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.

Watermarking biomedical time series data

This thesis addresses the problem of information hiding in low dimensional digital data focussing on issues of privacy and security in Electronic Patient Health Records (EPHRs). The thesis proposes a new security protocol based on data hiding techniques for EPHRs. This thesis contends that embedding of sensitive patient information inside the EPHR is the most appropriate solution currently available to resolve the issues of security in EPHRs. Watermarking techniques are applied to one-dimensional time series data such as the electroencephalogram (EEG) to show that they add a level of confidence (in terms of privacy and security) in an individual’s diverse bio-profile (the digital fingerprint of an individual’s medical history), ensure belief that the data being analysed does indeed belong to the correct person, and also that it is not being accessed by unauthorised personnel. Embedding information inside single channel biomedical time series data is more difficult than the standard application for images due to the reduced redundancy. A data hiding approach which has an in built capability to protect against illegal data snooping is developed. The capability of this secure method is enhanced by embedding not just a single message but multiple messages into an example one-dimensional EEG signal. Embedding multiple messages of similar characteristics, for example identities of clinicians accessing the medical record helps in creating a log of access while embedding multiple messages of dissimilar characteristics into an EPHR enhances confidence in the use of the EPHR. The novel method of embedding multiple messages of both similar and dissimilar characteristics into a single channel EEG demonstrated in this thesis shows how this embedding of data boosts the implementation and use of the EPHR securely.

Quantifying short-term dynamics of Parkinson's disease using self-reported symptom data from an internet social network

Background: Parkinson’s disease (PD) is an incurable neurological disease with approximately 0.3% prevalence. The hallmark symptom is gradual movement deterioration. Current scientific consensus about disease progression holds that symptoms will worsen smoothly over time unless treated. Accurate information about symptom dynamics is of critical importance to patients, caregivers, and the scientific community for the design of new treatments, clinical decision making, and individual disease management. Long-term studies characterize the typical time course of the disease as an early linear progression gradually reaching a plateau in later stages. However, symptom dynamics over durations of days to weeks remains unquantified. Currently, there is a scarcity of objective clinical information about symptom dynamics at intervals shorter than 3 months stretching over several years, but Internet-based patient self-report platforms may change this. Objective: To assess the clinical value of online self-reported PD symptom data recorded by users of the health-focused Internet social research platform PatientsLikeMe (PLM), in which patients quantify their symptoms on a regular basis on a subset of the Unified Parkinson’s Disease Ratings Scale (UPDRS). By analyzing this data, we aim for a scientific window on the nature of symptom dynamics for assessment intervals shorter than 3 months over durations of several years. Methods: Online self-reported data was validated against the gold standard Parkinson’s Disease Data and Organizing Center (PD-DOC) database, containing clinical symptom data at intervals greater than 3 months. The data were compared visually using quantile-quantile plots, and numerically using the Kolmogorov-Smirnov test. By using a simple piecewise linear trend estimation algorithm, the PLM data was smoothed to separate random fluctuations from continuous symptom dynamics. Subtracting the trends from the original data revealed random fluctuations in symptom severity. The average magnitude of fluctuations versus time since diagnosis was modeled by using a gamma generalized linear model. Results: Distributions of ages at diagnosis and UPDRS in the PLM and PD-DOC databases were broadly consistent. The PLM patients were systematically younger than the PD-DOC patients and showed increased symptom severity in the PD off state. The average fluctuation in symptoms (UPDRS Parts I and II) was 2.6 points at the time of diagnosis, rising to 5.9 points 16 years after diagnosis. This fluctuation exceeds the estimated minimal and moderate clinically important differences, respectively. Not all patients conformed to the current clinical picture of gradual, smooth changes: many patients had regimes where symptom severity varied in an unpredictable manner, or underwent large rapid changes in an otherwise more stable progression. Conclusions: This information about short-term PD symptom dynamics contributes new scientific understanding about the disease progression, currently very costly to obtain without self-administered Internet-based reporting. This understanding should have implications for the optimization of clinical trials into new treatments and for the choice of treatment decision timescales.

