Alsmadi, H (2021) Long-term Follow-up of Hydrocephalus Patients and Prediction of Risk Factors using Machine Learning. Doctoral thesis, Liverpool John Moores University.

Text 2020HibaAlsmadiPhD.pdf - Published Version Restricted to Repository staff only until 1 August 2023. Available under License Creative Commons Attribution Non-commercial. Download (2MB)

Abstract

Hydrocephalus is a disorder when an excessive amount of cerebrospinal fluid (CSF) accumulates inside the subarachnoid space, which can lead to an enlargement of the ventricular system of the brain and increase the pressure inside the head. Paediatric population, adults, and most elderly ones can be affected by hydrocephalus. This neurological condition can have an excellent diagnosis if treated. However, it also can be life threatening if not treated correctly. With the increasing roll-out of ‘digital hospitals’, electronic medical records, new data capture and analysis technologies, as well as a digitally enabled health consumer, the healthcare workforce is required to become digitally literate to manage the significant changes in the healthcare landscape. In this study, Machine learning techniques are employed for the long-term follow-up for hydrocephalus patients, for which a data set of 3,262 records of ICP signals of shunted patients from Alder Hey Hospital, was used. Six popular machine-learning based classifiers have been evaluated for the classification of monitoring shunted patients and produce the required risk assessments to follow up shunted patients within a supervised learning setting, which are Ensemble Bagged Tree, Ensemble Boosted Tree, Fine Tree, Quadratic SVM, Gaussian SVM and Cubic SVM. The classifier Ensemble Boosted Tree achieved the highest aggregate performance outcomes of accuracy 98.90, sensitivity 100, specificity 100 and precision of 100. The study concludes that using machine learning techniques represents an alternative procedure that could assist healthcare professionals, as well as the specialist nurse and junior doctor to improve the quality of care and follow-up with hydrocephalus disorder.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Machine Learning; AI; Health Care; Hydrocephalus Patients; Computer Aided Diagnosis System; Mobile Application
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > R Medicine (General)
Divisions:	Computer Science & Mathematics
Date Deposited:	29 Jul 2021 08:42
Last Modified:	23 Nov 2022 09:55
DOI or Identification number:	10.24377/LJMU.t.00015313
Supervisors:	Al-Jumeily, D, Hussain, A and Chalmers, C
URI:	https://researchonline.ljmu.ac.uk/id/eprint/15313

Actions (login required)

View Item