Search

In this study, we employed various machine learning models to predict metabolic phenotypes, focusing on thyroid function, using a dataset from the National Health and Nutrition Examination Survey (NHANES) from 2007 to 2012. Our analysis utilized laboratory parameters relevant to thyroid function or metabolic dysregulation in addition to demographic features, aiming to uncover potential associations between thyroid function and metabolic phenotypes by various machine learning methods. Multinomial Logistic Regression performed best to identify the relationship between thyroid function and metabolic phenotypes, achieving an area under receiver operating characteristic curve (AUROC) of 0.818, followed closely by Neural Network (AUROC: 0.814). Following the above, the performance of Random Forest, Boosted Trees, and K Nearest Neighbors was inferior to the first two methods (AUROC 0.811, 0.811, and 0.786, respectively). In Random Forest, homeostatic model assessment for insulin resistance, serum uric acid, serum albumin, gamma glutamyl transferase, and triiodothyronine/thyroxine ratio were positioned in the upper ranks of variable importance. These results highlight the potential of machine learning in understanding complex relationships in health data. However, it's important to note that model performance may vary depending on data characteristics and specific requirements. Furthermore, we emphasize the significance of accounting for sampling weights in complex survey data analysis and the potential benefits of incorporating additional variables to enhance model accuracy and insights. Future research can explore advanced methodologies combining machine learning, sample weights, and expanded variable sets to further advance survey data analysis. [ABSTRACT FROM AUTHOR]

Background: The aim of this study was to evaluate the impact of intravenous palonosetron compared to ondansetron on hypotension induced by spinal anesthesia in women undergoing cesarean section. Methods: Fifty-four women scheduled for elective cesarean section were, randomly allocated to ondansetron group (n = 27) or palonosetron group (n = 27). Ten minutes prior to the administration of spinal anesthesia, participants received an intravenous injection of either ondansetron or palonosetron. A prophylactic phenylephrine infusion was initiated immediately following the intrathecal administration of bupivacaine and fentanyl. The infusion rate was titrated to maintain adequate blood pressure until the time of fetal delivery. The primary outcome was total dose of phenylephrine administered. The secondary outcomes were nausea or vomiting, the need for rescue antiemetics, hypotension, bradycardia, and shivering. Complete response rate, defined as the absence of postoperative nausea and vomiting and no need for additional antiemetics, were assessed for up to 24 hours post-surgery. Results: No significant differences were observed in the total dose of phenylephrine used between the ondansetron and palonosetron groups (387.5 μg [interquartile range, 291.3–507.8 μg versus 428.0 μg [interquartile range, 305.0–507.0 μg], P = 0.42). Complete response rates also showed no significant differences between the groups both within two hours post-spinal anesthesia (88.9% in the ondansetron group versus 100% in the palonosetron group; P = 0.24) and at 24 hours post-surgery (81.5% in the ondansetron group versus 88.8% in the palonosetron group; P = 0.7). In addition, there was no difference in other secondary outcomes. Conclusion: Prophylactic administration of palonosetron did not demonstrate a superior effect over ondansetron in mitigating hemodynamic changes or reducing phenylephrine requirements in patients undergoing spinal anesthesia with bupivacaine and fentanyl for cesarean section. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the common CT findings of high-grade (HG) PanIN and clinical effects in the remnant pancreas in patients with intraductal papillary mucinous neoplasm (IPMN) of the pancreas. Materials and methods: Two hundred fifty-one patients with surgically confirmed IPMNs (118 malignant [invasive carcinoma/high-grade dysplasia] and 133 benign [low-grade dysplasia]) were retrospectively enrolled. The grade of PanIN (233 absent/low-grade and 18 high-grade) was recorded, and all patients underwent serial CT follow-up before and after surgery. Two radiologists analyzed CT findings of high-risk stigmata or worrisome features according to 2017 international consensus guidelines. They also analyzed tumor recurrence on serial follow-up CT after surgery. Statistical analyses were performed to identify significant predictors and clinical impact on postoperative outcomes of HG PanIN. Results: PanIN grade showed a significant association with IPMN grade (p = 0.012). Enhancing mural nodules ≥5 mm, abrupt main pancreatic duct (MPD) changes with distal pancreatic atrophy, increased mural nodule size and MPD diameter were common findings in HG PanIN (P<0.05). In multivariate analysis, abrupt MPD change with distal pancreatic atrophy (odds ratio (OR) 6.59, 95% CI: 2.32–18.72, <0.001) and mural nodule size (OR, 1.05; 95% CI, 1.02–1.08, 0.004) were important predictors for HG PanIN. During postoperative follow-up, HG PanIN (OR, 4.98; 95% CI, 1.22–20.33, 0.025) was significantly associated with cancer recurrence in the remnant pancreas. Conclusion: CT can be useful for predicting HG PanIN using common features, such as abrupt MPD changes and mural nodules. In HG PanIN, extra caution is needed to monitor postoperative recurrence during follow-up. [ABSTRACT FROM AUTHOR]

