Supervised Aggregative Feature Extraction for Big Data Time Series Regression

In many applications, and especially those where batch processes are involved, a target scalar output of interest is often dependent on one or more time series of data. With the exponential growth in data logging in modern industries such time series are increasingly available for statistical modeling in soft sensing applications. In order to exploit time series data for predictive modelling, it is necessary to summarise the information they contain as a set of features to use as model regressors. Typically this is done in an unsupervised fashion using simple techniques such as computing statistical moments, principal components or wavelet decompositions, often leading to significant information loss and hence suboptimal predictive models. In this paper, a functional learning paradigm is exploited in a supervised fashion to derive continuous, smooth estimates of time series data (yielding aggregated local information), while simultaneously estimating a continuous shape function yielding optimal predictions. The proposed Supervised Aggregative Feature Extraction (SAFE) methodology can be extended to support nonlinear predictive models by embedding the functional learning framework in a Reproducing Kernel Hilbert Spaces setting. SAFE has a number of attractive features including closed form solution and the ability to explicitly incorporate first and second order derivative information. Using simulation studies and a practical semiconductor manufacturing case study we highlight the strengths of the new methodology with respect to standard unsupervised feature extraction approaches.

Predicting conversion to dementia in a memory clinic: A standard clinical approach compared with an empirically defined clustering method (latent profile analysis) for mild cognitive impairment subtyping

Introduction
Mild cognitive impairment (MCI) has clinical value in its ability to predict later dementia. A better understanding of cognitive profiles can further help delineate who is most at risk of conversion to dementia. We aimed to (1) examine to what extent the usual MCI subtyping using core criteria corresponds to empirically defined clusters of patients (latent profile analysis [LPA] of continuous neuropsychological data) and (2) compare the two methods of subtyping memory clinic participants in their prediction of conversion to dementia.

Methods
Memory clinic participants (MCI, n = 139) and age-matched controls (n = 98) were recruited. Participants had a full cognitive assessment, and results were grouped (1) according to traditional MCI subtypes and (2) using LPA. MCI participants were followed over approximately 2 years after their initial assessment to monitor for conversion to dementia.

Results
Groups were well matched for age and education. Controls performed significantly better than MCI participants on all cognitive measures. With the traditional analysis, most MCI participants were in the amnestic multidomain subgroup (46.8%) and this group was most at risk of conversion to dementia (63%). From the LPA, a three-profile solution fit the data best. Profile 3 was the largest group (40.3%), the most cognitively impaired, and most at risk of conversion to dementia (68% of the group).

Discussion
LPA provides a useful adjunct in delineating MCI participants most at risk of conversion to dementia and adds confidence to standard categories of clinical inference.

How useful is dual energy lateral vertebral assessment in a clinic setting?

Screening for osteoporotic vertebral fractures traditionally involves X-ray of the thoracic and lumbar spine. We evaluated use of dual energy X-ray technology in patients with osteoporosis. We found this technology useful in the clinic setting and it has advantages in that less radiation is delivered to the patient.

Visual outcomes of cataract surgery performed by supervised novice surgeons during training in rural China

To assess the outcomes of cataract surgery performed by novice surgeons during training in a rural programme. Design: Retrospective study. Participants: Three hundred thirty-four patients operated by two trainees under supervision at rural Chinese county hospitals. Methods: Two trainees performed surgeries under supervision. Visual acuity, refraction and examinations were carried out 3 months postoperatively. Main Outcome Measures: Postoperative uncorrected visual acuity, pinhole visual acuity, causes of visual impairment (postoperative uncorrected visual acuity<6/18) Results: Among 518 operated patients, 426 (82.2%) could be contacted and 334 (64.4% of operated patients) completed the examinations. The mean age was 74.1±8.8 years and 62.9% were women. Postoperative uncorrected visual acuity was available in 372 eyes. Among them, uncorrected visual acuity was ≥6/18 in 278 eyes (74.7%) and <6/60 in 60 eyes (16.1%), and 323 eyes (86.8%) had pinhole visual acuity≥6/18 and 38 eyes (10.2%) had pinhole visual acuity<6/60. Main causes of visual impairment were uncorrected refractive error (63.9%) and comorbid eye disease (24.5%). Comorbid eye diseases associated with pinhole visual acuity<6/60 (n=23, 6.2%) included glaucoma, other optic nerve atrophy, vitreous haemorrhage and retinal detachment. Conclusions: The findings suggest that hands-on training remains safe and effective even when not implemented in centralized training centres. Further refinement of the training protocol, providing postoperative refractive services and more accurate preoperative intraocular lens calculations, can help optimize outcomes. © 2012 The Authors Clinical and Experimental Ophthalmology © 2012 Royal Australian and New Zealand College of Ophthalmologists.

Health care professionals’ experience, understanding and perception of need of advanced cancer patients with cachexia and their families: The benefits of a dedicated clinic.

