講師資料
Talks：
Beyond the Sleep Lab: Integrating Sleep Apnea, Sleep Regularity, and Circadian Rhythm Through Sleep Technology
超越睡眠實驗室：以睡眠科技整合監測睡眠呼吸中止症、睡眠規律性與晝夜節律
Name：
李佩玲（Pei-Lin Lee）
Position：
1. Clinical Associate Professor, Department of Internal Medicine, College of Medicine, National Taiwan University
2. Director, Sleep and Chronobiology Center, National Taiwan University Hospital Hsin-Chu Branch
Affiliation：
1. National Taiwan University
2. National Taiwan University Hospital Hsin-Chu Branch
Email：
Photo：
Research Interests：
1. New technology and big data in sleep medicine
2. Intervention on sleep and cardiometabolism in sleep disordered breathing.
Selected Publications：
1. PL Lee et al. Current evidence on cardiovascular risks in female obstructive sleep apnea. Sleep Medicine Clinics 2026; 21(2):183-193.
2. PL Lee et al. Obstructive Sleep Apnea in Women: Evolution Across Life Span. In :Hsueh-Yu Li (eds). Snoring and Obstructive Sleep Apnea. Springer, Singapore 2025.
3. PL Lee et al. From Screening at Clinic to Diagnosis at Home: How AI/ ML/DL Algorithms are Transforming Sleep Apnea Detection. In: Richard Berry, Panos M. Pardalos, and Xiaochen Xian. Handbook of AI and Data Sciences for Sleep Disorders, Florida: Springer 2024. Online ISBN 978-3-031-68263-6
4. PL Lee & YW Wu et al. Recommended assessment and management of sleep disordered breathing in patients with atrial fibrillation, hypertension and heart failure: Taiwan Society of Cardiology/Taiwan Society of Sleep Medicine/Taiwan Society of Pulmonary and Critical Care Medicine joint consensus statement. Journal of the Formosan Medical Association. 2024; 123(2):159-178.
5. PK Liu et al. Validation of Photoplethysmography and Acceleration-Based Sleep Staging in a Community Sample: Comparison With Polysomnography and Actiwatch. Journal of Clinical Sleep Medicine. J Clin Sleep Med. 2023;1;19(10):1797-1810.
6. WC Huang & PL Lee et al. Support Vector Machine Prediction of Obstructive Sleep Apnea in a Large-Scale Chinese Clinical Sample. SLEEP, 2020;13;43(7):zsz295
7. PL Lee et al. Automatic sleep staging in patients with obstructive sleep apnea using single-channel frontal EEG. Journal of Clinical Sleep Medicine. 2019; 15(10), 1411-1420.
Abstract：
Advances in wearable and non-wearable sleep technologies, together with artificial intelligence, have extended sleep assessment beyond the sleep laboratory. Current technologies can detect obstructive sleep apnea (OSA) while providing longitudinal information on sleep duration, timing, regularity, and circadian patterns.
This presentation will review current approaches to OSA detection using medical- and consumer-grade technologies and discuss the additional information derived from repeated measurements. The apnea-hypopnea index (AHI) may vary substantially across nights, while single-night testing provides limited information on habitual sleep patterns. Longitudinal monitoring allows assessment of AHI variability together with sleep duration and regularity, chronotype, and circadian rhythm. Physiological measures, including hypoxic burden and apnea-specific pulse-rate responses, may further characterize the consequences of OSA beyond event frequency. Integrating apnea detection with sleep and circadian information provides a broader assessment of OSA and sleep health. How these multidimensional measures should be interpreted and incorporated into clinical practice remains an important consideration as sleep technologies continue to evolve.[1]


1. Lee P-L, Chirakalwasan N, Cheng W-J. Obstructive Sleep Apnea in Women: Evolution Across Life Span. In: Li H-Y, ed. Snoring and Obstructive Sleep Apnea: Evolution and Innovation. Singapore: Springer Nature Singapore; 2025: 261–276.
2026年會：