What are tests for? The implications of stuttering steps along the patient pathway

This article explores the implications of how US family physicians make decisions about ordering diagnostic tests for their patients. Data is based on a study of 256 physicians interviewed after viewing a video vignette of a presenting patient. The qualitative analysis of 778 statements relating to trustworthiness of evidence for their decision making, the use of any kind of technology and diagnostic testing suggests a range of internal and external constraints on physician decision making. Test-ordering for family physicians in the United States is significantly influenced by both hidden cognitive processes related to the physician's calculation of patient resources and a health insurance system that requires certain types of evidence in order to permit further tests or particular interventions. The consequence of the need for physicians to meet multiple forms of proof that may not always relate to relevant treatment delays a diagnosis and treatment plan agreed not only by the physician and patient but also the insurance company. This results in a patient journey that is made up of stuttering steps to a confirmed diagnosis and treatment undermining patient-centred practice, compromising patient care, constraining physician autonomy and creating additional expense. © 2014 Elsevier Ltd.

Patient involvement in primary care mental health:a focus group study

Background: Patient involvement in health care is a strong political driver in the NHS. However in spite of policy prominence, there has been only limited previous work exploring patient involvement for people with serious mental illness. Aim: To describe the views on, potential for, and types of patient involvement in primary care from the perspectives of primary care health professionals and patients with serious mental illness. Design of study: Qualitative study consisting of six patient, six health professional and six combined focus groups between May 2002 and January 2003. Setting: Six primary care trusts in the West Midlands, England. Method: Forty-five patients with serious mental illness, 39 GPs, and eight practice nurses participated in a series of 18 focus groups. All focus groups were audiotaped and fully transcribed. Nvivo was used to manage data more effectively. Results: Most patients felt that only other people with lived experience of mental illness could understand what they were going through. This experience could be used to help others navigate the health- and social-care systems, give advice about medication, and offer support at times of crisis. Many patients also saw paid employment within primary care as a way of addressing issues of poverty and social exclusion. Health professionals were, however, more reluctant to see patients as partners, be it in the consultation or in service delivery. Conclusions: Meaningful change in patient involvement requires commitment and belief from primary care practitioners that the views and experiences of people with serious mental illness are valid and valuable.

Inhaled human insulin (Exubera®):clinical profile and patient considerations

Inhaled human insulin (Exubera®) is a rapid-acting regular human insulin administered by oral inhalation before meals. It provides a non-invasive alternative to multiple subcutaneous injections for the treatment of hyperglycemia in adult patients with type 1 and type 2 diabetes. Compared with subcutaneous rapid-acting insulin analogs, Exubera provides equivalent HbA1c control. As a monotherapy or in combination with oral agents, Exubera also provides greater glycemic control than oral agents alone, at least in patients with high levels of HbA1c. Exubera demonstrates improved patient satisfaction compared with subcutaneous insulin or oral agents alone. When offered as a treatment option together with standard treatments in uncontrolled patients naive to insulin, Exubera increases acceptance of insulin therapy three-fold compared with patients offered standard regimens only. Exubera is well tolerated in comparison to subcutaneous insulin, with a similar incidence of mild to moderate hypoglycemia. Although cough is a common adverse effect early in therapy, this leads to treatment discontinuations in less than 1% of patients. Despite an increased incidence of insulin antibodies compared with subcutaneous administration, and a consistent but minor impact on pulmonary function, long-term safety data of up to 4 years continue to support the safety profile of Exubera.

