Nour Kanso is a Postdoctoral Research Associate in the Department of Biostatistics & Health Informatics at the Institute of Psychiatry, Psychology & Neuroscience at King's College London. 

Her research focuses on applying advanced statistical methods and machine learning to large-scale electronic health records and longitudinal cohort data to better understand mental health treatment outcomes and support more personalised, equitable care.

She is particularly interested in the development and evaluation of clinical prediction models, with an emphasis on their clinical usefulness, generalisability and fairness across different population groups.

She completed her PhD at King's College London, funded by the DRIVE-Health Centre for Doctoral Training and supervised by Dr Ewan Carr and Professor Thalia Eley. Her doctoral research investigated predictors of outcomes following psychological treatment for depression and anxiety using electronic health records from NHS Talking Therapies services.

Combining statistical learning with longitudinal modelling, she examined how routinely collected information, including changes in symptoms during treatment, can be used to improve predictions of individual outcomes.

In her current postdoctoral role, Nour works on the Treatment Outcomes and Predictions Study, a Wellcome-funded project investigating individual differences in response to psychological treatment for anxiety. Her research aims to identify individuals at risk of poor treatment response early in their treatment journey, who may benefit from additional or alternative interventions.

Drawing on national NHS Talking Therapies records and longitudinal cohort datasets, she explores the added value of clinical, sociodemographic and other individual-level information, as well as the extent to which findings generalise across populations and settings.

Nour holds a BSc in Biomedical Sciences and an MRes in Cancer Informatics. Her methodological expertise includes penalised regression, longitudinal analysis, dynamic prediction modelling, model validation and the assessment of predictive performance across population subgroups. Alongside her research, she contributes to statistical teaching and supervises undergraduate and postgraduate research projects.

Research interests

• Clinical prediction modelling
• Mental health research
• Longitudinal data analysis
• NHS Talking Therapies
• Depression and anxiety
• Personalised mental healthcare
• Dynamic prediction modelling
• Model validation and calibration
• Fairness and health inequalities
• Causal inference