A web-based telemedicine system for low-resource settings 13 years on: insights from referrers and specialists

Background: One way to tackle health inequalities in resource-poor settings is to establish links between doctors and health professionals there and specialists elsewhere using web-based telemedicine. One such system run by the Swinfen Charitable Trust has been in existence for 13 years which is an unusually long time for such systems.

Objective: We wanted to gain some insights into whether and how this system might be improved.

Methods: We carried out a survey by questionnaire of referrers and specialists over a six months period.

Results: During the study period, a total of 111 cases were referred from 35 different practitioners, of whom 24% were not doctors. Survey replies were received concerning 67 cases, a response rate of 61 per cent. Eighty-seven per cent of the responding referrers found the telemedicine advice useful, and 78% were able to follow the advice provided. As a result of the advice received, the diagnosis was changed in 22% of all cases and confirmed in a further 18 per cent. Patient management was changed in 33 per cent. There was no substantial difference between doctors and non-doctors. During the study period, the 111 cases were responded to by 148 specialists, from whom 108 replies to the questionnaire were received, a response rate of 73 per cent. About half of the specialists (47%) felt that their advice had improved the management of the patients. There were 62 cases where it was possible to match up the opinions of the referrer and the consultants about the value of a specific teleconsultation. In 34 cases (55%) the referrers and specialists agreed about the value. However, in 28 cases (45%) they did not: specialists markedly underestimated the value of a consultation compared to referrers. Both referrers and specialist were extremely positive about the system which appears to be working well. Minor changes such as a clearer referral template and an improved web interface for specialists may improve it.

Analysis of VSC-based HVDC System under DC Faults

This paper analyzes the behavior of a Voltage Source Converter Based HVDC system under DC cable fault conditions. The behavior of the HVDC system during a permanent line-to-earth fault is analyzed, outlining the systems configuration and behavior at each stage of the fault timeline. Operation of the proposed system under a single earthing configurations i.e. Converter (solid) earthed/AC transformer unearthed, was analyzed and simulated, with particular attention paid to the converters operation. It was observed that the development of potential earth loops within the system as a result of DC line- toearth faults leads to substantial overcurrent and results in system configuration oscillation.

Proposing the deep dynamic Bayesian network as a future computer based medical system

The development of new learning models has been of great importance throughout recent years, with a focus on creating advances in the area of deep learning. Deep learning was first noted in 2006, and has since become a major area of research in a number of disciplines. This paper will delve into the area of deep learning to present its current limitations and provide a new idea for a fully integrated deep and dynamic probabilistic system. The new model will be applicable to a vast number of areas initially focusing on applications into medical image analysis with an overall goal of utilising this approach for prediction purposes in computer based medical systems.

Host-based P2P flow identification and use in real-time

Data identification is a key task for any Internet Service Provider (ISP) or network administrator. As port fluctuation and encryption become more common in P2P traffic wishing to avoid identification, new strategies must be developed to detect and classify such flows. This paper introduces a new method of separating P2P and standard web traffic that can be applied as part of a data mining process, based on the activity of the hosts on the network. Unlike other research, our method is aimed at classifying individual flows rather than just identifying P2P hosts or ports. Heuristics are analysed and a classification system proposed. The accuracy of the system is then tested using real network traffic from a core internet router showing over 99% accuracy in some cases. We expand on this proposed strategy to investigate its application to real-time, early classification problems. New proposals are made and the results of real-time experiments compared to those obtained in the data mining research. To the best of our knowledge this is the first research to use host based flow identification to determine a flows application within the early stages of the connection.

Tissue microarray study for classification of breast tumors

Clinical and pathological heterogeneity of breast cancer hinders selection of appropriate treatment for individual cases. Molecular profiling at gene or protein levels may elucidate the biological variance of tumors and provide a new classification system that correlates better with biological, clinical and prognostic parameters. We studied the immunohistochemical profile of a panel of seven important biomarkers using tumor tissue arrays. The tumor samples were then classified with a monothetic (binary variables) clustering algorithm. Two distinct groups of tumors are characterized by the estrogen receptor (ER) status and tumor grade (p = 0.0026). Four biomarkers, c-erbB2, Cox-2, p53 and VEGF, were significantly overexpressed in tumors with the ER-negative (ER-) phenotype. Eight subsets of tumors were further identified according to the expression status of VEGF, c-erbB2 and p53. The malignant potential of the ER-/VEGF+ subgroup was associated with the strong correlations of Cox-2 and c-erb132 with VEGF. Our results indicate that this molecular classification system, based on the statistical analysis of immunohistochemical profiling, is a useful approach for tumor grouping. Some of these subgroups have a relative genetic homogeneity that may allow further study of specific genetically-controlled metabolic pathways. This approach may hold great promise in rationalizing the application of different therapeutic strategies for different subgroups of breast tumors. (C) 2003 Elsevier Inc. All rights reserved.