A KM perspective on implementing an electronic patient record within an NHS hospital

The Electronic Patient Record (EPR) is being developed by many hospitals in the UK and across the globe. We class an EPR system as a type of Knowledge Management System (KMS), in that it is a technological tool developed to support the process of knowledge management (KM). Healthcare organisations aim to use these systems to provide a vehicle for more informed and improved clinical decision making thereby delivering reduced errors and risks, enhanced quality and consequently offering enhanced patient safety. Finding an effective way for a healthcare organisation to practically implement these systems is essential. In this study we use the concept of the business process approach to KM as a theoretical lens to analyse and explore how a large NHS teaching hospital developed, executed and practically implemented an EPR system. This theory advocates the importance of taking into account all organizational activities - the business processes - in considering any KM initiatives. Approaching KM through business processes allows for a more holistic view of the requirements across a process: emphasis is placed on how particular activities are performed, how they are structured and what knowledge demanded and not just supplied across each process. This falls in line with the increased emphasis in healthcare on patient-centred approaches to care delivery. We have found in previous research that hospitals are happy with the delivery of patient care being referred to as their 'business'. A qualitative study was conducted over a two and half year period with data collected from semi-structured interviews with eight members of the strategic management team, 12 clinical users and 20 patients in addition to non- participant observation of meetings and documentary data. We believe that the inclusion of patients within the study may well be the first time this has been done in examining the implementation of a KMS. The theoretical propositions strategy was used as the overarching approach for data analysis. Here Initial theoretical research themes and propositions were used to help shape and organise the case study analysis. This paper will present preliminary findings about the hospital's business strategy and its links to the KMS strategy and process.

Handling varying amounts of missing data when classifying mental-health risk levels

One of the main challenges of classifying clinical data is determining how to handle missing features. Most research favours imputing of missing values or neglecting records that include missing data, both of which can degrade accuracy when missing values exceed a certain level. In this research we propose a methodology to handle data sets with a large percentage of missing values and with high variability in which particular data are missing. Feature selection is effected by picking variables sequentially in order of maximum correlation with the dependent variable and minimum correlation with variables already selected. Classification models are generated individually for each test case based on its particular feature set and the matching data values available in the training population. The method was applied to real patients' anonymous mental-health data where the task was to predict the suicide risk judgement clinicians would give for each patient's data, with eleven possible outcome classes: zero to ten, representing no risk to maximum risk. The results compare favourably with alternative methods and have the advantage of ensuring explanations of risk are based only on the data given, not imputed data. This is important for clinical decision support systems using human expertise for modelling and explaining predictions.

Pathway to clozapine use:a comparison between a patient cohort from New Zealand and a cohort from the United Kingdom

Background and Objective: Clozapine has been available since the early 1990s. Studies continue to demonstrate its superior efficacy in treatment-resistant schizophrenia. Despite this, numerous studies show under-utilisation, delayed access and reluctance by psychiatrists to prescribe clozapine. This retrospective cross-sectional study compared the prescribing of clozapine in two adult cohorts under the care of large public mental health services in Auckland (New Zealand) and Birmingham (United Kingdom) on 31 March 2007. Method: Time from first presentation to clozapine initiation, prior antipsychotics trialled and antipsychotic co-prescribing were compared. Data included demographics, psychiatric diagnosis, co-morbid conditions, year of first presentation, admissions and pharmacological treatment (clozapine dose, start date, prior antipsychotics, co-prescribed antipsychotic). Results: Overall, 664 people were prescribed clozapine (402 Auckland; 262 Birmingham); mean daily dose of 384 mg (Auckland) and 429 mg (Birmingham). 53 % presented after 1990 and the average duration of time before starting clozapine was significantly longer in the Birmingham cohort (6.5 vs. 5.3 years) but this reduced in both cohorts to a 1-year mean in those presenting within the last 3 years. The average number of antipsychotics trialled pre-clozapine for those presenting since 1990 was significantly higher in the Birmingham cohort (4.3 vs. 3.1) but in both cohorts this similarly reduced in those presenting within the last 3 years. Antipsychotic co-prescribing was significantly higher in the Birmingham cohort (22.9 vs. 10.7 %). Conclusions: There is evidence that access to clozapine has improved over time in both cohorts, with a reduction in the duration between presentation and initiation of clozapine and number of different antipsychotics trialled pre-clozapine. These are very positive findings in terms of optimising outcomes with clozapine and are possibly due to the impact of guideline recommendations, increasing clinician, consumer and carer knowledge, and experience with clozapine and funding changes. © 2014 Springer International Publishing.

