The four-variable modification of diet in renal disease formula underestimates glomerular filtration rate in obese type 2 diabetic individuals with chronic kidney disease.

AIMS/HYPOTHESIS: GFR is commonly estimated using the four-variable Modification of Diet in Renal Disease (MDRD) formula and this forms the basis for classification of chronic kidney disease (CKD). We investigated the effect of obesity on the estimation of glomerular filtration rate in type 2 diabetic participants with CKD. METHODS: We enrolled 111 patients with type 2 diabetes mellitus in different stages of CKD. GFR was measured using (51)Cr-labelled EDTA plasma clearance and was estimated using the four-variable MDRD formula. RESULTS: The bias between estimated and measured GFR was -22.4 (-33.8 to -11.0) p < 0.001 in the obese group compared with -6.04 (-17.6 to -5.5) p = 0.299 in the non-obese group. When GFR was indexed to body surface area of 1.73 m(2), the bias remained significant at -9.4 (-13.4 to -5.4) p < 0.001 in the obese participants. CONCLUSIONS/INTERPRETATION: This study suggests that the four-variable MDRD formula significantly underestimates GFR in obese type 2 diabetic participants with CKD.

Removal of eye movement artefacts from single channel recordings of retinal evoked potentials using synchronous dynamical embedding and independent component analysis.

A system is described for the removal of eye movement and blink artefacts from single channel pattern reversal electroretinogram recordings of very poor signal-to-noise ratios. Artefacts are detected and removed by using a blind source separation technique based on the jadeR independent component analysis algorithm. The single channel data are arranged as a series of overlapping time-delayed vectors forming a dynamical embedding matrix. The structure of this matrix is constrained to the phase of the stimulation epoch: the term synchronous dynamical embedding is coined. A novel method using a marker channel with a non-independent synchronous feature is employed to identify the single most relevant source estimation for reconstruction and signal recovery. This method is non-lossy, all underlying signal being recovered. In synthetic datasets of defined noise content and in standardised real data recordings, the performance of this technique is compared to conventional fixed-threshold hard-limit rejection. The most significant relative improvements are achieved when movement and blink artefacts are greatest: no improvement is demonstrable for the random noise only situation.

What impact did a Paediatric Early Warning system have on emergency admissions to the paediatric intensive care unit? An observational cohort study.

UNLABELLED: The ideology underpinning Paediatric Early Warning systems (PEWs) is that earlier recognition of deteriorating in-patients would improve clinical outcomes. OBJECTIVE: To explore how the introduction of PEWs at a tertiary children's hospital affects emergency admissions to the Paediatric Intensive Care Unit (PICU) and the impact on service delivery. To compare 'in-house' emergency admissions to PICU with 'external' admissions transferred from District General Hospitals (without PEWs). METHOD: A before-and-after observational study August 2005-July 2006 (pre), August 2006-July 2007 (post) implementation of PEWs at the tertiary children's hospital. RESULTS: The median Paediatric Index of Mortality (PIM2) reduced; 0.44 vs 0.60 (p<0.001). Fewer admissions required invasive ventilation 62.7% vs 75.2% (p=0.015) for a shorter median duration; four to two days. The median length of PICU stay reduced; five to three days (p=0.002). There was a non-significant reduction in mortality (p=0.47). There was no comparable improvement in outcome seen in external emergency admissions to PICU. A 39% reduction in emergency admission total beds days reduced cancellation of major elective surgical cases and refusal of external PICU referrals. CONCLUSIONS: Following introduction of PEWs at a tertiary children's hospital PIM2 was reduced, patients required less PICU interventions and had a shorter length of stay. PICU service delivery improved.

A review of evidence of health benefit from artificial neural networks in medical intervention.

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rjle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer.

A Bayesian framework is introduced to carry out Automatic Relevance Determination (ARD) in feedforward neural networks to model censored data. A procedure to identify and interpret the prognostic group allocation is also described. These methodologies are applied to 1616 records routinely collected at Christie Hospital, in a monthly cohort study with 5-year follow-up. Two cohort studies are presented, for low- and high-risk patients allocated by standard clinical staging. The results of contrasting the Partial Logistic Artificial Neural Network (PLANN)-ARD model with the proportional hazards model are that the two are consistent, but the neural network may be more specific in the allocation of patients into prognostic groups. With automatic model selection, the regularised neural network is more conservative than the default stepwise forward selection procedure implemented by SPSS with the Akaike Information Criterion.