Low Complexity Spectral Analysis of Heart-Rate-Variability through a Wavelet based FFT

In this paper, a low complexity system for spectral analysis of heart rate variability (HRV) is presented. The main idea of the proposed approach is the implementation of the Fast-Lomb periodogram that is a ubiquitous tool in spectral analysis, using a wavelet based Fast Fourier transform. Interestingly we show that the proposed approach enables the classification of processed data into more and less significant based on their contribution to output quality. Based on such a classification a percentage of less-significant data is being pruned leading to a significant reduction of algorithmic complexity with minimal quality degradation. Indeed, our results indicate that the proposed system can achieve up-to 45% reduction in number of computations with only 4.9% average error in the output quality compared to a conventional FFT based HRV system.

An Efficient LS-SVM-Based Method for Fuzzy System Construction

This paper proposes an efficient learning mechanism to build fuzzy rule-based systems through the construction of sparse least-squares support vector machines (LS-SVMs). In addition to the significantly reduced computational complexity in model training, the resultant LS-SVM-based fuzzy system is sparser while offers satisfactory generalization capability over unseen data. It is well known that the LS-SVMs have their computational advantage over conventional SVMs in the model training process; however, the model sparseness is lost, which is the main drawback of LS-SVMs. This is an open problem for the LS-SVMs. To tackle the nonsparseness issue, a new regression alternative to the Lagrangian solution for the LS-SVM is first presented. A novel efficient learning mechanism is then proposed in this paper to extract a sparse set of support vectors for generating fuzzy IF-THEN rules. This novel mechanism works in a stepwise subset selection manner, including a forward expansion phase and a backward exclusion phase in each selection step. The implementation of the algorithm is computationally very efficient due to the introduction of a few key techniques to avoid the matrix inverse operations to accelerate the training process. The computational efficiency is also confirmed by detailed computational complexity analysis. As a result, the proposed approach is not only able to achieve the sparseness of the resultant LS-SVM-based fuzzy systems but significantly reduces the amount of computational effort in model training as well. Three experimental examples are presented to demonstrate the effectiveness and efficiency of the proposed learning mechanism and the sparseness of the obtained LS-SVM-based fuzzy systems, in comparison with other SVM-based learning techniques.

EGF61 polymorphism predicts complete pathologic response to cetuximab-based chemoradiation independent of KRAS status in locally advanced rectal cancer patients

BACKGROUND: Cetuximab has shown significant clinical activity in metastatic colon cancer. However, cetuximab-containing neoadjuvant chemoradiation has not been shown to improve tumor response in locally advanced rectal cancer patients in recent phase I/II trials. We evaluated functional germline polymorphisms of genes involved in epidermal growth factor receptor pathway, angiogenesis, antibody-dependent cell-mediated cytotoxicity, DNA repair, and drug metabolism, for their potential role as molecular predictors for clinical outcome in locally advanced rectal cancer patients treated with preoperative cetuximab-based chemoradiation.

METHODS: 130 patients (74 men and 56 women) with locally advanced rectal cancer (4 with stage II, 109 with stage III, and 15 with stage IV, 2 unknown) who were enrolled in phase I/II clinical trials treated with cetuximab-based chemoradiation in European cancer centers were included. Genomic DNA was extracted from formalin-fixed paraffin-embedded tumor samples and genotyping was done by using PCR-RFLP assays. Fisher's exact test was used to examine associations between polymorphisms and complete pathologic response (pCR) that was determined by a modified Dworak classification system (grade III vs. grade IV: complete response).

RESULTS: Patients with the epidermal growth factor (EGF) 61 G/G genotype had pCR of 45% (5/11), compared with 21% (11/53) in patients heterozygous, and 2% (1/54) in patients homozygous for the A/A allele (P < 0.001). In addition, this association between EGF 61 G allele and pCR remained significant (P = 0.019) in the 59 patients with wild-type KRAS.

CONCLUSION: This study suggested EGF A+61G polymorphism to be a predictive marker for pCR, independent of KRAS mutation status, to cetuximab-based neoadjuvant chemoradiation of patients with locally advanced rectal cancer.

A systematic review of evidence-based assessment practices by allied health practitioners for children with cerebral palsy

AIM: The routine use of psychometrically robust assessment tools is integral to best practice. This systematic review aims to determine the extent to which evidence-based assessment tools were used by allied health practitioners for children with cerebral palsy (CP).

