Computer aided diagnosis systems with the capability of automatically decide if a patient has or not a pathology and to hold the decision on the dificult cases, are becoming more frequent. The latter are afterwards reviewed by an expert reducing therefore time consuption on behalf of the expert. The number of cases to review depends on the cost of erring the diagnosis. In this work we analyse the incorporation of the option to hold a decision on the diagnostic of pathologies on the vertebral column. A comparison with several state of the art techniques is performed. We conclude by showing that the use of the reject option techniques is an asset in line with the current view of the research community.

Background and Aims There is little information on the incremental prognostic importance of frailty beyond conventional prognostic variables in heart failure (HF) populations from different country income levels. Methods A total of 3429 adults with HF (age 61 ± 14 years, 33% women) from 27 high-, middle- and low-income countries were prospectively studied. Baseline frailty was evaluated by the Fried index, incorporating handgrip strength, gait speed, physical activity, unintended weight loss, and self-reported exhaustion. Mean left ventricular ejection fraction was 39 ± 14% and 26% had New York Heart Association Class III/IV symptoms. Participants were followed for a median (25th to 75th percentile) of 3.1 (2.0–4.3) years. Cox proportional hazard models for death and HF hospitalization adjusted for country income level; age; sex; education; HF aetiology; left ventricular ejection fraction; diabetes; tobacco and alcohol use; New York Heart Association functional class; HF medication use; blood pressure; and haemoglobin, sodium, and creatinine concentrations were performed. The incremental discriminatory value of frailty over and above the MAGGIC risk score was evaluated by the area under the receiver-operating characteristic curve. Results At baseline, 18% of participants were robust, 61% pre-frail, and 21% frail. During follow-up, 565 (16%) participants died and 471 (14%) were hospitalized for HF. Respective adjusted hazard ratios (95% confidence interval) for death among the pre-frail and frail were 1.59 (1.12–2.26) and 2.92 (1.99–4.27). Respective adjusted hazard ratios (95% confidence interval) for HF hospitalization were 1.32 (0.93–1.87) and 1.97 (1.33–2.91). Findings were consistent among different country income levels and by most subgroups. Adding frailty to the MAGGIC risk score improved the discrimination of future death and HF hospitalization. Conclusions Frailty confers substantial incremental prognostic information to prognostic variables for predicting death and HF hospitalization. The relationship between frailty and these outcomes is consistent across countries at all income levels.

No abstract

This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021). The competition attracted a total of 10 participating teams with valid submissions. The affiliations of these teams are diverse and associated with academia and industry in nine different countries. These teams successfully submitted 18 valid solutions. The competition is designed to motivate solutions aiming at enhancing the face recognition accuracy of masked faces. Moreover, the competition considered the deployability of the proposed solutions by taking the compactness of the face recognition models into account. A private dataset representing a collaborative, multisession, real masked, capture scenario is used to evaluate the submitted solutions. In comparison to one of the topperforming academic face recognition solutions, 10 out of the 18 submitted solutions did score higher masked face verification accuracy.