Classification of healthcare data using genetic fuzzy logic system and wavelets

Healthcare plays an important role in promoting the general health and well-being of people around the world. The difficulty in healthcare data classification arises from the uncertainty and the high-dimensional nature of the medical data collected. This paper proposes an integration of fuzzy standard additive model (SAM) with genetic algorithm (GA), called GSAM, to deal with uncertainty and computational challenges. GSAM learning process comprises three continual steps: rule initialization by unsupervised learning using the adaptive vector quantization clustering, evolutionary rule optimization by GA and parameter tuning by the gradient descent supervised learning. Wavelet transformation is employed to extract discriminative features for high-dimensional datasets. GSAM becomes highly capable when deployed with small number of wavelet features as its computational burden is remarkably reduced. The proposed method is evaluated using two frequently-used medical datasets: the Wisconsin breast cancer and Cleveland heart disease from the UCI Repository for machine learning. Experiments are organized with a five-fold cross validation and performance of classification techniques are measured by a number of important metrics: accuracy, F-measure, mutual information and area under the receiver operating characteristic curve. Results demonstrate the superiority of the GSAM compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. The proposed approach is thus helpful as a decision support system for medical practitioners in the healthcare practice.

Finite element modeling and analysis of thrombosis in middle cerebral artery

Thrombotic stroke, which is caused by blood clot in the cerebral artery, is a major source of increased mortality and morbidity. Considering as efficient and fastest methods, mathematical approaches have gained significant importance for analyzing and understanding the biological events like thrombosis. This paper presents a computational model to analyze the effects of thrombosis using the theory of coupled fluid dynamics-structure interaction. The finite element method is used for the modeling of thrombosis (blood clot) of different stages in the middle cerebral artery with physiological compliance. The developed model is used to investigate the consequences that occur due to the various sizes of clots in the artery in the form of blood flow velocity, blood pressure, and artery wall stress. Such numerical assessment will facilitate better understanding of the biophysical process in case of thrombosis and thus would support medical practitioners to take faster curing steps.

Responsible management of motor vehicle drivers with dementia

When Bridget Driscoll, a 44-year-old mother of two died after being struck by a motor vehicle, considered to be the first motor vehicle fatality in UK and possibly the world, the coroner stated 'I trust this sort of nonsense will never happen again'.1 Sadly, the coroner, medical practitioners and general public would be deeply and repeatedly disappointed. It was 1896. Motor vehicles were a curiosity. Drivers did not undergo any form of testing, be it medical fitness, driving ability or otherwise, and there were no licensing regulatory agencies. By 2010, road injury was the ninth most common cause of death globally (1.3 million deaths per annum) and dementia the fourth most common in high income countries.2 By 2030 the number of all licensed UK drivers who are 65 years or older will increase by almost 50% to almost one in every four drivers.3 If the juxtaposition of driving with dementia in an ageing population is not already a contentious social, political and medical issue, it certainly will become so.

Critically impaired infants and end of life decision making : resource allocation and difficult decisions

Decisions to withdraw or withhold life-sustaining treatment are contentious, and offer difficult moral dilemmas to both medical practitioners and the judiciary. This issue is exacerbated when the patient is unable to exercise autonomy and is entirely dependent on the will of others.This book focuses on the legal and ethical complexities surrounding end of life decisions for critically impaired and extremely premature infants. Neera Bhatia explores decisions to withdraw or withhold life-sustaining treatment from critically impaired infants and addresses the controversial question, which lives are too expensive to treat? Bringing to bear such key issues as clinical guidance, public awareness, and resource allocation, the book provides a rational approach to end of life decision making, where decisions to withdraw or withhold treatment may trump other competing interests.The book will be of great interest and use to scholars and students of bioethics, medical law, and medical practitioners.

An integrated framework for suicide risk prediction

Suicide is a major concern in society. Despite of great attention paid by the community with very substantive medico-legal implications, there has been no satisfying method that can reliably predict the future attempted or completed suicide. We present an integrated machine learning framework to tackle this challenge. Our proposed framework consists of a novel feature extraction scheme, an embedded feature selection process, a set of risk classifiers and finally, a risk calibration procedure. For temporal feature extraction, we cast the patient’s clinical history into a temporal image to which a bank of one-side filters are applied. The responses are then partly transformed into mid-level features and then selected in 1-norm framework under the extreme value theory. A set of probabilistic ordinal risk classifiers are then applied to compute the risk probabilities and further re-rank the features. Finally, the predicted risks are calibrated. Together with our Australian partner, we perform comprehensive study on data collected for the mental health cohort, and the experiments validate that our proposed framework outperforms risk assessment instruments by medical practitioners.

Healthcare in continuum for an ageing population - national self monitoring or remote offshore monitoring for Australia?

