![Ann-Kathrin Schalkamp](https://profiles-cardiff.imgix.net/attachments/439?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Overview
My research interest lies in the intersection of machine learning, medicine, and neuroscience. My goal is to contribute to the advancement of personalised medicine through research in computational neuroscience/medicine.
I focus on neurodegenerative disorders, especially Parkinson's Disease, and try to understand the heterogeneity observed within them. Deeply phenotyped cohorts allow me to investigate a whole person on multiple scale levels (genetics, omics, imaging, clinical data, environment). I make use of Machine Learning, Bayesian Modelling, and occasionally Deep Learning to handle complex, high dimensional data.
Publication
2023
- MacIver, C. et al. 2023. Macro- and micro-structural Insights into primary dystonia A UK Biobank study. Journal of Neurology (10.1007/s00415-023-12086-2)
- Schalkamp, A. 2023. Addressing Parkinson’s Disease risk analysis, early diagnosis, progression, and stratification using data-driven approaches in deeply phenotyped cohorts. PhD Thesis, Cardiff University.
- Schalkamp, A., Peall, K. J., Harrison, N. A. and Sandor, C. 2023. Wearable movement-tracking data identify Parkinson's disease years before clinical diagnosis. Nature Medicine 29, pp. 2048-2056. (10.1038/s41591-023-02440-2)
- Stevenson-Hoare, J., Schalkamp, A., Sandor, C., Hardy, J. and Escott-Price, V. 2023. New cases of dementia are rising in elderly populations in Wales, UK. Journal of the Neurological Sciences 451, article number: 120715. (10.1016/j.jns.2023.120715)
2022
- Sandor, C. et al. 2022. Universal clinical Parkinson’s disease axes identify a major influence of neuroinflammation. Genome Medicine 14, article number: 129. (10.1186/s13073-022-01132-9)
- Schalkamp, A., Rahman, N., Monzón-Sandoval, J. and Sandor, C. 2022. Deep phenotyping for precision medicine in Parkinson's disease. Disease Models and Mechanisms 15(6), article number: dmm049376. (10.1242/dmm.049376)
Articles
- MacIver, C. et al. 2023. Macro- and micro-structural Insights into primary dystonia A UK Biobank study. Journal of Neurology (10.1007/s00415-023-12086-2)
- Schalkamp, A., Peall, K. J., Harrison, N. A. and Sandor, C. 2023. Wearable movement-tracking data identify Parkinson's disease years before clinical diagnosis. Nature Medicine 29, pp. 2048-2056. (10.1038/s41591-023-02440-2)
- Stevenson-Hoare, J., Schalkamp, A., Sandor, C., Hardy, J. and Escott-Price, V. 2023. New cases of dementia are rising in elderly populations in Wales, UK. Journal of the Neurological Sciences 451, article number: 120715. (10.1016/j.jns.2023.120715)
- Sandor, C. et al. 2022. Universal clinical Parkinson’s disease axes identify a major influence of neuroinflammation. Genome Medicine 14, article number: 129. (10.1186/s13073-022-01132-9)
- Schalkamp, A., Rahman, N., Monzón-Sandoval, J. and Sandor, C. 2022. Deep phenotyping for precision medicine in Parkinson's disease. Disease Models and Mechanisms 15(6), article number: dmm049376. (10.1242/dmm.049376)
Thesis
- Schalkamp, A. 2023. Addressing Parkinson’s Disease risk analysis, early diagnosis, progression, and stratification using data-driven approaches in deeply phenotyped cohorts. PhD Thesis, Cardiff University.
Research
I am interested in developing methods and applying Machine Learning for the advancement of healthcare towards personalised medicine.
Currently, diagnosis and treatment selection, especially in psychiatry, rely on self-report and subjective decisions made by physicians. Augmenting their decision process by means of machine learning could largely fasten and objectify this process. Visualizing medical data in a human comprehensible way or providing diagnoses and related uncertainties are possible augmentations. An automatic, data-driven assessment of a patient’s health status can considerably alleviate the workload of physicians, enable early disease detection, and extract meaningful insights from the abundance of the medical data available.
I have a background in Cognitive Science with a focus on Machine Learning. Over the course of my education I had the opportunity to work with a wide range of data modalities: brain imaging, electroencephalography, genetics, biospecimen, and clinical data. During my PhD I get to work with datasets that provide all these data modalities and learn about a new resource, omics. I work with UK Biobank, PPMI, OPDC, and ADNI. I do most of my analyses in python but also have experience with bash, R, Matlab, and toolboxes like plink and SPM.
In general, I am an advocator for open science and reproducibility and try follow these principles in my own research.