No abstract

Differentiation between transient osteoporosis (TOH) and avascular necrosis (AVN) of the hip is a longstanding challenge in musculoskeletal radiology. The purpose of this study was to utilize MRI-based radiomics and machine learning (ML) for accurate differentiation between the two entities. A total of 109 hips with TOH and 104 hips with AVN were retrospectively included. Femoral heads and necks with segmented radiomics features were extracted. Three ML classifiers (XGboost, CatBoost and SVM) using 38 relevant radiomics features were trained on 70% and validated on 30% of the dataset. ML performance was compared to two musculoskeletal radiologists, a general radiologist and two radiology residents. XGboost achieved the best performance with an area under the curve (AUC) of 93.7% (95% CI from 87.7 to 99.8%) among ML models. MSK radiologists achieved an AUC of 90.6% (95% CI from 86.7% to 94.5%) and 88.3% (95% CI from 84% to 92.7%), respectively, similar to residents. The general radiologist achieved an AUC of 84.5% (95% CI from 80% to 89%), significantly lower than of XGboost (p = 0.017). In conclusion, radiomics-based ML achieved a performance similar to MSK radiologists and significantly higher compared to general radiologists in differentiating between TOH and AVN.

The HYPEDIA study aimed at evaluating the implementation of the 2018 European guidelines for treating hypertension in primary care. A nationwide prospective non-interventional cross-sectional study was performed in consecutive untreated or treated hypertensives recruited mainly in primary care in Greece. Participants’ characteristics, office blood pressure (BP) (triplicate automated measurements, Microlife BPA3 PC) and treatment changes were recorded on a cloud platform. A total of 3,122 patients (mean age 64 ± 12.5 [SD] years, 52% males) were assessed by 181 doctors and 3 hospital centers. In 772 untreated hypertensives (25%), drug treatment was initiated in the majority, with monotherapy in 53.4%, two-drug combination in 36.3%, and three drugs in 10.3%. Angiotensin receptor blocker (ARB) monotherapy was initiated in 30%, ARB/calcium channel blocker (CCB) 20%, ARB/thiazide 8%, angiotensin converting enzyme inhibitor (ACEi)-based 19%. Of the combinations used, 97% were in single-pill. Among 977 treated hypertensives aged <65 years, 79% had BP ≥ 130/80 mmHg (systolic and/or diastolic), whereas among 1,373 aged ≥65 years, 66% had BP ≥ 140/80 mmHg. ARBs were used in 69% of treated hypertensives, CCBs 47%, ACEis 19%, diuretics 39%, beta-blockers 19%. Treatment modification was decided in 53% of treated hypertensives aged <65 years with BP ≥ 130/80 mmHg and in 62% of those ≥65 years with BP ≥ 140/80 mmHg. Renin-angiotensin system blocker-based therapy constitutes the basis of antihypertensive drug treatment in most patients in primary care, with wide use of single-pill combinations. In almost half of treated uncontrolled hypertensives, treatment was not intensified, suggesting suboptimal implementation of the guidelines and possible physician inertia.

Differential diagnosis between avascular necrosis (AVN) and transient osteoporosis of the hip (TOH) can be complicated even for experienced MSK radiologists. Our study attempted to use MR images in order to develop a deep learning methodology with the use of transfer learning and a convolutional neural network (CNN) ensemble, for the accurate differentiation between the two diseases. An augmented dataset of 210 hips with TOH and 210 hips with AVN was used to finetune three ImageNet-trained CNNs (VGG-16, InceptionResNetV2, and InceptionV3). An ensemble decision was reached in a hard-voting manner by selecting the outcome voted by at least two of the CNNs. Inception-ResNet-V2 achieved the highest AUC (97.62%) similar to the model ensemble, followed by InceptionV3 (AUC of 96.82%) and VGG-16 (AUC 96.03%). Precision for the diagnosis of AVN and recall for the detection of TOH were higher in the model ensemble compared to Inception-ResNet-V2. Ensemble performance was significantly higher than that of an MSK radiologist and a fellow (P < 0.001). Deep learning was highly successful in distinguishing TOH from AVN, with a potential to aid treatment decisions and lead to the avoidance of unnecessary surgery.