Bradford Scholars
Bradford Scholars is the University of Bradford online research archive. Access is free to anyone interested in research being conducted at Bradford. In the repository you will find a range of materials from journal articles and conference papers to research reports and theses.
Contact the repository team via openaccess@bradford.ac.uk with any queries about Open Access or how to deposit your research papers.
Communities in Bradford Scholars
Select a community to browse its collections.
Recent Submissions
Publication Conversational assessment using artificial intelligence is as clinically useful as depression scales and preferred by users(2024-04-15)Background: Depression is prevalent, chronic, and burdensome. Due to limited screening access, depression often remains undiagnosed. Artificial intelligence (AI) models based on spoken responses to interview questions may offer an effective, efficient alternative to other screening methods. Objective: The primary aim was to use a demographically diverse sample to validate an AI model, previously trained on human-administered interviews, on novel bot-administered interviews, and to check for algorithmic biases related to age, sex, race, and ethnicity. Methods: Using the Aiberry app, adults recruited via social media (N = 393) completed a brief bot-administered interview and a depression self-report form. An AI model was used to predict form scores based on interview responses alone. For all meaningful discrepancies between model inference and form score, clinicians performed a masked review to determine which one they preferred. Results: There was strong concurrent validity between the model predictions and raw self-report scores (r = 0.73, MAE = 3.3). 90 % of AI predictions either agreed with self-report or with clinical expert opinion when AI contradicted self-report. There was no differential model performance across age, sex, race, or ethnicity. Limitations: Limitations include access restrictions (English-speaking ability and access to smartphone or computer with broadband internet) and potential self-selection of participants more favorably predisposed toward AI technology. Conclusion: The Aiberry model made accurate predictions of depression severity based on remotely collected spoken responses to a bot-administered interview. This study shows promising results for the use of AI as a mental health screening tool on par with self-report measures.Publication Artemisinin-acetylenedicarboxylic acid cocrystal: Screening, structure determination, and physicochemical property characterisation(2022)Artemisinin is used to treat multi-drug resistant strains of malaria and is also in the early stages of development as an anti-cancer drug. However, the usage of artemisinin is limited due to its low aqueous solubility. Herein a large scale cocrystal screening of artemisinin was conducted using both computational and experimental approaches, leading to a new 2 : 1 artemisinin and acetylenedicarboxylic acid (ART2-ACA) cocrystal. ART2-ACA crystallises in the P212121 space group of the orthorhombic system with cell parameters a = 10.5089 Å, b = 24.083 Å, and c = 6.4952 Å. The asymmetric unit of the cocrystal contains two ART molecules and a single ACA molecule, assembled into discrete trimeric units held together by two supramolecular heterosynthons. It was shown that ART2-ACA cocrystals have higher solubility and a faster dissolution rate compared to the parent drug artemisinin. This journal isPublication Ultra-quantum coherent states in a single finite quantum system(2023-10)A set of n coherent states is introduced in a quantum system with d-dimensional Hilbert space H(d). It is shown that they resolve the identity, and also have a discrete isotropy property. A finite cyclic group acts on the set of these coherent states, and partitions it into orbits. A n-tuple representation of arbitrary states in H(d), analogous to the Bargmann representation, is defined. There are two other important properties of these coherent states which make them ‘ultra-quantum’. The first property is related to the Grothendieck formalism which studies the ‘edge’ of the Hilbert space and quantum formalisms. Roughly speaking the Grothendieck theorem considers a ‘classical’ quadratic form C that uses complex numbers in the unit disc, and a ‘quantum’ quadratic form Q that uses vectors in the unit ball of the Hilbert space. It shows that if C ≤ 1, the corresponding Q might take values greater than 1, up to the complex rothendieck constant kG. Q related to these coherent states is shown to take values in the ‘Grothendieck region’ (1, kG), which is classically forbidden in the sense that C does not take values in it. The second property complements this, showing that these coherent states violate logical Bell-like inequalities (which for a single quantum system are quantum versions of the Frechet probabilistic inequalities). In this sense also, our coherent states are deep into the quantum region.Publication A novel integrative multimodal classifier to enhance the diagnosis of Parkinson's disease(2025-03)Parkinson’s disease (PD) is a complex, progressive neurodegenerative disorder with high heterogeneity, making early diagnosis difficult. Early detection and intervention are crucial for slowing PD progression. Understanding PD’s diverse pathways and mechanisms is key to advancing knowledge. Recent advances in noninvasive imaging and multi-omics technologies have provided valuable insights into PD’s underlying causes and biological processes. However, integrating these diverse data sources remains challenging, especially when deriving meaningful low-level features that can serve as diagnostic indicators. This study developed and validated a novel integrative, multimodal predictive model for detecting PD based on features derived from multimodal data, including hematological information, proteomics, RNA sequencing, metabolomics, and dopamine transporter scan imaging, sourced from the Parkinson’s Progression Markers Initiative. Several model architectures were investigated and evaluated, including support vector machine, eXtreme Gradient Boosting, fully connected neural networks with concatenation and joint modeling (FCNN_C and FCNN_JM), and a multimodal encoder-based model with multi-head cross-attention (MMT_CA). The MMT_CA model demonstrated superior predictive performance, achieving a balanced classification accuracy of 97.7%, thus highlighting its ability to capture and leverage cross-modality inter-dependencies to aid predictive analytics. Furthermore, feature importance analysis using SHapley Additive exPlanations not only identified crucial diagnostic biomarkers to inform the predictive models in this study but also holds potential for future research aimed at integrated functional analyses of PD from a multi-omics perspective, ultimately revealing targets required for precision medicine approaches to aid treatment of PD aimed at slowing down its progression.Publication School vision screening programmes: the benefits of including measurements of refractive error.Following a comprehensive review of vision screening in 1997, various research studies have since been conducted and extensive literature is now available on the detection of amblyopia in vision screening programmes. However, little attention has been paid to the role of detecting refractive error namely hyperopia thus far. The purpose of this thesis was to determine the benefits of including a refractive error assessment at vision screening. The value of including a refraction was investigated by retrospectively analysing those children who had passed screening but were later found to have a significant refractive error. To ascertain which method of refraction would be most appropriate, non-cycloplegic and cycloplegic retinoscopy readings were used to compare the level of agreement of the Welch Allyn Sure Sight (WASS) autorefractor. The accuracy of using visual acuity assessment alone for the detection of amblyopia was also assessed. Overall, it was found that a refractive error assessment does have a role in vision screening. Double the number of children were detected as having a significant refractive error compared to screening without a refractive error assessment. These studies demonstrate that the WASS, which is a portable and easy to use device, has reasonable accuracy within a range of refractive errors. The sensitivity and specificity of the vision screening programme when refractive error assessment was included was very good. It was found that visual acuity assessment for detection for amblyopia was fair, however it could be improved if a refractive error assessment was included at screening.