This study aimed to identify underlying demographic and clinical characteristics among individuals who had previously attempted suicide, utilizing the comprehensive Health Insurance Review and Assessment Service (HIRA) database. Data of patients aged 18 and above who had attempted suicide between January 1 and December 31, 2014, recorded in HIRA, were extracted. The index date was identified when a suicide attempt was made within the year 2014. The medical history of the three years before the index date and seven years of follow-up data after the index date were analyzed. Kaplan-Meier estimate was used to infer reattempt of the suicide attempters, and Cox-proportional hazard analysis was used to investigate risk factors associated with suicide reattempts. A total of 17,026 suicide attempters were identified, of which 1,853 (10.9%) reattempted suicide; 4,925 (28.9%) patients had been diagnosed with depressive disorder. Of the reattempters, 391 (21.1%) demonstrated a history of suicide attempts in the three years before the index date, and the mean number of prior attempts was higher compared to that of the non-reattempters (1.7 vs.1.3, p-value < 0.01). Prior psychiatric medication, polypharmacy, and an increase in the number of psychotropics were associated with suicide reattempt in overall suicide attempters. (Hazard ratio (HR) = 3.20, 95% confidence interval [CI] = 2.56–4.00; HR = 2.42, 95% CI = 1.87–3.14; HR = 19.66, 95% CI = 15.22–25.39 respectively). The risk of reattempt decreased in individuals receiving antidepressant prescriptions compared to those unmedicated, showing a reduction of 78% when prescribed by non-psychiatrists and 89% when prescribed by psychiatrists. Similar risk factors for suicide reattempts were observed in the depressive disorder subgroup, but the median time to reattempt was shorter (556.5 days) for this group compared to that for the overall attempters (578 days). Various risk factors including demographics, clinical characteristics, and medications should be considered to prevent suicide reattempts among suicide attempters, and patients with depressive disorder should be monitored more closely. [ABSTRACT FROM AUTHOR]

Verifying habitats, including the foraging and nesting areas for sea turtles, enables an understanding of their spatial ecology and successful planning of their conservation and management strategies. Recently, the observation frequency and bycatch of loggerhead (Caretta caretta) and green (Chelonia mydas) turtles have increased in the northern limit of their distribution range, in the northern part of the East China Sea and East (Japan) Sea. We conducted satellite tracking to investigate the habitat use of seven loggerhead and eight green turtles from June 2016 to August 2022 in this area, where little is known about their spatial ecology. We applied a 50 percent volume contour method to determine their main foraging areas and analyzed 6 environmental variables to characterize their habitats. Loggerhead turtles mainly stayed in and used the East China Sea as a foraging area during the tracking period, while two individuals among them also used the East Sea as a seasonal foraging area. Most green turtles also used the East China Sea as a foraging area, near South Korea and Japan, with one individual among them using the lower area of the East Sea as a seasonal foraging area. Notably, one green turtle traveled to Hainan Island in the South China Sea, a historical nesting area. Our results showed that the two sea turtle species included the East Sea as a seasonal foraging area, possibly owing to the abundance of food sources available, despite its relatively lower sea temperature. Considering that loggerhead and green sea turtles were observed using the northern part of the East China Sea and East Sea more frequently than previously known and that the sea temperature gradually increases due to climate change, conservation and management activities are required for sea turtles in these areas. [ABSTRACT FROM AUTHOR]

Students' performance is an important factor for the evaluation of teaching quality in colleges. The prediction and analysis of students' performance can guide students' learning in time. Aiming at the low accuracy problem of single model in students' performance prediction, a combination prediction method is put forward based on ant colony algorithm. First, considering the characteristics of students' learning behavior and the characteristics of the models, decision tree (DT), support vector regression (SVR) and BP neural network (BP) are selected to establish three prediction models. Then, an ant colony algorithm (ACO) is proposed to calculate the weight of each model of the combination prediction model. The combination prediction method was compared with the single Machine learning (ML) models and other methods in terms of accuracy and running time. The combination prediction model with mean square error (MSE) of 0.0089 has higher performance than DT with MSE of 0.0326, SVR with MSE of 0.0229 and BP with MSE of 0.0148. To investigate the efficacy of the combination prediction model, other prediction models are used for a comparative study. The combination prediction model with MSE of 0.0089 has higher performance than GS-XGBoost with MSE of 0.0131, PSO-SVR with MSE of 0.0117 and IDA-SVR with MSE of 0.0092. Meanwhile, the running speed of the combination prediction model is also faster than the above three methods. [ABSTRACT FROM AUTHOR]