Validated at scale.
Peer-⁠reviewed.

ObjectiveTo evaluate the clinical impact of Rho on bone health screening at a large independent health facility, measuring its effect on DXA referrals and downstream diagnoses.

MethodsOver 13 months, Rho analyzed X-rays from patients aged 50 and older at a large independent health facility. Radiologists could opt to include Rho-flagged findings in their X-ray reports. DXAs occurring within 6 months were categorized as either Rho-generated or arranged through usual standard-of-care, and outcomes compared.

ResultsOf 34,162 X-rays analyzed, Rho flagged 19,004 (56%) for low BMD. Radiologists included this information in 7,726 (41%) of reports. Initial and surveillance DXAs increased by factors of 1.8 and 1.4, respectively. Rho-generated DXAs identified a greater proportion of patients with low BMD compared to pre-planned DXAs (87% vs 69%, p<0.001). The diagnostic yield was particularly marked in patients undergoing their first-ever DXA (84% vs 60%) and in males aged 65 and older (83% vs 45%).

ConclusionIncorporating Rho into the radiology workflow nearly doubled initial bone health assessments and prompted additional surveillance DXA evaluations. Rho captured higher rates of true low BMD than standard-of-care practices, particularly in older men, an under-screened population.

BackgroundDespite the prevalence and fracture risk of osteoporosis, access to gold-standard DXA scans remains limited, especially in rural communities. This study independently validates Rho by evaluating its performance against DXA in a retrospective cohort of patients.

MethodsRetrospective study of 4,878 patients (mean age 70, 80% female) with DXA acquired within one year of a radiograph. Performance was evaluated by AUC for identifying patients at risk for low BMD (T-Score ≤ -1) and osteoporosis (T-Score ≤ -2.5). Subgroup analyses by radiograph location, sex, and rural vs urban populations were performed.

ResultsOverall AUC was 0.840 (95% CI: 0.831-0.848) for predicting low BMD and 0.815 (95% CI: 0.806-0.824) for osteoporosis. Rural and urban populations both showed strong AUCs for low BMD (0.873 and 0.873) and osteoporosis (0.865 and 0.812). Performance was comparable across men and women.

ConclusionRho identified patients at risk of low BMD with an AUC of 0.840, with similar results in rural and urban populations. The authors see a role for Rho in prioritizing patients for DXA in communities with limited access to it. Osteoporosis, also analyzed, is not part of Rho’s intended use.

PurposeTo evaluate Rho's ability to prospectively identify patients at risk for low BMD from standard X-rays, its adoption rate by radiologists, and acceptance by primary care providers.

MethodsProspective study at Sunnybrook Health Sciences Centre. Patients aged 50 and older were recruited when undergoing an X-ray of a Rho-eligible body part for any clinical indication. Questionnaires were completed at baseline and 6-month follow-up. PCPs of Rho-Positive patients were asked for feedback.

ResultsOf 1,145 patients consented, 987 had X-rays screened by Rho, and 655 were flagged as Rho-Positive. Radiologists included this finding in 524 (80%) of reports. Of all Rho-Positive patients, 125 had a DXA within 6 months; Rho had a 74% positive predictive value for DXA T-Score <-1. From 51 PCP responses, 78% found Rho beneficial. Of 389 patients with follow-up data, a greater proportion of Rho-Positive vs Rho-Negative patients had discussed bone health with their PCP since study start (36% vs 18%, p<0.001) or were newly diagnosed with osteoporosis (11% vs 5%, p=0.03).

ConclusionBy identifying patients at risk of low BMD with acceptability of reporting by radiologists and generally positive PCP feedback, Rho has the potential to improve low osteoporosis screening rates by leveraging existing X-ray data.

OverviewReview of the Canadian clinical deployment of Rho, written for a German clinical audience and published in Osteologie.

ContextOsteoporosis, characterized by reduced bone mineral density, affects 200 million people worldwide. Osteoporosis-associated deterioration of bone quality increases an individual's risk of fragility fracture. Reduction of primary fragility fractures requires patient awareness of risk factors and initiation of strategies to optimize bone health.

The Rho approachRho analyzes routine X-rays acquired for any clinical indication and alerts a radiologist at time of reporting if the patient is at risk of having low BMD. By including the opportunistic finding in their X-ray report, the radiologist can prompt the often-overlooked clinical fracture risk assessment.

Canadian deploymentAt publication, Rho had prospectively screened over 250,000 patients in Canada as part of routine care. In studies that have assessed outcomes of Rho findings, many patients have been newly diagnosed with osteoporosis or elevated fracture risk.

ImplicationThe authors propose opportunistic screening with Rho for patients in Germany and across Europe. Rho received the CE mark in January 2026.

BackgroundOsteoporosis is under-screened. The ability to estimate BMD at the femoral neck and lumbar vertebrae from standard radiographs would enable opportunistic screening of low BMD in individuals undergoing X-ray for any clinical indication.

MethodsRadiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, and knee, paired with DXA acquired within one year, were obtained from community imaging centers (62,023 X-ray-DXA pairs). Rho was developed using X-ray, age, and sex as inputs, outputting the likelihood of low BMD. Performance was assessed in three independent test sets: community imaging centers (n=3,729), the Canadian Multicentre Osteoporosis Study (n=1,780), and the Osteoarthritis Initiative (n=591).

ResultsAreas under the ROC curves were 0.89 (0.87-0.90), 0.87 (0.85-0.88), and 0.82 (0.79-0.85), respectively. Subset analyses showed similar performance for each sex, body part, and race.

ConclusionRho can opportunistically screen patients at risk of low BMD from radiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, or knee, including when the femoral neck and lumbar vertebrae are not in the image.