Background Recently, endoscopic submucosal dissection (ESD) for early gastric cancer (EGC) has been performed on patients with severe comorbidities because it is less invasive, although little is known regarding long-term outcomes. This study aimed to assess the long-term outcomes of ESD for patients with severe and non-severe comorbidities. Methods We enrolled 1081 patients who underwent ESD for EGC between February 2004 and June 2013. Based on the American Society of Anesthesiologists Physical Status (ASA-PS) classification, we defined patients with severe and nonsevere comorbidities as ASA-PS 3 and 1/2, respectively. We retrospectively compared the overall survival, risk factors for mortality, and adverse events between these two groups using propensity score matching and inverse probability of treatment weighting. Results A total of 488 patients met the eligibility criteria. After matching, the ASA-PS 3 group showed a significantly shorter survival than the ASA-PS 1/2 group (5-year overall survival rate, 79.1 vs. 87.7%; p < 0.01). In addition, only the ASA-PS 3 group had a significant risk factor for mortality using both the Cox analysis [hazard ratio (HR), 2.56; 95% confidence interval (CI) 1.18-5.52; p = 0.02] and the IPTW method (HR, 3.14; 95% CI 1.91-5.14; p < 0.01). There was no significant difference in adverse events after matching between the two groups (p = 0.21). Conclusions The long-term outcome of gastric ESD for patients with severe comorbidities was worse than for those with non-severe comorbidities. Further studies will be necessary to determine if ESD is truly warranted in these patients.