nonREMuni

nonREMuni is an open-source software platform for automated analysis and visualization of non-rapid eye movement (non-REM) sleep data. The name combines "non-REM" with "uni" to reflect its aim of providing a unified toolkit for researchers, clinicians, and device developers working with sleep recordings.

The platform integrates signal processing and machine learning techniques to perform tasks such as sleep stage classification, spindle and slow-wave detection, spectral analysis, and artifact rejection. It accepts common input modalities including electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), and actigraphy, and can process polysomnography files or streaming data from wearable sensors.

nonREMuni was developed by a multidisciplinary consortium of neuroscientists, clinicians, and software engineers and is distributed under an open-source license to encourage reproducibility and community contributions. Its architecture emphasizes modularity, allowing users to swap algorithms, retrain models on new datasets, and extend visualization components.

In research contexts, nonREMuni has been used for large-scale sleep studies, cross-cohort comparisons, and exploratory analysis of sleep microarchitecture. In applied settings, it has been integrated into pilot clinical workflows and consumer sleep-monitoring products. Reported limitations include the need for additional validation across diverse populations, sensitivity to recording quality, and the requirement for expert review in diagnostic use. Ongoing development efforts focus on improving generalization, transparency of models, and interoperability with health data standards.