Using secondary knowledge to support decision tree classification of retrospective clinical data

Retrospective clinical data presents many challenges for data mining and machine learning. The transcription of patient records from paper charts and subsequent manipulation of data often results in high volumes of noise as well as a loss of other important information. In addition, such datasets often fail to represent expert medical knowledge and reasoning in any explicit manner. In this research we describe applying data mining methods to retrospective clinical data to build a prediction model for asthma exacerbation severity for pediatric patients in the emergency department. Difficulties in building such a model forced us to investigate alternative strategies for analyzing and processing retrospective data. This paper describes this process together with an approach to mining retrospective clinical data by incorporating formalized external expert knowledge (secondary knowledge sources) into the classification task. This knowledge is used to partition the data into a number of coherent sets, where each set is explicitly described in terms of the secondary knowledge source. Instances from each set are then classified in a manner appropriate for the characteristics of the particular set. We present our methodology and outline a set of experiential results that demonstrate some advantages and some limitations of our approach. © 2008 Springer-Verlag Berlin Heidelberg.

Prevalence of subclinical thyroid dysfunction and its relation to socioeconomic deprivation in the elderly:a community-based cross-sectional survey

Context: Population-based screening has been advocated for subclinical thyroid dysfunction in the elderly because the disorder is perceived to be common, and health benefits may be accrued by detection and treatment. Objective: The objective of the study was to determine the prevalence of subclinical thyroid dysfunction and unidentified overt thyroid dysfunction in an elderly population. Design, Setting, and Participants: A cross-sectional survey of a community sample of participants aged 65 yr and older registered with 20 family practices in the United Kingdom. Exclusions: Exclusions included current therapy for thyroid disease, thyroid surgery, or treatment within 12 months. Outcome Measure: Tests of thyroid function (TSH concentration and free T 4 concentration in all, with measurement of free T3 in those with low TSH) were conducted. Explanatory Variables: These included all current medical diagnoses and drug therapies, age, gender, and socioeconomic deprivation (Index of Multiple Deprivation, 2004) Analysis: Standardized prevalence rates were analyzed. Logistic regression modeling was used to determine factors associated with the presence of subclinical thyroid dysfunction Results: A total of 5960 attended for screening. Using biochemical definitions, 94.2% [95% confidence interval (CI) 93.8-94.6%] were euthyroid. Unidentified overt hyper- and hypothyroidism were uncommon (0.3, 0.4%, respectively). Subclinical hyperthyroidism and hypothyroidism were identified with similar frequency (2.1%, 95% CI 1.8-2.3%; 2.9%, 95% CI 2.6-3.1%, respectively). Subclinical thyroid dysfunction was more common in females (P < 0.001) and with increasing age (P < 0.001). After allowing for comorbidities, concurrent drug therapies, age, and gender, an association between subclinical hyperthyroidism and a composite measure of socioeconomic deprivation remained. Conclusions: Undiagnosed overt thyroid dysfunction is uncommon. The prevalence of subclinical thyroid dysfunction is 5%. We have, for the first time, identified an independent association between the prevalence of subclinical thyroid dysfunction and deprivation that cannot be explained solely by the greater burden of chronic disease and/or consequent drug therapies in the deprived population. Copyright © 2006 by The Endocrine Society.

The growth and awareness of health and safety at work, 1780-1900

This thesis examines the growth and awareness of health and safety at work between 1780 and 1900. In this period the hazards at work were increased by the intensification of production brought about by the Industrial Revolution, and new risks to health arose from the wider range of toxic substances in use by manufacturing industry. There is discussion in the thesis of the extent to which the problems were identified in an age of short life expectancy and limited medical knowledge. The sources studied have been largely medical, governmental, trade and press reports. The emphasis is on the first effects seen and recommendations made, and where possible, the extent of the problem and the effectiveness of any preventative measures adopted and examined. There is discussion of the growing involvement of the Government in industrial health and safety. The subject is viewed in the light of modern thinking on industrial health but uses a classification appropriate to historical resources. Psychological and minor afflictions, neglected in the 19th century, are not considered. The available literature is reviewed in each section. Three detailed case studies conclude the thesis, two on the notoriously dangerous occupations of metal grinding and pottery, and one on occupational eye injuries. Each study is based on a different type of source material. The thesis overall shows that there was extensive concern for health and safety at work, but no systematic approach and only ad hoc implementation of preventative measures; and that the rate at which conditions improved varied between different industries and different categories of workers . However, some modern principles of health and safety at work can be seen emerging, and the period laid the necessary medical, technical and legal foundations for developments in the present century.

