Search

Methadone is an opioid receptor agonist with a high potential for abuse. The current study aimed to compare different machine learning models to predict the outcomes following methadone poisoning. This six-year retrospective longitudinal study utilizes National Poison Data System (NPDS) data. The severity of outcomes was derived from the NPDS Coding Manual. Our database was divided into training (70%) and test (30%) sets. We used a light gradient boosting machine (LGBM), extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR) to predict the outcomes of methadone poisoning. A total of 3847 patients with methadone exposures were included. Our results demonstrated that machine learning models conferred high accuracy and reliability in determining the outcomes of methadone poisoning cases. The performance evaluation showed all models had high accuracy, precision, specificity, recall, and F1-score values. All models could reach high specificity (more than 96%) and high precision (80% or more) for predicting major outcomes. The models could also achieve a high sensitivity to predict minor outcomes. Finally, the accuracy of all models was about 75%. However, XGBoost and LGBM models achieved the best performance among all models. This study showcased the accuracy and reliability of machine learning models in the outcome prediction of methadone poisoning. [ABSTRACT FROM AUTHOR]

Bupropion is widely used for the treatment of major depressive disorder and for smoking cessation assistance. Unfortunately, there are no practical systems to assist clinicians or poison centres in predicting outcomes based on clinical features. Hence, the purpose of this study was to use a decision tree approach to inform early diagnosis of outcomes secondary to bupropion overdose. This study utilized a dataset from the National Poison Data System, a 6‐year retrospective cohort study on toxic exposures and patient outcomes. A machine learning algorithm (decision tree) was applied to the dataset using the sci‐kit‐learn library in Python. Shapley Additive exPlanations (SHAP) were used as an explainable method. Comparative analysis was performed using random forest (RF), Gradient Boosting classification, eXtreme Gradient Boosting, Light Gradient Boosting (LGM) and voting ensembling. ROC curve and precision–recall curve were used to analyse the performance of each model. LGM and RF demonstrated the highest performance to predict outcome of bupropion exposure. Multiple seizures, conduction disturbance, intentional exposure, and confusion were the most influential factors to predict the outcome of bupropion exposure. Coma and seizure, including single, multiple and status, were the most important factors to predict major outcomes. [ABSTRACT FROM AUTHOR]

Background: Diphenhydramine (DPH) is an antihistamine medication that in overdose can result in anticholinergic symptoms and serious complications, including arrhythmia and coma. We aimed to compare the value of various machine learning (ML) models, including light gradient boosting machine (LGBM), logistic regression (LR), and random forest (RF), in the outcome prediction of DPH poisoning. Materials and Methods: We used the National Poison Data System database and included all of the human exposures of DPH from January 01, 2017 to December 31, 2017, and excluded those cases with missing information, duplicated cases, and those who reported co-ingestion. Data were split into training and test datasets, and three ML models were compared. We developed confusion matrices for each, and standard performance metrics were calculated. Results: Our study population included 53,761 patients with DPH exposure. The most common reasons for exposure, outcome, chronicity of exposure, and formulation were captured. Our results showed that the average precision-recall area under the curve (AUC) of 0.84. LGBM and RF had the highest performance (average AUC of 0.91), followed by LR (average AUC of 0.90). The specificity of the models was 87.0% in the testing groups. The precision of models was 75.0%. Recall (sensitivity) of models ranged between 73% and 75% with an F1 score of 75.0%. The overall accuracy of LGBM, LR, and RF models in the test dataset was 74.8%, 74.0%, and 75.1%, respectively. In total, just 1.1% of patients (mostly those with major outcomes) received physostigmine. Conclusion: Our study demonstrates the application of ML in the prediction of DPH poisoning. [ABSTRACT FROM AUTHOR]

Aim: There is mounting evidence that eating habits affect sleeping patterns and their quality. The goal of this study was to evaluate the associations between major dietary patterns, identified using principal component analysis (PCA) and insomnia in young women. Methods: The study subjects comprised 159 healthy young women aged 18–25 years. Neuropsychological assessment was performed using standard instruments, including a cognitive ability questionnaire (CAQ), depression and anxiety stress scales (DASS‐21), insomnia severity index (ISI), Epworth sleepiness scale (ESS), and quality of life questionnaire (QLQ). Dietary patterns were obtained from a 65‐item validated food frequency questionnaire (FFQ) in this study, using PCA. Results: Two major dietary patterns were identified that were termed: "Traditional" and "Western." The Western pattern was characterized by a high intake of snacks, nuts, dairy products, tea, fast foods, chicken, and vegetable oils. Subjects with moderate/severe insomnia were found to have lower scores for total cognitive ability task, nocturnal sleep hours, and physical and mental health, but higher scores for depression, anxiety, stress, and daytime sleepiness compared to those without insomnia (p < 0.05). After adjustment for potential confounders, high adherence to the Western dietary pattern was associated with higher odds of insomnia (OR = 5.9; 95% confidence intervals: 1.9–18.7; p = 0.003). Conclusion: Our findings indicated adherence to Western pattern may increase the odds of insomnia. Prospective research is required to determine the feasibility of targeting dietary patterns to decrease the odds of insomnia. [ABSTRACT FROM AUTHOR]

