Enhancement of medical named entity recognition using graph-based features

Named Entity Recognition (NER) is a crucial step in text mining. This paper proposes a new graph-based technique for representing unstructured medical text. The new representation is used to extract discriminative features that are able to enhance the NER performance. To evaluate the usefulness of the proposed graph-based technique, the i2b2 medication challenge data set is used. Specifically, the 'treatment' named entities are extracted for evaluation using six different classifiers. The F-measure results of five classifiers are enhanced, with an average improvement of up to 26% in performance.

Stabilizing sparse cox model using statistic and semantic structures in electronic medical records

Stability in clinical prediction models is crucial for transferability between studies, yet has received little attention. The problem is paramount in high dimensional data, which invites sparse models with feature selection capability. We introduce an effective method to stabilize sparse Cox model of time-to-events using statistical and semantic structures inherent in Electronic Medical Records (EMR). Model estimation is stabilized using three feature graphs built from (i) Jaccard similarity among features (ii) aggregation of Jaccard similarity graph and a recently introduced semantic EMR graph (iii) Jaccard similarity among features transferred from a related cohort. Our experiments are conducted on two real world hospital datasets: a heart failure cohort and a diabetes cohort. On two stability measures – the Consistency index and signal-to-noise ratio (SNR) – the use of our proposed methods significantly increased feature stability when compared with the baselines.

Lab-on-a-chip or chip-in-a-lab: challenges of commercialization lost in translation

Lab-on-a-chip technology has been long envisaged to have tremendous commercial potential, owing to the ability of such devices to encapsulate a full range of laboratory processes in a single instrument and operate in a portable manner, rapidly and at low cost. Devices are believed to have potential in fields ranging across medical diagnostics, environmental sampling and a range of consumer products, however, to date very few devices have attained commercial success. This review examines the challenges relating to the commercialization of lab-on-a-chip technology from fundamental research to mass manufacturing and aims to provide insight to both academics and product development specialists the perceived hindrances to commercialization and a strategy by which future work could be translated into commercial success.

Simplifying medical additive manufacturing: making the surgeon the designer

Additive Manufacturing, a technology which has been in existence since three decades, is now successfully being transitioned from a research setting to finding technologically and financially viable end-user applications. A key sector in which Additive Manufacturing is being used is the medical devices and healthcare sector. Drivers in this sector include the ability to create customized, patient specific devices and implants with quick turnaround time in a cost-effective manner. Doctors and surgeons are important change agents and innovators in the creation of new healthcare devices as well as surgical methods. Often times, they may find it necessary at first to build devices and plan surgeries which are not even being thought of or acted upon by the major healthcare companies. In this sense, they perform the roles of designers, creating new ideas and improving on them until they can be implemented and adopted by others. However, the scope for performing this creative activity is often limited in their workplaces, with resource, time and financial impediments often being present. Additive Manufacturing can be helpful to speed up the iterative process of designing such medical devices or planning surgeries as well as help convince people outside of the surgery room of the feasibility and business case for such innovations. This paper proposes to introduce a framework of design, processes and tools which will enable non-engineers (specifically surgeons) to create custom-built products. It is hoped that this paper will motivate more surgeons and non-engineers to get involved in the process of designing for additive manufacturing.

BioKin: an ambulatory platform for gait kinematic and feature assessment

A platform to move gait analysis, which is normally restricted to a clinical environment in a well-equipped gait laboratory, into an ambulatory system, potentially in non-clinical settings is introduced. This novel system can provide functional measurements to guide therapeutic interventions for people requiring rehabilitation with limited access to such gait laboratories. BioKin system consists of three layers: a low-cost wearable wireless motion capture sensor, data collection and storage engine, and the motion analysis and visualisation platform. Moreover, a novel limb orientation estimation algorithm is implemented in the motion analysis platform. The performance of the orientation estimation algorithm is validated against the orientation results from a commercial optical motion analysis system and an instrumented treadmill. The study results demonstrate a root-mean-square error less than 4° and a correlation coefficient more than 0.95 when compared with the industry standard system. These results indicate that the proposed motion analysis platform is a potential addition to existing gait laboratories in order to facilitate gait analysis in remote locations.

Reasons and remedies for under-representation of women in medical leadership roles: a qualitative study from Australia

OBJECTIVE: To elicit medical leaders' views on reasons and remedies for the under-representation of women in medical leadership roles.

