Exploiting medical hierarchies for concept-based information retrieval

Search technologies are critical to enable clinical sta to rapidly and e ectively access patient information contained in free-text medical records. Medical search is challenging as terms in the query are often general but those in rel- evant documents are very speci c, leading to granularity mismatch. In this paper we propose to tackle granularity mismatch by exploiting subsumption relationships de ned in formal medical domain knowledge resources. In symbolic reasoning, a subsumption (or `is-a') relationship is a parent-child rela- tionship where one concept is a subset of another concept. Subsumed concepts are included in the retrieval function. In addition, we investigate a number of initial methods for combining weights of query concepts and those of subsumed concepts. Subsumption relationships were found to provide strong indication of relevant information; their inclusion in retrieval functions yields performance improvements. This result motivates the development of formal models of rela- tionships between medical concepts for retrieval purposes.

Exploiting SNOMED CT concepts and relationships for clinical information retrieval : Australian e-Health Research Centre and Queensland University of Technology at the TREC 2012 Medical Track

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2012 Medical Records Track. This paper reports on our methods, results and experience using an approach that exploits the concept and inter-concept relationships defined in the SNOMED CT medical ontology. Our concept-based approach is intended to overcome specific challenges in searching medical records, namely vocabulary mismatch and granularity mismatch. Queries and documents are transformed from their term-based originals into medical concepts as defined by the SNOMED CT ontology, this is done to tackle vocabulary mismatch. In addition, we make use of the SNOMED CT parent-child `is-a' relationships between concepts to weight documents that contained concept subsumed by the query concepts; this is done to tackle the problem of granularity mismatch. Finally, we experiment with other SNOMED CT relationships besides the is-a relationship to weight concepts related to query concepts. Results show our concept-based approach performed significantly above the median in all four performance metrics. Further improvements are achieved by the incorporation of weighting subsumed concepts, overall leading to improvement above the median of 28% infAP, 10% infNDCG, 12% R-prec and 7% Prec@10. The incorporation of other relations besides is-a demonstrated mixed results, more research is required to determined which SNOMED CT relationships are best employed when weighting related concepts.

Semantic judgement of medical concepts : combining syntagmatic and paradigmatic information with the tensor encoding model

This paper outlines a novel approach for modelling semantic relationships within medical documents. Medical terminologies contain a rich source of semantic information critical to a number of techniques in medical informatics, including medical information retrieval. Recent research suggests that corpus-driven approaches are effective at automatically capturing semantic similarities between medical concepts, thus making them an attractive option for accessing semantic information. Most previous corpus-driven methods only considered syntagmatic associations. In this paper, we adapt a recent approach that explicitly models both syntagmatic and paradigmatic associations. We show that the implicit similarity between certain medical concepts can only be modelled using paradigmatic associations. In addition, the inclusion of both types of associations overcomes the sensitivity to the training corpus experienced by previous approaches, making our method both more effective and more robust. This finding may have implications for researchers in the area of medical information retrieval.

How should Australia regulate voluntary euthanasia and assisted suicide?

