Engineering and Information Technology Collected Works - Research Publications

Permanent URI for this collection

Search Results

Now showing 1 - 10 of 526
  • Item
    No Preview Available
    Seizure occurrence is linked to multiday cycles in diverse physiological signals
    Gregg, NM ; Attia, TP ; Nasseri, M ; Joseph, B ; Karoly, P ; Cui, J ; Stirling, RE ; Viana, PF ; Richner, TJ ; Nurse, ES ; Schulze-Bonhage, A ; Cook, MJ ; Worrell, GA ; Richardson, MP ; Freestone, DR ; Brinkmann, BH (WILEY, 2023-06)
    OBJECTIVE: The factors that influence seizure timing are poorly understood, and seizure unpredictability remains a major cause of disability. Work in chronobiology has shown that cyclical physiological phenomena are ubiquitous, with daily and multiday cycles evident in immune, endocrine, metabolic, neurological, and cardiovascular function. Additionally, work with chronic brain recordings has identified that seizure risk is linked to daily and multiday cycles in brain activity. Here, we provide the first characterization of the relationships between the cyclical modulation of a diverse set of physiological signals, brain activity, and seizure timing. METHODS: In this cohort study, 14 subjects underwent chronic ambulatory monitoring with a multimodal wrist-worn sensor (recording heart rate, accelerometry, electrodermal activity, and temperature) and an implanted responsive neurostimulation system (recording interictal epileptiform abnormalities and electrographic seizures). Wavelet and filter-Hilbert spectral analyses characterized circadian and multiday cycles in brain and wearable recordings. Circular statistics assessed electrographic seizure timing and cycles in physiology. RESULTS: Ten subjects met inclusion criteria. The mean recording duration was 232 days. Seven subjects had reliable electroencephalographic seizure detections (mean = 76 seizures). Multiday cycles were present in all wearable device signals across all subjects. Seizure timing was phase locked to multiday cycles in five (temperature), four (heart rate, phasic electrodermal activity), and three (accelerometry, heart rate variability, tonic electrodermal activity) subjects. Notably, after regression of behavioral covariates from heart rate, six of seven subjects had seizure phase locking to the residual heart rate signal. SIGNIFICANCE: Seizure timing is associated with daily and multiday cycles in multiple physiological processes. Chronic multimodal wearable device recordings can situate rare paroxysmal events, like seizures, within a broader chronobiology context of the individual. Wearable devices may advance the understanding of factors that influence seizure risk and enable personalized time-varying approaches to epilepsy care.
  • Item
    No Preview Available
    Developing a deep learning natural language processing algorithm for automated reporting of adverse drug reactions
    McMaster, C ; Chan, J ; Liew, DFL ; Su, E ; Frauman, AG ; Chapman, WW ; Pires, DEV (ACADEMIC PRESS INC ELSEVIER SCIENCE, 2023-01)
    The detection of adverse drug reactions (ADRs) is critical to our understanding of the safety and risk-benefit profile of medications. With an incidence that has not changed over the last 30 years, ADRs are a significant source of patient morbidity, responsible for 5%-10% of acute care hospital admissions worldwide. Spontaneous reporting of ADRs has long been the standard method of reporting, however this approach is known to have high rates of under-reporting, a problem that limits pharmacovigilance efforts. Automated ADR reporting presents an alternative pathway to increase reporting rates, although this may be limited by over-reporting of other drug-related adverse events. We developed a deep learning natural language processing algorithm to identify ADRs in discharge summaries at a single academic hospital centre. Our model was developed in two stages: first, a pre-trained model (DeBERTa) was further pre-trained on 1.1 million unlabelled clinical documents; secondly, this model was fine-tuned to detect ADR mentions in a corpus of 861 annotated discharge summaries. This model was compared to a version without the pre-training step, and a previously published RoBERTa model pretrained on MIMIC III, which has demonstrated strong performance on other pharmacovigilance tasks. To ensure that our algorithm could differentiate ADRs from other drug-related adverse events, the annotated corpus was enriched for both validated ADR reports and confounding drug-related adverse events using. The final model demonstrated good performance with a ROC-AUC of 0.955 (95% CI 0.933 - 0.978) for the task of identifying discharge summaries containing ADR mentions, significantly outperforming the two comparator models.
  • Item
    Thumbnail Image
    Capturing prediction uncertainty in upstream cell culture models using conformal prediction and Gaussian processes
    Pham, TD ; Aickelin, U ; Bassett, R ; Papadopoulos, H ; Nguyen, KA ; Boström, H ; Carlsson, L (ML Research Press, 2023)
    This extended abstract compares the efficacy of Gaussian process and conformal XGBoost regressions in capturing prediction uncertainty in simulated and industrial cell culture data.