Measurement of intervertebral cervical motion by means of dynamic X-ray image processing and data interpolation

Accurate measurement of intervertebral kinematics of the cervical spine can support the diagnosis of widespread diseases related to neck pain, such as chronic whiplash dysfunction, arthritis, and segmental degeneration. The natural inaccessibility of the spine, its complex anatomy, and the small range of motion only permit concise measurement in vivo. Low dose X-ray fluoroscopy allows time-continuous screening of cervical spine during patient's spontaneous motion. To obtain accurate motion measurements, each vertebra was tracked by means of image processing along a sequence of radiographic images. To obtain a time-continuous representation of motion and to reduce noise in the experimental data, smoothing spline interpolation was used. Estimation of intervertebral motion for cervical segments was obtained by processing patient's fluoroscopic sequence; intervertebral angle and displacement and the instantaneous centre of rotation were computed. The RMS value of fitting errors resulted in about 0.2 degree for rotation and 0.2 mm for displacements. © 2013 Paolo Bifulco et al.

Modeling Data for Complications in Diabetics Using Logistic Regression

2010 Mathematics Subject Classification: 62P10.

Assessing the queuing process using data envelopment analysis:an application in health centres

Queuing is one of the very important criteria for assessing the performance and efficiency of any service industry, including healthcare. Data Envelopment Analysis (DEA) is one of the most widely-used techniques for performance measurement in healthcare. However, no queue management application has been reported in the health-related DEA literature. Most of the studies regarding patient flow systems had the objective of improving an already existing Appointment System. The current study presents a novel application of DEA for assessing the queuing process at an Outpatients’ department of a large public hospital in a developing country where appointment systems do not exist. The main aim of the current study is to demonstrate the usefulness of DEA modelling in the evaluation of a queue system. The patient flow pathway considered for this study consists of two stages; consultation with a doctor and pharmacy. The DEA results indicated that waiting times and other related queuing variables included need considerable minimisation at both stages.

Implementing a knowledge management system within an NHS hospital:a case study exploring the roll-out of an Electronic Patient Record (EPR)

This research aims to contribute to understanding the implementation of knowledge management systems (KMS) in the field of health through a case study, leading to theory building and theory extension. We use the concept of the business process approach to knowledge management as a theoretical lens to analyse and explore how a large teaching hospital developed, executed and practically implemented a KMS. A qualitative study was conducted over a 2.5 year period with data collected from semi-structured interviews with eight members of the strategic management team, 12 clinical users and 20 patients in addition to non-participant observation of meetings and documents. The theoretical propositions strategy was used as the overarching approach for data analysis. Our case study provides evidence that true patient centred approaches to supporting care delivery with a KMS benefit from process thinking at both the planning and implementation stages, and an emphasis on the knowledge demands resulting from: the activities along the care pathways; where cross-overs in care occur; and knowledge sharing for the integration of care. The findings also suggest that despite the theoretical awareness of KMS implementation methodologies, the actual execution of such systems requires practice and learning. Flexible, fluid approaches through rehearsal are important and communications strategies should focus heavily on transparency incorporating both structured and unstructured communication methods.

