Adequate oxygenation and airway management during deep sedation can be challenging. We investigated the effect of high-flow nasal cannula (group HF) and conventional nasal cannula (group CO) during sedation for endoscopic submucosal dissection (ESD). Patients undergoing ESD with deep sedation were enrolled. The primary outcome was difference in lowest oxygen saturation (SpO2) between the groups. Incidence of hypoxia (SpO2 < 90%), patients with SpO2 < 95%, hypercapnia, and airway interventions; operator satisfaction; and adverse events were recorded. Thirty-two patients in each group completed the study. The mean of minimum SpO2 values was significantly higher in group HF than in group CO (96.8% ± 4.2% vs. 93.3% ± 5.3%, p = 0.005). The incidence of hypoxia was comparable between the groups (4 [12.5%] vs. 6 [18.8%], p = 0.491); however, patients with SpO2 < 95% were significantly less in group HF (5 [15.6%] vs. 18 [56.3%], p = 0.003). Incidence of hypercapnia was higher in group HF than in group CO (14 [46.7%] vs. 5 [16.7%], p = 0.013). Airway rescue interventions were significantly less common in group HF. Satisfaction of operators and post-procedural complications were comparable between the two groups. In multivariable analysis, group CO and higher body mass index were risk factors for airway managements (odds ratio [95% confidence interval]: 6.204 [1.784-21.575], p = 0.004; 1.337 [1.043-1.715], p = 0.022, respectively). Compared to conventional nasal cannula, high-flow nasal cannula maintained higher minimum SpO2 value during deep sedation with propofol-remifentanil for ESD. Clinical Trial Registry of the Republic of Korea (KCT0006618, https://cris.nih.go.kr ; registered September 29, 2021; principal investigator: Ji Won Choi).