Development and Validation of Machine Learning Models to Predict Postoperative Delirium Using Clinical Features and Polysomnography Variables.

Background: Delirium affects up to 50% of patients following high-risk surgeries and is associated with poor long-term prognosis. This study employed machine learning to predict delirium using polysomnography (PSG) and sleep-disorder questionnaire data, and aimed to identify key sleep-related factors for improved interventions and patient outcomes. Methods: We studied 912 adults who underwent surgery under general anesthesia at a tertiary hospital (2013-2024) and had PSG within 5 years of surgery. Delirium was assessed via clinical diagnoses, antipsychotic prescriptions, and psychiatric consultations within 14 days postoperatively. Sleep-related data were collected using PSG and questionnaires. Machine learning predictions were performed to identify postoperative delirium, focusing on model accuracy and feature importance. Results: This study divided the 912 patients into an internal training set (700) and an external test set (212). Univariate analysis identified significant delirium risk factors: midazolam use, prolonged surgery duration, and hypoalbuminemia. Sleep-related variables such as fewer rapid eye movement (REM) episodes and higher daytime sleepiness were also linked to delirium. An extreme gradient-boosting-based classification task achieved an AUC of 0.81 with clinical variables, 0.60 with PSG data alone, and 0.84 with both, demonstrating the added value of PSG data. Analysis of Shapley additive explanations values highlighted important predictors: surgery duration, age, midazolam use, PSG-derived oxygen saturation nadir, periodic limb movement index, and REM episodes, demonstrating the relationship between sleep patterns and the risk of delirium. Conclusions: The artificial intelligence model integrates clinical and sleep variables and reliably identifies postoperative delirium, demonstrating that sleep-related factors contribute to its identification. Predicting patients at high risk of developing postoperative delirium and closely monitoring them could reduce the costs and complications associated with delirium.

Headache in Brain Tumors.

The prevalence of brain tumors in patients with headache is very low; however, 48% to 71% of patients with brain tumors experience headache. The clinical presentation of headache in brain tumors varies according to age; intracranial pressure; tumor location, type, and progression; headache history; and treatment. Brain tumor-associated headaches can be caused by local and distant traction on pain-sensitive cranial structures, mass effect caused by the enlarging tumor and cerebral edema, infarction, hemorrhage, hydrocephalus, and tumor secretion. This article reviews the current findings related to epidemiologic details, clinical manifestations, mechanisms, diagnostic approaches, and management of headache in association with brain tumors.

Coffee consumption and migraine: a population-based study.

Although coffee is one of the most consumed caffeinated beverages worldwide, the role of coffee consumption in migraine is controversial. This study examined the relationship between coffee consumption and clinical characteristics in participants with migraine compared to those with non-migraine headache. This cross-sectional study used data from a nationwide survey on headache and sleep. Coffee consumption was classified as no-to-low (< 1 cup/day), moderate (1-2 cups/day), or high (≥ 3 cups/day). Of the 3030 survey participants, 170 (5.6%) and 1,768 (58.3%) were identified as having migraine and non-migraine headache, respectively. Coffee consumption tended to increase in the order of non-headache, non-migraine headache, and migraine (linear-by-linear association, p = 0.011). Although psychiatric comorbidities (depression for migraine and anxiety for non-migraine headache) and stress significantly differed according to coffee consumption, most headache characteristics and accompanying symptoms did not differ among the three groups for participants with migraine and non-migraine headache. Response to acute headache treatment-adjusted for age, sex, depression, anxiety, stress, preventive medication use, and current smoking-was not significantly different by coffee consumption in participants with migraine and non-migraine headache. In conclusion, most headache-related characteristics and acute treatment response did not significantly differ by coffee consumption in migraine and non-migraine headache.