O ver the past decades, governments have taken steps towards improving women’s health in line with commitments made in key international summits. Progress has been made in reducing maternal mortality,1 which accelerated with the launch of the United Nations secretary general’s Global Strategy for Women’s and Children’s Health in 2010. Use of maternal healthcare and family planning has increased...

In this paper we show how methods for approximating phone error as normally used for Minimum Phone Error (MPE) discriminative training, can be used instead as a decoding criterion for lattice rescoring. This is an alternative to Confusion Networks (CN) which are commonly used in speech recognition. The standard (Maximum A Posteriori) decoding approach is a Minimum Bayes Risk estimate with respe...

OBJECTIVE The aim of this guideline is to assist FPs and other primary care providers with recognizing features that should raise their suspicions about the presence of lung cancer in their patients. COMPOSITION OF THE COMMITTEE Committee members were selected from among the regional primary care leads from the Cancer Care Ontario Provincial Primary Care and Cancer Network and from among the ...

PURPOSE To identify the main issues of importance when living with long-term conditions to refine a conceptual framework for informing the item development of a patient-reported outcome measure for long-term conditions. MATERIALS AND METHODS Semi-structured qualitative interviews (n=48) were conducted with people living with at least one long-term condition. Participants were recruited throug...

A method is presented for augmenting word n-gram counts in a matrix which represents a 2-gram Language Model (LM). This method is based on numerical distances in a reduced space obtained by Singular Value Decomposition (SVD). Rescoring word lattices in a spoken dialogue application using an LM containing augmented counts has lead to a Word Error Rate (WER) reduction of 6.5%. By further interpol...

Arabic has a large number of affixes that can modify a stem to form words. In automatic speech recognition (ASR) this leads to a high out-of-vocabulary (OOV) rate for typical lexicon size, and hence a potential increase in WER. This is even more pronounced for dialects of Arabic where additional affixes are often introduced and the available data is typically sparse. To address this problem we ...

OBJECTIVES Population ageing and the increasing burden of chronic conditions challenge traditional metrics of assessing the efficacy of health care interventions and as a consequence policy and planning. Using chronic heart failure (CHF) as an exemplar this manuscript seeks to describe the importance of patient-reported outcomes to inform policy decisions. METHODS The method of an integrative...

ROVER [1] and its successor voting procedures have been shown to be quite effective in reducing the recognition word error rate (WER). The success of these methods has been attributed to their minimum Bayes-risk (MBR) nature: they produce the hypothesis with the least expected word error. In this paper we develop a general procedure within the MBR framework, called segmental MBR recognition, th...

BACKGROUND In the past 10 years, medication errors have come to be recognised as an important cause of iatrogenic disease in hospital patients. AIMS To determine the incidence and type of medication errors in a large UK paediatric hospital over a five year period, and to ascertain whether any error prevention programmes had influenced error occurrence. METHODS Retrospective review of medica...

OBJECTIVES To assess Texas pharmacists' knowledge of adverse drug event (ADE) reporting to the Food and Drug Administration (FDA) and to determine demographic and practice characteristics associated with this knowledge. DESIGN Cross-sectional descriptive study. SETTING Austin, TX, in June and July 2009. PARTICIPANTS 377 pharmacists practicing in hospital and community settings. INTERVEN...