DESIGN: Qualitative study using semistructured interviews with medical practitioners who work in medical leadership roles. Interviews were transcribed verbatim and transcripts were analysed using thematic analysis.

SETTING: Public hospitals, private healthcare providers, professional colleges and associations and government organisations in Australia.

PARTICIPANTS: 30 medical practitioners who hold formal medical leadership roles.

RESULTS: Despite dramatic increases in the entry of women into medicine in Australia, there remains a gross under-representation of women in formal, high-level medical leadership positions. The male-dominated nature of medical leadership in Australia was widely recognised by interviewees. A small number of interviewees viewed gender disparities in leadership roles as a 'natural' result of women's childrearing responsibilities. However, most interviewees believed that preventable gender-related barriers were impeding women's ability to achieve and thrive in medical leadership roles. Interviewees identified a range of potential barriers across three broad domains-perceptions of capability, capacity and credibility. As a counter to these, interviewees pointed to a range of benefits of women adopting these roles, and proposed a range of interventions that would support more women entering formal medical leadership roles.

CONCLUSIONS: While women make up more than half of medical graduates in Australia today, significant barriers restrict their entry into formal medical leadership roles. These constraints have internalised, interpersonal and structural elements that can be addressed through a range of strategies for advancing the role of women in medical leadership. These findings have implications for individual medical practitioners and health services, as well as professional colleges and associations.

Assessment of eating rate and food intake in spoon versus fork users in a laboratory setting

Accumulating evidence show positive relationships between eating rate and body weight. Acute food intake is affected by eating rate, bite size, and palatability. The objective was to assess differences between participants who chose to use a spoon vs. fork in eating rate and food intake of four meals that differ in palatability (low vs. high salt) and in energy density (low vs. high fat). Forty-eight healthy adults (16 males, 18-54 y, BMI: 17.8-34.4 kg/m2) were recruited. Participants attended four lunch time sessions after a standardised breakfast. Meals were either (1) low-fat/low-salt, (2) low-fat/high-salt, (3) high-fat/low-salt, or (4) high-fat/high-salt. Nineteen participants (6 males) consistently used a fork and 21 (8 males) used a spoon, 8 participants were inconsistent in cutlery use and excluded from analyses. Spoon users had on average a higher BMI than fork users (p=0.006). Effects of cutlery use, BMI status (BMI<25 vs. BMI>25), salt, and fat, and their interactions were assessed in a General Linear Model. Spoon users consumed faster (fork: 53±2.8g/min; spoon: 62±2.1g/min, p=0.022) and tended to consume more (p=0.09), whereas the duration of the meals were similar (fork: 6.9±0.3min; spoon: 6:7±0.2min, p=0.55). BMI status affected both eating rate and food intake (p=0.005). There were no significant two-way or three-way interactions between salt, fat, and cutlery use on eating rate or food intake. In conclusion, participants who chose to consume with forks ate slower compared to spoon users.

Online mining abnormal period patterns from multiple medical sensor data streams

With the advanced technology of medical devices and sensors, an abundance of medical data streams are available. However, data analysis techniques are very limited, especially for processing massive multiple physiological streams that may only be understood by medical experts. The state-of-the-art techniques only allow multiple medical devices to independently monitor different physiological parameters for the patient's status, thus they signal too many false alarms, creating unnecessary noise, especially in the Intensive Care Unit (ICU). An effective solution which has been recently studied is to integrate information from multiple physiologic parameters to reduce alarms. But it is a challenge to detect abnormalities from high frequently changed physiological streams data, since abnormalities occur gradually due to the complex situation of patients. An analysis of ICU physiological data streams shows that many vital physiological parameters are changed periodically (such as heart rate, arterial pressure, and respiratory impedance) and thus abnormalities are generally abnormal period patterns. In this paper, we develop a Mining Abnormal Period Patterns from Multiple Physiological Streams (MAPPMPS) method to detect and rank abnormalities in medical sensor streams. The efficiency and effectiveness of the MAPPMPS method is demonstrated by a real-world massive database of multiple physiological streams sampled in ICU, comprising 250 patients' streams (each stream involving over 1.3 million data points) with a total size of 28 GB data.

