Show simple item record

dc.contributor.advisorSheikh, Aziz
dc.contributor.advisorTsanas, Thanasis
dc.contributor.advisorHorne, Robert
dc.contributor.authorTibble, Holly
dc.date.accessioned2022-01-25T14:23:45Z
dc.date.available2022-01-25T14:23:45Z
dc.date.issued2021-12-08
dc.identifier.urihttps://hdl.handle.net/1842/38466
dc.identifier.urihttp://dx.doi.org/10.7488/era/1730
dc.description.abstractBackground Asthma attacks cause approximately 270 hospitalisations and four deaths per day in the United Kingdom (UK). Previous attempts to construct data-driven risk prediction models of asthma attacks have lacked clinical utility: either producing inaccurate predictions or requiring patient data which are not cost-effective to collect on a large scale (such as electronic monitoring device data). Electronic Health Record (EHR) use throughout the UK enables researchers to harness comprehensive and panoramic patient data, but their cleaning and pre-processing requires sophisticated empirical experimentation and data analytics approaches. My objectives were to appraise the previously utilised methods in asthma attack risk prediction modelling for feature extraction, model development, and model selection, and to train and test a model in Scottish EHRs. Methods In this thesis, I used a Scottish longitudinal primary care EHR dataset with linked secondary care records, to investigate the optimisation of an asthma attack risk prediction model. To inform the model, I refined methods for estimation of asthma medication adherence from EHRs, compared model training data enrichment procedures, and evaluated measures for validating model performance. After conducting a critical appraisal of the methods employed in the literature, I trained and tested four statistical learning algorithms for prediction in the next four weeks, i.e. logistic regression, naïve Bayes classification, random forests, and extreme gradient boosting, and validated model performance in an unseen hold-out dataset. Training data enrichment methods were compared across all algorithms to establish whether the sensitivity of estimating relatively uncommon event incidence, such as asthma attacks in the general asthma population, could be improved. Secondary event horizons were also examined, such as prediction in the next six months. Empirical experimentation established the balanced accuracy to be the most appropriate prediction model performance measure, and the calibration between estimated and observed risk was additionally assessed using the Area Under the Receiver-Operator Curve (AUC). Results Data were available for over 670,000 individuals, followed for up to 17 years (177,306 person-years in total). Binary prediction of asthma attacks in the following four-week period resulted in 1,203,476 data samples, of which 1% contained one or more attacks (12,193 total attacks). In the preliminary model selection phase, the random forest algorithm provided the best balance between accuracy in those with asthma attacks (sensitivity) and in those predicted to have attacks (positive predictive value) in the following four weeks. In an unseen data partition, the final random forest model, with optimised hyper-parameters, achieved an AUC of 0.91, and a balanced accuracy of 73.6% after the application of an optimised decision threshold. Accurate predictions were made for a median of 99.6% of those who did not go on to have attacks (specificity). As expected with rare event predictions, the sensitivity was lower at 47.7%, but this was well balanced with the positive predictive value of 48.9%. Furthermore, several of the secondary models, including predicting asthma attacks in the following 12 weeks, achieved state-of-the-art performance and still had high potential clinical utility. Conclusions I successfully developed an EHR-based model for predicting asthma attacks in the next four weeks. Accurately predicting asthma attacks occurrence may facilitate closer monitoring to ensure that preventative therapy is adequately managing symptoms, reinforce the need to keep abreast of triggers, and allow rescue treatments to be administered quickly when necessary.en
dc.language.isoenen
dc.publisherThe University of Edinburghen
dc.relation.hasversionTibble H, Chan AHY, Mitchell EA, Horne E, Doudesis D, Horne R, Mizani MA, Sheikh A, Tsanas A. (2021) A Data-Driven Typology of Asthma Medication Adherence using Cluster Analysis. Scientific Reports. 10(1). 14999.en
dc.relation.hasversionTibble H, Lay-Flurrie J, Sheikh A, Horne R, Mizani MA, Tsanas A., The Salford Lung Study Team. (2020) Linkage of Primary Care Prescribing Records and Pharmacy Dispensing Records in the Salford Lung Study: Application in Asthma. BMC Medical Research Methodology. 20(1). 303.en
dc.relation.hasversionTibble H, Flook M, Sheikh A, Tsanas A, Horne R, Vrijens B, De Geest S, Stagg HR. (2020) Measuring and reporting treatment adherence: what can we learn by comparing two respiratory conditions? British Journal of Clinical Pharmacology. 87(3). 825-836en
dc.relation.hasversionTibble H, Horne E, Horne R, Mizani AM, Simpson CR, Sheikh A, Tsanas A. (2019) Predicting asthma attacks in primary care: protocol for developing a machine learning-based prediction model. BMJ Open. 9(7), e028375en
dc.relation.hasversionTibble H, Chan A, Mitchell EA, Horne R, Mizani MA, Sheikh A, Tsanas A. (2019) Heterogeneity in Asthma Medication Adherence Measurement. 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). p. 899-903.en
dc.relation.hasversionTibble H, Sheikh A, Tsanas A, Horne R, Mizani M, Simpson C, Lay-Flurrie, J. (2019) Linkage of Primary Care Prescribing Records and Pharmacy Dispensing Records in Asthma Controller Medications. International Journal of Population Data Science, 4(3).en
dc.subjectasthma attack predictionen
dc.subjectdata-driven risk predictionen
dc.subjectElectronic Health Recorden
dc.subjectEHR useen
dc.subjectpatient dataen
dc.subjectmodel developmenten
dc.subjectdatasetsen
dc.subjectbalanced accuracyen
dc.titleData-driven approaches for predicting asthma attacks in adults in primary careen
dc.typeThesis or Dissertationen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD Doctor of Philosophyen


Files in this item

This item appears in the following Collection(s)

Show simple item record