  • Item
    Thumbnail Image
    The Challenge of Cartilage Integration: Understanding a Major Barrier to Chondral Repair
    Trengove, A ; Di Bella, C ; O'Connor, AJ (MARY ANN LIEBERT, INC, 2022-02-01)
    Articular cartilage defects caused by injury frequently lead to osteoarthritis, a painful and costly disease. Despite widely used surgical methods to treat articular cartilage defects and a plethora of research into regenerative strategies as treatments, long-term clinical outcomes are not satisfactory. Failure to integrate repair tissue with native cartilage is a recurring issue in surgical and tissue-engineered strategies, seeing eventual degradation of the regenerated or surrounding tissue. This review delves into the current understanding of why continuous and robust integration with native cartilage is so difficult to achieve. Both the intrinsic limitations of chondrocytes to remodel injured cartilage, and the significant challenges posed by a compromised biomechanical environment are described. Recent scaffold and cell-based techniques to repair cartilage are also discussed, and limitations of existing methods to evaluate integrative repair. In particular, the importance of evaluating the mechanical integrity of the interface between native and repair tissue is highlighted as a meaningful assessment of any strategy to repair this load-bearing tissue. Impact statement The failure to integrate grafts or biomaterials with native cartilage is a major barrier to cartilage repair. An in-depth understanding of the reasons cartilage integration remains a challenge is required to inform cartilage repair strategies. In particular, this review highlights that integration of cartilage repair strategies is frequently assessed in terms of the continuity of tissue, but not the mechanical integrity. Given the load-bearing nature of cartilage, evaluating integration in terms of interfacial strength is essential to assessing the potential success of cartilage repair methods.
  • Item
    Thumbnail Image
    Diagnostic Clinical Decision Support based on Deep Learning and Knowledge-based Systems for Psoriasis: From Diagnosis to Treatment Options
    Yaseliani, M ; Ijadi Maghsoodi, A ; Hassannayebi Project, E ; Aickelin, U (Elsevier, 2023-11)
    Psoriasis is an acute immuno-dermatological disease, affecting people of all ages, which significantly decreases quality of life. While the standard approach to identification and diagnosis of psoriasis is based on dermatologist decisions, various Deep Learning (DL) methods have been utilized to create Computer-Aided Diagnosis (CAD) systems to detect and classify psoriasis cases. In response to the knowledge gap of an existing practical and functional DL-based solution to psoriasis diagnosis, this study proposed an ensemble Convolutional Neural Network (CNN) model using Residual Network 50 Version 2 (ResNet50V2), ResNet101V2, and ResNet152V2 networks to create a CAD system for detecting and classifying psoriatic images. This ensemble model determines whether an input image is psoriatic using a binary classification procedure in the initial stage and classifies the psoriatic images into seven variants utilizing a multi-class classification. Furthermore, a treatment suggestion system was embedded within the diagnostic algorithm to suggest the best treatment options for psoriasis variants using a Multi-Criteria Decision Making (MCDM) method with the aim of reducing the disease symptoms in patients. A web-based Decision and Diagnostic Support System (D&DSS) is constructed to determine whether an input image is psoriatic, classify the psoriatic images into different variants, and accordingly recommend the best treatment options based on the observed disease symptoms in a patient. Nevertheless, the functionality and reliability of the proposed D&DSS are validated with high accuracy rates in both diagnostic and identification stages of the approach, which ratifies the practicality of this proposition.
  • Item
    Thumbnail Image
    An operational planning for emergency medical services considering the application of IoT
    Valizadeh, J ; Zaki, A ; Movahed, M ; Mazaheri, S ; Talaei, H ; Tabatabaei, SM ; Khorshidi, H ; Aickelin, U (Springer, 2023)
    In the last two years, the worldwide outbreak of the COVID-19 pandemic and the resulting heavy casualties have highlighted the importance of further research in healthcare. In addition, the advent of new technologies such as the Internet of Things (IoT) and their applications in preventing and detecting casualty cases has attracted a lot of attention. The IoT is able to help organize medical services by collecting significant amounts of data and information. This paper proposes a novel mathematical model for Emergency Medical Services (EMS) using the IoT. The proposed model is designed in two phases. In the first phase, the data is collected by the IoT, and the demands for ambulances are categorized and prioritized. Then in the second phase, ambulances are allocated to demand areas (patients). Two main objectives of the proposed model are reducing total costs and the mortality risk due to lack of timely service. In addition, demand uncertainty for ambulances is considered with various scenarios at demand levels. Numerical experiments have been conducted on actual data from a case study in Kermanshah, Iran. Due to the NP-hard nature of the mathematical model, three meta-heuristic algorithms Multi-Objective Simulated Annealing (MOSA) algorithm and Multi-Objective Particle Swarm Optimization (MOPSO) algorithm, and L-MOPSO have been used to solve the proposed model on medium and large scales in addition to the exact solution method. The results show that the proposed model significantly reduces mortality risk, in addition to reducing total cost. Data analysis also led to useful managerial insights.
