TPThomas Pichl

Thomas Pichl

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Thomas Pichl has a total of 17 co-authors. Here are the top co-authors by number of shared publications:

  • Karsten Borgwardt

    Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany

    2 shared publications
  • Lucas Miranda

    Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany

    2 shared publications
  • Bernhard Roth

    Department of Pediatrics and Adolescent Medicine, University of Cologne, Faculty of Medicine and University Hospital, D-50931 Cologne, Germany

    1 shared publication
  • Catherine J. Wedderburn

    Neuroscience Institute, University of Cape Town, Cape Town, South Africa

    1 shared publication
  • Chandrashekar Hoskote

    Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, Queen Square, London, UK

    1 shared publication
  • Christoph Hünseler

    Department of Pediatrics and Adolescent Medicine, University of Cologne, Faculty of Medicine and University Hospital, D-50931 Cologne, Germany

    1 shared publication

Latest Publications

  • Open Access

    Early detection of ampicillin susceptibility in Enterococcus faecium with MALDI-TOF/MS and machine learning

    by Thomas Pichl, Lucas Miranda, Matthias T. Warkotsch, Nina Wantia, Karsten Borgwardt, Janko Sattler


  • Open Access

    Early detection of ampicillin susceptibility in Enterococcus faecium with MALDI-TOF MS and machine learning

    by Thomas Pichl, Lucas Miranda, Nina Wantia, Karsten Borgwardt, Janko Sattler

    Background: Enterococcus faecium can cause severe infections and is often resistant to the first-line antibiotic ampicillin. Consequently, clinicians usually prescribe broad-spectrum antibiotics, promoting the selection of multidrug-resistant bacteria. In this study, we investigate the application of machine learning techniques to detect ampicillin susceptibility directly from MALDI-TOF mass spectrometry. This technique could enable an earlier optimised treatment in infections with ampicillin-susceptible E. faecium . Methods: Two datasets of clinical E. faecium MALDI-TOF spectra and their resistance phenotype were analysed: our own Technical University of Munich (TUM) dataset and the publicly available MS-UMG dataset. We tested logistic regression (LR) and LightGBM models on each dataset via nested cross-validation and explored transferability on the respective other dataset. Results: LightGBM demonstrated slightly better performance than LR in identifying susceptible isolates in the TUM dataset (area under the precision-recall curve (AUPRC) 0.907 ± 0.016 vs 0.902 ± 0.030) as well as in the MS-UMG dataset (AUPRC 0.902 ± 0.029 vs 0.899 ± 0.054). External validation demonstrated good model transferability (AUPRC of 0.784 ± 0.039 when trained on MS-UMG; 0.804 ± 0.013 when trained on TUM). SHAP analysis consistently identified a top-ranked spectral feature corresponding to a peak at an m/z of 5091 in resistant isolate spectra. Conclusion: This study demonstrates that LR and LightGBM models can identify ampicillin-susceptible E. faecium isolates from MALDI-TOF spectra and generalise well to unseen datasets. While clinical implementation currently still requires confirmatory testing, the addition of larger datasets in the future will support the development of more robust machine learning models.


  • Open Access

    A systematic review of brain imaging findings in neurological infection with Japanese encephalitis virus compared with Dengue virus

    by Thomas Pichl, Catherine J Wedderburn, Chandrashekar Hoskote, Lance Turtle, Tehmina Bharucha


  • Open Access

    Effects of ketamine on neurogenesis, extracellular matrix homeostasis and proliferation in hypoxia‑exposed HT22 murine hippocampal neurons

    by Thomas Pichl, Titus Keller, Christoph Hünseler, Bernhard Roth, Ruth Janoschek, Sarah Appel, Eva Hucklenbruch‑Rother

    Ketamine is a widely used drug in pediatric anesthesia, and both neurotoxic and neuroprotective effects have been associated with its use. There are only a few studies to date which have examined the effects of ketamine on neurons under hypoxic conditions, which may lead to severe brain damage and poor neurocognitive outcomes in neonates. In the present study, the effects of ketamine on cellular pathways associated with neurogenesis, extracellular matrix homeostasis and proliferation were examined in vitro in hypoxia‑exposed neurons. Differentiated HT22 murine hippocampal neurons were treated with 1, 10 and 20 µM ketamine and cultured under hypoxic or normoxic conditions for 24 h followed by quantitative PCR analysis of relevant candidate genes. Ketamine treatment did not exert any notable effects on the mRNA expression levels of markers of neurogenesis (neuronal growth factor and syndecan 1), extracellular matrix homeostasis (matrix‑metalloproteinase 2 and 9, tenascin C and tenascin R) or proliferation markers (Ki67 and proliferating cell nuclear antigen) compared with the respective untreated controls. However, there was a tendency towards downregulation of multiple cellular markers under hypoxic conditions and simultaneous ketamine treatment. No dose‑dependent association was found in the ketamine treated groups for genetic markers of neurogenesis, extracellular matrix homeostasis or proliferation. Based on the results, ketamine may have increased the vulnerability of hippocampal neurons in vitro to hypoxia, independent of the dose. The results of the present study contribute to the ongoing discussion on the safety concerns around ketamine use in pediatric clinical practice from a laboratory perspective.