Patient experiences of serious adverse drug reactions and their attitudes to medicines:a qualitative study of survivors of Stevens-Johnson syndrome and toxic epidermal necrolysis in the UK

Background: Adverse drug reactions (ADRs) cause significant morbidity and mortality and account for around 6.5% of hospital admissions. Patient experiences of serious ADRs and their long-term impact on patients' lives, including their influence on current attitudes towards medicines, have not been previously explored. Objective: The aim of the study was to explore the experiences, beliefs, and attitudes of survivors of serious ADRs, using drug-induced Stevens-Johnson syndrome (SJS) and Toxic Epidermal Necrolysis (TEN) as a paradigm. Methods: A retrospective, qualitative study was undertaken using detailed semi-structured interviews. Fourteen adult survivors of SJS and TEN, admitted to two teaching hospitals in the UK, one the location of a tertiary burns centre, were interviewed. Interview transcripts were independently analysed by three different researchers and themes emerging from the text identified. Results: All 14 patients were aware that their condition was drug induced, and all but one knew the specific drug(s) implicated. Several expressed surprise at the perceived lack of awareness of the ADR amongst healthcare professionals, and described how the ADR was mistaken for another condition. Survivors believed that causes of the ADR included (i) being given too high a dose of the drug; (ii) medical staff ignoring existing allergies; and (iii) failure to monitor blood tests. Only two believed that the reaction was unavoidable. Those who believed that the condition could have been avoided had less trust in healthcare professionals. The ADR had a persisting impact on their current lives physically and psychologically. Many now avoided medicines altogether and were fearful of becoming ill enough to need them. © 2011 Adis Data Information BV. All rights reserved. Conclusions: Life-threatening ADRs continued to affect patients’ lives long after the event. Patients’ beliefs regarding the cause of the ADR differed, and may have influenced their trust in healthcare professionals and medicines. We propose that clear communication during the acute phase of a serious ADR may therefore be important.

Discovering biomarkers for antidepressant response:protocol from the Canadian biomarker integration network in depression (CAN-BIND) and clinical characteristics of the first patient cohort

Background: Major Depressive Disorder (MDD) is among the most prevalent and disabling medical conditions worldwide. Identification of clinical and biological markers ("biomarkers") of treatment response could personalize clinical decisions and lead to better outcomes. This paper describes the aims, design, and methods of a discovery study of biomarkers in antidepressant treatment response, conducted by the Canadian Biomarker Integration Network in Depression (CAN-BIND). The CAN-BIND research program investigates and identifies biomarkers that help to predict outcomes in patients with MDD treated with antidepressant medication. The primary objective of this initial study (known as CAN-BIND-1) is to identify individual and integrated neuroimaging, electrophysiological, molecular, and clinical predictors of response to sequential antidepressant monotherapy and adjunctive therapy in MDD. Methods: CAN-BIND-1 is a multisite initiative involving 6 academic health centres working collaboratively with other universities and research centres. In the 16-week protocol, patients with MDD are treated with a first-line antidepressant (escitalopram 10-20 mg/d) that, if clinically warranted after eight weeks, is augmented with an evidence-based, add-on medication (aripiprazole 2-10 mg/d). Comprehensive datasets are obtained using clinical rating scales; behavioural, dimensional, and functioning/quality of life measures; neurocognitive testing; genomic, genetic, and proteomic profiling from blood samples; combined structural and functional magnetic resonance imaging; and electroencephalography. De-identified data from all sites are aggregated within a secure neuroinformatics platform for data integration, management, storage, and analyses. Statistical analyses will include multivariate and machine-learning techniques to identify predictors, moderators, and mediators of treatment response. Discussion: From June 2013 to February 2015, a cohort of 134 participants (85 outpatients with MDD and 49 healthy participants) has been evaluated at baseline. The clinical characteristics of this cohort are similar to other studies of MDD. Recruitment at all sites is ongoing to a target sample of 290 participants. CAN-BIND will identify biomarkers of treatment response in MDD through extensive clinical, molecular, and imaging assessments, in order to improve treatment practice and clinical outcomes. It will also create an innovative, robust platform and database for future research. Trial registration: ClinicalTrials.gov identifier NCT01655706. Registered July 27, 2012.