As a medical statistician, I focus on risk prediction modelling. In healthcare, improving lives and properly administrating available resources are of maximum importance. Risk prediction tools can help clinicians to identify patients that would benefit most from particular interventions. These tools can be used to quantify the likelihood of
- a patient developing a disease, e.g. diabetes (risk modelling)
- the patient having the disease (diagnostic modelling), or,
- the patient’s outcomes (e.g. survival rate, disease progression) once the disease is diagnosed (prognostic modelling).
Many studies focus on these issues but few of them follow rigorous methodological development and validation processes that would allow the models to be used in practice. I disseminate good practice and create examples of well-developed and well-validated models.
Before joining the Nuffield Department of Primary Care Health Sciences in 2008, I completed a PhD in Statistics at the University of Warwick (UK), a MSc in Statistics at Centro de Investigación en Matemáticas/Universidad de Guanajuato (Mexico), and a BSc in Mathematics at the Universidad de Yucatan (Mexico).
I had a secondment at the Centre for Statistics in Medicine between 2013 and 2015 as an NIHR Oxford Biomedical Research Centre (BRC) Research Fellow, and then between 2017 and 2019, as a collaborator on the Prognostic Biomarkers in Heart Failure project, funded by the British Heart Foundation.
I have provided statistical expertise in medical studies in mental health, online learning, ophthalmology, chronic diseases (diabetes, kidney disease, cancer), and hearth failure, using a variety of statistical methods (eg statistical control process, latent class analysis, multilevel modelling, propensity score methods, survival analysis). I am an ongoing collaborator of a systematic review of prognostic biomarker models for heart failure.
My teaching includes coordinating the online module Introduction to Statistics for Health Care Research on the Oxford Postgraduate Programme in Evidence-Based Health Care, tutoring for the Human Sciences Prelims module Introduction to Probability Theory and Statistics, and several modules in the MSc in Evidence Based Health Care and EBHC Medical Statistics.
I am using big data (Clinical Practice Research Datalink (CPRD) and Infections in Oxfordshire Research Database (IORD)) to help improving the diagnosis and management of recurrent urinary tract infection in women 16 and older, a condition which affects a large number of women impacting their lives, from experiencing severe symptoms to relationship difficulties and systemic illness.
I am also collaborating in the development and validation of tools for the risk assessment of repeat self-harm and suicide in Sweden. Further assessment of the validity and accuracy of these tools in different settings and populations will be required.
- Kreuzberger N. et al, (2020), Prognostic models for newly-diagnosed chronic lymphocytic leukaemia in adults: a systematic review and meta-analysis. Cochrane Database of Systematic Reviews, 2020
- Fanshawe TR. and Vazquez-Montes M., (2020), How to reduce diagnostic error: ‘neutral zone’ approach, BMJ Evidence-Based Medicine
- Hirst JA. et al, (2020), Prevalence of chronic kidney disease in the community using data from OxRen: A UK population-based cohort study, British Journal of General Practice, 70, E285 – E293
- Vazquez-Montes MDLA. et al, (2020), UMBRELLA protocol: systematic reviews of multivariable biomarker prognostic models developed to predict clinical outcomes in patients with heart failure. Diagn Progn Res, 4
- Fazel S. et al, (2019), Prediction of violent reoffending in prisoners and individuals on probation: a Dutch validation study (OxRec), Scientific Reports, 9
- Vazquez-Montes MDLA. et al, (2018), Control charts for monitoring mood stability as a predictor of severe episodes in patients with bipolar disorder, International Journal of Bipolar Disorders, 6