An ontological approach to personalized medical knowledge recommendation

Knowledge recommendation has become a promising method in supporting the clinicians decisions and improving the quality of medical services in the constantly changing clinical environment. However, current medical knowledge management systems cannot understand users requirements accurately and realize personalized recommendation. Therefore this paper proposes an ontological approach based on semiotic principles to personalized medical knowledge recommendations. In particular, healthcare domain knowledge is conceptualized and an ontology-based user profile is built. Furthermore, the personalized recommendation mechanism is illustrated.

An ontological approach to personalized medical knowledge matching

Knowledge management has become a promising method in supporting the clinicians′ decisions and improving the quality of medical services in the constantly changing clinical environment. However, current medical knowledge management systems cannot understand users′ requirements accurately and realize personalized matching. Therefore this paper proposes an ontological approach based on semiotic principles to personalized medical knowledge matching. In particular, healthcare domain knowledge is conceptualized and an ontology-based user profile is built. Furthmore, the personalized matching mechanism and algorithm are illustrated.

Applying robust control theory to solve problems in bio-medical sciences: study of an apoptotic model

Biological models of an apoptotic process are studied using models describing a system of differential equations derived from reaction kinetics information. The mathematical model is re-formulated in a state-space robust control theory framework where parametric and dynamic uncertainty can be modelled to account for variations naturally occurring in biological processes. We propose to handle the nonlinearities using neural networks.

Roles of the non-medical prescribing leads within organisations across a Strategic Health Authority: perceived functions and factors supporting the role

Objectives Extending the roles of nurses, pharmacists and allied health professionals to include prescribing has been identified as one way of improving service provision. In the UK, over 50 000 non-medical healthcare professionals are now qualified to prescribe. Implementation of non-medical prescribing ( NMP) is crucial to realise the potential return on investment. The UK Department of Health recommends a NMP lead to be responsible for the implementation of NMP within organisations. The aim of this study was to explore the role of NMP leads in organisations across one Strategic Health Authority (SHA) and to inform future planning with regards to the criteria for those adopting this role, the scope of the role and factors enabling the successful execution of the role. Methods Thirty-nine NMP leads across one SHA were approached. Semi-structured telephone interviews were conducted. Issues explored included the perceived role of the NMP lead, safety and clinical governance procedures and facilitators to the role. Transcribed audiotapes were coded and analysed using thematic analytical techniques. Key findings In total, 27/39 (69.2%) NMP leads were interviewed. The findings highlight the key role that the NMP lead plays with regards to the support and development of NMP within National Health Service trusts. Processes used to appoint NMP leads lacked clarity and varied between trusts. Only two NMP leads had designated or protected time for their role. Strategic influence, operational management and clinical governance were identified as key functions. Factors that supported the role included organisational support, level of influence and dedicated time. Conclusion The NMP lead plays a significant role in the development and implementation of NMP. Clear national guidance is needed with regards to the functions of this role, the necessary attributes for individuals recruited into this post and the time that should be designated to it. This is important as prescribing is extended to include other groups of non-medical healthcare professionals.

Children’s physic: medical perceptions and treatment of sick children in early modern England, c. 1580-1720

Historians of medicine, childhood, and paediatrics, have often assumed that early modern doctors neither treated children, nor adapted their medicines to suit the peculiar temperaments of the young. Through an examination of medical textbooks and doctors’ casebooks, this article refutes these assumptions. It argues that medical authors and practising doctors regularly treated children, and were careful to tailor their remedies to complement the distinctive constitutions of children. Thus, this article proposes that a concept of ‘children’s physic’ existed in early modern England: this term refers to the notion that children were physiologically distinct, requiring special medical care. Children’s physic was rooted in the ancient traditions of Hippocratic and Galenic medicine: it was the child’s humoral makeup that underpinned all medical ideas about children’s bodies, minds, diseases, and treatments. Children abounded in the humour blood, which made them humid and weak, and in need of medicines of a particularly gentle nature.

Multiprobabilistic prediction in early medical diagnoses

This paper describes the methodology of providing multiprobability predictions for proteomic mass spectrometry data. The methodology is based on a newly developed machine learning framework called Venn machines. Is allows to output a valid probability interval. The methodology is designed for mass spectrometry data. For demonstrative purposes, we applied this methodology to MALDI-TOF data sets in order to predict the diagnosis of heart disease and early diagnoses of ovarian cancer and breast cancer. The experiments showed that probability intervals are narrow, that is, the output of the multiprobability predictor is similar to a single probability distribution. In addition, probability intervals produced for heart disease and ovarian cancer data were more accurate than the output of corresponding probability predictor. When Venn machines were forced to make point predictions, the accuracy of such predictions is for the most data better than the accuracy of the underlying algorithm that outputs single probability distribution of a label. Application of this methodology to MALDI-TOF data sets empirically demonstrates the validity. The accuracy of the proposed method on ovarian cancer data rises from 66.7 % 11 months in advance of the moment of diagnosis to up to 90.2 % at the moment of diagnosis. The same approach has been applied to heart disease data without time dependency, although the achieved accuracy was not as high (up to 69.9 %). The methodology allowed us to confirm mass spectrometry peaks previously identified as carrying statistically significant information for discrimination between controls and cases.