  • Item
    Thumbnail Image
    An Uncertainty-Accuracy-Based Score Function for Wrapper Methods in Feature Selection
    Maadi, M ; Khorshidi, HA ; Aickelin, U (IEEE, 2023-08-13)
    Feature Selection (FS) is an effective preprocessing method to deal with the curse of dimensionality in machine learning. Redundant features in datasets decrease the classification performance and increase the computational complexity. Wrapper methods are an important category of FS methods that evaluate various feature subsets and select the best one using performance measures related to a classifier. In these methods, the accuracy of classifiers is the most common performance measure for FS. Although the performance of classifiers depends on their uncertainty, this important criterion is neglected in these methods. In this paper, we present a new performance measure called Uncertainty-Accuracy-based Performance Measure for Feature Selection (UAPMFS) that uses an ensemble approach to measure both the accuracy and uncertainty of classifiers. UAPMFS uses bagging and uncertainty confusion matrix. This performance measure can be used in all wrapper methods to improve FS performance. We design two experiments to evaluate the performance of UAPMFS in wrapper methods. In experiments, we use the leave-one-variable-out strategy as the common strategy in wrapper methods to evaluate features. We also define a feature score function based on UAPMFS to rank and select features. In the first experiment, we investigate the importance of considering uncertainty in the FS process and show how neglecting uncertainty affects FS performance. In the second experiment, we compare the performance of the UAPMFS-based feature score function with the most common feature score functions for FS. Experimental results show the effectiveness of the proposed performance measure on different datasets.
  • Item
    No Preview Available
    A decision modeling approach for smart e-tourism data management applications based on spherical fuzzy rough environment (vol 143, 110297, 2023)
    Mohammed, RT ; Alamoodi, AH ; Albahri, OS ; Zaidan, AA ; Alsattar, HA ; Aickelin, U ; Albahri, AS ; Zaidan, BB ; Ismail, AR ; Malik, RQ (ELSEVIER, 2023-12)
    The authors regret the inadvertent omission of second affiliation of author A.S. Albahri. Affiliation is presented as below: Department of Computer Technology Engineering, College of Information Technology, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq. The authors would like to apologise for any inconvenience caused.
  • Item
    No Preview Available
    Effectiveness of Opioid Switching in Advanced Cancer Pain: A Prospective Observational Cohort Study
    Wong, AKK ; Somogyi, AA ; Rubio, J ; Pham, TD ; Le, B ; Klepstad, P ; Philip, J (MDPI, 2023-07)
    Opioid switching is a common practice of substituting one opioid for another to improve analgesia or adverse effects; however, it has limited evidence. This study aimed to examine the effectiveness of opioid switching in advanced cancer. This multi-center prospective cohort study recruited patients assessed to switch opioids (opioid switch group) or to continue ongoing opioid treatment (control group). Clinical data (demographics, opioids) and validated instruments (pain and adverse effects) were collected over two timepoints seven days apart. Descriptive analyses were utilized. Non-parametric tests were used to determine differences. Fifty-four participants were recruited (23 control group, 31 switch group). At the follow-up, opioid switching reduced pain (worst, average, and now) (p < 0.05), uncontrolled breakthrough pain (3-fold reduction, p = 0.008), and psychological distress (48% to 16%, p < 0.005). The switch group had a ≥25% reduction in the reported frequency of seven moderate-to-severe adverse effects (score ≥ 4), compared to a reduction in only one adverse effect in the control group. The control group experienced no significant pain differences at the follow-up. Opioid switching is effective at reducing pain, adverse effects, and psychological distress in a population with advanced cancer pain, to levels of satisfactory symptom control in most patients within 1 week.
  • Item
    No Preview Available
    Catalytic degradation of benzene at room temperature over FeN4O2 sites embedded in porous carbon
    Ding, H ; Xue, L ; Cui, J ; Wang, Y ; Zhao, D ; Zhi, X ; Liu, R ; Fu, J ; Liu, S ; Fu, B ; Shi, J ; Xu, X ; Li, GK (ELSEVIER, 2023-10-15)
    Benzene and its aromatic derivatives are typical volatile organic compounds for indoor and outdoor air pollution, harmful to human health and the environment. It has been considered extremely difficult to break down benzene rings at ambient conditions without external energy input, due to the extraordinary stability of the aromatic structure. Here, we show one such solution that can thoroughly degrade benzene to basically water and carbon dioxide at 25 °C in air using atomically dispersed Fe in N-doped porous carbon, with almost 100% benzene conversion. Further experimental studies combined with molecular simulations reveal the mechanism of this catalytic reaction. Hydroxyl radicals (·OH) evolved on the atomically dispersed FeN4O2 catalytic centers were found responsible for initiating and completing the oxidation of benzene. This work provides a new chemistry to degrade aromatics at ambient conditions and also a pathway to generate active ·OH oxidant for generic remediation of organic pollutants.