Garzonis, Katherine;
(2019)
Using Patient Profiling Tools to Predict and Enhance Therapy Outcomes.
Doctoral thesis (D.Clin.Psy), UCL (University College London).
Preview |
Text
Thesis_submission_volume1_Garzonis.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Algorithm-based decisions and personalised treatment are two major contemporary healthcare trends. This thesis investigates their utility and potential impact. Part One is a literature review on the effectiveness of predictive decision support algorithms to improve mental health outcomes. It examines thirty papers to indicate their efficacy in practice and risks to uptake. Overall these systems are effective, but have a number of practical and psychological barriers to overcome to be implemented successfully. The review summarises eight hypotheses for effectiveness, which act as guidelines for designing future decision support systems. Part Two examines a previously developed decision support algorithm and its ability to influence mental health recovery and improvement rates through individualised therapy allocation. Several ways of modelling the original algorithm are developed and compared on their ability to predict clinical outcomes, and then used to investigate historical trends in recovery rates at a particular service. Over time, service clinicians appear to naturally allocate more appropriate therapeutic intensities. Allocation as usual was compared with the decision support algorithm for clinical utility. The algorithm did not improve clinical outcomes but was more cost-effective. Part Three is a critical appraisal and reflection on the research process in the context of wider technological and epistemological trends. It discusses the past role of people in research and how they may be involved in future scientific discovery given rapid advances in automating research procedures. It then examines the research project using conclusions from the literature review to inform a critical evaluation.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | D.Clin.Psy |
| Title: | Using Patient Profiling Tools to Predict and Enhance Therapy Outcomes |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2019. Original content in this thesis is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/ 4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. |
| Keywords: | algorithms, psychology, latent profile analysis, realist synthesis |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10076027 |
Archive Staff Only
 |
View Item |
