Securing medical research data with a rights management system

We propose a digital rights management approach for sharing electronic health records for research purposes and argue advantages of the approach. We give an outline of our implementation, discuss challenges that we faced and future directions.

Interactive image manipulation for surgical planning

The Australian e-Health Research Centre in collaboration with the Queensland University of Technology's Paediatric Spine Research Group is developing software for visualisation and manipulation of large three-dimensional (3D) medical image data sets. The software allows the extraction of anatomical data from individual patients for use in preoperative planning. State-of-the-art computer technology makes it possible to slice through the image dataset at any angle, or manipulate 3D representations of the data instantly. Although the software was initially developed to support planning for scoliosis surgery, it can be applied to any dataset whether obtained from computed tomography, magnetic resonance imaging or any other imaging modality.

CAD/CAm-assisted breast reconstruction

The application of computer-aided design and manufacturing (CAD/CAM) techniques in the clinic is growing slowly but steadily. The ability to build patient-specific models based on medical imaging data offers major potential. In this work we report on the feasibility of employing laser scanning with CAD/CAM techniques to aid in breast reconstruction. A patient was imaged with laser scanning, an economical and facile method for creating an accurate digital representation of the breasts and surrounding tissues. The obtained model was used to fabricate a customized mould that was employed as an intra-operative aid for the surgeon performing autologous tissue reconstruction of the breast removed due to cancer. Furthermore, a solid breast model was derived from the imaged data and digitally processed for the fabrication of customized scaffolds for breast tissue engineering. To this end, a novel generic algorithm for creating porosity within a solid model was developed, using a finite element model as intermediate.

Feasibility study for thermal treatment of solid tire wastes in Bangladesh by using pyrolysis technology

In this study on the basis of lab data and available resources in Bangladesh, feasibility study has been carried out for pyrolysis process converting solid tire wastes into pyrolysis oils, solid char and gases. The process considered for detailed analysis was fixed-bed fire-tube heating pyrolysis reactor system. The comparative techno-economic assessment was carried out in US$ for three different sizes plants: medium commercial scale (144 tons/day), small commercial scale (36 tons/day), pilot scale (3.6 tons/day). The assessment showed that medium commercial scale plant was economically feasible, with the lowest unit production cost than small commercial and pilot scale plants for the production of crude pyrolysis oil that could be used as boiler fuel oil and for the production of upgraded liquid-products.

Randomised controlled trial of an automated, interactive telephone intervention (TLC Diabetes) to improve type 2 diabetes management : Baseline findings and six-month outcomes

Background: Effective self-management of diabetes is essential for the reduction of diabetes-related complications, as global rates of diabetes escalate. Methods: Randomised controlled trial. Adults with type 2 diabetes (n = 120), with HbA1c greater than or equal to 7.5 %, were randomly allocated (4 × 4 block randomised block design) to receive an automated, interactive telephone-delivered management intervention or usual routine care. Baseline sociodemographic, behavioural and medical history data were collected by self-administered questionnaires and biological data were obtained during hospital appointments. Health-related quality of life (HRQL) was measured using the SF-36. Results: The mean age of participants was 57.4 (SD 8.3), 63 % of whom were male. There were no differences in demographic, socioeconomic and behavioural variables between the study arms at baseline. Over the six-month period from baseline, participants receiving the Australian TLC (Telephone-Linked Care) Diabetes program showed a 0.8 % decrease in geometric mean HbA1c from 8.7 % to 7.9 %, compared with a 0.2 % HbA1c reduction (8.9 % to 8.7 %) in the usual care arm (p = 0.002). There was also a significant improvement in mental HRQL, with a mean increase of 1.9 in the intervention arm, while the usual care arm decreased by 0.8 (p = 0.007). No significant improvements in physical HRQL were observed. Conclusions: These analyses indicate the efficacy of the Australian TLC Diabetes program with clinically significant post-intervention improvements in both glycaemic control and mental HRQL. These observed improvements, if supported and maintained by an ongoing program such as this, could significantly reduce diabetes-related complications in the longer term. Given the accessibility and feasibility of this kind of program, it has strong potential for providing effective, ongoing support to many individuals with diabetes in the future.

Cartilage regeneration using zonal chondrocyte subpopulations : a promising approach or an overcomplicated strategy?

Cartilage defects heal imperfectly and osteoarthritic changes develop frequently as a result. Although the existence of specific behaviours of chondrocytes derived from various depth-related zones in vitro has been known for over 20 years, only a relatively small body of in vitro studies has been performed with zonal chondrocytes and current clinical treatment strategies do not reflect these native depth-dependent (zonal) differences. This is surprising since mimicking the zonal organization of articular cartilage in neo-tissue by the use of zonal chondrocyte subpopulations could enhance the functionality of the graft. Although some research groups including our own have made considerable progress in tailoring culture conditions using specific growth factors and biomechanical loading protocols, we conclude that an optimal regime has not yet been determined. Other unmet challenges include the lack of specific zonal cell sorting protocols and limited amounts of cells harvested per zone. As a result, the engineering of functional tissue has not yet been realized and no long-term in vivo studies using zonal chondrocytes have been described. This paper critically reviews the research performed to date and outlines our view of the potential future significance of zonal chondrocyte populations in regenerative approaches for the treatment of cartilage defects. Secondly, we briefly discuss the capabilities of additive manufacturing technologies that can not only create patient-specific grafts directly from medical imaging data sets but could also more accurately reproduce the complex 3D zonal extracellular matrix architecture using techniques such as hydrogel-based cell printing.

A medical data reliability assessment model

There is currently a strong focus worldwide on the potential of large-scale Electronic Health Record (EHR) systems to cut costs and improve patient outcomes through increased efficiency. This is accomplished by aggregating medical data from isolated Electronic Medical Record databases maintained by different healthcare providers. Concerns about the privacy and reliability of Electronic Health Records are crucial to healthcare service consumers. Traditional security mechanisms are designed to satisfy confidentiality, integrity, and availability requirements, but they fail to provide a measurement tool for data reliability from a data entry perspective. In this paper, we introduce a Medical Data Reliability Assessment (MDRA) service model to assess the reliability of medical data by evaluating the trustworthiness of its sources, usually the healthcare provider which created the data and the medical practitioner who diagnosed the patient and authorised entry of this data into the patient’s medical record. The result is then expressed by manipulating health record metadata to alert medical practitioners relying on the information to possible reliability problems.

A time-variant medical data trustworthiness assessment model

Electronic Health Record (EHR) systems are being introduced to overcome the limitations associated with paper-based and isolated Electronic Medical Record (EMR) systems. This is accomplished by aggregating medical data and consolidating them in one digital repository. Though an EHR system provides obvious functional benefits, there is a growing concern about the privacy and reliability (trustworthiness) of Electronic Health Records. Security requirements such as confidentiality, integrity, and availability can be satisfied by traditional hard security mechanisms. However, measuring data trustworthiness from the perspective of data entry is an issue that cannot be solved with traditional mechanisms, especially since degrees of trust change over time. In this paper, we introduce a Time-variant Medical Data Trustworthiness (TMDT) assessment model to evaluate the trustworthiness of medical data by evaluating the trustworthiness of its sources, namely the healthcare organisation where the data was created and the medical practitioner who diagnosed the patient and authorised entry of this data into the patient’s medical record, with respect to a certain period of time. The result can then be used by the EHR system to manipulate health record metadata to alert medical practitioners relying on the information to possible reliability problems.

Identification of alcohol involvement in injury-related hospitalisations using routine data compared to medical record review

Objective: To quantify the extent to which alcohol related injuries are adequately identified in hospitalisation data using ICD-10-AM codes indicative of alcohol involvement. Method: A random sample of 4373 injury-related hospital separations from 1 July 2002 to 30 June 2004 were obtained from a stratified random sample of 50 hospitals across 4 states in Australia. From this sample, cases were identified as involving alcohol if they contained an ICD-10-AM diagnosis or external cause code referring to alcohol, or if the text description extracted from the medical records mentioned alcohol involvement. Results: Overall, identification of alcohol involvement using ICD codes detected 38% of the alcohol-related sample, whilst almost 94% of alcohol-related cases were identified through a search of the text extracted from the medical records. The resultant estimate of alcohol involvement in injury-related hospitalisations in this sample was 10%. Emergency department records were the most likely to identify whether the injury was alcohol-related with almost three-quarters of alcohol-related cases mentioning alcohol in the text abstracted from these records. Conclusions and Implications: The current best estimates of the frequency of hospital admissions where alcohol is involved prior to the injury underestimate the burden by around 62%. This is a substantial underestimate that has major implications for public policy, and highlights the need for further work on improving the quality and completeness of routine administrative data sources for identification of alcohol-related injuries.

Using digital rights management for securing data in a medical research environment

We propose a digital rights management approach for sharing electronic health records in a health research facility and argue advantages of the approach. We also give an outline of the system under development and our implementation of the security features and discuss challenges that we faced and future directions.

Analysis of the effect of negation on information retrieval of medical data

Most information retrieval (IR) models treat the presence of a term within a document as an indication that the document is somehow "about" that term, they do not take into account when a term might be explicitly negated. Medical data, by its nature, contains a high frequency of negated terms - e.g. "review of systems showed no chest pain or shortness of breath". This papers presents a study of the effects of negation on information retrieval. We present a number of experiments to determine whether negation has a significant negative affect on IR performance and whether language models that take negation into account might improve performance. We use a collection of real medical records as our test corpus. Our findings are that negation has some affect on system performance, but this will likely be confined to domains such as medical data where negation is prevalent.

