Developing a novel prediction model in opioid overdose using machine learning; a pilot analytical study.

Background and Aims: The opioid epidemic has extended to many countries. Data regarding the accuracy of conventional prediction models including the Simplified Acute Physiologic Score (SAPS) II and acute physiology and chronic health evaluation (APACHE) II are scarce in opioid overdose cases. We evaluate the efficacy of adding quantitative electroencephalogram (qEEG) data to clinical and paraclinical data in the prediction of opioid overdose mortality using machine learning. Methods: In a prospective study, we collected clinical/paraclinical, and qEEG data of 32 opioid-poisoned patients. After preprocessing and Fast Fourier Transform analysis, absolute power was computed. Also, SAPS II was calculated. Eventually, data analysis was performed using SAPS II as a benchmark at three levels to predict the patient's course in comparison with SAPS II. First, the qEEG data set was used alone, secondly, the combination of the clinical/paraclinical, SAPS II, qEEG datasets, and the SAPS II-based model was included in the pool of classifier models. Results: Seven out of 32 (22%) died. SAPS II (cut-off of 50.5) had a sensitivity/specificity/positive/negative predictive values of 85.7%, 84.0%, 60.0%, and 95.5% in predicting mortality, respectively. Adding majority voting on random forest with qEEG and clinical data, improved the model sensitivity, specificity, and positive and negative predictive values to 71.4%, 96%, 83.3%, and 92.3% (not significant). The model fusion level has 40% less prediction error. Conclusion: Considering the higher specificity and negative predictive value in our proposed model, it could predict survival much better than mortality. The model would constitute an indicator for better care of opioid poisoned patients in low resources settings, where intensive care unit beds are limited.

Investigation of ischemic and demyelinating lesions by cerebral vasoreactivity based on transcranial Doppler sonography: a comparative study.

PURPOSE: Variations of cerebral blood flow in response to hypoxia and hyperoxia in different disease conditions can provide new insights into disease etiopathogenesis. This study aimed to determine the characteristics of cerebral vasoreactivity for ischemia and demyelination. MATERIALS AND METHODS: This case-control study included: 28 patients with lacunar infarctions verified by history, physical examination, and MRI; 28 age- and sex-matched healthy controls; 28 patients with relapsing-remitting multiple sclerosis (MS), based on McDonald criteria; and 28 age- and sex-matched healthy controls for the MS group. Transcranial Doppler sonography was undertaken in all subjects to calculate the mean flow velocity (MFV) of the right middle cerebral artery (MCA) and, after a breath-holding (BH) maneuver, the breath-holding index (BHI) was determined. RESULTS: There was no significant difference of BHI and changes of MFV of the MCA in MS patients compared to controls (1.02 ± 0.4 vs 1.02 ± 0.3, p = 0.993; and 16.8 ± 8.1 vs 11.3 ± 10.8, p = 0.057). BHI in patients with lacunar infarctions was significantly lower (0.8 ± 0.4 vs 1.2 ± 0.3, p < 0.001) compared to controls. The BHI (p = 0.040) and variations of MFV of MCA (p = 0.007) in MS patients were significantly higher than in patients with lacunar infarctions. The vasoreactivity of demyelinating lesions was higher than that of ischemic ones. CONCLUSION: Therefore, cerebral vasoreactivity determined by transcranial Doppler could be utilized for differentiating demyelinating from ischemic lesions.

The role of NMDA receptor and nitric oxide/cyclic guanosine monophosphate pathway in the antidepressant-like effect of dextromethorphan in mice forced swimming test and tail suspension test.

Depression is a devastating disorder which has a high impact on the wellbeing of overall society. As such, need for innovative therapeutic agents are always there. Most of the researchers focused on N-methyl-d-aspartate receptor to explore the antidepressant like activity of new therapeutic agents. Dextromethorphan is a cough suppressant agent with potential antidepressant activity reported in mouse force swimming test. Considering N-methyl-d-aspartate as a forefront in exploring antidepressant agents, here we focused to unpin the antidepressant mechanism of dextromethorphan targeting N-methyl-d-aspartate receptor induced nitric oxide-cyclic guanosine monophosphate signaling. Dextromethorphan administered at a dose of 10 and 30mg/kg i.p significantly reduced the immobility time. Interestingly, this effect of drug (30mg/kg) was inhibited when the animals were pretreated either with N-methyl-d-aspartate (75mg/kg), or l-arginine (750mg/kg) as a nitric oxide precursor and/or sildenafil (5mg/kg) as a phosphodiesterase 5 inhibitor. However, the antidepressant effect of Dextromethorphan subeffective dose (3mg/kg) was augmented when the animals were administered with either L-NG-Nitroarginine methyl ester (10mg/kg) non-specific nitric oxide synthase inhibitor, 7-Nitroindazole (30mg/kg) specific neural nitric oxide synthase inhibitor, MK-801 (0.05mg/kg) an N-methyl-d-aspartate receptor antagonist but not aminoguanidine (50mg/kg) which is specific inducible nitric oxide synthase inhibitor as compared to the drugs when administered alone. No remarkable effect on locomotor activity was observed during open field test when the drugs were administered at the above mentioned doses. Therefore, it is evident that the antidepressant like effect of Dextromethorphan is owed due to its inhibitory effect on N-methyl-d-aspartate receptor and NO- Cyclic guanosine monophosphate pathway.