An analysis on the utilisation of health information technology to support clinical operation of chinese medicine

Chinese Medicine (CM) has become increasingly demanding globally. Recent World Health Organisation traditional and complementary medicine strategy of integrating CM to Western Medicine (WM) indicates that it is crucial that CM developments have strong literature, scientific, and evidence-based medical approval and support. To achieve this, there is a need to form a synthesis foundation or platform for future studies. This chapter serves to discover this synthesis that is suitable for CM by discussing the basics of inquiring and Knowledge Management (KM) systems. It suggests that CM should follow a combination of Hegelian and Kantian inquiring systems with the support of Singerian and Leibnizian inquiring systems and KM features. This proposed synthesis is one of the first, if not the first study to apply Churchman's inquiring systems into the context of CM and differentiate them from WM.

Can the direct medical cost of chronic disease be transferred across different countries? Using cost-of-illness studies on type 2 diabetes, epilepsy and schizophrenia as examples

OBJECTIVES: To systematically review cost of illness studies for schizophrenia (SC), epilepsy (EP) and type 2 diabetes mellitus (T2DM) and explore the transferability of direct medical cost across countries.

METHODS: A comprehensive literature search was performed to yield studies that estimated direct medical costs. A generalized linear model (GLM) with gamma distribution and log link was utilized to explore the variation in costs that accounted by the included factors. Both parametric (Random-effects model) and non-parametric (Boot-strapping) meta-analyses were performed to pool the converted raw cost data (expressed as percentage of GDP/capita of the country where the study was conducted).

RESULTS: In total, 93 articles were included (40 studies were for T2DM, 34 studies for EP and 19 studies for SC). Significant variances were detected inter- and intra-disease classes for the direct medical costs. Multivariate analysis identified that GDP/capita (p<0.05) was a significant factor contributing to the large variance in the cost results. Bootstrapping meta-analysis generated more conservative estimations with slightly wider 95% confidence intervals (CI) than the parametric meta-analysis, yielding a mean (95%CI) of 16.43% (11.32, 21.54) for T2DM, 36.17% (22.34, 50.00) for SC and 10.49% (7.86, 13.41) for EP.

CONCLUSIONS: Converting the raw cost data into percentage of GDP/capita of individual country was demonstrated to be a feasible approach to transfer the direct medical cost across countries. The approach from our study to obtain an estimated direct cost value along with the size of specific disease population from each jurisdiction could be used for a quick check on the economic burden of particular disease for countries without such data.

The e-health literacy framework: A conceptual framework for characterizing e-health users and their interaction with e-health systems

In current e-health research and development there is a need for a broader understanding of the capabilities and resources required for individuals to use and benefit from e-health services, i.e. their e-health literacy. The aim of
this study was to develop a new conceptualisation of e-health literacy with consideration of the experiences of a wide range of stakeholders and in alignment with current technologies. Concept mapping was used to generate a comprehensive and grounded model of e-health literacy. Concept mapping workshop participants included patients, health professionals and medical informatics experts. Eight workshops, carried out in Denmark and United Kingdom, generated 450 statements, separated into 128 clusters. Through an inductive structured analysis, seven domains were identified: 1. Ability to process information, 2. Engagement in own health, 3. Ability to engage actively with digital services, 4. Feeling safe and in control, 5. Motivation to engage with digital services, 6. Having access to systems that work, and 7. Digital services that suit individual needs. These empirically derived domains form an e-health literacy framework (eHLF) and provide new insights into the user’s ability to understand, access and use e-health technologies. The eHLF offers a framework for evaluating an individual’s or a population’s capacity to understand, use and benefit from technology to promote and maintain their health. Such a framework also provides a potential checklist for the development and improvement of e-health services.

Future of medical engagement

Although it has long been recognised that doctors play a crucial role in the effectiveness and efficiency of health organisations, patient experience and clinical outcomes, over the past 20 years the topic of medical engagement has started to garner significant international attention. Australia currently lags behind other countries in its heedfulness to, and evidence base for, medical engagement. This Perspective piece explores the link between medical engagement and health system performance and identifies some key questions that need to be addressed in Australia if we are to drive more effective engagement.

Securely sharing dynamic medical information in e-health

This thesis has introduced an infrastructure to share dynamic medical data between mixed health care providers in a secure way, which could benefit the health care system as a whole. The study results of the universally data sharing into a varied patient information system prototypes.