Tobias Hepp, Dr. rer. biol. hum.

Research Interests

• Statistical learning:
  • Model-based gradient boosting
  • Interpretable neural networks
• (Robust) distributional regression
• Modelling latent structures (e.g. mixtures of regression models)
• Advanced biostatistical applications

Publications

• Seifert, Q.E., Thielmann, A., Bergherr, E., Säfken, B., Zierk, J., Rauh, M. and Hepp, T. (PREPRINT): Penalized regression splines in mixture density networks.
• Plechschmidt, J., Fietkau, K., Hepp, T., Dietrich, P., Fischer, S., Krebs, S., Neurath, M.F., Dörje, F. and Atreya, R. (2024). Clinical Pharmacist counselling improves long-term medication safety and patient reported outcomes in anti-TNF treated patients with inflammatory bowel diseases: The prospective, randomised AdPhaNCED trial. Inflammatory Bowel Diseases, accpeted
• Schleier, M., Lubig, J., Kehl, S., Hebert, S., Woelfle, J., van der Donk, A., Bär, A., Reutter, H., Hepp, T. and Morhart, P. (2024). Diagnostic Utility of Interleukin-6 in Early-Onset Sepsis among Term Newborns: Impact of Maternal Risk Factors and CRP Evaluation. Children, 11(1): 53
• Bär, A., Schmitt-Grohe, S., Held, J., Lubig, J., Hanslik, G., Fahlbusch, F., Reutter, H.,Woelfle, J., van der Donk, A., Schleier, M., Hepp, T. and Morhart, P. (2023). Evaluating the Use of Neonatal Colonization Screening for Empiric Antibiotic Therapy of Sepsis and Pneumonia. Antibiotics, 12(2): 189.
• Philipps, A., Hepp, T., Silbermann, A., Morawa, E., Stemmler, M. and Erim, Y. (2022). Women-only versus mixed-gender groups in multimodal, day clinic treatment of trauma-related disorders. Zeitschrift für Psychosomatische Medizin und Psychotherapie, 68(4): 378-396.
• Hepp, T., Zierk, J., Rauh, M., Metzler, M. and Seitz, S. (2022): Mixture density networks for the indirect estimation of reference intervals. BMC Bioinformatics 23(1).
• Hepp, T., Wuest, W., Heiss, R., May, MS., Kopp, M., Wetzl, M., Treutlein, C., Uder, M. and Wiesmueller, M. (2022): Apparent Diffusion Coefficient (ADC) Histogram Analysis in Parotid Gland Tumors: Evaluating a Novel Approach for Differentiation between Benign and Malignant Parotid Lesions Based on Full Histogram Distributions. Diagnostics. 2022; 12(8):1860.
• Zhang, B., Hepp, T., Greven, S. and Bergherr, E. (2022): Adaptive step-length selection in gradient boosting for Gaussian location and scale models. Computational Statistics.. 1-38.
• Forster, C., Prax, K., Jaensch, P., Müller, S., Hepp, T., Schlager, H., Friedland, C. and Zerth, J. (2022): Die gesundheitsökonomische Evaluation der GLICEMIA 2.0-Studie als Beispiel für eine komplexe Intervention. Das Gesundheitswesen. 84(12): 1165-1173
• Madl, M., Lieb, M., Schieber, K., Hepp, T. and Erim, Y. (2021): A taxonomy for psycho-oncological intervention techniques in an acute care hospital in Germany. Oncology Research and Treatment. 44(7-8): 382–389.
• Rhein, C., Zoicas, I., Marx, L.M., Zeitler, S., Hepp, T., von Zimmermann, C., Mühle, C., Richter-Schmidinger, T., Lenz, B., Erim, Y., Reichel, M., Gulbins, E. and Kornhuber, J. (2021): mRNA expression of SMPD1 encoding acid sphingomyelinase decreases upon antidepressant treatment. International Journal of Molecular Sciences. 22(11): 5700
• Prax, K., Schmiedel, K., Hepp, T., Schlager, H. and Friedland, K. (2021): Preventive Care in Type 2 Diabetes: Results of a Randomized, Controlled Trial in Community Pharmacies. Diabetes Care.44(8):e157–e159
• Rhein, C., Hepp, T., Kraus, O., von Majewski, K., Lieb, M., Rohleder, N. and Erim, Y. (2021): Interleukin-6 secretion upon acute psychosocial stress as a potential predictor of psychotherapy outcome in posttraumatic stress disorder. Journal of Neural Transmission. 128(9): 1301-1310.
• Hepp, T., Marquart, P., Jauck, C. and Gefeller, O. (2021): Auswirkungen der Ausgangsbeschränkungen im Zusammenhang mit Covid-19 auf Supermarktbesuche in Deutschland. Das Gesundheitswesen. 83(03): 166-172
• Hepp, T., Zierk, J., Rauh, M., Metzler, M. and Mayr, A. (2020): Latent class distributional regression for the estimation of non-linear reference limits from contaminated data sources. BMC Bioinformatics. 21(1)
• Lieb, M., Hepp, T., Schiffer, M., Ogenoorth, M. and Erim, Y. (2020): Accuracy and concordance of measurement methods to assess non-adherence after renal transplantation-a prospective study. BMC Nephrology. 21(1)
• Lieb, M., Tagay, S., Breidenstein, A., Hepp, T., Le Guin, C., Scheel, J., Lohmann, D., Bornfeld, N., Teufel, M., and Erim, Y. (2020): Psychosocial impact of prognostic genetic testing in uveal melanoma patients: a controlled prospective clinical observational study. BMC Psychology. 8(1)
• Treutlein, C., Bäuerle, T., Nagel, AM., Guermazi, A., Kleyer, A., Simon, D., Schett, G., Hepp, T., Uder, M. and Roemer, F. (2020): Comprehensive assessment of knee joint synovitis at 7 T MRI using contrast-enhanced and non-enhanced sequences. BMC Musculoskeletal Disorders. 21(1)
• Saake, M., Hepp, T., Schmidle, A., Wuest, W., Heiss, R., Dörfler, A., Uder, M., and Bäuerle, T. (2019): Influence of artifact corrections on MRI signal intensity ratios for assessment of gadolinium brain retention. Academic Radiology. 27(5)
• Treutlein, C., Wiesmüller, M., May, MS., Heiss, R., Hepp, T., Uder, M., and Wuest, W. (2019): Complete free breathing adenosine stress cardiac MRI using compressed sensing and motion correction – Comparison of functional parameters, perfusion and late enhancement with the standard examination in breathhold. Radiology: Cardiothoracic Imaging. 1(3), e180017.
• Hepp, T., Schmid, M. and Mayr, A. (2019): Significance tests for boosted location and scale models with linear base-learners. The International Journal of Biostatistics. 15(1)
• Saake, M., Schmidle, A., Kopp, M., Hanspach, J., Hepp, T., Laun, F., Nagel, A., Dörfler, A., Uder, M., and Bäuerle, T. (2019): MRI brain signal intensity and relaxation times in individuals with prior exposure to gadobutrol. Radiology. 290(3), 659–668.
• Mayr, A., Hofner, B., Waldmann, E., Hepp, T., Meyer, S. and Gefeller, O. (2017): An update on statistical boosting in biomedicine. Computational and Mathematical Methods in Medicine. vol. 2017, Article ID 6083072, 12 pages.
• Thomas, J.,Hepp, T., Mayr, A. and Bischl, B. (2017): Probing for sparse and fast variable selection with model-based boosting. Computational and Mathematical Methods in Medicine. vol. 2017, Article ID 1421409, 8 pages.
• Faschingbauer, F., Heimrich, J., Raabe, E., Kehl, S., Schneider, M., Schmid, M., Beckmann, M., Hepp, T., Luebke, A., Mayr, A. and Schild, RL. (2017): Longitudinal assessment of examiner experience on the accuracy of sonographic fetal weight estimation at term. Journal of Ultrasound in Medicine. 36(1), 163-174.
• Hepp, T., Schmid, M., Gefeller, O., Waldmann, E. and Mayr, A. (2016): Approaches to regularized regression – A comparison between gradient boosting and the lasso. Methods of Information in Medicine. 455(5), 422-430.