Premature cardiovascular events and mortality in south Asians with type 2 diabetes in the United Kingdom Asian Diabetes Study - effect of ethnicity on risk

Background/Aim - People of south Asian origin have an excessive risk of morbidity and mortality from cardiovascular disease. We examined the effect of ethnicity on known risk factors and analysed the risk of cardiovascular events and mortality in UK south Asian and white Europeans patients with type 2 diabetes over a 2 year period. Methods - A total of 1486 south Asian (SA) and 492 white European (WE) subjects with type 2 diabetes were recruited from 25 general practices in Coventry and Birmingham, UK. Baseline data included clinical history, anthropometry and measurements of traditional risk factors – blood pressure, total cholesterol, HbA1c. Multiple linear regression models were used to examine ethnicity differences in individual risk factors. Ten-year cardiovascular risk was estimated using the Framingham and UKPDS equations. All subjects were followed up for 2 years. Cardiovascular events (CVD) and mortality between the two groups were compared. Findings - Significant differences were noted in risk profiles between both groups. After adjustment for clustering and confounding a significant ethnicity effect remained only for higher HbA1c (0.50 [0.22 to 0.77]; P?=?0.0004) and lower HDL (-0.09 [-0.17 to -0.01]; P?=?0.0266). Baseline CVD history was predictive of CVD events during follow-up for SA (P?

Comparative risk of microalbuminuria and proteinuria in UK residents of south Asian and white European ethnic background with type 2 diabetes:a report from UKADS

Objective - This study investigated and compared the prevalence of microalbuminuria and overt proteinuria and their determinants in a cohort of UK resident patients of white European or south Asian ethnicity with type 2 diabetes mellitus. Research design and methods - A total of 1978 patients, comprising 1486 of south Asian and 492 of white European ethnicity, in 25 general practices in Coventry and Birmingham inner city areas in England were studied in a cross-sectional study. Demographic and risk factor data were collected and presence of microalbuminuria and overt proteinuria assessed. Main outcome measures - Prevalences of microalbuminuria and overt proteinuria. Results - Urinary albumin:creatinine measurements were available for 1852 (94%) patients. The south Asian group had a lower prevalence of microalbuminuria, 19% vs. 23% and a higher prevalence of overt proteinuria, 8% vs. 3%, X2?=?15.85, 2df, P?=?0.0004. In multiple logistic regression models, adjusted for confounding factors, significantly increased risk for the south Asian vs. white European patients for overt proteinuria was shown; OR (95% CI) 2.17 (1.05, 4.49), P?=?0.0365. For microalbuminuria, an interaction effect for ethnicity and duration of diabetes suggested that risk for south Asian patients was lower in early years following diagnosis; OR for SA vs. WH at durations 0 and 1 year were 0.56 (0.37, 0.86) and 0.59 (0.39, 0.89) respectively. After 20 years’ duration, OR?=?1.40 (0.63, 3.08). Limitations - Comparability of ethnicity defined groups; statistical methods controlled for differences between groups, but residual confounding may remain. Analyses are based on a single measure of albumin:creatinine ratio. Conclusions - There were significant differences between ethnicity groups in risk factor profiles and microalbuminuria and overt proteinuria outcomes. Whilst south Asian patients had no excess risk of microalbuminuria, the risk of overt proteinuria was elevated significantly, which might be explained by faster progression of renal dysfunction in patients of south Asian ethnicity.

Psychological influence of the media on patients commencing oral anticoagulation in atrial fibrillation:a qualitative analysis

Background: Oral anticoagulation (OAC) reduces stroke risk in patients with atrial fibrillation (AF); however it is still underutilized and sometimes refused by patients. Two inter-related studies were undertaken to understand the experiences and what influences this un- derutilisation of warfarin treatment in AF patients. These studies explored physician and patient experiences of AF and OAC treatment. The paper focuses on specific sub-themes from the study that explored patients’ experiences will be discussed. Aim: The study in question aimed to explore the experiences which influence patients’ decisions to accept, decline or discontinue OAC. Methods: Semi-structured individual interviews with patients were con- ducted. Three sub-groups of patients (n = 11) diagnosed with AF were interviewed; those who accepted, refused, and who discontinued war- farin. Interpretative phenomenological analysis (IPA) was used to examine the data. IPA is a qualitative method that focuses on how participants make sense of an experiences phenomenon Results: Three over-arching themes comprised patients’ experiences: (i)the initial consultation, (ii) life after the consultation, and (iii) patients’reflections. In the last theme, patients reflected on their perceptions ofaspirin and warfarin. Aspirin was perceived as a natural wonder-drugwhile warfarin was perceived as a dangerous drug usually given to peo-ple at the end of their life. Interestingly they perceive both drugs as‘old’. However, for aspirin it had a positive association, old meaningtried and tested. While for warfarin, old meant ‘has been around fortoo long’.Conclusion: Media had an important role in how patients’ perceptionsof these two drugs were influenced. Literature shows that framingtechniques, i.e. using certain words or phrases such as ‘rat poison’, areprocesses adopted by media to alter medical knowledge into lay per-son’s language. Patients in turn form negative cognitive schemas,between the word ‘poison’ and warfarin, leading to the negative per-ception of warfarin which could influence non-adherence to treatment.This qualitative research highlighted the potential influences of themedia on AF patient perceptions commencing OAC treatment. Theassociation between media stimuli and patient perceptions on OACshould be further explored. The influential power of lay-media couldalso be instrumental in disseminating appropriate educational materialto the public

