FlauBERT vs. CamemBERT: Understanding patient's answers by a French medical chatbot.

In a number of circumstances, obtaining health-related information from a patient is time-consuming, whereas a chatbot interacting efficiently with that patient might help saving health care professional time and better assisting the patient. Making a chatbot understand patients' answers uses Natural Language Understanding (NLU) technology that relies on 'intent' and 'slot' predictions. Over the last few years, language models (such as BERT) pre-trained on huge amounts of data achieved state-of-the-art intent and slot predictions by connecting a neural network architecture (e.

Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models.

Background And Objective: Machine learning and deep learning models are very powerful in predicting the presence of a disease. To achieve good predictions, those models require a certain amount of data to train on, whereas this amount i) is generally limited and difficult to obtain; and, ii) increases with the complexity of the interactions between the outcome (disease presence) and the model variables. This study compares the ways training dataset size and interactions affect the performance of those prediction models.

Accelerated Hepatitis A and B Immunization in a Substance Abuse Treatment Program.

An accelerated dosing program for hepatitis A and B vaccination among veterans receiving treatment for addictive disorders was successfully implemented, although many veterans with hepatitis C did not complete the immunization series.

Housing assistance and case management: improving access to substance use disorder treatment for homeless veterans.

The problem of waiting list attrition in addiction treatment programs is widespread, and homeless and marginally housed individuals are particularly susceptible. This naturalistic, retrospective study describes an intervention (Transitional Supportive Housing and Case Management) that effectively promoted treatment admission for this high-risk group above and beyond that which could be explained by certain pretreatment factors. The clinical records of 211 military veterans referred to intensive outpatient addiction treatment were reviewed for factors related to treatment program admission, including 3 interventions designed to prevent waiting list attrition.

Propylhexedrine: a vintage drug of abuse, rediscovered.

In 1949, propylhexedrine replaced amphetamine sulfate as the active ingredient in over the counter Benzedrex due to reports of widespread abuse, psychosis and sudden death. Since its introduction, cases of psychosis, myocardial infarction, pulmonary vascular disease, pulmonary hypertension, and sudden death attributed to propylhexedrine abuse have been well documented, usually in the form of single case reports. Although growing concerns during the 1980's regarding its abuse potential and its use as a precursor in the manufacture of compounds of even higher abuse potential caused propylhexedrine to be reviewed by the WHO Expert Committee on Drug Dependence, no formal studies of the dependence potential of propylhexedrine exists to date.

Managing acute and chronic pain in a substance abuse treatment program for the addicted individual early in recovery: a current controversy.

Patients early in recovery from addictive disorders are in a tenuous position and when these individuals are stressed from acute or chronic pain they face even more challenges. Physicians are often conflicted by the desire to help the patient achieve pain control and maintain sobriety. While there have been a handful of studies examining patients in either active addiction with pain or with a more remote history of addiction with pain, there have been very few, if any, that look at treating patients during their addiction recovery process who suffer from pain.

Effects of magnesium sulfate in kainic acid-induced status epilepticus.

Because magnesium has antiseizure effects in some animal models of epilepsy, and possible neuroprotective effects in some models of neuronal injury, we aimed to investigate its effects in the kainic acid (KA) model of status epilepticus (SE) in prepubescent rats. This age was chosen because it is a common age for onset of epilepsy and of SE in humans. Three groups of P35 rats were studied: Group I (MgKA) received magnesium sulfate MgSO4 (270 mg/kg then 27 mg/kg every 20 minutes for 5 hours) and 10 mg/kg KA.

Effects of creatine and cyclocreatine supplementation on kainate induced injury in pre-pubescent rats.

Purpose: To investigate if energy precursor supplementation is neuroprotective in two neuroexcitotoxicity models; the kainate and the kainate followed by chronic phenobarbital models.

Methods: Rats in experiment 1 received 1% creatine or cyclocreatine chow from age (P) 21-65 days, underwent kainate induced status epilepticus on P35 and were compared, as adults, to kainate alone rats and to normal controls. Rats in experiment 2 received 1% creatine chow (P21-P85), underwent kainate status epilepticus on P35, received daily phenobarbital (or saline) injections (P36-P85) and were compared, as adults, to kainate, kainate-phenobarbital and to normal control rats that received regular chow.