Issues in online patient self-reporting of health status.

Patient self-reporting of symptoms and quality of life following surgical interventions is generally delivered in the form of paper-based questionnaires to be completed in the outpatient clinic or at home. A commonly used tool for patient self-reporting of quality of life is the EQ5D health status questionnaire which, while limited in scope, has general applicability across a range of health interventions. In this article we examine the issues relating to online patient self-reporting using this questionnaire and the wider implications for the online reporting of health status.

Determination of mode of ventilation using OSRE.

This study classifies the mode of ventilation using respiratory rate, inhaled and exhaled carbon dioxide concentrations in anaesthetised patients. Thirty seven patients were breathing spontaneously (SPONT) and 50 were on a ventilator (intermittent positive pressure ventilation, IPPV). A data-based methodology for rule inference from trained neural networks, orthogonal search-based rule extraction, identified two sets of low-order Boolean rules for differential identification of the mode of ventilation. Combining both models produced three possible outcomes; IPPV, SPONT and 'Uncertain'. The true positive rates were approximately maintained at 96% for IPPV and 93% for SPONT, with false positive rates of 0.4% for each category and 4.3% 'Uncertain' inferences.

Continuous and discrete time survival analysis: neural network approaches.

In this paper we describe and compare two neural network models aimed at survival analysis modeling, based on formulations in continuous and discrete time. Learning in both models is approached in a Bayesian inference framework. We test the models on a real survival analysis problem, and we show that both models exhibit good discrimination and calibration capabilities. The C index of discrimination varied from 0.8 (SE=0.093) at year 1, to 0.75 (SE=0.034) at year 7 for the continuous time model; from 0.81 (SE=0.07) at year 1, to 0.75 (SE=0.033) at year 7 for the discrete time model. For both models the calibration was good (p<0.05) up to 7 years.

Breast cancer predictions by neural networks analysis: a comparison with logistic regression.

This paper presents an exploratory fixed time study to identify the most significant covariates as a precursor to a longitudinal study of specific mortality, disease free survival and disease recurrences. The data comprise consecutive patients diagnosed with primary breast cancer and entered into the study from 1996 at a single French clinical center, Centre Léon Bérard, based in Lyon, where they received standard treatment. The methodology was to compare and contrast multi-layer perceptron neural networks (NN) with logistic regression (LR), to identify key covariates and their interactions and to compare the selected variables with those routinely used in clinical severity of illness indices for breast cancer. The Logistic regression in this work was chosen as an accepted standard for prediction by biostatisticians in order to evaluate the neural network. Only covariates available at the time of diagnosis and immediately following surgery were used. We used for comparison classification performance indices: AUROC (AREA Under Receiver-Operating Characteristics) curves, sensitivity, specificity, accuracy and positive predictive value for the two following events of interest: Specific Mortality and Disease Free Survival.

Tumour grading from magnetic resonance spectroscopy: a comparison of feature extraction with variable selection.

Magnetic resonance spectroscopy (MRS) provides a non-invasive measurement of the biochemistry of living tissue. However, signal variation due to tissue heterogeneity causes considerable mixing between different disease categories, making accurate class assignments difficult. This paper compares a systematic methodology for classifier design using multivariate bayesian variable selection (MBVS), with one based on feature extraction using independent component analysis (ICA). We illustrate the methodology and assess the classification performance using a data set comprising 41 magnetic resonance spectra acquired in vivo from two grades of brain tumour, namely low- and medium-grade astrocytic tumours, labelled astrocytomas (AST), and high-grade gliomas and glioblastomas labelled glioblastomas (GL). The aim of this study is threefold. First, to describe the application of the alternative methodologies to MRS, then to benchmark their classification performance, and finally to interpret the classification models in terms of biologically relevant signals derived from the spectra. The classification performance is assessed using the bootstrap method and by application to a test sample in a retrospective study.