The present study was designed to indicate the protective effects of curcumin on dyslipidemia. Main databases were searched to recognise randomised clinical trials evaluating the effect of curcumin on blood lipid profiles. The pooled odds ratio with a 95% confidence interval (CI) was used to evaluate the effect of curcumin on blood lipid parameters. HDL-C levels in the curcumin group were 0.04-fold lower than placebo (95% CI:−0.36–0.29; Z = 0.23; p =.82). LDL-C levels in the curcumin group reduced by 0.17 versus the placebo group (95% CI: −0.43–0.09; Z = 1.27; p =.2). TC levels in the curcumin group were 0.21 lower versus the placebo group (95% CI: −0.55–0.13; Z = 1.22; p =.22). TG level in the curcumin group were 0.05 lower versus the placebo (95% CI: −0.20–0.11; Z = 0.58; p =.56). This study suggests that curcumin may reduce blood lipid levels and can be used as a hypolipidemic agent. [ABSTRACT FROM AUTHOR]

The present systematic and meta-analysis study was designed to show the protective impact of saffron and crocin supplementation on hyperlipidaemia and hyperglycaemia in randomised and clinical trials (RCTs). A pooled analysis using a model for random-effects showed that HDL-C levels were 0.21 fold higher in the saffron and 0.01 fold higher in the crocin group than placebo. LDL-C levels in the saffron group reduced by 0.51 and 0.04 fold in the crocin group versus the placebo. Moreover, TC levels in the saffron group were 0.19 lower and 0.11 fold lower in crocin group than in the placebo group. TG level in saffron group was 0.04 lower and 0.02 fold lower in crocin than the control group. The blood glucose levels did not significantly differ from the control group. This study suggests that saffron and crocin may modulate the serum lipid profile in patient with metabolic disorders. [ABSTRACT FROM AUTHOR]

Acetaminophen is one of the most commonly used analgesic drugs in the United States. However, the outcomes of acute acetaminophen overdose might be very serious in some cases. Therefore, prediction of the outcomes of acute acetaminophen exposure is crucial. This study is a 6‐year retrospective cohort study using National Poison Data System (NPDS) data. A decision tree algorithm was used to determine the risk predictors of acetaminophen exposure. The decision tree model had an accuracy of 0.839, an accuracy of 0.836, a recall of 0.72, a specificity of 0.86 and an F1_score of 0.76 for the test group and an accuracy of 0.848, a recall of 0.85, a recall of 0.74, a specificity of 0.87 and an F1_score of 0.78 for the training group. Our results showed that elevated serum levels of liver enzymes, other liver function test abnormality, anorexia, acidosis, electrolyte abnormality, increased bilirubin, coagulopathy, abdominal pain, coma, increased anion gap, tachycardia and hypotension were the most important factors in determining the outcome of acute acetaminophen exposure. Therefore, the decision tree model is a reliable approach in determining the prognosis of acetaminophen exposure cases and can be used in an emergency room or during hospitalization. [ABSTRACT FROM AUTHOR]

Acetaminophen is a frequently used over-the-counter or prescribed medication in the United States. Exposure to acetaminophen can lead to acute liver cytolysis, acute liver failure, acute kidney injury, encephalopathy, and coagulopathy. This retrospective cohort study (1/1/2012 to 12/31/2017) investigated the clinical outcomes of intentional and unintentional acetaminophen exposure using the National Poison Data System data. The frequency of outcomes, chronicity, gender, route of exposure, the reasons for exposure, and treatments as described. Binary logistic regression was used to estimate the prognostic factors and odds ratios (OR) with 95% confidence intervals (CI) for outcomes. This study included 39,022 patients with acetaminophen exposure. Our study demonstrated that the likelihood of developing severe outcomes increased by aging (OR = 1.12, 95% CI: 1.08–1.015) and was lower in females (OR = 0.88, 95% CI: 0.78–0.99). Drowsiness/lethargy (OR = 1.48, 95% CI: 1.22–1.82), agitation (OR = 1.66, 95% CI: 1.11–2.50), coma (OR = 23.95, 95% CI: 17.05–33.64), bradycardia (OR = 2.29, 95% CI: 1.22–4.32), rhabdomyolysis (OR = 8.84, 95% CI: 3.71–21.03), hypothermia (OR = 4.1, 95% CI: 1.77–9.51), and hyperthermia 2.10 (OR = 2.10, 95% CI: 1.04–4.22) were likely associated with major outcomes or death. Treatments included intravenous N-acetylcysteine (61%), oral N-acetylcysteine (10%), vasopressor (1%), hemodialysis (0.7%), fomepizole (0.1%), hemoperfusion (0.03%), and liver transplant (0.1%). In conclusion, it is important to consider clinical presentations of patients with acetaminophen toxicity that result in major outcomes and mortality to treat them effectively. [ABSTRACT FROM AUTHOR]

