Use this URL to cite or link to this record in EThOS:
Title: The application of process mining to care pathway analysis in the NHS
Author: Siddiqi, Bushra
ISNI:       0000 0004 7657 7009
Awarding Body: Imperial College London
Current Institution: Imperial College London
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Access from Institution:
Background: Prostate cancer is the most common cancer in men in the UK and the sixth-fastest increasing cancer in males. Within England survival rates are improving, however, these are comparatively poorer than other countries. Currently, information available on outcomes of care is scant and there is an urgent need for techniques to improve healthcare systems and processes. Aims: To provide prostate cancer pathway analysis, by applying concepts of process mining and visualisation and comparing the performance metrics against the standard pathway laid out by national guidelines. Methods: A systematic review was conducted to see how process mining has been used in healthcare. Appropriate datasets for prostate cancer were identified within Imperial College Healthcare NHS Trust London. A process model was constructed by linking and transforming cohort data from six distinct database sources. The cohort dataset was filtered to include patients who had a PSA from 2010-2015, and validated by comparing the medical patient records against a Case-note audit. Process mining techniques were applied to the data to analyse performance and conformance of the prostate cancer pathway metrics to national guideline metrics. These techniques were evaluated with stakeholders to ascertain its impact on user experience. Results: Case note audit revealed 90% match against patients found in medical records. Application of process mining techniques showed massive heterogeneity as compared to the homogenous path laid out by national guidelines. This also gave insight into bottlenecks and deviations in the pathway. Evaluation with stakeholders showed that the visualisation and technology was well accepted, high quality and recommended to be used in healthcare decision making. Conclusion: Process mining is a promising technique used to give insight into complex and flexible healthcare processes. It can map the patient journey at a local level and audit it against explicit standards of good clinical practice, which will enable us to intervene at the individual and system level to improve care.
Supervisor: Aylin, Paul ; Mayer, Erik ; Vale, Justin Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral