No abstract

No abstract

Background:Owing to the limited validity of clinical data on the treatment of prostate cancer (PCa) and bone metastases, biochemical markers are a promising tool for predicting survival, disease progression and skeletal-related events (SREs) in these patients. The aim of this study was to evaluate the predictive capacity of biochemical markers of bone turnover for mortality risk, disease progression and SREs in patients with PCa and bone metastases undergoing treatment with zoledronic acid (ZA).Methods:This was an observational, prospective and multicenter study in which ninety-eight patients were included. Patients were treated with ZA (4 mg every 4 weeks for 18 months). Data were collected at baseline and 3, 6, 9, 12, 15 and 18 months after the beginning of treatment. Serum levels of bone alkaline phosphtase (BALP), aminoterminal propeptide of procollagen type I (P1NP) and beta-isomer of carboxiterminal telopeptide of collagen I (β-CTX) were analysed at all points in the study. Data on disease progression, SREs development and survival were recorded.Results:Cox regression models with clinical data and bone markers showed that the levels of the three markers studied were predictive of survival time, with β-CTX being especially powerful, in which a lack of normalisation in visit 1 (3 months after the beginning of treatment) showed a 6.3-times more risk for death than in normalised patients. Levels of these markers were also predictive for SREs, although in this case BALP and P1NP proved to be better predictors. We did not find any relationship between bone markers and disease progression.Conclusion:In patients with PCa and bone metastases treated with ZA, β-CTX and P1NP can be considered suitable predictors for mortality risk, while BALP and P1NP are appropriate for SREs. The levels of these biomarkers 3 months after the beginning of treatment are especially important.

This paper aims to solve two important issues that frequently occur in existing automatic personality analysis systems: 1. Attempting to use very short video segments or even single frames, rather than long-term behaviour, to infer personality traits; 2. Lack of methods to encode person-specific facial dynamics for personality recognition. To deal with these issues, this paper firstly proposes a novel Rank Loss which utilizes the natural temporal evolution of facial actions, rather than personality labels, for self-supervised learning of facial dynamics. Our approach first trains a generic U-net style model that can infer general facial dynamics learned from a set of unlabelled face videos. Then, the generic model is frozen, and a set of intermediate filters are incorporated into this architecture. The self-supervised learning is then resumed with only person-specific videos. This way, the learned filters' weights are person-specific, making them a valuable source for modeling person-specific facial dynamics. We then propose to concatenate the weights of the learned filters as a person-specific representation, which can be directly used to predict the personality traits without needing other parts of the network. We evaluate the proposed approach on both self-reported personality and apparent personality datasets. In addition to achieving promising results in the estimation of personality trait scores from videos, we show that the tasks conducted by the subject in the video matters, that fusion of a combination of tasks reaches highest accuracy, and that multi-scale dynamics are more informative than single-scale dynamics.

No abstract