Azathioprine and hydroxychloroquine overdose in Sjögren's syndrome patient with hypocalcemia: a case report.

INTRODUCTION: Hydroxychloroquine and azathioprine have been routinely used to control and treat primary and secondary Sjögren's syndrome, which potentially triggered some overdoses by these drugs. Toxicity from hydroxychloroquine and azathioprine manifests in the form of cardiac conduction abnormalities, nausea, vomiting, and muscle weakness. Recognizing these unique drug overdoses and management of these toxicities is important. This case report aims to expand our current understanding of these drug overdoses and their management and also underscores the importance of anticipating and identifying fewer common complications, such as hypocalcemia. CASE REPORT: A 34-year-old Persian woman with a history of Sjögren's syndrome presented to the emergency department 3.5-4 hours after an intentional overdose of hydroxychloroquine and azathioprine and severe hypotension and loss of consciousness. Although the patient was regularly taking other medications, such as fluoxetine, naproxen, and prednisolone, she explicitly clarified that these were not the substances involved in her overdose. Early investigations showed hypokalemia (2.4 mEq/L), hypocalcemia (7.5 mg/dL), and hypoglycemia (65 mg/dL). She was also diagnosed with metabolic acidosis and respiratory alkalosis. The electrocardiogram showed changes in favor of hypokalemia; other lab tests were run on the patient. Supportive treatments were applied, including rapid intravenous fluid dextrose 5%, normal saline, potassium chloride 30 mEq, and calcium gluconate 100 mg. The patient was managed and monitored overnight in the emergency room and recovered without residual side effects. CONCLUSION: Hydroxychloroquine and azathioprine toxicity are considered rare, but it is likely to increase in frequency given the prevalence and increase in autoimmune diseases and the increasing usage of these drugs in treating such diseases. We found hypocalcemia as the presentation to this patient, which needs further investigation into the probable mechanism. Clinicians need to consider the unique effects of hydroxychloroquine and azathioprine poisoning and initiate appropriate emergency interventions to improve the outcomes in similar patients.

Cinnamon and cognitive function: a systematic review of preclinical and clinical studies.

Cinnamon is the inner bark of trees named Cinnamomum. Studies have shown that cinnamon and its bioactive compounds can influence brain function and affect behavioral characteristics. This study aimed to systematically review studies about the relationship between cinnamon and its key components in memory and learning. Two thousand six hundred five studies were collected from different databases (PubMed, Scopus, Google Scholar, and Web of Science) in September 2021 and went under investigation for eligibility. As a result, 40 studies met our criteria and were included in this systematic review. Among the included studies, 33 were In vivo studies, five were In vitro, and two clinical studies were also accomplished. The main outcome of most studies (n = 40) proved that cinnamon significantly improves cognitive function (memory and learning). In vivo studies showed that using cinnamon or its components, such as eugenol, cinnamaldehyde, and cinnamic acid, could positively alter cognitive function. In vitro studies also showed that adding cinnamon or cinnamaldehyde to a cell medium can reduce tau aggregation, Amyloid ß and increase cell viability. For clinical studies, one study showed positive effects, and another reported no changes in cognitive function. Most studies reported that cinnamon might be useful for preventing and reducing cognitive function impairment. It can be used as an adjuvant in the treatment of related diseases. However, more studies need to be done on this subject.

Clinical and pharmacokinetics overview of intranasal administration of fentanyl.

Due to the presence of large surfaces and high blood supply, drug delivery through the nasal route of administration is the appropriate route to administrate drugs with rapid onsets of action. Bypassing first-pass metabolism can increase drug bioavailability. The physicochemical properties of fentanyl led to a need to develop formulations for delivery by multiple routes. Several approved inter-nasal fentanyl products in Europe and the USA have been used in prehospital and emergency departments to treat chronic cancer pain and used to treat severe acute abdominal and flank pain. Analgesia durations and onsets were not significantly different between intranasal and intravenous fentanyl in patients with cancer breakthrough pain and were well-tolerated in the long term. Intranasal Fentanyl (INF) at a 50 µg/ml concentration decreased renal colic pain to the lowest level in 30 min. Possible adverse effects specific to INF are epistaxis, nasal wall ulcer, rhinorrhea, throat irritation, dysgeusia, nausea, and vomiting. However, there is limited available literature about the serious adverse effects of INF in adults and children. Intranasal Fentanyl Spray (INFS) results in significantly higher plasma concentrations and has a lower Tmax than oral transmucosal formulation, and the bioavailability of fentanyl in intranasal formulations is very high (89 %), particularly in pectin-containing formulations such as PecFent and Lazanda.