Australia is a country, similar to other developed nations, confronting an ageing population with complex demographics. Ensuring continued healthcare for the ageing, while providing sufficient support for the already aged population requiring assistance, is at the forefront of the national agenda. Varied initiatives are with foci to leverage the advantages of ICTs leading to e-Health provisioning and assisted technologies. While these initiatives increasingly put budgetary constraints on local and federal governments, there is also a case for offshore resourcing of non-critical health services, to support, streamline and enhance the continuum of care, as the nation faces acute shortages of medical practitioners and nurses. However, privacy and confidentiality concerns in this context are a significant issue in Australia. In this paper, we take the position that if the National and state electronic health records system initiatives, are fully implemented, offshore resourcing can be a feasible complementary option resulting in a win-win situation of cutting costs and enabling the continuum of healthcare.

Hierarchical gene selection and genetic fuzzy system for cancer microarray data classification

This paper introduces a novel approach to gene selection based on a substantial modification of analytic hierarchy process (AHP). The modified AHP systematically integrates outcomes of individual filter methods to select the most informative genes for microarray classification. Five individual ranking methods including t-test, entropy, receiver operating characteristic (ROC) curve, Wilcoxon and signal to noise ratio are employed to rank genes. These ranked genes are then considered as inputs for the modified AHP. Additionally, a method that uses fuzzy standard additive model (FSAM) for cancer classification based on genes selected by AHP is also proposed in this paper. Traditional FSAM learning is a hybrid process comprising unsupervised structure learning and supervised parameter tuning. Genetic algorithm (GA) is incorporated in-between unsupervised and supervised training to optimize the number of fuzzy rules. The integration of GA enables FSAM to deal with the high-dimensional-low-sample nature of microarray data and thus enhance the efficiency of the classification. Experiments are carried out on numerous microarray datasets. Results demonstrate the performance dominance of the AHP-based gene selection against the single ranking methods. Furthermore, the combination of AHP-FSAM shows a great accuracy in microarray data classification compared to various competing classifiers. The proposed approach therefore is useful for medical practitioners and clinicians as a decision support system that can be implemented in the real medical practice.

Hidden Markov models for cancer classification using gene expression profiles

This paper introduces an approach to cancer classification through gene expression profiles by designing supervised learning hidden Markov models (HMMs). Gene expression of each tumor type is modelled by an HMM, which maximizes the likelihood of the data. Prominent discriminant genes are selected by a novel method based on a modification of the analytic hierarchy process (AHP). Unlike conventional AHP, the modified AHP allows to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test and signal to noise ratio. The modified AHP aggregates ranking results of individual gene selection methods to form stable and robust gene subsets. Experimental results demonstrate the performance dominance of the HMM approach against six comparable classifiers. Results also show that gene subsets generated by modified AHP lead to greater accuracy and stability compared to competing gene selection methods, i.e. information gain, symmetrical uncertainty, Bhattacharyya distance, and ReliefF. The modified AHP improves the classification performance not only of the HMM but also of all other classifiers. Accordingly, the proposed combination between the modified AHP and HMM is a powerful tool for cancer classification and useful as a real clinical decision support system for medical practitioners.

Disciplinary proceedings against doctors who abuse controlled substances

Study examined 27 reports from disciplinary tribunals against medical practitioners who abused narcotic analgesics (often combined with other drugs of addiction) between 2010 and 2015. The study covered all States and Territories except Tasmania (no reports were accessible for this jurisdiction. The reports revealed that 12 medical practitioners were in their 40s; five in their 30s; and one person still in the 20s. Although majority were General Practitioners (15 out of 27), other medical specialties were also represented. Self-administered Pethidine was the most prevalent opioid (11 out of 27), and was the only drug used alone. Morphine was self-administered by six doctors; the same number used high doses of Panadeine Forte, Codeine and Codeine Phosphate, and Fentanyl was abused by five doctors. Surprisingly, fewer medical practitioners appear to use such opiates such as Propofol, Tramadol and Tramol, Oxycodone and Endone. The examination of cases suggests lack of consistency in the imposition of professional sanctions and penalties by the relevant tribunals. The study concludes that disciplinary tribunals should apply the test of proportionality in the form of ‘reasonable necessity’ when deciding whether to remove or suspend the addicted medical practitioner from the Register.

Mass spectrometry cancer data classification using wavelets and genetic algorithm

This paper introduces a hybrid feature extraction method applied to mass spectrometry (MS) data for cancer classification. Haar wavelets are employed to transform MS data into orthogonal wavelet coefficients. The most prominent discriminant wavelets are then selected by genetic algorithm (GA) to form feature sets. The combination of wavelets and GA yields highly distinct feature sets that serve as inputs to classification algorithms. Experimental results show the robustness and significant dominance of the wavelet-GA against competitive methods. The proposed method therefore can be applied to cancer classification models that are useful as real clinical decision support systems for medical practitioners.

Cutting the cord: Can society over-invest in extremely premature and critically impaired neonates?

