A5015095497- Machine Learning in Healthcare
- Radiomics and Machine Learning in Medical Imaging
- Explainable Artificial Intelligence (XAI)
- Artificial Intelligence in Healthcare and Education
- Artificial Intelligence in Healthcare
- Anomaly Detection Techniques and Applications
- Emergency and Acute Care Studies
- Privacy, Security, and Data Protection
- Pancreatic and Hepatic Oncology Research
- Ethics in Clinical Research
- Sepsis Diagnosis and Treatment
- Adversarial Robustness in Machine Learning
- Chronic Disease Management Strategies
- Privacy-Preserving Technologies in Data
- Infrastructure Maintenance and Monitoring
- Vehicle License Plate Recognition
- COVID-19 diagnosis using AI
- Inflammatory Biomarkers in Disease Prognosis
- Handwritten Text Recognition Techniques
- Cancer Treatment and Pharmacology
- Patient Safety and Medication Errors
- IoT and GPS-based Vehicle Safety Systems
- Retinal Imaging and Analysis
- 3D Shape Modeling and Analysis
- Generative Adversarial Networks and Image Synthesis
Durham University
2021-2025
University College London Hospitals NHS Foundation Trust
2024
University College London
2024
Commonwealth Scientific and Industrial Research Organisation
2021
Health Sciences and Nutrition
2021
Renaissance Computing Institute
2021
Stanford University
2012
Northwick Park Hospital
1974
We present a novel Markov chain Monte Carlo (MCMC) algorithm that generates samples from transdimensional distributions encoding complex constraints. use factor graphs, type of graphical model, to encode constraints as factors. Our proposed MCMC method, called locally annealed reversible jump MCMC, exploits knowledge how dimension changes affect the structure graph. employ sequence during sampling process, allowing us explore state space across different dimensionalities more freely. This...
Deep Learning of neural networks has progressively become more prominent in healthcare with models reaching, or even surpassing, expert accuracy levels. However, these success stories are tainted by concerning reports on the lack model transparency and bias against some medical conditions patients' sub-groups. Explainable methods considered gateway to alleviate many concerns. In this study we demonstrate that generated explanations volatile changes training perpendicular classification task...
Explainable machine learning has become increasingly prevalent, especially in healthcare where explainable models are vital for ethical and trusted automated decision making. Work on the susceptibility of deep to adversarial attacks shown ease designing samples mislead a model into making incorrect predictions. In this work, we propose agnostic explainability-based method accurate detection two datasets with different complexity properties: Electronic Health Record (EHR) chest X-ray (CXR)...
Background Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic records data identifying ultimately provide better outcomes. Objective Our study investigated performance to forecast HbA1c levels by employing several machine learning models. We also examined use patient record longitudinal in...
In those receiving chemotherapy, renal and hepatic dysfunction can increase the risk of toxicity should therefore be monitored. We aimed to develop a machine learning model identify patients that need closer monitoring, enabling safer more efficient service.We used retrospective data from large academic hospital, for treated with chemotherapy breast cancer, colorectal cancer diffuse-large B-cell lymphoma, train validate Multi-Layer Perceptrons (MLP) predict outcomes unacceptable rises in...
Healthcare is seen as one of the most influential applications Deep Learning (DL). Increasingly, DL models have been shown to achieve high-levels performance on medical diagnosis tasks, in some cases achieving levels on-par with experts. Yet, very few are deployed into real-life scenarios. One main reasons for this lack trust those by professionals driven black-box nature models. Numerous explainability techniques developed alleviate issue providing a view how model reached given decision....
It has been shown that identical deep learning (DL) architectures will produce distinct explanations when trained with different hyperparameters are orthogonal to the task (e.g. random seed, training set order). In domains such as healthcare and finance, where transparency explainability is paramount, this can be a significant barrier DL adoption. study we present further analysis of explanation (in)consistency on 6 tabular datasets/tasks, focus Electronic Health Records data. We propose...
Objectives Routine monitoring of renal and hepatic function during chemotherapy ensures that treatment-related organ damage has not occurred clearance subsequent treatment is hindered; however, frequency timing are optimal. Model bias data heterogeneity concerns have hampered the ability machine learning (ML) to be deployed into clinical practice. This study aims develop models could support individualised decisions on while exploring effect shift model performance. Methods analysis We used...
Objectives Increasing operational pressures on emergency departments (ED) make it imperative to quickly and accurately identify patients requiring urgent clinical intervention. The widespread adoption of electronic health records (EHR) makes rich feature patient data sets more readily available. These large stores lend themselves use in modern machine learning (ML) models. This paper investigates the transformer-based models critical deterioration unplanned ED admissions, using free-text...
Roadway safety, especially in rural areas, is one of the most critical components transportation planning. In collaboration with North Carolina Department Transportation (NCDOT), UNC Highway Safety Research Center (HSRC), and DOT Volpe National Systems Center, Renaissance Computing Institute (RENCI) developed a roadside feature detection solution leveraging multiple convolutional neural networks. The used an iterative active learning (AL) computer vision model training pipeline integrated...
<sec> <title>BACKGROUND</title> Data science offers an unparalleled opportunity to identify new insights into many aspects of human life with recent advances in health care. Using data digital raises significant challenges regarding privacy, transparency, and trustworthiness. Recent regulations enforce the need for a clear legal basis collecting, processing, sharing data, example, European Union’s General Protection Regulation (2016) United Kingdom’s Act (2018). For care providers, use...
<sec> <title>BACKGROUND</title> Predicting the risk of glycated hemoglobin (HbA<sub>1c</sub>) elevation can help identify patients with potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic records data identifying ultimately provide better outcomes. </sec> <title>OBJECTIVE</title> Our study investigated performance to forecast HbA<sub>1c</sub> levels by...