Outcome prediction of methadone poisoning in the United States: implications of machine learning in the National Poison Data System (NPDS).

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.

Identify successful restrictions in suppressing the early outbreak of COVID-19 in Arizona, United States: Interrupted time series analysis.

COVID-19 was responsible for many deaths and economic losses around the globe since its first case report. Governments implemented a variety of policies to combat the pandemic in order to protect their citizens and save lives. Early in 2020, the first cases were reported in Arizona State and continued to rise until the discovery of the vaccine in 2021. A variety of strategies and interventions to stop or decelerate the spread of the pandemic has been considered. It is recommended to define which strategy was successful for disease propagation prevention and could be used in further similar situations. This study aimed to evaluate the effect of people's contact interventions strategies which were implemented in Arizona State and their effect on reducing the daily new COVID-19 cases and deaths. Their effect on daily COVID-19 cases and deaths were evaluated using an interrupted time series analysis during the pandemic's first peaks to better understand the onward situation. Canceling the order of staying at home (95% CI, 1718.52 to 6218.79; p<0.001) and expiring large gatherings (95% CI, 1984.99 to 7060.26; p<0.001) on June 30 and August 17, 2020, respectively, had a significant effect on the pandemic, leading to the daily cases to grow rapidly. Moreover, canceling the stay at home orders led to an increase in the number of COVID-19 daily deaths by 67.68 cases (95% CI, 27.96 to 107.40; p<0.001) after about 21 days while prohibiting large gatherings significantly decreased 66.76 (95% CI: 20.56 to 112.96; p = 0.004) the number of daily deaths with about 21 days' lag. The results showed that strategies aimed at reducing people's contact with one another could successfully help fight the pandemic. Findings from this study provide important evidence to support state-level policies that require observance of social distancing by the general public for future pandemics.

Deep learning neural network derivation and testing to distinguish acute poisonings.

INTRODUCTION: Acute poisoning is a significant global health burden, and the causative agent is often unclear. The primary aim of this pilot study was to develop a deep learning algorithm that predicts the most probable agent a poisoned patient was exposed to from a pre-specified list of drugs. RESEARCH DESIGN & METHODS: Data were queried from the National Poison Data System (NPDS) from 2014 through 2018 for eight single-agent poisonings (acetaminophen, diphenhydramine, aspirin, calcium channel blockers, sulfonylureas, benzodiazepines, bupropion, and lithium). Two Deep Neural Networks (PyTorch and Keras) designed for multi-class classification tasks were applied. RESULTS: There were 201,031 single-agent poisonings included in the analysis. For distinguishing among selected poisonings, PyTorch model had specificity of 97%, accuracy of 83%, precision of 83%, recall of 83%, and a F1-score of 82%. Keras had specificity of 98%, accuracy of 83%, precision of 84%, recall of 83%, and a F1-score of 83%. The best performance was achieved in the diagnosis of single-agent poisoning in diagnosing poisoning by lithium, sulfonylureas, diphenhydramine, calcium channel blockers, then acetaminophen, in PyTorch (F1-score = 99%, 94%, 85%, 83%, and 82%, respectively) and Keras (F1-score = 99%, 94%, 86%, 82%, and 82%, respectively). CONCLUSION: Deep neural networks can potentially help in distinguishing the causative agent of acute poisoning. This study used a small list of drugs, with polysubstance ingestions excluded.Reproducible source code and results can be obtained at https://github.com/ashiskb/npds-workspace.git.