Bayesian mixtures for modelling complex medical data : a case study in Parkinson’s disease

Mixture models are a flexible tool for unsupervised clustering that have found popularity in a vast array of research areas. In studies of medicine, the use of mixtures holds the potential to greatly enhance our understanding of patient responses through the identification of clinically meaningful clusters that, given the complexity of many data sources, may otherwise by intangible. Furthermore, when developed in the Bayesian framework, mixture models provide a natural means for capturing and propagating uncertainty in different aspects of a clustering solution, arguably resulting in richer analyses of the population under study. This thesis aims to investigate the use of Bayesian mixture models in analysing varied and detailed sources of patient information collected in the study of complex disease. The first aim of this thesis is to showcase the flexibility of mixture models in modelling markedly different types of data. In particular, we examine three common variants on the mixture model, namely, finite mixtures, Dirichlet Process mixtures and hidden Markov models. Beyond the development and application of these models to different sources of data, this thesis also focuses on modelling different aspects relating to uncertainty in clustering. Examples of clustering uncertainty considered are uncertainty in a patient’s true cluster membership and accounting for uncertainty in the true number of clusters present. Finally, this thesis aims to address and propose solutions to the task of comparing clustering solutions, whether this be comparing patients or observations assigned to different subgroups or comparing clustering solutions over multiple datasets. To address these aims, we consider a case study in Parkinson’s disease (PD), a complex and commonly diagnosed neurodegenerative disorder. In particular, two commonly collected sources of patient information are considered. The first source of data are on symptoms associated with PD, recorded using the Unified Parkinson’s Disease Rating Scale (UPDRS) and constitutes the first half of this thesis. The second half of this thesis is dedicated to the analysis of microelectrode recordings collected during Deep Brain Stimulation (DBS), a popular palliative treatment for advanced PD. Analysis of this second source of data centers on the problems of unsupervised detection and sorting of action potentials or "spikes" in recordings of multiple cell activity, providing valuable information on real time neural activity in the brain.

Towards a translational medical research ecosystem

In this paper we introduce a novel design for a translational medical research ecosystem. Translational medical research is an emerging field of work, which aims to bridge the gap between basic medical science research and clinical research/patient care. We analyze the key challenges of digital ecosystems for translational research, based on real world scenarios posed by the Lab for Translational Research at the Harvard Medical School and the Genomics Research Centre of the Griffith University, and show how traditional IT approaches fail to fulfill these challenges. We then introduce our design for a translational research ecosystem. Several key contributions are made: A novel approach to managing ad-hoc research ecosystems is introduced; a new security approach for translational research is proposed which allows each participating site to retain control over its data and define its own policies to ensure legal and ethical compliance; and a design for a novel interactive access control framework which allows users to easily share data, while adhering to their organization's policies is presented.

Overview of the ShARe/CLEF eHealth Evaluation Lab 2014

This paper reports on the 2nd ShARe/CLEFeHealth evaluation lab which continues our evaluation resource building activities for the medical domain. In this lab we focus on patients' information needs as opposed to the more common campaign focus of the specialised information needs of physicians and other healthcare workers. The usage scenario of the lab is to ease patients and next-of-kins' ease in understanding eHealth information, in particular clinical reports. The 1st ShARe/CLEFeHealth evaluation lab was held in 2013. This lab consisted of three tasks. Task 1 focused on named entity recognition and normalization of disorders; Task 2 on normalization of acronyms/abbreviations; and Task 3 on information retrieval to address questions patients may have when reading clinical reports. This year's lab introduces a new challenge in Task 1 on visual-interactive search and exploration of eHealth data. Its aim is to help patients (or their next-of-kin) in readability issues related to their hospital discharge documents and related information search on the Internet. Task 2 then continues the information extraction work of the 2013 lab, specifically focusing on disorder attribute identification and normalization from clinical text. Finally, this year's Task 3 further extends the 2013 information retrieval task, by cleaning the 2013 document collection and introducing a new query generation method and multilingual queries. De-identified clinical reports used by the three tasks were from US intensive care and originated from the MIMIC II database. Other text documents for Tasks 1 and 3 were from the Internet and originated from the Khresmoi project. Task 2 annotations originated from the ShARe annotations. For Tasks 1 and 3, new annotations, queries, and relevance assessments were created. 50, 79, and 91 people registered their interest in Tasks 1, 2, and 3, respectively. 24 unique teams participated with 1, 10, and 14 teams in Tasks 1, 2 and 3, respectively. The teams were from Africa, Asia, Canada, Europe, and North America. The Task 1 submission, reviewed by 5 expert peers, related to the task evaluation category of Effective use of interaction and targeted the needs of both expert and novice users. The best system had an Accuracy of 0.868 in Task 2a, an F1-score of 0.576 in Task 2b, and Precision at 10 (P@10) of 0.756 in Task 3. The results demonstrate the substantial community interest and capabilities of these systems in making clinical reports easier to understand for patients. The organisers have made data and tools available for future research and development.