Explainable artificial intelligence (XAI) for predicting the need for intubation in methanol-poisoned patients: a study comparing deep and machine learning models.

The need for intubation in methanol-poisoned patients, if not predicted in time, can lead to irreparable complications and even death. Artificial intelligence (AI) techniques like machine learning (ML) and deep learning (DL) greatly aid in accurately predicting intubation needs for methanol-poisoned patients. So, our study aims to assess Explainable Artificial Intelligence (XAI) for predicting intubation necessity in methanol-poisoned patients, comparing deep learning and machine learning models. This study analyzed a dataset of 897 patient records from Loghman Hakim Hospital in Tehran, Iran, encompassing cases of methanol poisoning, including those requiring intubation (202 cases) and those not requiring it (695 cases). Eight established ML (SVM, XGB, DT, RF) and DL (DNN, FNN, LSTM, CNN) models were used. Techniques such as tenfold cross-validation and hyperparameter tuning were applied to prevent overfitting. The study also focused on interpretability through SHAP and LIME methods. Model performance was evaluated based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior performance in accuracy (94.0%), sensitivity (99.0%), specificity (94.0%), and F1-score (97.0%). CNN led in ROC with 78.0%. For ML models, RF excelled in accuracy (97.0%) and specificity (100%), followed by XGB with sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%). Overall, RF and XGB outperformed other models, with accuracy (97.0%) and specificity (100%) for RF, and sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%) for XGB. ML models surpassed DL models across all metrics, with accuracies from 93.0% to 97.0% for DL and 93.0% to 99.0% for ML. Sensitivities ranged from 98.0% to 99.37% for DL and 93.0% to 99.0% for ML. DL models achieved specificities from 78.0% to 94.0%, while ML models ranged from 93.0% to 100%. F1-scores for DL were between 93.0% and 97.0%, and for ML between 96.0% and 98.27%. DL models scored ROC between 68.0% and 78.0%, while ML models ranged from 84.0% to 96.08%. Key features for predicting intubation necessity include GCS at admission, ICU admission, age, longer folic acid therapy duration, elevated BUN and AST levels, VBG_HCO3 at initial record, and hemodialysis presence. This study as the showcases XAI's effectiveness in predicting intubation necessity in methanol-poisoned patients. ML models, particularly RF and XGB, outperform DL counterparts, underscoring their potential for clinical decision-making.

Prediction of acute methanol poisoning prognosis using machine learning techniques.

Methanol poisoning is a global public health concern, especially prevalent in developing nations. This study focuses on predicting the severity of methanol intoxication using machine learning techniques, aiming to improve early identification and prognosis assessment. The study, conducted at Loghman Hakim Hospital in Tehran, Iran. The data pertaining to individuals afflicted with methanol poisoning was retrieved retrospectively and divided into training and test groups at a ratio of 70:30. The selected features were then inputted into various machine learning methods. The models were implemented using the Scikit-learn library in the Python programming language. Ultimately, the efficacy of the developed models was assessed through ten-fold cross-validation techniques and specific evaluation criteria, with a confidence level of 95%. A total number of 897 patients were included and divided in three groups including without sequel (n = 573), with sequel (n = 234), and patients who died (n = 90). The two-step feature selection was yielded 43 features in first step and 23 features in second step. In best model (Gradient Boosting Classifier) test dataset metric by 32 features younger age, higher methanol ingestion, respiratory symptoms, lower GCS scores, type of visual symptom, duration of therapeutic intervention, ICU admission, and elevated CPK levels were among the most important features predicting the prognosis of methanol poisoning. The Gradient Boosting Classifier demonstrated the highest predictive capability, achieving AUC values of 0.947 and 0.943 in the test dataset with 43 and 23 features, respectively. This research introduces a machine learning-driven prognostic model for methanol poisoning, demonstrating superior predictive capabilities compared to traditional statistical methods. The identified features provide valuable insights for early intervention and personalized treatment strategies.

Co-occurrence of celiac disease and glycogen storage disease in a five-year-old patient with diabetes mellitus; a case report.

A patient presented with edema, ascites and jaundice. Histologic report was consistent with Celiac Disease. Liver biopsy commensurate with Glycogen storage disease III, which was confirmed by genetic testing. A gluten-free diet was initiated. After 2 months, ascites was relieved, hepatic function was improved, and hepatic size reduced.

Evaluation of chest CT-scan appearances of COVID-19 according to RSNA classification system.

