In recent years, the impressive growth of new wireless technologies, together with the appearance of new requirements in applications and services, is progressively changing the use of networks. Due ...to the high mobility required, the network must adapt to the infrastructure to meet the demands of the users. As a result, service providers currently have to over-provision network capacity, which is costly. In addition, considering efficient resource planning in advance involves a lot of labor-intensive efforts. Consequently, network usage analysis is a very useful tool that allows network administrators to find patterns and anomalies. Whilst pattern detection provides administrators the ability to define the infrastructure, anomaly detection provides rich and valuable information for certain applications, for example, to avoid network saturation in urban areas during peak hours. This article proposes a new methodology based on orthogonal projections over Call Detail Records (CDR) for anomaly detection to help in the dynamic management of the network in an urban area. The method is evaluated in a real scenario provided by an Italian telecommunications operator, considering different locations in the Milan metropolitan area, differentiated by the geographic resolution of the data, reaching F1 scores above 0.8. In addition, a new ground truth is presented, hoping it will become a reference data set for the community, in the form of a set of locations that have been corroborated for use in evaluating anomaly detection techniques.
To assess how the current practice of newborn screening (NBS) for homocystinurias compares with published recommendations.
Twenty-two of 32 NBS programmes from 18 countries screened for at least one ...form of homocystinuria. Centres provided pseudonymised NBS data from patients with cystathionine beta-synthase deficiency (CBSD, n = 19), methionine adenosyltransferase I/III deficiency (MATI/IIID, n = 28), combined remethylation disorder (cRMD, n = 56) and isolated remethylation disorder (iRMD), including methylenetetrahydrofolate reductase deficiency (MTHFRD) (n = 8). Markers and decision limits were converted to multiples of the median (MoM) to allow comparison between centres.
NBS programmes, algorithms and decision limits varied considerably. Only nine centres used the recommended second-tier marker total homocysteine (tHcy). The median decision limits of all centres were ≥ 2.35 for high and ≤ 0.44 MoM for low methionine, ≥ 1.95 for high and ≤ 0.47 MoM for low methionine/phenylalanine, ≥ 2.54 for high propionylcarnitine and ≥ 2.78 MoM for propionylcarnitine/acetylcarnitine. These decision limits alone had a 100%, 100%, 86% and 84% sensitivity for the detection of CBSD, MATI/IIID, iRMD and cRMD, respectively, but failed to detect six individuals with cRMD. To enhance sensitivity and decrease second-tier testing costs, we further adapted these decision limits using the data of 15,000 healthy newborns.
Due to the favourable outcome of early treated patients, NBS for homocystinurias is recommended. To improve NBS, decision limits should be revised considering the population median. Relevant markers should be combined; use of the postanalytical tools offered by the CLIR project (Collaborative Laboratory Integrated Reports, which considers, e.g. birth weight and gestational age) is recommended. tHcy and methylmalonic acid should be implemented as second-tier markers.
PDF