The value of machine learning for prognosis prediction of diphenhydramine exposure: National analysis of 50,000 patients in the United States.

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.

Using a decision tree algorithm to distinguish between repeated supra-therapeutic and acute acetaminophen exposures.

BACKGROUND: This study aimed to compare clinical and laboratory characteristics of supra-therapeutic (RSTI) and acute acetaminophen exposures using a predictive decision tree (DT) algorithm. METHODS: We conducted a retrospective cohort study using the National Poison Data System (NPDS). All patients with RSTI acetaminophen exposure (n = 4,522) between January 2012 and December 2017 were included. Additionally, 4,522 randomly selected acute acetaminophen ingestion cases were included. After that, the DT machine learning algorithm was applied to differentiate acute acetaminophen exposure from supratherapeutic exposures. RESULTS: The DT model had accuracy, precision, recall, and F1-scores of 0.75, respectively. Age was the most relevant variable in predicting the type of acetaminophen exposure, whether RSTI or acute. Serum aminotransferase concentrations, abdominal pain, drowsiness/lethargy, and nausea/vomiting were the other most important factors distinguishing between RST and acute acetaminophen exposure. CONCLUSION: DT models can potentially aid in distinguishing between acute and RSTI of acetaminophen. Further validation is needed to assess the clinical utility of this model.

Medically important snakes and snakebite envenoming in Iran.

Snakebite is a relatively common health condition in Iran with a diverse snake fauna, especially in tropical southern and mountainous western areas of the country with a plethora of snake species. The list of medically important snakes, circumstances and effects of their bite, and necessary medical care require critical appraisal and should be updated regularly. This study aims to review and map the distributions of medically important snake species of Iran, re-evaluate their taxonomy, review their venomics, describe the clinical effects of envenoming, and discuss medical management and treatment, including the use of antivenom. Nearly 350 published articles and 26 textbooks with information on venomous and mildly venomous snake species and snakebites of Iran, were reviewed, many in Persian (Farsi) language, making them relatively inaccessible to an international readership. This has resulted in a revised updated list of Iran's medically important snake species, with taxonomic revisions of some, compilation of their morphological features, remapping of their geographical distributions, and description of species-specific clinical effects of envenoming. Moreover, the antivenom manufactured in Iran is discussed, together with treatment protocols that have been developed for the hospital management of envenomed patients.

Differences in clinical and lab characteristics of sepsis between opium user patients and patients with no illicit drug addiction.

BACKGROUND: Sepsis is a significant cause of mortality worldwide. This study aimed to compare clinical and laboratory characteristics of sepsis in patients addicted to illicit drugs versus patients with no illicit drug addiction. METHODS: In this cross-sectional study, all patients hospitalized with sepsis diagnosis were recruited within six months from September to March 2019. Sixty patients for each group (illicit drug-addicted and non-addicted individuals) were selected. The data relating to illicit drug consumption, serum indices, the current focus of infection, duration of hospitalization, and disease outcomes were collected. Patients who had an illicit drug addiction were compared with non-addicted patients in terms of clinical and laboratory parameters. The data collected were analyzed using SPSS software (version 19). RESULTS: The bacterial load in the urine culture was statistically significant in both groups and higher in the non-addicted group. The frequency distributions of focus of infection, duration of hospitalization, and outcome were not significantly different between the two groups. The serum sodium and total neutrophils were significantly higher in the addicted group. However, the MCHC level was significantly lower (p<0.05). CONCLUSION: Opium may have stimulated the immune system and reduced bacterial infection in septic patient users.

Comparison of decision tree with common machine learning models for prediction of biguanide and sulfonylurea poisoning in the United States: an analysis of the National Poison Data System.

