↓Skip to main content

Publications #

AI & ML #

  • SurvSHAP(t): Time-dependent explanations of machine learning survival models
    M. Krzyziński, M. Spytek, H. Baniecki, P. Biecek
    Knowledge-Based Systems, 2023
    paper | arXiv | code

  • survex: an R package for explaining machine learning survival models
    M. Spytek, M. Krzyziński, S. H. Langbein, H. Baniecki, M. N. Wright, P. Biecek
    Bioinformatics, 2023
    paper | arXiv | package | website

  • Performance is not enough: the story told by a Rashomon quartet
    P. Biecek, H. Baniecki, M. Krzyziński, D. Cook
    Journal of Computational and Graphical Statistics, 2024
    paper | arXiv | code

  • Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Data
    K. Kobylińska, M. Krzyziński, R. Machowicz, M. Adamek, P. Biecek
    IEEE Journal of Biomedical and Health Informatic, to appear
    arXiv

Mathematics #

  • Coloring squares of planar graphs with small maximum degree
    M. Krzyziński, P. Rzążewski, Sz. Tur
    Discussiones Mathematicae Graph Theory, in press (published online: 2022)
    paper

Applied ML & applied statistics #

  • A novel radiomics approach for predicting tace outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation
    K. Bartnik, M. Krzyziński, T. Bartczak, K. Korzeniowski, K. Lamparski, T. Wróblewski, M. Grąt, W. Hołówko, K. Mech, J. Lisowska, M. Januszewicz, P. Biecek
    Nature Scientific Reports, 2024
    paper

  • Machine learning models demonstrate that clinicopathologic variables are comparable to gene expression prognostic signature in predicting survival in uveal melanoma
    P. Donizy, M. Krzyziński, A. Markiewicz, P. Karpinski, K. Kotowski, A. Kowalik, J. Orlowska-Heitzman, B. Romanowska-Dixon, P. Biecek, M. P. Hoang
    European Journal of Cancer, 2022
    paper

  • Co-Targeting of DTYMK and PARP1 as a Potential Therapeutic Approach in Uveal Melanoma
    S. Oziębło, J. Mizera, A. Górska, M. Krzyziński, P. Karpiński, A. Markiewicz, M. M. Sąsiadek, B. Romanowska-Dixon, P. Biecek, M. P. Hoang, A. J. Mazur, P. Donizy
    Cells, 2024
    paper

  • SATB2, CKAE1/AE3, and synaptophysin as a sensitive immunohistochemical panel for the detection of lymph node metastases of Merkel cell carcinoma
    A. Szumera-Cieckiewicz, D. Massi, A. Cassisa, M. Krzyziński, M. Dudzisz-Sledz, P. Biecek, P. Rutkowski, A. Marszalek, M. P. Hoang, P. Donizy
    Virchows Archiv, 2023
    paper

  • Ki67 is a better marker than PRAME in risk stratification of BAP1-positive and BAP1-loss uveal melanomas
    P. Donizy, M. Spytek, M. Krzyziński, K. Kotowski, A. Markiewicz, B. Romanowska-Dixon, P. Biecek, M. P. Hoang
    British Journal of Ophthalmology, 2023
    paper

  • Amelanotic uveal melanomas evaluated by indirect ophthalmoscopy reveal better long-term prognosis than pigmented primary tumours — a aingle centre experience
    A. Markiewicz, P. Donizy, M. Nowak, M. Krzyziński, M. Elas, P. M. Płonka, J. Orłowska-Heitzmann, P. Biecek, M. P. Hoang, B. Romanowska-Dixon
    Cancers, 2022
    paper

Conference Papers #

  • Climate Policy Tracker: Pipeline for automated analysis of public climate policies
    A. Żółkowski, M. Krzyziński, P. Wilczyński, S. Giziński, E. Wiśnios, B. Pieliński, J. Sienkiewicz, P. Biecek
    NeurIPS 2022 Workshop: Tackling Climate Change with Machine Learning, 2022
    paper | poster

Preprints & Submitted Papers #

  • Interpretable machine learning for survival analysis
    S. H. Langbein, M. Krzyziński, M. Spytek, H. Baniecki, P. Biecek, M. N. Wright
    arXiv

  • Explaining and visualizing black-box models through counterfactual paths
    B. Pfeifer, M. Krzyziński, H. Baniecki, A. Saranti, A. Holzinger, P. Biecek
    arXiv

  • HADES: Homologous Automated Document Exploration and Summarization
    P. Wilczyński, A. Żółkowski, M. Krzyziński, E. Wiśnios, B. Pieliński, S. Giziński, J. Sienkiewicz, P. Biecek
    arXiv

Talks & Miscaleanous #

  • Explainability of machine learning models for survival analysis
    ECR DEMON workshop: Explainable AI for Neuroimaging in Dementia, online, 27/11/2023
    abstract

  • Dancing with censored data: how to survive with explainable survival analysis?
    (tutorial given with M. Spytek)
    ML in PL Conference, Warsaw, 29/10/2023
    abstract | materials

  • Explainability of machine learning models for survival analysis: current state and challenges
    CEN IBS Conference, Basel, 05/09/2023
    abstract | slides

  • Give me your policy, I’ll tell you who you are
    (with E. Wiśnios, A. Żółkowski, P. Wilczyński)
    Data Science Summit, Warsaw, 16/12/2022

  • SurvSHAP(t): Time-dependent explanations of machine learning survival models
    ML in PL Conference, Warsaw, 04/11/2022
    slides

  • Extensions of the SHAP method: using Shapley value to interpret models with dependencies and survival analysis models
    Warsaw.AI Episode 15, Warsaw, 02/06/2022
    abstract

↑