PURPOSE: Accurate predictions of postoperative pain intensity are necessary for customizing analgesia plans. Insomnia is a risk factor for severe postoperative pain. Moreover, heart rate variability (HRV) can provide information on the sympathetic-parasympathetic balance in response to noxious stimuli. We developed a prediction model that uses the insomnia severity index (ISI), HRV, and other demographic factors to predict the odds of higher postoperative pain. METHODS: We recruited gynecological surgery patients classified as American Society of Anesthesiologists class 1-3. An ISI questionnaire was completed 1 day before surgery. HRV was calculated offline using intraoperative electrocardiogram data. Pain severity at the postanesthesia care unit (PACU) was assessed with the 0-10 numerical rating scale (NRS). The primary outcome was the model\'s predictive ability for moderate-to-severe postoperative pain. The secondary outcome was the relationship between individual risk factors and opioid consumption in the PACU. RESULTS: Our study enrolled 169 women. Higher ISI scores (p = 0.001), higher parasympathetic activity (rMSSD, pNN50, HF; p < 0.001, p < 0.001, p < 0.001), loss of fractal dynamics (SD2, alpha 1; p = 0.012, p = 0.039) in HRV analysis before the end of surgery were associated with higher NRS scores, while laparoscopic surgery (p = 0.031) was associated with lower NRS scores. We constructed a multiple logistic model (area under the curve = 0.852) to predict higher NRS scores at PACU arrival. The five selected predictors were age (OR: 0.94; p = 0.020), ISI score (OR: 1.14; p = 0.002), surgery type (laparoscopic or open; OR: 0.12; p < 0.001), total power (OR: 2.02; p < 0.001), and alpha 1 (OR: 0.03; p < 0.001). CONCLUSION: We employed a multiple logistic regression model to determine the likelihood of moderate-to-severe postoperative pain upon arrival at the PACU. Physicians could personalize analgesic regimens based on a deeper comprehension of the factors that contribute to postoperative pain.