Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images.

BACKGROUND: Artificial intelligence shows promise in assessing knee osteoarthritis (OA) progression on MR images, but faces challenges in accuracy and interpretability. PURPOSE: To introduce a temporal-regional graph convolutional network (TRGCN) on MR images to study the association between knee OA progression status and network outcome. STUDY TYPE: Retrospective. POPULATION: 194 OA progressors (mean age, 62 ± 9 years) and 406 controls (mean age, 61 ± 9 years) from the OA Initiative were randomly divided into training (80%) and testing (20%) cohorts. FIELD STRENGTH/SEQUENCE: Sagittal 2D IW-TSE-FS (IW) and 3D-DESS-WE (DESS) at 3T. ASSESSMENT: Anatomical subregions of cartilage, subchondral bone, meniscus, and the infrapatellar fat pad at baseline, 12-month, and 24-month were automatically segmented and served as inputs to form compartment-based graphs for a TRGCN model, which containing both regional and temporal information. The performance of models based on (i) clinical variables alone, (ii) radiologist score alone, (iii) combined features (containing i and ii), (iv) composite TRGCN (combining TRGCN, i and ii), (v) radiomics features, (vi) convolutional neural network based on Densenet-169 were compared. STATISTICAL TESTS: DeLong test was performed to compare the areas under the ROC curve (AUC) of all models. Additionally, interpretability analysis was done to evaluate the contributions of individual regions. A P value <0.05 was considered significant. RESULTS: The composite TRGCN outperformed all other models with AUCs of 0.841 (DESS) and 0.856 (IW) in the testing cohort (all P < 0.05). Interpretability analysis highlighted cartilage's importance over other structures (42%-45%), tibiofemoral joint's (TFJ) dominance over patellofemoral joint (PFJ) (58%-67% vs. 12%-37%), and importance scores changes in compartments over time (TFJ vs. PFJ: baseline: 44% vs. 43%, 12-month: 52% vs. 39%, 24-month: 31% vs. 48%). DATA CONCLUSION: The composite TRGCN, capturing temporal and regional information, demonstrated superior discriminative ability compared with other methods, providing interpretable insights for identifying knee OA progression. TECHNICAL EFFICACY: Stage 2.

Using a participatory design to develop an implementation framework for integrating falls prevention for older people within the Chinese primary health care system.

BACKGROUND: Chinese National Essential Public Health Service Package (NEPHSP) has mandated primary health care providers to provide falls prevention for community-dwelling older people. But no implementation framework is available to guide better integration of falls prevention for older people within the primary health care system. METHODS: This is a two-stage online participatory design study consisting of eight workshops with stakeholders from three purposively selected cities. First, two workshops were organised at each study site to jointly develop the framework prototype. Second, to refine, optimise and finalise the prototype via two workshops with all study participants. Data analysis and synthesis occurred concurrently with data collection, supported by Tencent Cloud Meeting software. RESULTS: All participants confirmed that the integration of falls prevention for older people within the NEPHSP was weak and reached a consensus on five opportunities to better integrate falls prevention, including workforce training, community health promotion, health check-ups, health education and scheduled follow-up, during the delivery of NEPHSP. Three regional-tailored prototypes were then jointly developed and further synthesised into a generic implementation framework by researchers and end-users. Guided by this framework, 11 implementation strategies were co-developed under five themes. CONCLUSIONS: The current integration of falls prevention in the NEPHSP is weak. Five opportunities for integrating falls prevention in the NEPHSP and a five-themed implementation framework with strategies are co-identified and developed, using a participatory design approach. These findings may also provide other regions or countries, facing similar challenges, with insights for promoting falls prevention for older people.

KEYPOINTS: The integration of falls prevention for older people was weak in the Chinese PHC system.Five opportunities were identified for better integrating falls prevention for older people in the Chinese PHC system.We developed an implementation framework to strengthen the solid integration of falls prevention in the Chinese PHC system.

Characteristics of falls among older hip fracture patients from six Chinese hospitals: a post-hoc descriptive analysis.

BACKGROUND: There is well-established evidence to understand the characteristics of falls among the older patients with hip fracture in many countries, but very little knowledge existed in China. This study described the characteristics of falls in older patients with hip fractures from six Chinese hospitals. METHODS: This cross-sectional study is a post-hoc descriptive analysis of a recently completed trial. Eligible patients were aged 65 years and older, with confirmed hip fractures due to falls, and were admitted to the hospital within 21 days of the fracture. All patients were consecutively enrolled and screened within one year (November 15, 2018, to November 14, 2019). The collected data included patient demographics and fall-related information. RESULTS: A total of 1,892 patients' fall-related information were described. Most patients with hip fractures caused by falls were in the oldest old age group (60.4% in age group ≥ 80), with an overall average age of 80.7 (7.6) years. There were more females (n = 1,325, 70.0%) than males (n = 567, 30.0%). The majority lived in urban (n = 1,409, 74.5%). Most falls (n = 1,237, 67.3%) occurred during the daytime (6:01-18:00). There were 1,451 patients had their falls occurring at home (76.7%). Lost balance (n = 1,031, 54.5%) was reported as the primary reason to cause falls. The most common activity during a fall was walking (n = 1,079, 57.0%). CONCLUSIONS: Although the incidence of fall-related hip fractures in China is unclear, preventing falls and fall-related hip fractures in older people remains an urgent health concern as the ageing society increases. Studies with larger sample size and diverse population are needed to robustly understand this growing epidemic.

Functional-structural sub-region graph convolutional network (FSGCN): Application to the prognosis of head and neck cancer with PET/CT imaging.

BACKGROUND AND OBJECTIVE: Accurate risk stratification is crucial for enabling personalized treatment for head and neck cancer (HNC). Current PET/CT image-based prognostic methods include radiomics analysis and convolutional neural network (CNN), while extracting radiomics or deep features in grid Euclidean space has inherent limitations for risk stratification. Here, we propose a functional-structural sub-region graph convolutional network (FSGCN) for accurate risk stratification of HNC. METHODS: This study collected 642 patients from 8 different centers in The Cancer Imaging Archive (TCIA), 507 patients from 5 centers were used for training, and 135 patients from 3 centers were used for testing. The tumor was first clustered into multiple sub-regions by using PET and CT voxel information, and radiomics features were extracted from each sub-region to characterize its functional and structural information, a graph was then constructed to format the relationship/difference among different sub-regions in non-Euclidean space for each patient, followed by a residual gated graph convolutional network, the prognostic score was finally generated to predict the progression-free survival (PFS). RESULTS: In the testing cohort, compared with radiomics or FSGCN or clinical model alone, the model PETCTFea_CTROI + Cli that integrates FSGCN prognostic score and clinical parameter achieved the highest C-index and AUC of 0.767 (95% CI: 0.759-0.774) and 0.781 (95% CI: 0.774-0.788), respectively for PFS prediction. Besides, it also showed good prognostic performance on the secondary endpoints OS, RFS, and MFS in the testing cohort, with C-index of 0.786 (95% CI: 0.778-0.795), 0.775 (95% CI: 0.767-0.782) and 0.781 (95% CI: 0.772-0.789), respectively. CONCLUSIONS: The proposed FSGCN can better capture the metabolic or anatomic difference/interaction among sub-regions of the whole tumor imaged with PET/CT. Extensive multi-center experiments demonstrated its capability and generalization of prognosis prediction in HNC over conventional radiomics analysis.