Background: The Radiologic Society of North America (RSNA) divides patients into four sections: negative, atypical, indeterminate, and typical coronavirus disease 2019 (COVID-19) pneumonia based on their computed tomography (CT) scan findings. Herein, we evaluate the frequency of the chest CT-scan appearances of COVID-19 according to each RSNA categorical group. Methods: A total of 90 patients with real-time reverse transcriptase-polymerase chain reaction (RT-PCR)-confirmed COVID-19 were enrolled in this study and differences in age, sex, cardiac characteristics, and imaging features of lung parenchyma were evaluated in different categories of RSNA classification. Results: According to the RSNA classification 87.8, 5.56, 4.44, and 2.22% of the patients were assigned as typical, indeterminate, atypical, and negative, respectively. The proportion of "atypical" patients was higher in the patients who had mediastinal lymphadenopathy and pleural effusion. Moreover, ground-glass opacity (GGO) and consolidation were more pronounced in the lower lobes and left lung compared to the upper lobes and right lung, respectively. While small nodules were mostly seen in the atypical group, small GGO was associated with the typical group, especially when it is present in the right lung and indeterminate group. Conclusion: Regardless of its location, non-round GGO is the most prevalent finding in the typical group of the RSNA classification systems. Mediastinal lymphadenopathy, pleural effusion, and small nodules are mostly observed in the atypical group and small GGO in the right lung is mostly seen in the typical group.

Neurological Manifestations and their Correlated Factors in COVID-19 Patients; a Cross-Sectional Study.

INTRODUCTION: COVID-19 might present with other seemingly unrelated manifestations; for instance, neurological symptoms. This study aimed to evaluate the neurologic manifestations and their correlated factors in COVID-19 patients. METHODS: This retrospective observational study was conducted from March 17, 2020 to June 20, 2020 in a tertiary hospital in Iran. The study population consisted of adult patients with a positive result for COVID-19 real-time reverse transcriptase polymerase chain reaction (RT-PCR) using nasopharyngeal swabs. Both written and electronic data regarding baseline characteristic, laboratory findings, and neurological manifestations were evaluated and reported. RESULTS: 727 COVID-19 patients with the mean age of 49.94 ± 17.49 years were studied (56.9% male). At least one neurological symptom was observed in 403 (55.4%) cases. Headache (29.0%), and smell (22.3%) and taste (22.0%) impairment were the most prevalent neurological symptoms, while seizure (1.1%) and stroke (2.3%) were the least common ones. Patients with neurological manifestations were significantly older (p = 0.04), had greater body mass index (BMI) (p = 0.02), longer first symptom to admission duration (p < 0.001) and were more frequently opium users (p = 0.03) compared to COVID-19 patients without neurological symptoms. O2 saturation was significantly lower in patients with neurological manifestations (p = 0.04). In addition, medians of neutrophil count (p = 0.006), neutrophil-lymphocyte ratio (NLR) (p = 0.02) and c-reactive protein (CRP) (p = 0.001) were significantly higher and the median of lymphocyte count (p = 0.03) was significantly lower in patients with neurological manifestations. CONCLUSION: The prevalence of neurological manifestations in the studied cases was high (55.4%). This prevalence was significantly higher in older age, grated BMI, longer lasting disease, and opium usage.

Electroosmotic flow in a water column surrounded by an immiscible liquid.

In this paper, we conducted numerical simulation of the electroosmotic flow in a column of an aqueous solution surrounded by an immiscible liquid. While governing equations in this case are the same as that in the electroosmotic flow through a microchannel with solid walls, the main difference is the types of interfacial boundary conditions. The effects of electric double layer (EDL) and surface charge (SC) are considered to apply the most realistic model for the velocity boundary condition at the interface of the two fluids. Effects on the flow field of ς-potential and viscosity ratio of the two fluids were investigated. Similar to the electroosmotic flow in microchannels, an approximately flat velocity profile exists in the aqueous solution. In the immiscible fluid phase, the velocity decreases to zero from the interface toward the immiscible fluid phase. The velocity in both phases increases with ς-potential at the interface of the two fluids. The higher values of ς-potential also increase the slip velocity at the interface of the two fluids. For the same applied electric field and the same ς-potential at the interface of the two fluids, the more viscous immiscible fluid, the slower the system moves. The viscosity of the immiscible fluid phase also affects the flatness of the velocity profile in the aqueous solution.