Introduction: Our aim was to investigate and evaluate the influence of metformin on cancer-related biomarkers in clinical trials. Methods: This systematic study was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. Major databases, including Scopus, Web of Sciences, PubMed, Ovid-Medline, and Cochrane, were systematically reviewed by February 2020. Clinical trials investigating metformin effects on the evaluation of homeostatic models of insulin resistance (HOMA-IR), Ki-67, body mass index (BMI), fasting blood sugar (FBS), and insulin were selected for further analysis. Quality assessment was performed with version 2 of the Cochrane tool for determining the bias risk for randomized trials (RoB 2). Heterogeneity among the included studies was assessed using the Chi-square test. After quality assessment, a random effects model was performed to summarize the data related to insulin, HOMA-IR, Ki-67, and a fixed-effect model for FBS and BMI in a meta-analysis. Results: Nine clinical trials with 716 patients with operable breast and endometrial cancer and 331 with primary breast cancer were involved in the current systematic and meta-analysis study. Systematic findings on the nine publications indicated metformin decreased insulin levels in four studies, FBS in one, BMI in two, Ki-67 in three studies, and HOMA-IR in two study. The pooled analysis indicated that metformin had no significant effect on the following values: insulin (standardized mean differences (SMD) = −0.87, 95% confidence intervals (CI) (−1.93, 0.19), p = 0.11), FBS (SMD = −0.18, 95% CI (−0.30, −0.05), p = 0.004), HOMA-IR (SMD = −0.17, 95% CI (−0.52, 0.19), p = 0.36), and BMI (SMD = −0.13, 95% CI (−0.28, 0.02), p = 0.09). Metformin could decrease Ki-67 in patients with operable endometrial cancer versus healthy subjects (SMD = 0.47, 95% CI (−1.82, 2.75), p = 30.1). According to Egger’s test, no publication bias was observed for insulin, FBS, BMI, HOMA-IR, and Ki-67. Conclusions: Patients with operable breast and endometrial cancer under metformin therapy showed no significant changes in the investigated metabolic biomarkers in the most of included study. It was also found that metformin could decrease Ki-67 in patients with operable endometrial cancer. In comparison to the results obtained of our meta-analysis, due to the high heterogeneity and bias of the included clinical trials, the present findings could not confirm or reject the efficacy of metformin for patients with breast cancer and endometrial cancer. [ABSTRACT FROM AUTHOR]

Lead is one of the most toxic heavy metals in the environment. The present review aimed to highlight hazardous pollution sources, management, and review symptoms of lead poisonings in various parts of the world. The present study summarized the information available from case reports and case series studies from 2009 to March 2020 on the lead pollution sources and clinical symptoms. All are along with detoxification methods in infants, children, and adults. Our literature compilation includes results from 126 studies on lead poisoning. We found that traditional medication, occupational exposure, and substance abuse are as common as previously reported sources of lead exposure for children and adults. Ayurvedic medications and gunshot wounds have been identified as the most common source of exposure in the United States. However, opium and occupational exposure to the batteries were primarily seen in Iran and India. Furthermore, neurological, gastrointestinal, and hematological disorders were the most frequently occurring symptoms in lead-poisoned patients. As for therapeutic strategies, our findings confirm the safety and efficacy of chelating agents, even for infants. Our results suggest that treatment with chelating agents combined with the prevention of environmental exposure may be an excellent strategy to reduce the rate of lead poisoning. Besides, more clinical studies and long-term follow-ups are necessary to address all questions about lead poisoning management. • Ayurvedic medicines and gunshot injuries are common in the United States. • Opium and occupational exposure to the batteries are common in Iran and India. • Neurological, gastrointestinal, and hematological symptoms are frequent. • Chelating agents are safe and efficient in the treatment of lead poisoning. [ABSTRACT FROM AUTHOR]