The motivation for this research is to develop an approach that reliably captures the disease dynamics of COVID-19 for an entire population in order to identify the key events driving change in the epidemic through accurate estimation of daily COVID-19 cases. This has been achieved through the new CP-ABM approach which uniquely incorporates Change Point detection into an Agent Based Model taking advantage of genetic algorithms for calibration and an efficient infection centric procedure for computational efficiency. The CP-ABM is applied to the Northern Ireland population where it successfully captures patterns in COVID-19 infection dynamics over both waves of the pandemic and quantifies the significant effects of non-pharmaceutical interventions (NPI) on a national level for lockdowns and mask wearing. To our knowledge, there is no other approach to date that has captured NPI effectiveness and infection spreading dynamics for both waves of the COVID-19 pandemic for an entire country population.

This paper introduces the real-time Healthcare 4.0 system, the VILIAlert system and a new approach that we propose for the robust assessment of it's performance. The VILIAlert system alerts clinicians when a patient's tidal volume value rises above the clinically accepted level of 8 ml/kg as beyond this point (> 8 ml/kg), a patient is considered high risk of permanent damage to their lungs. In order to ensure success with the VILIAlert system, the ideal scenario is to ensure that as soon as patients in the Intensive Care Unit experience tidal volume values beyond the 8 ml/kg level, a clinical intervention can be carried out so to minimise the risk of patients ever having permanent damage. The approach has been implemented in the Intensive Care Unit at the Royal Victoria Hospital Belfast, Northern Ireland demonstrating the potential for such an approach to be used across all hospitals in the region.

The development of new learning models has been of great importance throughout recent years, with a focus on creating advances in the area of deep learning. Deep learning was first noted in 2006, and has since become a major area of research in a number of disciplines. This paper will delve into the area of deep learning to present its current limitations and provide a new idea for a fully integrated deep and dynamic probabilistic system. The new model will be applicable to a vast number of areas initially focusing on applications into medical image analysis with an overall goal of utilising this approach for prediction purposes in computer based medical systems.

Health care providers continue to feel the pressure in providing adequate care for an increasing elderly population. If length of stay patterns for elderly patients in care can be captured through analytical modelling, then accurate predictions may be made on when they are expected to leave hospital. The Discrete Conditional Phase-type (DC-Ph) model is an effective technique through which length of stay in hospital can be modelled and consists of both a conditional and a process component. This research expands the DC-Ph model by introducing a survival tree as the conditional component, whereby covariates are used to partition patients into cohorts based on their distribution of length of stay in hospital. The Coxian phase-type distribution is then used to model the length of stay for patients belonging to each cohort. A demonstration of how patient length of stay may be predicted for new admissions using this methodology is then given. This tool has the benefit of providing an aid to the decision making processes undertaken by hospital managers and has the potential to result in the more effective allocation of hospital resources. Hospital admission data from the Lombardy region of Italy is used as a case-study.

Type 2 diabetes (T2D) is a major public health problem. The prevalence of the disease is growing at an alarming rate and the sharp increase in T2D shows no signs of slowing down. The increased number of T2D cases worldwide has caused a simultaneous increase in the number of T2D related complications. This paper demonstrates how a survival tree based approach can be used to enable predictions to be made concerning when an individual is expected to experience a complication of T2D. A survival tree is used to identify cohorts of individuals with significantly different survival distributions from T2D to complication. By fitting appropriate survival distributions to the individual leaves of the tree, the expected time until complication can be calculated for each group of individuals. Survival trees were built for death, stroke/acute myocardial infarction (AMI) and amputation/coronary revascularisation.

Retinopathy of prematurity (ROP) is a rare disease in which retinal blood vessels of premature infants fail to develop normally, and is one of the major causes of childhood blindness throughout the world. The Discrete Conditional Phase-type (DC-Ph) model consists of two components, the conditional component measuring the inter-relationships between covariates and the survival component which models the survival distribution using a Coxian phase-type distribution. This paper expands the DC-Ph models by introducing a support vector machine (SVM), in the role of the conditional component. The SVM is capable of classifying multiple outcomes and is used to identify the infant's risk of developing ROP. Class imbalance makes predicting rare events difficult. A new class decomposition technique, which deals with the problem of multiclass imbalance, is introduced. Based on the SVM classification, the length of stay in the neonatal ward is modelled using a 5, 8 or 9 phase Coxian distribution.

This paper introduces a discrete conditional survival model (DC-S) with a classification component for predicting patient outcome and survival component for predicting length of stay in hospital. The DC-S model consists of two components; the conditional component which utilises a classification tree and the survival component which models the survival distribution. The survival component of the model is conditioned on the discrete conditional component, the classification tree. The DC-S model with classification tree is applied to a healthcare scenario where the length of stay of babies in neonatal wards in Northern Ireland (United Kingdom) is modelled using the baby characteristics known on the first day of admission. The resulting model can accurately predict length of stay of babies and thus has the potential to be used in bed planning. Hospitals could use such good estimates for the length of stay of patients (determined on the day of arrival) to plan ahead to make the correct provisions available during their stay. Not only does this have resource implications, it can also help patient families. The resulting model can also predict the occurrence (or otherwise) of late onset sepsis, which has implications on a patients stay.

This paper introduces a Dynamic Bayesian network (DBN) model for representing survival of patients suffering from ischaemic heart disease (IHD). The main purpose of the model is to investigate the potential association between patient variables, the risk of developing cardiovascular disease (IHD) and survival. Of particular interest is whether, a combination of risk factors known as Metabolic syndrome are the key variables of interest in determining IHD risk or whether there are others considered just as significant, such as age, smoking and BMI that are not associated with the syndrome. The resulting Dynamic Bayesian network provides a straightforward illustration of the causal relationships between patient variables, disease occurrence and survival with the aim of understanding patient needs and the possibility of highlighting health interventions. It is hoped that such a model can help inform patient management decisions by illustrating where a change in certain patient characteristics could produce a health improvement and reduced risk. The DBN has the additional capacity to allow the representation of repeated measures data where patient variables may be available at more than one time point.