The purpose of this paper is to provide a basis from which to start an informed and rational dialogue in Australia about voluntary euthanasia (VE) and assisted suicide (AS). It does this by seeking to chart the broad landscape of issues that can be raised as relevant to how this conduct should be regulated by the law. It is not our purpose to persuade. Rather, we have attempted to address the issues as neutrally as possible and to canvass both sides of the argument in an even-handed manner. We hope that this exercise places the reader in a position to consider the question posed by this paper: How should Australia regulate voluntary euthanasia and assisted suicide? In line with the approach taken in the paper, this question does not take sides in the debate. It simply asks how VE and AS should be regulated, acknowledging that both prohibition and legalisation of such conduct involve regulation. We begin by considering the wider legal framework that governs end of life decision-making. Decisions to withhold or withdraw life-sustaining treatment that result in a person’s death can be lawful. This could be because, for example, a competent adult refuses such treatment. Alternatively, stopping or not providing treatment can be lawful when it is no longer in a person’s best interests to receive it. The law also recognises that appropriate palliative care should not attract criminal responsibility. By contrast, VE and AS are unlawful in Australia and could lead to prosecution for crimes such as murder, manslaughter or aiding and abetting suicide. But this is not to say that such conduct does not occur in practice. Indeed, there is a body of evidence that VE and AS occur in Australia, despite them being unlawful. There have been repeated efforts to change the law in this country, mainly by the minor political parties. However, apart from a brief period when VE and AS was lawful in the Northern Territory, these attempts to reform the law have been unsuccessful. The position is different in a small but increasing number of jurisdictions overseas where such conduct is lawful. The most well known is the Netherlands but there are also statutory regimes that regulate VE and/or AS in Belgium and Luxembourg in Europe, and Oregon and Washington in the United States. A feature of these legislative models is that they incorporate review or oversight processes that enable the collection of data about how the law is being used. As a result, there is a significant body of evidence that is available for consideration to assess the operation of the law in these jurisdictions and some of this is considered briefly here. Assisting a suicide, if done for selfless motives, is also legal in Switzerland, and this has resulted in what has been referred to as ‘euthanasia tourism’. This model is also considered. The paper also identifies the major arguments in favour of, and against, legalisation of VE and AS. Arguments often advanced in favour of law reform include respect for autonomy, that public opinion favours reform, and that the current law is incoherent and discriminatory. Key arguments against legalising VE and AS point to the sanctity of life, concerns about the adequacy and effectiveness of safeguards, and a ‘slippery slope’ that will allow euthanasia to occur for minors or for adults where it is not voluntary. We have also attempted to step beyond these well trodden and often rehearsed cases ‘for and against’. To this end, we have identified some ethical values that might span both sides of the debate and perhaps be the subject of wider consensus. We then outline a framework for considering the issue of how Australia should regulate VE and AS. We begin by asking whether such conduct should be criminal acts (as they presently are). If VE and AS should continue to attract criminal responsibility, the next step is to enquire whether the law should punish such conduct more or less than is presently the case, or whether the law should stay the same. If a change is favoured as to how the criminal law punishes VE and AS, options considered include sentencing reform, creating context-specific offences or developing prosecutorial guidelines for how the criminal justice system deals with these issues. If VE and AS should not be criminal acts, then questions arise as to how and when they should be permitted and regulated. Possible elements of any reform model include: ensuring decision-making is competent and voluntary; ascertaining a person’s eligibility to utilise the regime, for example, whether it depends on him or her having a terminal illness or experiencing pain and suffering; and setting out processes for how any decision must be made and evidenced. Options to bring about decriminalisation include challenging the validity of laws that make VE and AS unlawful, recognising a defence to criminal prosecution, or creating a statutory framework to regulate the practice. We conclude the paper where we started: with a call for rational and informed consideration of a difficult and sensitive issue. How should Australia regulate voluntary euthanasia and assisted suicide?

The battered child syndrome : changes in the law and child advocacy

In 1962, Dr C. Henry Kempe and his colleagues published the single most important article written to date about child maltreatment: The Battered-Child Syndrome. This chapter analyses the threefold nature of what these authors achieved: clearly identifing the medical evidence of severe child physical abuse and naming it as a syndrome; identifying the medical profession's resistance to its identification; and then translating their scholarship into advocacy for social and legal change. The chapter also traces some of the effects of Kempe's work, including the nature and effect of the subsequent introduction of mandatory reporting laws in the USA and internationally.