This article provides a critical examination of the allocation of scarce public health care funds in relation to extremely premature and sick neonates. Decisions to withdraw or withhold life-sustaining treatment from neonates born extremely premature are generally informed by arbitrary and often subjective considerations of those involved in their care – namely parents and medical practitioners. This article argues for a sharp and immediate focus in decisions to treat such neonates based on the allocation of limited health care resources. Accordingly, decisions to save and preserve the lives of imperilled neonates should not be limited to the immediate financial costs of medical treatment. More explicitly there should be a full appreciation of the cost of disability to the family, requirements for long-term care, and the benefits and associated costs of life, not only to the patient, but also to society.

Using Twitter to learn about the autism community

Considering the raising socio-economic burden of autism spectrum disorder (ASD), timely and evidence-driven public policy decision-making and communication of the latest guidelines pertaining to the treatment and management of the disorder is crucial. Yet evidence suggests that policy makers and medical practitioners do not always have a good understanding of the practices and relevant beliefs of ASD-afflicted individuals’ carers who often follow questionable recommendations and adopt advice poorly supported by scientific data. The key goal of the present work is to explore the idea that Twitter, as a highly popular platform for information exchange, could be used as a data-mining source to learn about the population affected by ASD—their behaviour, concerns, needs, etc. To this end, using a large data set of over 11 million harvested tweets as the basis for our investigation, we describe a series of experiments which examine a range of linguistic and semantic aspects of messages posted by individuals interested in ASD. Our findings, the first of their nature in the published scientific literature, strongly motivate additional research on this topic and present a methodological basis for further work.

Australian doctors’ non-clinical activities: results from the MABEL survey of doctors

Objective. The aim of the present study was to investigate non-clinical work conducted by Australian doctors.
Methods. This study was an exploratory descriptive study using data from Wave 5 of the Medicine in Australia: Balancing Employment and Life (MABEL) longitudinal survey, collected in 2012 from Australian medical practitioners (2200 general practitioners (GPs), 3455 specialists, 1270 specialists in training and 1656 hospital non-specialists). The main outcome measure was the number of hours worked per week in non-clinical work. Regression analysis was used to determine associations between non-clinical activities (i.e. education-related, management and administration and other) and personal and professional characteristics, including age, gender, job and life satisfaction, total clinical working hours, sector of practice
(public or private) and doctor type.
Results. Australian doctors spend an average of just under 7 h per week, or 16% of their working time, on non-clinical activities. Doctors who worked more hours on non-clinical activities overall, and in education-related and management and
administration specifically, were male, younger, had lower life satisfaction and generally spent fewer hours on clinical work. Lower job satisfaction was associated with longer management and administration hours, but not with time spent in
education-related activities. Specialists were more likely to work long non-clinical hours, whereas GPs were more likely to report none. Hospital non-specialists reported relatively high management and administration hours.
Conclusions. Further work is required to better understand the full range of non-clinical activities doctors are involved in and how this may impact future workforce projections.

Modified AHP for gene selection and cancer classification using type-2 fuzzy logic

This paper proposes a modification to the analytic hierarchy process (AHP) to select the most informative genes that serve as inputs to an interval type-2 fuzzy logic system (IT2FLS) for cancer classification. Unlike the conventional AHP, the modified AHP allows us to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test, and signal-to-noise ratio. The IT2FLS is introduced for the classification task due to its great ability for handling nonlinear, noisy, and outlier data, which are common problems in cancer microarray gene expression profiles. An unsupervised learning strategy using the fuzzy c-means clustering is employed to initialize parameters of the IT2FLS. Other classifiers such as multilayer perceptron network, support vector machine, and fuzzy ARTMAP are also implemented for comparisons. Experiments are carried out on three well-known microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, and prostate. Rather than the traditional cross validation, leave-one-out cross-validation strategy is applied for the experiments. Results demonstrate the performance dominance of the IT2FLS against the competing classifiers. More noticeably, the modified AHP improves the classification performance not only of the IT2FLS but of all other classifiers as well. Accordingly, the proposed combination between the modified AHP and IT2FLS is a powerful tool for cancer classification and can be implemented as a real clinical decision support system that is useful for medical practitioners.

General practitioners' perspectives regarding competence and confidentiality in an adolescent with suspected anorexia nervosa: legal and ethical considerations

In Victoria, Australia, the legal position regarding young people's competence to make medical treatment decisions has not been clarified in legislation, and a number of often vague common law decisions must be relied on for guidance. This situation produces a degree of uncertainty about appropriate professional practice, while also potentially impeding young people's rights claims in health care settings. With this in mind, the present research explored general practitioners' competence and confidentiality decisions regarding a 17-year-old female who presented with symptoms of an eating disorder. Questionnaires were sent to a random sample of 500 Victorian general practitioners, of whom 190 responded. After reading a case vignette, general practitioners indicated whether they would find the hypothetical patient competent and if they would maintain her confidentiality. Seventy-three per cent of respondents found the patient competent and most would have maintained confidentiality, at least initially. However, subsequent analysis of the rationales supplied for these decisions revealed a wide diversity in general practitioners' understandings and implementations of extant legal authority. This research highlights the need for general practitioners to be exposed to up-to-date and clinically relevant explanations of contemporary legal positions.