Talks and Presentations

07/2024	Component-wise gradient boosting for mixtures of distributional regression models	Statistical Computing 2024, Günzburg, Germany
12/2023	Session Organizer: Regression models for latent structures	CMStatistics 2023, Berlin, Germany
07/2023	Component-wise boosting for mixture distributional regression models	IWSM 2023, Dortmund, Germany
03/2022	Distributional latent class modelling for the indirect estimation of reference distributions using mixture density networks	DAGStat 2022, Hamburg, Germany
07/2019	Adaptive step-lengths in model-based gradient boosting algorithms for distributional regression	Statistical Computing 2019, Günzburg, Germany
03/2019	Proper imputation for GAMLSS inference	DAGStat 2019, München, Germany
09/2018	Estimation of smooth reference limits from contaminated data sources	Statistische Woche 2018, Linz, Austria
07/2018	Estimating dynamic reference intervals from contaminated data sources	Statistical Computing 2018, Günzburg, Germany
12/2017	Tuning model-based gradient boosting algorithms with focus on variable selection	CMStatistics 2017, London, UK
07/2017	Variable selection for model-based gradient boosting using random probes	Statistical Computing 2017, Günzburg, Germany
12/2016	Assessing the significance of effects in boosted location and scale models	CMStatistics 2016, Sevilla, Spain
07/2016	Assessing the significance of effects in boosted location and scale models	Statistical Computing 2016, Günzburg, Germany
03/2016	Regularization methods in statistical modelling – A comparison between gradient boosting and the lasso	DAGStat 2016, Göttingen, Germany
07/2015	Regularization methods in statistical modelling – A comparison between gradient boosting and the lasso	Statistical Computing 2015, Günzburg, Germany