Issues in the prescribing of psychotropic and psychoactive medication for persons with learning disability: quantitative and qualitative perspectives

The administration of psychotropic and psychoactive medication for persons with learning disability and accompanying mental illness and/or challenging behaviour has undergone much critical review over the past two decades. Assessment and diagnosis of mental illness in this population continues to be psychopharmacological treatment include polypharmacy, irrational prescription procedures and frequent over-prescription. It is clear that all forms of treatment including non-pharmacological interventions need to be driven by accurate and appropriate diagnoses. Where a psychiatric diagnosis has been identified, it greatly aides the selection of appropriate medication, although a specific medication for each diagnosis, as was once hoped, is simply no longer a reality in practice. Part one of the present thesis seeks to address many of the current issues in mental health problems and pharmacological treatment to date. The author undertook a drug prevalence study within both residential and community facilities for persons with learning disability within the Mid-West region of Ireland in order to ascertain the current level of prescribing of psychotropic and psychoactive medications for this population. While many attempts have been made to account for the variation in prescribing, little systematic and empirical research has been undertaken to investigate the factors thought to influence such prescribing. While studies investigating the prescribing behaviours of General Practitioners (GP's) have illustrated the complex nature of the decision making process in the context of general practice, no similar efforts have yet been directed at examining the prescribing behaviours of Consultant Psychiatrists. Using The Critical Incident Technique, the author interviewed Consultant Psychiatrists in the Republic of Ireland to gather information relating not only to their patterns of prescribing for learning disabled populations, but also to examine reasons influencing their prescribing in addition to several related factors. Part two of this thesis presents the findings from this study and a number of issues are raised, not only in relation to attempting to account for the findings from part one of the thesis, but also with respect to implications for improved management and clinical practice.

Power system parameters forecasting using Hilbert-Huang transform and machine learning

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.