Machine learning-based identification of the risk factors for postoperative nausea and vomiting in adults.

Postoperative nausea and vomiting (PONV) is a common adverse effect of anesthesia. Identifying risk factors for PONV is crucial because it is associated with a longer stay in the post-anesthesia care unit, readmissions, and perioperative costs. This retrospective study used artificial intelligence to analyze data of 37,548 adult patients (aged ≥20 years) who underwent surgery under general anesthesia at Tohoku University Hospital from January 1, 2010 to December 31, 2019. To evaluate PONV, patients who experienced nausea and/or vomiting or used antiemetics within 24 hours after surgery were extracted from postoperative medical and nursing records. We create a model that predicts probability of PONV using the gradient tree boosting model, which is a widely used machine learning algorithm in many applications due to its efficiency and accuracy. The model implementation used the LightGBM framework. Data were available for 33,676 patients. Total blood loss was identified as the strongest contributor to PONV, followed by sex, total infusion volume, and patient's age. Other identified risk factors were duration of surgery (60-400 min), no blood transfusion, use of desflurane for maintenance of anesthesia, laparoscopic surgery, lateral positioning during surgery, propofol not used for maintenance of anesthesia, and epidural anesthesia at the lumbar level. The duration of anesthesia and the use of either sevoflurane or fentanyl were not identified as risk factors for PONV. We used artificial intelligence to evaluate the extent to which risk factors for PONV contribute to the development of PONV. Intraoperative total blood loss was identified as the potential risk factor most strongly associated with PONV, although it may correlate with duration of surgery, and insufficient circulating blood volume. The use of sevoflurane and fentanyl and the anesthesia time were not identified as risk factors for PONV in this study.

Growth hormone increase by luteinizing hormone-releasing hormone reflects gonadotroph-related characteristics in acromegaly.

PURPOSE: We previously showed the clinical characteristics of acromegaly with a paradoxical growth hormone (GH) response to oral glucose or thyrotropin-releasing hormone. However, the clinical characteristics of acromegaly with an increased GH response to luteinizing hormone-releasing hormone (LHRH responders) remain unclear. The aim of the present study was to evaluate the clinical characteristics, especially gonadotroph-related characteristics of LHRH responders in acromegaly. METHODS: The clinical characteristics of 33 LHRH responders and 81 LHRH nonresponders were compared. RESULTS: No differences in age, sex or basal serum levels of GH, insulin-like growth factor-1 (IGF-1), and gonadotropin were observed between the two groups. Steroidogenic factor 1 (SF-1), gonadotropin-releasing hormone receptor (GnRHR), and LH expression was more frequently observed in LHRH responders (P < 0.05). In addition, a greater increased rate of GH after LHRH loading, and the proportion of GnRHR and gonadotropin expression was observed in pituitary tumor with SF-1 expression than that without the expression (P < 0.01). LHRH responders showed a greater GH decrease in the octreotide test and a greater IGF-1 decrease after first-generation somatostatin ligand than LHRH nonresponders (P < 0.05). Furthermore, the proportion of hypointense pituitary tumors on T2-weighted magnetic resonance imaging and tumors with densely granulated type was higher in LHRH responders than in LHRH nonresponders, respectively (P < 0.05). No difference between the two groups was observed in either somatostatin receptor 2 or 5 expression. CONCLUSIONS: The increased GH response to LHRH is associated with the gonadotroph-related characteristics. This response may reflect the biological characteristics of somatotroph tumors.