BACKGROUND: Biguanides and sulfonylurea are two classes of anti-diabetic medications that have commonly been prescribed all around the world. Diagnosis of biguanide and sulfonylurea exposures is based on history taking and physical examination; thus, physicians might misdiagnose these two different clinical settings. We aimed to conduct a study to develop a model based on decision tree analysis to help physicians better diagnose these poisoning cases. METHODS: The National Poison Data System was used for this six-year retrospective cohort study.The decision tree model, common machine learning models multi layers perceptron, stochastic gradient descent (SGD), Adaboosting classiefier, linear support vector machine and ensembling methods including bagging, voting and stacking methods were used. The confusion matrix, precision, recall, specificity, f1-score, and accuracy were reported to evaluate the model's performance. RESULTS: Of 6183 participants, 3336 patients (54.0%) were identified as biguanides exposures, and the remaining were those with sulfonylureas exposures. The decision tree model showed that the most important clinical findings defining biguanide and sulfonylurea exposures were hypoglycemia, abdominal pain, acidosis, diaphoresis, tremor, vomiting, diarrhea, age, and reasons for exposure. The specificity, precision, recall, f1-score, and accuracy of all models were greater than 86%, 89%, 88%, and 88%, respectively. The lowest values belong to SGD model. The decision tree model has a sensitivity (recall) of 93.3%, specificity of 92.8%, precision of 93.4%, f1_score of 93.3%, and accuracy of 93.3%. CONCLUSION: Our results indicated that machine learning methods including decision tree and ensembling methods provide a precise prediction model to diagnose biguanides and sulfonylureas exposure.

The Impact of Metabolic Syndrome on the Prognosis of High-Risk Alcoholic Hepatitis Patients: Redefining Alcoholic Hepatitis.

Background: Alcoholic hepatitis (AH) is characterized by acute symptomatic hepatitis associated with heavy alcohol use. This study was designed to assess the impact of metabolic syndrome on high-risk patients with AH with discriminant function (DF) score ≥ 32 and its effect on mortality. Methods: We searched the hospital database for ICD-9 diagnosis codes of acute AH, alcoholic liver cirrhosis, and alcoholic liver damage. The entire cohort was categorized into two groups: AH and AH with metabolic syndrome. The effect of metabolic syndrome on mortality was evaluated. Also, an exploratory analysis was used to create a novel risk measure score to assess mortality. Results: A large proportion (75.5%) of the patients identified in the database who had been treated as AH had other etiologies and did not meet the American College of Gastroenterology (ACG)-defined diagnosis of acute AH, thus had been misdiagnosed as AH. Such patients were excluded from analysis. The mean body mass index (BMI), hemoglobin (Hb), hematocrit (HCT), and alcoholic liver disease/non-alcoholic fatty liver disease index (ANI) were significantly different between two groups (P < 0.05). The results of a univariate Cox regression model showed that age, BMI, white blood cells (WBCs), creatinine (Cr), international normalized ratio (INR), prothrombin time (PT), albumin levels, albumin < 3.5, total bilirubin, Na, Child-Turcotte-Pugh (CTP), model for end-stage liver disease (MELD), MELD ≥ 21, MELD ≥ 18, DF score, and DF ≥ 32 had a significant effect on mortality. Patients with a MELD greater than 21 had a hazard ratio (HR) (95% confidence interval (CI) of 5.81 (2.74 - 12.30) (P < 0.001). The adjusted Cox regression model results showed that age, Hb, Cr, INR, Na, MELD score, DF score, and metabolic syndrome were independently associated with high patient mortality. However, the increase in BMI and mean corpuscular volume (MCV) and sodium significantly reduced the risk of death. We found that a model including age, MELD ≥ 21, and albumin < 3.5 was the best model in identifying patient mortality. Our study showed that patients admitted with a diagnosis of alcoholic liver disease with metabolic syndrome had an increased mortality risk compared to patients without metabolic syndrome, in high-risk patients with DF ≥ 32 and MELD ≥ 21. A bivariate correlation analysis revealed that patients with AH with metabolic syndrome were more likely to have infection (43%) compared to AH (26%) with correlation coefficient of 0.176 (P = 0.03, CI: 0.018 - 1.0). Conclusion: In clinical practice, the diagnosis of AH is inaccurately applied. Metabolic syndrome significantly increases the mortality risk in high-risk AH. It signifies that the presence of features of metabolic syndrome modifies the behavior of AH in acute settings, warranting different therapeutic strategies. We propose that in defining AH, patients overlapping with metabolic syndrome may need to be excluded as their outcome is different with regard to risk of renal dysfunctions, infections and death.

