{
  "id": 12318965,
  "title": "Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors",
  "url": "https://urgent.news/2026/10/05/deep-learning-for-sleep-heart-rate-estimation-from-accelerometers",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-05T17:56:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.06823v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-based temporal corrector for sleep heart rate (HR) estimation from wrist accelerometry. SeqSmoother combines spectral descriptors with an intermediate Nightbeat-derived…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}