Background: Cachexia has been defined as an on-going loss of skeletal muscle mass that cannot be fully reversed by conventional nutritional support. It can be found in up to 80% of patients with advanced cancer and has profound psycho-social consequences for patients and their families. There is a paucity of studies examining the role and experience of healthcare professionals in relation to cachexia and existing studies suggest that professional staff have limited understanding and do not intervene effectively.
Aim: To identify barriers and facilitators to good practice in cachexia care in order to inform future developments in service provision.
Design: An exploratory qualitative study was conducted employing semi-structured interviews with a range of healthcare professionals recruited purposefully from an Australian hospital. Interviews were conducted in private rooms within the hospital.
Setting/participants: A range of healthcare professionals responsible for cancer care were recruited from a large Australian teaching hospital.
Results: Interviews were conducted with 8 healthcare professionals responsible for delivering cancer care. Four themes were identified: formal and informal education, knowledge and understanding, truth telling in cachexia and palliative care, and, a multi-disciplinary approach. Findings show how improved knowledge and understanding across a staff body can lead to improved staff confidence and a willingness to address cancer cachexia and its consequences with patients and their families.
Conclusion: Comparison with previous studies illustrates the importance of improving knowledge and understanding about cachexia and how this can contribute to staff having the skills and experience necessary to address cachexia and provide an improved care experience for patients and carers.

Ectopic bone formation in rapidly fabricated acellular injectable dense collagen-Bioglass hybrid scaffolds via gel aspiration-ejection

Gel aspiration-ejection (GAE) has recently been introduced as an effective technique for the rapid production of injectable dense collagen (IDC) gel scaffolds with tunable collagen fibrillar densities (CFDs) and microstructures. Herein, a GAE system was applied for the advanced production and delivery of IDC and IDC-Bioglass® (IDC-BG) hybrid gel scaffolds for potential bone tissue engineering applications. The efficacy of GAE in generating mineralizable IDC-BG gels (from an initial 75-25 collagen-BG ratio) produced through needle gauge numbers 8G (3.4 mm diameter and 6 wt% CFD) and 14G (1.6 mm diameter and 14 wt% CFD) was investigated. Second harmonic generation (SHG) imaging of as-made gels revealed an increase in collagen fibril alignment with needle gauge number. In vitro mineralization of IDC-BG gels was confirmed where carbonated hydroxyapatite was detected as early as day 1 in simulated body fluid, which progressively increased up to day 14. In vivo mineralization of, and host response to, acellular IDC and IDC-BG gel scaffolds were further investigated following subcutaneous injection in adult rats. Mineralization, neovascularization and cell infiltration into the scaffolds was enhanced by the addition of BG and at day 21 post injection, there was evidence of remodelling of granulation tissue into woven bone-like tissue in IDC-BG. SHG imaging of explanted scaffolds indicated collagen fibril remodelling through cell infiltration and mineralization over time. In sum, the results suggest that IDC-BG hybrid gels have osteoinductive properties and potentially offer a novel therapeutic approach for procedures requiring the injectable delivery of a malleable and dynamic bone graft that mineralizes under physiological conditions

The spectrum of paediatric cardiac disease presenting to an outpatient clinic in Malawi

BACKGROUND: As progress is made towards attaining Millennium Development Goal 4, further reductions in paediatric mortality will only be achieved by concentrating on the burden of non-communicable or neglected diseases. The literature relating to paediatric cardiac disease in sub-Saharan Africa is sparse. There are no published descriptions of paediatric cardiac disease from Malawi, making it impossible to estimate the contribution it makes to childhood morbidity and mortality.

FINDINGS: In 2008, a paediatric cardiac clinic with echocardiogram scanning was established in Blantyre, southern Malawi. Between January 2009 and February 2011, the age and cardiac diagnosis of every child with an abnormal echocardiogram was recorded in a database. Of 250 children, 139 (55.6%) had congenital heart disease, and 111 (44.4%) acquired heart disease. Ventricular septal defect (VSD) (24%), Tetralogy of Fallot (10%) and patent ductus arteriousus (7.2%) were the commonest forms of congenital heart disease. Rheumatic heart disease (RHD) (22.4%) and dilated cardiomyopathy (13.6%) were the commonest acquired diseases. The mean age of presentation was 3 years 2 months for VSD and 11 years 6 months for RHD.

CONCLUSIONS: In this cohort of children from one centre in Malawi, acquired heart disease - in particular rheumatic heart disease was almost as common as congenital heart disease. Most presented late. It is likely that untreated cardiac disease causes a large number of childhood deaths in Malawi. In addition to renewing secondary preventative efforts against rheumatic heart disease, adequate and accessible cardiothoracic surgical services should be established at a regional level.

Determinants of uptake and maintenance of active commuting to school

The objective was to identify determinants of uptake and maintenance of active school travel (AST) over 4 years in children aged 9 at baseline. Data from wave 1 (n=8502) and 2 (n=7479) of the Growing Up in Ireland study were analysed. At 9- and 13-years 25% and 20% engaged in AST. Children were more likely to maintain or take-up AST if they lived in an urban area. Change in distance to school influenced both maintenance and adoption of AST, with a negative impact seen for increased distance between 9 and 13 years and a positive impact seen for decreased distance. Some factors which predict uptake and maintenance of AST are modifiable and can inform intervention development.