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.

A study of load support and other criteria appropriate to the selection of industrial conveyor belts

A study of conveying practice demonstrates that belt conveyors provide a versatile and. much-used method of transporting bulk materials, but a review of belting manufacturers' design procedures shows that belt design and selection rules are often based on experience with all-cotton belts no longer in common use, and are net completely relevant to modern synthetic constructions. In particular, provision of the property "load support", which was not critical with cotton belts, is shown to determine the outcome of most belt selection exercises and lead to gross over specification of other design properties in many cases. The results of an original experimental investigation into this property, carried out to determine the belt and conveyor parameters that affect it, how the major role that belt stiffness plays in its provision; the basis for a belt stiffness test relevant to service conditions is given. A proposal for a more rational method of specifying load support data results from the work, but correlation of the test results with service performance is necessary before the absolute toad support capability required from a belt for given working conditions can be quantified. A study to attain this correlation is the major proposal for future work resulting from the present investigation, but a full review of the literature on conveyor design and a study of present practice within the belting industry demonstrate other, less critical, factors that could profitably be investigated. It is suggested that the most suitable method of studying these would be a rational data collection system to provide information on various facets of belt service behaviour; a basis for such a system is proposed. In addition to the work above, proposals for simplifying the present belt selection methods are made and a strain transducer suitable for use in future experimental investigations is developed.

Skin adhesive hydrogels for the topical delivery of active agents

This thesis illustrates the development of tailor-made, partially hydrated skin adhesive hydrogels as a vehicle for the topical delivery of moisturising agents. Maintaining an optimum hydration level of the stratum corneum ensures that the barrier properties of the skin are preserved. An unsaturated ionic monomer 2-acrylamido-2-methylpropanesulfonic acid sodium salt, glycerol, water, a photoinitiator Irgacure 184 and crosslinker Ebacryl II facilitated the production of monophasic sheet skin adhesives using photopolymerisation. The exploration and modification of the hydrogel components coupled with their influence on the adhesive and dynamic mechanical behaviour led to the development of novel monophasic and biphasic hydrogels. Biphasic pregels comprising of a hydrophobic monomer (epoxidised soybean oil acrylate, lauryl acrylate or stearyl acrylate) micellised with a non ionic surfactant Tween 60 allowed a homogeneous distribution throughout a predominantly hydrophilic phase (2-acrylamido-2-methylpropanesulfonic acid sodium salt, 4-acryloylmorpholine, glycerol and water). Further development of biphasic hydrogel technology led to the incorporation of preformed commercial O/W emulsions (Acronal, Flexbond 150, DM137 or Texicryl 13056WB) allowing the hydrophobic component to be added without prior stabilisation. The topical release of moisturising agents 2-pyrrolidone-5-carboxylic acid, lactobionic acid and d-calcium pantothenate results in the deposition onto the skin by an initial burst mechanism. The hydration level of the stratum corneum was measured using a Comeometer CM 825, Skin Reader MY810 or FT-ATR. The use of hydrophilic actives in conjunction with lipophilic agents for example Vitamin E or Jojoba oil provided an occlusive barrier, which reduced the rate of transepidermal water loss. The partition coefficients of the release agents provided invaluable information which enabled the appropriate gel technology to be selected. In summary the synthetic studies led to the understanding and generation of transferable technology. This enabled the synthesis of novel vehicles allowing an array of actives with a range of solubilities to be incorporated.

Appropriate wage rate and estimate of labour availability for a public works based safety net in Cambodia

Employment generating public works (EGPW) are an important part of Royal Government of Cambodia’s (RGC’s) strategy being developed through Council for Agriculture and Rural Development (CARD) to develop a comprehensive social safety net (SSN) to provide a measure of protection from shocks for the poor and vulnerable and to contribute to poverty alleviation through short-term unskilled employment.

Appropriate wage rate and related issues for employment intensive public works programmes in Timor Leste

Employment generating public works (EGPW) are an important part of GoTL’s strategy to reduce unemployment, underemployment and poverty and contribute to social stability. The term EGPW is used in this report as a generic term to encompass labour intensive (LI) and labourbased (LB) approaches. The distinction between these approaches is made below. SEFOPE is being supported by a number of international agencies to develop and implement employment generating public works programmes (EGPWPs). Other government ministries and agencies and NGOs offering different wage rates are also engaged in such programmes and projects. In setting wage rates for such programmes, it is necessary to take account of (a) the nature of benefits they offer (e.g. the balance between employment creation and effective use of labour); (b) the beneficiaries to be targeted, and (c) any adverse impacts on other economic activities. The purposes of this assignment are: (a) to make recommendations on appropriate wage rates for unskilled casual employment on public works programmes, and (b) make a broad assessment of the labour supply response to the employment opportunities created by employment intensive programmes. The latter would help in gauging the scale of such activities required.

Empirical prediction of peptide octanol-water partition coefficients

Peptides are of great therapeutic potential as vaccines and drugs. Knowledge of physicochemical descriptors, including the partition coefficient P (commonly expressed in logarithm form: logP), is useful for screening out unsuitable molecules and also for the development of predictive Quantitative Structure-Activity Relationships (QSARs). In this paper we develop a new approach to the prediction of LogP values for peptides based on an empirical relationship between global molecular properties and measured physical properties. Our method was successful in terms of peptide prediction (total r2 = 0.641). The final model consisted of 5 physicochemical descriptors (molecular weight, number of single bonds, 2D-VDW volume, 2D-VSA hydrophobic and 2D-VSA polar). The approach is peptide specific and its predictive accuracy was high. Overall, 67% of the peptides were able to be predicted within +/-0.5 log units from the experimental values. Our method thus represents a novel prediction method with proven predictive ability.