The role of decision tree and machine learning models for outcome prediction of bupropion exposure: A nationwide analysis of more than 14 000 patients in the United States.

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.

Utility of artificial intelligence to identify antihyperglycemic agents poisoning in the USA: introducing a practical web application using National Poison Data System (NPDS).

Clinical effects of antihyperglycemic agents poisoning may overlap each other. So, distinguishing exposure to these pharmaceutical drugs may take work. This study examined the application of machine learning techniques in identifying antihyperglycemic agent exposure using the national poisoning database in the USA. In this study, the data of single exposure due to Biguanides and Sulfonylureas (n=6183) was requested from the National Poison Data System (NPDS) for 2014-2018. We have tried five machine learning models (random forest classifier, k-nearest neighbors, Xgboost classifier, logistic regression, neural network Keras). For the multiclass classification modeling, we have divided the dataset into two parts: train (75%) and test (25%). The performance metrics used were accuracy, specificity, precision, recall, and F1-score. The algorithms used to get the classification results of different models to diagnose antihyperglycemic agents were very accurate. The accuracy of our model in determining these two antihyperglycemic agents was 91-93%. The precision-recall curve showed average precision of 0.91, 0.97, 0.97, and 0.98 for k-nearest neighbors, logistic regression, random forest, and XGB, respectively. The logistic regression, random forest, and XGB had the highest AUC (AUC=0.97) among both biguanides and sulfonylureas groups. The negative predictive values (NPV) for all the models were between 89 and 93%. We introduced a practical web application to help physicians distinguish between these agents. Despite variations in accuracy among the different types of algorithms used, all of them could accurately determine the specific exposure to biguanides and sulfonylureas retrospectively. Machine learning can distinguish antihyperglycemic agents, which may be useful for physicians without any background in medical toxicology. Besides, Our suggested ML-based Web application might help physicians in their diagnosis.

Pharmaceutical toxicity is a common pattern of inpatient acute poisonings in Birjand City, East of Iran.

Information on the pattern of acute poisonings in hospitals of Birjand city, Iran, is limited. This study aimed to address this knowledge gap by examining the admissions in a major poisoning center in eastern Iran. This cross-sectional study included patients admitted to the Imam Reza Hospital in Birjand over 12 months. Medical records of the poisoned patients were reviewed, and the study variables were used for data analysis. During the study period, 534 cases of acute poisonings were evaluated. The patient's ages ranged from 12 to 84 years, with a high rate of poisonings between 15 and 35 years. The female predominance in poisoning cases was 52.1%. Most cases of poisonings occurred in spring, and the common route of exposure was oral (93.1%). The incidence of poisoning in married couples, uneducated patients, and residents of urban areas was 56.5%, 90.1%, and 74.6%, respectively. Patients with a previous medical history experienced addiction and psychiatric disorders. Intentional poisoning accounted for 23.4% of acute poisoning cases referred to the hospital in the current study. The main groups of toxicants were pharmaceutical products (48.1%), narcotics (25.8%), chemical products (10.1%), envenomation (7.1%), and alcohol (1.7%). The mean hospital stay was 2.5 ± 3.0 days, and the final treatment outcome was complete recovery, except for one patient intoxicated by warfarin and alprazolam. Our results indicate that the high toxicity cases were related to pharmaceutical product and opioids abuse, especially methadone (8.4%), alprazolam (7.9%), clonazepam (7.5%), and acetaminophen (9.9%) taken orally and more commonly happened at home. Due to the high rate of deliberate poisonings, especially among young adults and students, monitoring drug distribution and exceptional attention to mental health should be seriously considered by national health authorities to prevent suicide attempts.

Decision tree algorithm can determine the outcome of repeated supratherapeutic ingestion (RSTI) exposure to acetaminophen: review of 4500 national poison data system cases.

