Recent research suggests that virtual reality (VR) games can engage players in physical activity with high levels of enjoyment. Understanding users’ motivation to engage and enjoy immersive VR exercise platforms is thus important to designers. We designed a VR exercise platform and conducted an experiment with two conditions, one with a static user interface (UI) and the other with an open world environment. Across participants there was significantly (p = 0.03*) greater enjoyment reported in an open world compared to static UI. Enjoyment in both static UI and open world conditions was positively correlated wih user’s psychological needs and experience; autonomy and immersion. Participants’ future play intention was also predicted by autonomy and immersion, but only within the open world condition. Our findings also suggest players can be classified into entertainment-focused and exercise-focused with different expectations and therefore different engagement behaviors with each VR exercise environment. The study highlights the value of informing VR design with measures of psychological need satisfaction.

In 2022, breast cancer will become an important factor affecting women's public health and HER2 positivity for approximately 15–20$ \% $ invasive breast cancer cases. Follow-up data for HER2-positive patients are rare, and research on prognosis and auxiliary diagnosis is still limited. In light of the findings obtained from the analysis of clinical features, we have developed a novel multiple instance learning (MIL) fusion model that integrates hematoxylin-eosin (HE) pathological images and clinical features to accurately predict the prognostic risk of patients. Specifically, we segmented the HE pathology images of patients into patches, clustered them by K-means, aggregated them into a bag feature-level representation through graph attention networks (GATs) and multihead attention networks, and fused them with clinical features to predict the prognosis of patients. We divided West China Hospital (WCH) patients (n = 1069) into a training cohort and internal validation cohort and used The Cancer Genome Atlas (TCGA) patients (n = 160) as an external test cohort. The 3-fold average C-index of the proposed OS-based model was 0.668, the C-index of the WCH test set was 0.765, and the C-index of the TCGA independent test set was 0.726. By plotting the Kaplan-Meier curve, the fusion feature (P = 0.034) model distinguished high- and low-risk groups more accurately than clinical features (P = 0.19). The MIL model can directly analyze a large number of unlabeled pathological images, and the multimodal model is more accurate than the unimodal models in predicting Her2-positive breast cancer prognosis based on large amounts of data.

Virtual reality (VR) can be combined with exergames technology to provide highly immersive physical activity experiences. The design of VR exergames, so they are enjoyable and engaging, for different age groups, is currently under-investigated. In this paper, we study enjoyment of physical activity on VR-Rides, a virtual exergaming platform with a recumbent trike controller. In our experiment, we assigned participants to one of the two conditions; a static user interface (UI) or an Open World VR environment which allowed participants to explore a virtual location using Google's Street View 360 panorama images. In both conditions, participants could track their activity data in real-time. The results suggest higher enjoyment and more activity time in an Open World condition, where participants are encouraged to explore a virtual location. Almost half of participants in the UI condition showed disinterest after a short interaction time, due to the static environment.