arXiv subjects

Lukas Heumos

Publications and source records attributed to Lukas Heumos.

4 recordsLinked to original sources

arXiv2026

A learning health system in Neurorehabilitation as a foundation for multimodal patient representation

Neurological disorders represent a growing global health burden requiring long-term, interdisciplinary rehabilitation. Computational neurorehabilitation (compNR) - the use of data-driven and model-based approaches to personalize treatment - offers new opportunities for precision rehabilitation. However, its clinical deployment is limited by fragmented data systems, poor interoperability, and low clinician engagement in model development. We embed the learning health system (LHS) framework in Neurorehabilitation through integration of multimodal data collection, model computation, and clinical visualization that enables clinician-ML collaboration in everyday neurorehabilitation practice. The system facilitates structured digital data capture, secure computational processing, and interoperable visualization of patient trajectories. Through a real-world deployment in stroke rehabilitation, we demonstrate how such an infrastructure bridges the gap between research models and clinical use, showcasing one approach to a translational pathway for compNR.

cs.HC↗

arXiv2026

GPU-accelerated single-cell analysis at scale with rapids-singlecell

Single-cell sequencing technologies reveal cellular heterogeneity at high resolution, advancing our understanding of biological complexity. As datasets start to scale to tens of millions of cells, computational workflows face substantial bottlenecks, with CPU-based analytical pipelines requiring hours or days for routine processing steps like filtering, normalization, and clustering. These scalability limitations fundamentally restrict common interactive data exploration and iterative hypothesis testing. Here we introduce rapids-singlecell, a GPU-accelerated framework that integrates natively with the scverse ecosystem and operates directly on the AnnData data structure, which delivers orders-of-magnitude speedups for single-cell workflows. Built on CuPy arrays and the NVIDIA CUDA-X Data Science (RAPIDS) ecosystem, rapids-singlecell provides near drop-in GPU replacements for core scanpy-based analysis steps. Across standard single-cell workflows such as preprocessing, dimensionality reduction, neighborhood graph construction, clustering, and batch correction, rapids-singlecell achieves speedups of up to several hundred-fold compared to optimized CPU baselines. This reduces analysis time from hours to minutes on standard hardware, while maintaining consistent biological interpretations. These performance improvements make it possible to analyze large data sets in close to real time, without the need for data splitting. Together with real-time parameter tuning and iterative workflows, rapids-singlecell makes interactive large-scale single-cell analysis possible.

q-bio.GN↗

arXiv2025

Embedding computational neurorehabilitation in clinical practice using a modular intelligent health system

A significant and rising proportion of the global population suffer from non-communicable diseases, such as neurological disorders. Neurorehabilitation aims to restore function and independence of neurological patients through providing interdisciplinary therapeutic interventions. Computational neurorehabilitation, an automated simulation approach to dynamically optimize treatment effectivity, is a promising tool to ensure that each patient has the best therapy for their current status. However, computational neurorehabilitation relies on integrated data flows between clinical assessments, predictive models, and healthcare professionals. Current neurorehabilitation practice is limited by low levels of digitalization and low data interoperability. We here propose and demonstrate an embedded intelligent health system that enables detailed digital data collection in a modular fashion, real-time data flows between patients, models, and clinicians, clinical integration, and multi-context capacities, as required for computational neurorehabilitation approaches. We give an outlook on how modern exploratory data analysis tools can be integrated to facilitate model development and knowledge inference from secondary use of observational data this system collects. With this blueprint, we contribute towards the development of integrated computational neurorehabilitation workflows for clinical practice.

cs.SE↗

arXiv2022

mlf-core: a framework for deterministic machine learning

Machine learning has shown extensive growth in recent years and is now routinely applied to sensitive areas. To allow appropriate verification of predictive models before deployment, models must be deterministic. However, major machine learning libraries default to the usage of non-deterministic algorithms based on atomic operations. Solely fixing all random seeds is not sufficient for deterministic machine learning. To overcome this shortcoming, various machine learning libraries released deterministic counterparts to the non-deterministic algorithms. We evaluated the effect of these algorithms on determinism and runtime. Based on these results, we formulated a set of requirements for deterministic machine learning and developed a new software solution, the mlf-core ecosystem, which aids machine learning projects to meet and keep these requirements. We applied mlf-core to develop deterministic models in various biomedical fields including a single cell autoencoder with TensorFlow, a PyTorch-based U-Net model for liver-tumor segmentation in CT scans, and a liver cancer classifier based on gene expression profiles with XGBoost.

cs.MS↗