Avatar

Sebastian Pölsterl

Post-Doctoral Researcher

Artificial Intelligence in Medical Imaging

About Me

I’m a researcher at the lab for Artificial Intelligence in Medical Imaging working on machine learning for biomedical applications. My research interests are time-to-event analysis (survival analysis) and using deep learning techniques to learn from non-Euclidean data such as graphs. Previously, I worked at The Institute of Cancer Research, London and was among the winners of the Prostate Cancer DREAM challenge. I’m the author of scikit-survival, a machine learning library for survival analysis built on top of scikit-learn.

Interests

  • Time-to-event analysis
  • Non-Euclidean data
  • High-dimensional data
  • Biomedical applications
  • Deep learning

Education

  • PhD in Computer Science, 2016

    Technische Universität München

  • MSc in Bioinformatics, 2011

    Ludwig-Maximilians-Universität & Technische Universität München

  • BSc in Bioinformatics, 2008

    Ludwig-Maximilians-Universität & Technische Universität München

Recent Posts

scikit-survival 0.17.2 released

I’m pleased to announce the release of scikit-survival 0.17.2. This release fixes several small issues with packaging scikit-survival and the documentation. For a full list of changes in scikit-survival 0.17.2, please see the release notes.

Most notably, binary wheels are now available for Linux, Windows, and macOS (Intel). This has been possible thanks to the cibuildwheel build tool, which makes it incredible easy to use GitHub Actions for building those wheels for multiple versions of Python. Therefore, you can now use pip without building everything from source by simply running

pip install scikit-survival

As before, pre-built conda packages are available too, by running

 conda install -c sebp scikit-survival

scikit-survival 0.17 released

This release adds support for scikit-learn 1.0, which includes support for feature names. If you pass a pandas dataframe to fit, the estimator will set a feature_names_in_ attribute containing the feature names. When a dataframe is passed to predict, it is checked that the column names are consistent with those passed to fit. The example below illustrates this feature.

For a full list of changes in scikit-survival 0.17.0, please see the release notes.

scikit-survival 0.16 released

I am proud to announce the release if version 0.16.0 of scikit-survival, The biggest improvement in this release is that you can now change the evaluation metric that is used in estimators’ score method. This is particular useful for hyper-parameter optimization using scikit-learn’s GridSearchCV. You can now use as_concordance_index_ipcw_scorer, as_cumulative_dynamic_auc_scorer, or as_integrated_brier_score_scorer to adjust the score method to your needs. The example below illustrates how to use these in practice.

For a full list of changes in scikit-survival 0.16.0, please see the release notes.

scikit-survival 0.15 Released

I am proud to announce the release if version 0.15.0 of scikit-survival, which brings support for scikit-learn 0.24 and Python 3.9. Moreover, if you fit a gradient boosting model with loss='coxph', you can now predict the survival and cumulative hazard function using the predict_cumulative_hazard_function and predict_survival_function methods.

The other enhancement is that cumulative_dynamic_auc now supports evaluating time-dependent predictions. For instance, you can now evaluate the predicted time-dependent risk of a RandomSurvivalForest rather than just evaluating the predicted total number of events per instance, which is what RandomSurvivalForest.predict returns.

scikit-survival 0.14 with Improved Documentation Released

Today marks the release of version 0.14.0 of scikit-survival. The biggest change in this release is actually not in the code, but in the documentation. This release features a complete overhaul of the documentation. Most importantly, the documentation has a more modern feel to it, thanks to the visually pleasing pydata Sphinx theme, which also powers pandas.

Moreover, the documentation now contains a User Guide section that bundles several topics surrounding the use of scikit-survival. Some of these were available as separate Jupyter notebooks previously, such as the guide on Evaluating Survival Models. There are two new guides: The first one is on penalized Cox models. It provides a hands-on introduction to Cox’s proportional hazards model with $\ell_2$ (Ridge) and $\ell_1$ (LASSO) penalty. The second guide, is on Gradient Boosted Models and covers how gradient boosting can be used to obtain a non-linear proportional hazards model or a non-linear accelerated failure time model by using regression tree base learners. The second part of this guide covers a variant of gradient boosting that is most suitable for high-dimensional data and is based on component-wise least squares base learners.

To make it easier to get started, all notebooks can now be run in a Jupyter notebook, right from your browser, just by clicking on

Projects

scikit-survival: machine learning for time-to-event analysis

scikit-survival is a Python module for survival analysis built on top of scikit-learn. It allows doing survival analysis while …