Discrete Conditional Phase-type (DC-Ph) models are a family of models which represent skewed survival data conditioned on specific inter-related discrete variables. The survival data is modeled using a Coxian phase-type distribution which is associated with the inter-related variables using a range of possible data mining approaches such as Bayesian networks (BNs), the naiumlve Bayes classification method and classification regression trees. This paper utilizes the discrete conditional phase-type model (DC-Ph) to explore the modeling of patient waiting times in an Accident and Emergency Department of a UK hospital. The resulting DC-Ph model takes on the form of the Coxian phase-type distribution conditioned on the outcome of a logistic regression model.

TEST 02 - Elsevier's Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.

The aim of this paper is to use Markov modelling to investigate survival for particular types of kidney patients in relation to their exposure to anti-hypertensive treatment drugs. In order to monitor kidney function an intuitive three point assessment is proposed through the collection of blood samples in relation to chronic kidney disease for Northern Ireland patients. A five state Markov model was devised using specific transition probabilities for males and females over all age groups. These transition probabilities were then adjusted appropriately using relative risk scores for the event death for different subgroups of patients. The model was built using TreeAge software package in order to explore the effects of anti-hypertensive drugs on patients.

The paper introduces a new modeling approach that represents the waiting times in an accident and emergency (A&E) department in a UK based national health service (NHS) hospital. The technique uses Bayesian networks to capture the heterogeneity of arriving patients by representing how patient covariates interact to influence their waiting times in the department. Such waiting times have been reviewed by the NHS as a means of investigating the efficiency of A&E departments (emergency rooms) and how they operate. As a result activity targets are now established based on the patient total waiting times with much emphasis on trolley waits.

This paper describes the development of a model to assess the distribution of response times for mobile volunteers of a Public Access Defibrillation (PAD) scheme in Northern Ireland. Using parameters based on a trial period, the model predicts that a PAD volunteer would arrive before the Emergency Medical Services (EMS) to 18.8% of events to which they are paged in a given year period. This is in agreement with what has actually been observed during the trial period (where volunteers have actually reached 15% of events before the EMS), and thus assisting validation of the model. Results from this model illustrate how ongoing volunteer commitment is key to the success of the scheme.

The ability to model and predict the progression of disease in a patient can have wide ranging benefits, including the ability to successfully manage bed allocation in hospitals or the increase understanding of the evolution of the disease. This paper describes a new method of modelling the progression of a disease through different stages called a Coxian hidden Markov model. This model can be used to increase understanding of the characteristics of the different stages of the disease and to predict patient survival time given repeated measurements of dynamically changing clinical variables. This knowledge could then be used to provide better patient management.

This paper extends a method for modeling the survival of patients in hospitals to allow the expected cost to be estimated for the patients' accumulated duration of time in care. An extension of Bayesian network (BN) theory has previously been developed to model patients' survival time in hospitals with respect to the graphical and probabilistic representation of the interrelationships between the patients' clinical variables. Unlike previous BN techniques, this extended model can accommodate continuous times that are skewed in nature. This paper presents the theory behind such an approach and extends it by attaching a cost variable to the survival times, enabling the costing and efficient management of groups of patients in hospitals. An application of the model is illustrated by considering a group of 4260 patients admitted into the geriatric department of a U.K. hospital between 1994-1997. Results are derived for the distribution for their length of stay in the hospital and associated costs. The model's practical use is highlighted by illustrating how hospital managers could benefit using such a method for investigating the influence of future decisions and policy changes on the hospital's expenditure.

This paper introduces a special computer-based roster scheme developed to allocate and manage volunteers working as part of a public access defibrillation trial. The roster scheme, developed for the urban region, is rooted on population statistics and demographics for that area and utilizes geographical mapping software and spatial modelling techniques to subdivide the geographical location into appropriate paging zones. The central location for zones was constrained to be within a reasonable travelling time for each volunteer. By estimating sudden cardiac arrest occurrences using a Poisson process, the model, together with road network information, selects a roster which minimizes volunteer response time.

This paper introduces a model for representing patient survival and cost. An extension of Bayesian network (BN) theory is developed to represent such a model whereby patient's continuous survival time in hospital is modelled with respect to the graphical and probabilistic representation of the interrelationships between the patient's clinical variables. Unlike previously defined BN techniques, this extended model can accommodate continuous times that are skewed in nature. This paper presents the theory behind such an approach and extends it by attaching a cost variable to the survival times, enabling the costing and efficient management of groups of patients in hospital The model, applied to 4722 patients admitted into a geriatric ward of a U.K. hospital between 1994 and 1997, could be beneficial to hospital managers as a method for investigating the influence of future decisions and policy changes on the hospital expenditure.

Systems that are subject to uncertainty in their behaviour are often modelled by Bayesian belief networks (BBNs). These are probabilistic models of the system in which the independence relations between the variables of interest are represented explicitly. A directed graph is used, in which two nodes are connected by an edge if one is a 'direct cause' of the other. However the Bayesian paradigm does not provide any direct means for modelling dynamic systems. There has been a considerable amount of research effort in recent years to address this. We review these approaches and propose a new dynamic extension to the BBN. Our discussion then focuses on fault management of complex telecommunications and how the dynamic Bayesian models can assist in the prediction of faults.