My research interests are in the application of machine learning, signal/image processing and computational models for the implementation of systems to improve clinical practice and healthcare service delivery. The following are examples of the research I have conducted and supervised:

Clinical Decision Support Systems

• Brain Tumour Diagnosis using Magnetic Resonance Spectroscopy (current)
• Diagnosis and Treatment in Breast Cancer Multidisciplinary Meetings

Machine Learning in Healthcare & Biomedicine

• GSK-UCL Collaboration: Machine Learning and Computational Models of Disease Trajectories from Electronic Health Record Data for Drug Discovery (J. P. Casas, C. Dale, D. Acosta (PI), £512K, ongoing).
• Predicting Cardiovascular Outcomes using Proteomic Data in the British Women’s Health and Heart Study using Machine Learning Methods (J. P. Casas (PI), D. Acosta, ongoing).
• Supervised Classification of Parkinson Disease Pharmacotherapy Management Scenarios Using Wearables Data (V. Nguyen, MSc Project, 2017).
• Predicting Early Pregnancy Outcomes using Urine MALDI-ToF Mass Spectrometry (R. Zmuidinaite, MSc Project, 2017).
• Automatic Classification of 1H MR Spectroscopy of Brain Masses Using Machine Learning Methods (W. Shi, MSc Project, 2017).
• Automatic Verification of Computerised Clinical Pathways (S. Satwilkar, MSc Project, 2016).
• Prediction of Hospital Admission using A&E Attendance Data: A Comparison of Classical and Machine Learning Methods on 388,910 attendances. (R. Shackleton, MSc Project, 2016).
• Predicting Number of Emergency Hospital Admissions using Time Series Models (I. Odera, MSc Project, 2014).
• Predicting Pulmonary Embolism in Post-Operative Orthopaedic Patients (P. Kesara, MSc Project, 2014).
• Matching A&E Supply To Demand using Computational Scheduling Algorithms (R. Wortham, MSc Project,2014).
  

Data-Driven Clinical Trials

• EHR4CR Project Electronic Health Records for Clinical Research (D. Kalra (PI), D. Acosta (co-I) UCL, Euros 16MM, 2016, InSite Platform)
  
• Automatically identifying patients for clinical trials in the Cardiovascular Foundation of Colombia (FCV, Bucaramanga). (J.P. Casas (PI), N. Romero, D. Acosta, ongoing)
• Clinical Trial Recruitment using OpenEyes Electronic Patient Record (MSc Project M. Clemo)

PhD Students

• Cancer Early Diagnosis using Disease Trajectories Machine Learning Models from Electronic Health Record Data of the National Guard Health Affairs, Saudi Arabia (A. AlFayez., ongoing).
• Re-use of EHR Data to Support Clinical Trials Design and Execution (J. W Choi, ongoing)
• Integration of Electronic health Records with Genomic data for Drug discovery (K. Khan, ongoing)
  
• Diagnostic and Treatment Action Selection in Chest Pain Rapid Access Clinics (K. Zacharias, ongoing)
• Quality framework for semantic interoperability in health informatics: definition and implementation (A. Moreno-Conde, PhD, 2016).