This study is aimed at establishing the outcome of RSTI exposure to acetaminophen based on a decision tree algorithm for the first time. This study used the National Poison Data System (NPDS) to conduct a six-year retrospective cohort analysis, which included 4522 individuals. The patients had a mean age of 26.75 ± 16.3 years (1-89). 3160 patients (70%) were females. Most patients had intentional exposure to acetaminophen. Almost all the patients had acetaminophen exposure via ingestion. In addition, 400 (8.8%) experienced major outcomes, 1500 (33.2%) experienced moderate outcomes, and 2622 (58%) of the patients experienced mild ones. The decision tree model performed well in the training and test groups. In the test group, the accuracy was 0.813, precision of 0.827, recall being 0.798, specificity 0.898, and an F1 score 0.80. In the training group, accuracy was 0.831, recall was 0.825, precision was 0.837, specificity was 0.90, and F1 score was 0.829. Our results showed that serum liver enzymes being present at elevated levels (Alanine aminotransferase (ALT), Aspartate aminotransferase (AST) greater than 1000 U/L followed by ALT, AST between 100 and 1000 U/L), prothrombin time (PT) prolongation, bilirubin increase, renal failure, confusion, age, hypotension, other coagulopathy (such as partial thromboplastin time (PTT) prolongation), acidosis, and electrolyte abnormality were the effective factors in determining the outcomes in these patients. The decision tree algorithm is a dependable method for establishing the prognosis of patients who have been exposed to RSTI acetaminophen and can be used throughout the patients' hospitalization period.

How much natural ventilation rate can suppress COVID-19 transmission in occupancy zones?

Background: Previous research has emphasized the importance of efficient ventilation in suppressing COVID-19 transmission in indoor spaces, yet suitable ventilation rates have not been suggested. Materials and Methods: This study investigated the impacts of mechanical, natural, single-sided, cross-ventilation, and three mask types (homemade, surgical, N95) on COVID-19 spread across eight common indoor settings. Viral exposure was quantified using a mass balance calculation of inhaled viral particles, accounting for initial viral load, removal via ventilation, and mask filtration efficiency. Results: Results demonstrated that natural cross-ventilation significantly reduced viral load, decreasing from 10,000 to 0 viruses over 15 minutes in a 100 m2 space by providing ~1325 m3/h of outdoor air via two 0.6 m2 openings at 1.5 m/s wind speed. In contrast, single-sided ventilation only halved viral load at best. Conclusion: Natural cross-ventilation with masks effectively suppressed airborne viruses, lowering potential infections and disease transmission. The study recommends suitable ventilation rates to reduce COVID-19 infection risks in indoor spaces.

Classification of acute poisoning exposures with machine learning models derived from the National Poison Data System.

The primary aim of this pilot study was to develop a machine learning algorithm to predict and distinguish eight poisoning agents based on clinical symptoms. Data were used from the National Poison Data System from 2014 to 2018, for patients 0-89 years old with single-agent exposure to eight drugs or drug classes (acetaminophen, aspirin, benzodiazepines, bupropion, calcium channel blockers, diphenhydramine, lithium and sulfonylureas). Four classifier prediction models were applied to the data: logistic regression, LightGBM, XGBoost, and CatBoost. There were 201 031 cases used to develop and test the algorithms. Among the four models, accuracy ranged 77%-80%, with precision and F1 scores of 76%-80% and recall of 77%-78%. Overall specificity was 92% for all models. Accuracy was highest for identifying sulfonylureas, acetaminophen, benzodiazepines and diphenhydramine poisoning. F1 scores were highest for correctly classifying sulfonylureas, acetaminophen and benzodiazepine poisonings. Recall was highest for sulfonylureas, acetaminophen, and benzodiazepines, and lowest for bupropion. Specificity was >99% for models of sulfonylureas, calcium channel blockers, lithium and aspirin. For single-agent poisoning cases among the eight possible exposures, machine learning models based on clinical signs and symptoms moderately predicted the causal agent. CatBoost and LightGBM classifier models had the highest performance of those tested.