Mastering medical terminology : Australia and New Zealand Workbook

Mastering Medical Terminology: Australia and New Zealand Workbook is the indispensable companion to Mastering Medical Terminology Textbook. Packed with a range of exercises and activities to accompany the main text, the Workbook provides an ideal resource for self-testing and revision in a fun, practical and accessible format, and forms a key part of the Mastering Medical Terminology suite of products which are all available for separate purchase enabling you to pick and choose the right package for your learning requirements. Featuring a variety of question types including crossword puzzles, anagrams, multiple-choice questions and label-the-diagram exercises, the Workbook uses entirely Australian spelling and aligns to the chapters of the main text. When used in combination with the main text and MedWords app, Mastering Medical Terminology: Australia and New Zealand Workbook will make the scholarship of medical terminology not only manageable, but fun!

Access to cardiac rehabilitation does not equate to attendance

Background/Aims Timely access to appropriate cardiac care is critical for optimizing positive outcomes after a cardiac event. Attendance at cardiac rehabilitation (CR) remains less than optimal (10%–30%). Our aim was to derive an objective, comparable, geographic measure reflecting access to cardiac services after a cardiac event in Australia. Methods An expert panel defined a single patient care pathway and a hierarchy of the minimum health services for CR and secondary prevention. Using geographic information systems a numeric/alpha index was modelled to describe access before and after a cardiac event. The aftercare phase was modelled into five alphabetical categories: from category A (access to medical service, pharmacy, CR, pathology within 1 h) to category E (no services available within 1 h). Results Approximately 96% or 19 million people lived within 1 h of the four basic services to support CR and secondary prevention, including 96% of older Australians and 75% of the indigenous population. Conversely, 14% (64,000) indigenous people resided in population locations that had poor access to health services that support CR after a cardiac event. Conclusion Results demonstrated that the majority of Australians had excellent ‘geographic’ access to services to support CR and secondary prevention. Therefore, it appears that it is not the distance to services that affects attendance. Our ‘geographic’ lens has identified that more research on socioeconomic, sociological or psychological aspects to attendance is needed.

(Mis)Using Pulse Oximetry : A Review of Pulse Oximetry use in Acute Care Medical Wards

Background: Nurses routinely use pulse oximetry (SpO2) monitoring equipment in acute care. Interpretation of the reading involves physical assessment and awareness of parameters including temperature, haemoglobin, and peripheral perfusion. However, there is little information on whether these clinical signs are routinely measured or used in pulse oximetry interpretation by nurses. Aim: The aim of this study was to review current practice of SpO2 measurement and the associated documentation of the physiological data that is required for accurate interpretation of the readings. The study reviewed the documentation practices relevant to SpO2 in five medical wards of a tertiary level metropolitan hospital. Method: A prospective casenote audit was conducted on random days over a three-month period. The audit tool had been validated in a previous study. Results: One hundred and seventy seven episodes of oxygen saturation monitoring were reviewed. Our study revealed a lack of parameters to validate the SpO2 readings. Only 10% of the casenotes reviewed had sufficient physiological data to meaningfully interpret the SpO2 reading and only 38% had an arterial blood gas as a comparator. Nursing notes rarely documented clinical interpretation of the results. Conclusion: The audits suggest that medical and nursing staff are not interpreting the pulse oximetry results in context and that the majority of the results were normal with no clinical indication for performing this observation. This reduces the usefulness of such readings and questions the appropriateness of performing “routine” SpO2 in this context.

Telehealth for nursing homes: the utilization of specialist services for residential care

Specialist care consultations were identified by two research nurses using documentation in patient records, appointment diaries, electronic billing services and on-site observations at a 441-bed long term care facility. Over a six-month period there were 3333 consultations (a rate of 1511 consultations per year per 100 beds). Most consultations were for general practice (n = 2589, 78%); these consultations were mainly on site (99%), with only 27 taking place off site. There were 744 consultations for specialities other than general practice. A total of 146 events related to an emergency or unplanned hospital admission. The remaining medical consultations (n = 598, 18%) related to 23 medical specialities. The largest number of consultations were for surgery (n = 106), podiatry (n = 100), nursing services including wound care (n = 74), imaging (n = 41) and ophthalmology (n = 40). Many services which are currently being provided on site to metropolitan long-term care facilities could be provided by telehealth in both urban and rural facilities.