Adverse drug reaction teaching in UK undergraduate medical and pharmacy programmes

Objectives: To assess the extent of teaching about the Committee on Safety of Medicine's Yellow Card scheme and adverse drug reactions within UK Schools of Medicine and Pharmacy. Methods: A self-completed questionnaire sent to all heads of undergraduate schools of medicine and pharmacy within the UK. Results: The majority of undergraduate syllabuses feature the Yellow Card Scheme. Knowledge of the Yellow Card Scheme was assessed in 79% of pharmacy programmes and 57% of medical schools. Specialist speakers on the Yellow Card Scheme were infrequently used. Fewer than half of respondents provided students with a guide to reporting ADRs (43% pharmacy and 43% medical). There is some disagreement about the value of supplying students with printed material about the Yellow Card Scheme. Half of medical Schools did not think that supplying 'Current Problems In Pharmacovigilance' would be useful. Conclusions: It was found that in both medicine and pharmacy, courses differed substantially in teaching about the Yellow Card Scheme and adverse drug reactions (ADRs). There is scope for increased involvement of the Medicines and Healthcare products Regulatory Agency in undergraduate education, in line with recommendations from the National Audit Office.

Using XML and XSLT for flexible elicitation of mental-health risk knowledge

Current tools for assessing risks associated with mental-health problems require assessors to make high-level judgements based on clinical experience. This paper describes how new technologies can enhance qualitative research methods to identify lower-level cues underlying these judgements, which can be collected by people without a specialist mental-health background. Content analysis of interviews with 46 multidisciplinary mental-health experts exposed the cues and their interrelationships, which were represented by a mind map using software that stores maps as XML. All 46 mind maps were integrated into a single XML knowledge structure and analysed by a Lisp program to generate quantitative information about the numbers of experts associated with each part of it. The knowledge was refined by the experts, using software developed in Flash to record their collective views within the XML itself. These views specified how the XML should be transformed by XSLT, a technology for rendering XML, which resulted in a validated hierarchical knowledge structure associating patient cues with risks. Changing knowledge elicitation requirements were accommodated by flexible transformations of XML data using XSLT, which also facilitated generation of multiple data-gathering tools suiting different assessment circumstances and levels of mental-health knowledge. © 2007 Informa UK Ltd All rights reserved.

A review of current knowledge on Electronic Vision Enhancement Systems for the visually impaired

Magnification can be provided to assist those with visual impairment to make the best use of remaining vision. Electronic transverse magnification of an object was first conceived for use in low vision in the late 1950s, but has developed slowly and is not extensively prescribed because of its relatively high cost and lack of portability. Electronic devices providing transverse magnification have been termed closed-circuit televisions (CCTVs) because of the direct cable link between the camera imaging system and monitor viewing system, but this description generally refers to surveillance devices and does not indicate the provision of features such as magnification and contrast enhancement. Therefore, the term Electronic Vision Enhancement Systems (EVES) is proposed to better distinguish and describe such devices. This paper reviews current knowledge on EVES for the visually impaired in terms of: classification; hardware and software (development of technology, magnification and field-of-view, contrast and image enhancement); user aspects (users and usage, reading speed and duration, and training); and potential future development of EVES. © 2003 The College of Optometrists.

Decision support based on genomics:integration of data-and knowledge-driven reasoning

The breadth and depth of available clinico-genomic information, present an enormous opportunity for improving our ability to study disease mechanisms and meet the individualised medicine needs. A difficulty occurs when the results are to be transferred 'from bench to bedside'. Diversity of methods is one of the causes, but the most critical one relates to our inability to share and jointly exploit data and tools. This paper presents a perspective on current state-of-the-art in the analysis of clinico-genomic data and its relevance to medical decision support. It is an attempt to investigate the issues related to data and knowledge integration. Copyright © 2010 Inderscience Enterprises Ltd.

Current knowledge on the role of the inferior frontal gyrus in Theory of Mind - a commentary on Schurz and Tholen (2016)

Schurz and Tholen (2016) argue that common approaches to studying the neural basis of “theory of mind” (ToM) obscure a potentially important role for inferior frontal gyrus (IFG) in managing conflict between perspectives, and urge new work to address this question: “to gain a full understanding of the IFG's role in ToM, we encourage future imaging studies to use a wider range of control conditions.” (p332). We wholeheartedly agree, but note that this observation has been made before, and has already led to a programme of work that provides evidence from fMRI, EEG, and TMS on the role of IFG in managing conflict between self and other perspectives in ToM. We highlight these works, and in particular we demonstrate how careful manipulation within ToM tasks has been used to act as an internal control condition, wherein conflict has been manipulated within-subject. We further add to the discussion by framing key questions that remain regarding IFG in the context of these. Using limitations in the existing research, we outline how best researchers can proceed with the challenge set by Schurz and Tholen (2016).