containing 1131 images from patients who underwent both skeletal bone mineral density measurement and hip radiography at a single general hospital between 2014 and 2019. Osteoporosis was assessed from the hip radiographs using five convolutional neural network (CNN) models. We also investigated ensemble models with clinical covariates added to each CNN. The accuracy, precision, recall, specificity, negative predictive value (npv), F1 score, and area under the curve (AUC) score were calculated for each network. In the evaluation of the five CNN models using only hip radiographs, GoogleNet and EfficientNet b3 exhibited the best accuracy, precision, and specificity. Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. The CNN models diagnosed osteoporosis from hip radiographs with high accuracy, and their performance improved further with the addition of clinical covariates from patient records.

Age related changes in the bone microstructure in patients with femoral neck fractures

BACKGROUND

The risk of femoral neck fracture progressively increases with age. However, the reasons behind this consistent increase in the fracture risk can't be completely justified by the decrease in the bone mineral density. The objective of this study was to analyze the correlation between various bone structural features and age.

STUDY DESIGN & METHODS

A total of 29 consecutive patients who suffered an intracapsular hip fracture and underwent joint replacement surgery between May 2012 and March 2013 were included in this study. A 2 cm × 1 cm Ø cylindrical trabecular bone sample was collected from the femoral heads and preserved in formaldehyde. Bone mineral density (BMD), microarchitecture, organic content and crystallography were analyzed using a Dual-energy X-ray absorptiometry scan, micro-CT scan, and high resolution magic-angle-spinning-nuclear magnetic resonance (MAS-NMR), respectively. Statistical correlations were made using Spearman´s or Pearson´s correlation tests depending on the distribution of the continuous variables.

RESULTS

The mean patient age was 79.83 ± 9.31 years. A moderate negative correlation was observed between age and the hydrogen content in bone (¹H), which is an indirect estimate to quantify the organic matrix (r = -0.512, p = 0.005). No correlations were observed between BMD, trabecular number, trabecular thickness, phosphorous content, apatite crystal size, and age (r = 0.06, p = 0.755; r = -0.008, p = 0.967; r = -0.046, p = 0.812; r = -0.152, p = 0.430, respectively). A weak positive correlation was observed between Charlson´s comorbidity index (CCI) and c-axis of the hydroxiapatite (HA) crystals (r = -0.400, p = 0.035).

CONCLUSION

The femoral head relative protein content progressively decreases with age. BMD was not correlated with other structural bone parameters and age. Patients with higher comorbidity scores had larger HA crystals. The present results suggest that the progressive increase in the hip fracture risk in elderly patients could be partially explained by the lower bone protein content in this age group.

Editorial. The Challenges of Orthopaedic Trauma in Spain

Spain is considered the healthiest nation in the world, due to lifepromoting aspects such as good diet, care facilities and a favourable family environment. However, although increased life expectancy is an indicator of development, it may have a negative impact on the other two variables of health service efficiency, namely health expenditure per capita and its relative weight in Gross Domestic Product.

Influence of cognitive impairment on mortality, complications and functional outcome after hip fracture: Dementia as a risk factor for sepsis and urinary infection

PURPOSE

To analyze the relation between cognitive impairment on arrival at hospital in patients older than 65 years with a hip fracture, and their mortality, medical and surgical complications, and functional outcomes.

PATIENTS AND METHODS

Observational study of a single-center prospective consecutive cohort of 955 patients older than 64 years diagnosed of hip fracture from December/2012 to December/2015. Average age was 86±7.2 (65-104) years and 725 (75.9%) were female. Fractures were extracapsular in 538 cases (56.3%) and intracapsular in 417 (43.7%). Patients were controlled clinically and radiographically in outpatient clinic after 1, 3, 6, and 12 months. Data about basal cognitive status, walking ability before the fracture, medical and surgical complications, functional outcomes and mortality were collected for the year following the fracture.

STATISTICAL ANALYSIS

Bivariate analysis (Pearson, Fisher, Mann-Whitney, Wilcoxon) was applied to study statistically significant relations, and contingence coefficients (CC) were calculated.

RESULTS

Patients with cognitive impairment showed a higher overall mortality, (p = 0,000; CC=0,197) even after hospital discharge (p = 0.000; CC=0.198). Similarly, patients with dementia presented a higher rate of respiratory infections (p = 0,029; CC=0,093), urinary tract infections (p = 0,008; CC=0,108) and sepsis (p = 0,011; CC=0,105). On the contrary, we found no correlations between mental status and surgical complications, even for prosthesis dislocation (p = 0.136). Patients with dementia started from poorer functional situations (p = 0,000; CC=0,367) and ended follow-up with lower walking ability (p = 0,000; CC=0,43), but cognitive impairment did not relate statistically with a worse functional recovery (p = 0,304): that is, the proportion of patients who maintained their previous ability to walk was similar in both groups, those with altered mental status and those without it.

CONCLUSIONS

Cognitive impairment is a risk factor for mortality in patients with a hip fracture. It is also a risk factor for suffering respiratory and urinary tract infection and sepsis. These two late risks factors have not been published previously. Functional recovery is not conditioned by cognitive impairment, although further studies need to be developed to evaluate the actual role of cognitive impairment on postoperative progression of patients.