SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model

• URL: http://arxiv.org/abs/2603.26738v2
• Date: Tue, 31 Mar 2026 13:40:53 GMT
• Title: SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model
• Abstract summary: SleepVLM is a rule-grounded vision-language model (VLM) designed to stage sleep from multi-channel polysomnography (PSG) waveform images.<n> SleepVLM generated clinician-readable rationales based on American Academy of Sleep Medicine (AASM) scoring criteria.<n>Expert evaluations validated the quality of the model's reasoning, with mean scores exceeding 4.0/5.0 for factual accuracy, evidence comprehensiveness, and logical coherence.
• Score: 9.741417444397799
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindered by a lack of auditable reasoning. We introduce SleepVLM, a rule-grounded vision-language model (VLM) designed to stage sleep from multi-channel polysomnography (PSG) waveform images while generating clinician-readable rationales based on American Academy of Sleep Medicine (AASM) scoring criteria. Utilizing waveform-perceptual pre-training and rule-grounded supervised fine-tuning, SleepVLM achieved Cohen's kappa scores of 0.767 on an held out test set (MASS-SS1) and 0.743 on an external cohort (ZUAMHCS), matching state-of-the-art performance. Expert evaluations further validated the quality of the model's reasoning, with mean scores exceeding 4.0/5.0 for factual accuracy, evidence comprehensiveness, and logical coherence. By coupling competitive performance with transparent, rule-based explanations, SleepVLM may improve the trustworthiness and auditability of automated sleep staging in clinical workflows. To facilitate further research in interpretable sleep medicine, we release MASS-EX, a novel expert-annotated dataset.

Related papers

• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• The Breakthrough of Sleep: A Contactless Approach for Accurate Sleep Stage Detection Using the Sleepal AI Lamp [15.791950475785113]
  Sleep staging is essential for the assessment of sleep-related disorders.<n>Conventional polysomnography (PSG) is intrusive, labor-intensive, and unsuitable for long-term monitoring.<n>This study evaluates the performance of the Sleepal AI Lamp, a contactless, radar-based consumer-grade sleep tracker.
  arXiv  Detail & Related papers  (2026-04-07T06:49:41Z)
• AI Generalisation Gap In Comorbid Sleep Disorder Staging [5.137280927017341]
  We introduce iSLEEPS, a newly clinically annotated ischemic stroke dataset.<n>We evaluate a SE-ResNet plus bidirectional LSTM model for single-channel EEG sleep staging.<n>Cross-domain performance between healthy and diseased subjects is poor.
  arXiv  Detail & Related papers  (2026-03-24T15:02:35Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• Sleep Position Classification using Transfer Learning for Bed-based Pressure Sensors [0.06282171844772422]
  Bed-based pressure-sensitive mats (PSMs) offer a non-intrusive way of monitoring patients during sleep.<n>We focus on four-way sleep position classification using data collected from a PSM placed under a mattress in a sleep clinic.
  arXiv  Detail & Related papers  (2025-05-12T22:54:03Z)
• WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions [46.60244609728416]
  Language Models (LMs) are being proposed for mental health applications where the heightened risk of adverse outcomes means predictive performance may not be a litmus test of a model's utility in clinical practice. We introduce an evaluation design that focuses on the robustness and explainability of LMs in identifying Wellness Dimensions (WDs) We reveal four surprising results about LMs/LLMs.
  arXiv  Detail & Related papers  (2024-06-17T19:50:40Z)
• MSSC-BiMamba: Multimodal Sleep Stage Classification and Early Diagnosis of Sleep Disorders with Bidirectional Mamba [5.606144017978037]
  We develop an automated model for sleep staging and disorder classification to enhance diagnostic accuracy and efficiency. Considering the characteristics of polysomnography (PSG) multi-lead sleep monitoring, we designed a multimodal sleep state classification model, MSSC-BiMamba. The model is the first to apply BiMamba to sleep staging with multimodal PSG data, showing substantial gains in computational and memory efficiency.
  arXiv  Detail & Related papers  (2024-05-30T15:16:53Z)
• aSAGA: Automatic Sleep Analysis with Gray Areas [2.47298967960367]
  State-of-the-art automatic sleep staging methods have already demonstrated comparable reliability and superior time efficiency to manual sleep staging. We propose a human-in-the-loop concept for sleep analysis, presenting an automatic sleep staging model (aSAGA) that performs effectively with both clinical polysomnographic recordings and home sleep studies.
  arXiv  Detail & Related papers  (2023-10-03T13:17:38Z)
• Sleep Activity Recognition and Characterization from Multi-Source Passively Sensed Data [67.60224656603823]
  Sleep Activity Recognition methods can provide indicators to assess, monitor, and characterize subjects' sleep-wake cycles and detect behavioral changes. We propose a general method that continuously operates on passively sensed data from smartphones to characterize sleep and identify significant sleep episodes. Thanks to their ubiquity, these devices constitute an excellent alternative data source to profile subjects' biorhythms in a continuous, objective, and non-invasive manner.
  arXiv  Detail & Related papers  (2023-01-17T15:18:45Z)
• SERF: Interpretable Sleep Staging using Embeddings, Rules, and Features [0.0]
  Clinician-determined sleep stages from polysomnogram (PSG) remain the gold standard for evaluating sleep quality. We propose SERF, interpretable Sleep staging using Embeddings, Rules, and Features to read PSG. SerF surpasses the current state-of-the-art for interpretable sleep staging by 2%.
  arXiv  Detail & Related papers  (2022-09-21T10:01:56Z)
• MSED: a multi-modal sleep event detection model for clinical sleep analysis [62.997667081978825]
  We designed a single deep neural network architecture to jointly detect sleep events in a polysomnogram. The performance of the model was quantified by F1, precision, and recall scores, and by correlating index values to clinical values.
  arXiv  Detail & Related papers  (2021-01-07T13:08:44Z)
• Automatic detection of microsleep episodes with deep learning [55.41644538483948]
  Brief fragments of sleep shorter than 15 s are defined as microsleep episodes (MSEs) maintenance of wakefulness test (MWT) is often used in a clinical setting to assess vigilance. MSEs are mostly not considered in the absence of established scoring criteria defining MSEs. We aimed for automatic detection of MSEs with machine learning based on raw EEG and EOG data as input.
  arXiv  Detail & Related papers  (2020-09-07T11:38:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.