METHOD: The Preferred Reporting Items for Systematic Reviews and Meta-Analysis protocols 2015 was employed. A search strategy applied the free text terms: 'allied health practitioner', 'assessment', and 'cerebral palsy', and related subject headings to seven databases. Included articles reported assessment practices of occupational therapists, physiotherapists, or speech pathologists working with children with CP aged 0 to 18 years, published from the year 2000.

RESULTS: Fourteen articles met the inclusion criteria. Eighty-eight assessment tools were reported, of which 23 were in high use. Of these, three tools focused on gross motor function and had acceptable validity for use with children with CP: Gross Motor Function Measure, Gross Motor Function Classification System, and goniometry. Validated tools to assess other activity components, participation, quality of life, and pain were used infrequently or not at all.

INTERPRETATION: Allied health practitioners used only a few of the available evidence-based assessment tools. Assessment findings in many areas considered important by children and families were rarely documented using validated assessment tools.

Oily fish consumption, dietary docosahexaenoic acid and eicosapentaenoic acid intakes, and associations with neovascular age-related macular degeneration

Background: Fish intake, the major source of docosahexaenoic acid (DHA) and eicosapentaenoic acid (EPA), may reduce the risk of age-related macular degeneration (AMD). Objective: We investigated the association of oily fish and dietary DHA and EPA with neovascular AMD (NV-AMD). Design: Participants aged =65 y in the cross-sectional population-based EUREYE study underwent fundus photography and were interviewed by using a food-frequency questionnaire. Fundus images were graded by the International Classification System for Age Related Maculopathy. Questionnaire data were converted to nutrient intakes with the use of food-composition tables. Survey logistic regression was used to calculate odds ratios (ORs) and 95% CIs of energy-adjusted quartiles of EPA or DHA with NV-AMD, taking into account potential confounders. Results: Dietary intake data and fundus images were available for 105 cases with NV-AMD and for 2170 controls without any features of early or late AMD. Eating oily fish at least once per week compared with less than once per week was associated with a halving of the odds of NV-AMD (OR = 0.47; 95% CI: 0.33, 0.68; P = 0.002). Compared with the lowest quartile, there was a significant trend for decreased odds with increasing quartiles of either DHA or EPA. ORs in the highest quartiles were 0.32 (95% CI: 0.12, 0.87; P = 0.03) for DHA and 0.29 (95% CI: 0.11, 0.73; P = 0.02) for EPA. Conclusions: Eating oily fish at least once per week compared with less than once per week was associated with a halving of the OR for NV-AMD. © 2008 American Society for Nutrition.

A Diagnostic System Using Broad Categories With Clinicaly Relevant Specifiers: Lessons for ICD-10

A diagnostic system for ICD-11 is proposed which commences with broad reorganization and simplification of the current categories and the use of clinically relevant specifiers. Such changes have implications for the positioning of diagnostic groups and lead to a range of possibilities for improving terminology and the juxtaposition of individual conditions. The development of ICD-11 provides the first opportunity in almost two decades to improve the validity and reliability of the international classification system. Widespread change in broad categories and criteria cannot be justified by research that has emerged since the last revision. It would also be disruptive to clinical practice and might devalue past research work. However, the case for reorganization of the categories is stronger and has recently been made by an eminent international group of researchers (Andrews et al., 2009). A simpler, interlinked diagnostic system is proposed here which is likely to have fewer categories than its predecessor. There are major advantages of such a system for clinical practice and research and it could also produce much needed simplification for primary care (Gask et al., 2008) and the developing world (Wig, 1990; Kohn et al., 2004).

Gender Classification via Lips: Static and Dynamic Features

Automatic gender classification has many security and commercial applications. Various modalities have been investigated for gender classification with face-based classification being the most popular. In some real-world scenarios the face may be partially occluded. In these circumstances a classification based on individual parts of the face known as local features must be adopted. We investigate gender classification using lip movements. We show for the first time that important gender specific information can be obtained from the way in which a person moves their lips during speech. Furthermore our study indicates that the lip dynamics during speech provide greater gender discriminative information than simply lip appearance. We also show that the lip dynamics and appearance contain complementary gender information such that a model which captures both traits gives the highest overall classification result. We use Discrete Cosine Transform based features and Gaussian Mixture Modelling to model lip appearance and dynamics and employ the XM2VTS database for our experiments. Our experiments show that a model which captures lip dynamics along with appearance can improve gender classification rates by between 16-21% compared to models of only lip appearance.