Osteoporotic vertebral fractures (OVFs) are often not reported by radiologists on routine chest radiographs. This study aims to investigate the clinical value of a newly developed artificial intelligence (AI) tool, Ofeye 1.0, for automated detection of OVFs on lateral chest radiographs in post-menopausal women (>60 years) who were referred to undergo chest x-rays for other reasons. A total of 510 de-identified lateral chest radiographs from three clinical sites were retrieved and analysed using the Ofeye 1.0 tool. These images were then reviewed by a consultant radiologist with findings serving as the reference standard for determining the diagnostic performance of the AI tool for the detection of OVFs. Of all the original radiologist reports, missed OVFs were found in 28.8% of images but were detected using the AI tool. The AI tool demonstrated high specificity of 92.8% (95% CI: 89.6, 95.2%), moderate accuracy of 80.3% (95% CI: 76.3, 80.4%), positive predictive value (PPV) of 73.7% (95% CI: 65.2, 80.8%), and negative predictive value (NPV) of 81.5% (95% CI: 79, 83.8%), but low sensitivity of 49% (95% CI: 40.7, 57.3%). The AI tool showed improved sensitivity compared with the original radiologist reports, which was 20.8% (95% CI: 14.5, 28.4). The new AI tool can be used as a complementary tool in routine diagnostic reports for the reduction in missed OVFs in elderly women.

Background/Objectives: Evidence-based guidelines and care standards recommend offering oral nutrition supplements to all older adults with hip fracture, not just those already malnourished. This study aimed to identify the proportion of inpatients in a sample of hospitals in two countries that were provided with oral nutritional supplementation (ONS) following a hip fracture and to identify factors associated with ONS provision. Methods: An analysis of prospectively collected data from a bi-national Hip Fracture Registry nutrition sprint and registry audit data limited to older adults (≥65 years) undergoing surgical intervention for a fractured hip from 1 to 31 August 2021. Multivariable logistic regression was used to identify factors associated with providing ONS. Results: Patient-level data was available for 385 older adults (median 85 years; 60.5% female) admitted to twenty-nine hospitals. Less than half (n = 47.3%) of the audited inpatients were provided ONS. After adjusting for covariates, ONS was more likely to be provided to older adults who were identified as malnourished on formal testing (OR 11.92; 95%CI 6.57, 21.69). Other factors associated with prescription of ONS included those who did not have a preoperative medical assessment (OR 2.26; 95%CI 1.19, 4.27) or were cognitively impaired (OR 1.83; 95%CI 1.01, 3.32), severely frail, or terminally ill (OR 3.17; 95%CI 1.10, 9.17). Conclusions: ONS was provided in line with evidence-based recommendations for less than half of the older adults with a hip fracture in 29 hospitals in two countries. A structured approach to implementation may be required to reduce complications and improve outcomes for all older adults after a hip fracture, not just those assessed as cognitively impaired, frail, and/or malnourished.

In Western Australia, vast distances between hospitals can limit a patient’s access to timely surgical intervention. The aim was to examine the effect of patient location on outcomes. Hip fracture data from all operative cases at the major Western Australian hospitals between 2015 and 2019 was retrospectively reviewed. A total of 5691 patients were separated into three groups based on hospital of first presentation - directly to the operative hospital (metropolitan), a hospital less than 2.5 hours by road from the operative centre (outer-metropolitan), or requiring transfer by air (rural). Impact of location on time to surgery, length of stay and 30-day and 120-day mortality was analysed. The mean time to surgery was 26.7 hours for metropolitan patients, 37.0 hours for outer-metropolitan, and 42.6 hours for rural patients. Outer-metropolitan patients were less likely to reach surgery within 48 hours than metropolitan patients (80.2% vs 91.5%, p<0.001), with even lower rates for rural patients (66.8%, p<0.001). Acute length of stay was longer for rural patients compared to outer-metropolitan (7.2 vs 5.8 days) and metropolitan patients (5.5 days) (p<0.001). There was no significant difference in 30-day or 120-day mortality for outer-metropolitan or rural patients compared to metropolitan patients despite requiring transfer. However, when considered as a whole group there was an increased 120-day mortality with increased time to surgery. Overall mortality was 8.7% at 30 days and 17.3% at 120 days. Patients presenting outside the metropolitan area with a hip fracture have a longer time to surgery and longer length of stay. Delay for outer-metropolitan patients is disproportionately longer than transit time alone and may provide opportunities for improvement.

Hip fracture is a common injury in older adults that causes significant morbidity and mortality. Older adults who sustain a hip fracture are at a higher risk of institutionalisation, reduced mobility and subsequent falls and, consequently, have increased rates of morbidity and mortality. Quality improvement strategies that address gaps in hip fracture care are needed to ensure best practice and improve health outcomes for older adults. This case study describes the development of a state-based hip fracture registry and incentive payment scheme in Western Australia (WA), which were designed to drive quality improvement. The registry monitored best practice in hip fracture care criteria across three tertiary hospitals in WA, and the incentive program provided premium payments to these hospitals for meeting six criteria in best practice clinical quality. The fracture registry commenced in 2011, and by 2014 all participating hospitals were eligible for payments. From 2014 to 2016, the proportion of patients who were operated on within 36 hours increased from 60% to 79%. This case study illustrates how a hip fracture registry in conjunction with small premium payments improved well-described process measures in hip fracture care. What is known about the topic?: Hip fracture is a common among older adults, usually resulting from a fall. International clinical quality registries have been shown to help drive quality improvements in patient care processes and outcomes. What does this paper add?: This paper adds an Australian perspective to the existing literature on the efficacy of hip fracture clinical quality registries. It offers an example of how a Western Australian hip fracture registry with an associated incentive payment program drove clinical care and process change to improve care provision and patient outcomes. What are the implications for practitioners?: This case study suggests regular monitoring and reporting on hip fracture care processes and patient outcomes can lead to improvements in both of these measures. Because incentive payments may have contributed to the best practice improvements noted in this case study, practitioners involved in designing future monitoring and reporting programs should consider the merits of incorporating financial incentives.