Machine learning (ML) models often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices as data drift may lead to unexpected performance. This work introduces a new framework for out of distribution (OOD) detection and data drift monitoring that combines ML and geometric methods with statistical process control (SPC).
View Article and Find Full Text PDFIntroduction: Quality of life (QoL) is impaired in patients with acne vulgaris. The Cardiff Acne Disability Index (CADI) that assesses QoL of acne patients was initially developed in English and is being currently used widely after being validated in different languages. This study was conducted to validate the CADI in Sinhala, a language used by the majority of Sri Lanka.
View Article and Find Full Text PDFObjective: To evaluate potential risk-factors of ADHD among primary school-children (PSC) in state schools in Colombo district of Sri Lanka.
Method: A case-control study was conducted with 73 cases and 264 controls selected randomly among 6 to 10-year-old PSC from Sinhala medium state schools in Colombo district. Primary care givers completed the SNAP-IV P/T-S scale to screen for ADHD and an interviewer-administered questionnaire on risk-factors.
Globally, the proportion of the elderly is increasing. In comparison to other Southeast Asian countries, Sri Lanka's population is rapidly aging. The elderly are a vulnerable age group that requires special attention to live a long and healthy life.
View Article and Find Full Text PDF