Time series causal relationships discovery through feature importance and ensemble models.

Inferring causal relationships from observational data is a key challenge in understanding the interpretability of Machine Learning models. Given the ever-increasing amount of observational data available in many areas, Machine Learning algorithms used for forecasting have become more complex, leading to a less understandable path of how a decision is made by the model. To address this issue, we propose leveraging ensemble models, e.g., Random Forest, to assess which input features the trained model prioritizes when making a forecast and, in this way, establish causal relationships between the variables. The advantage of these algorithms lies in their ability to provide feature importance, which allows us to build the causal network. We present our methodology to estimate causality in time series from oil field production. As it is difficult to extract causal relations from a real field, we also included a synthetic oil production dataset and a weather dataset, which is also synthetic, to provide the ground truth. We aim to perform causal discovery, i.e., establish the existing connections between the variables in each dataset. Through an iterative process of improving the forecasting of a target's value, we evaluate whether the forecasting improves by adding information from a new potential driver; if so, we state that the driver causally affects the target. On the oil field-related datasets, our causal analysis results agree with the interwell connections already confirmed by tracer information; whenever the tracer data are available, we used it as our ground truth. This consistency between both estimated and confirmed connections provides us the confidence about the effectiveness of our proposed methodology. To our knowledge, this is the first time causal analysis using solely production data is employed to discover interwell connections in an oil field dataset.

Relación del malestar emocional y el consumo de alcohol en adolescentes / Relationship of emotional distress and alcohol consumption in adolescents / Relação do sofrimento emocional e o consumo de álcool em adolescentes

Objetivo: determinar la relación y el efecto del malestar emocional en el consumo de alcohol de los adolescentes. Método: estudio cuantitativo transversal, descriptivo y predictivo, llevado a cabo en 200 adolescentes de ambos sexos de una institución pública de educación secundaria de Ciudad del Carmen Campeche, México; durante el mes enero de 2018. Se utilizó una cedula de datos sociodemográficos y antecedentes del consumo de alcohol y el Cuestionario de Factores de Riesgo y de Protección para el Consumo de Drogas. Los datos se procesaron en el programa SPSS a través de la estadística descriptiva e inferencial. Resultados: 19.5% de los adolescentes manifestaron haber ingerido alguna bebida alcohol en algún momento de su vida y el 14% en el último año. 64% presenta malestar emocional, de los cuales destaca la tristeza, alegría, aburrimiento y pensamientos repetitivos. Se observó una relación positiva (rs=.473, p=.003) y efecto (p=.001, f=10.787, gl=1) del malestar emocional con el consumo de alcohol. Conclusión: se pudo identificar que el malestar emocional está asociado a la ingesta de alcohol, esto como una forma de mitigar ese conjunto de emociones y sentimientos negativas y/o positivas característicos de esta etapa.

Objective: determine the relationship and effect of emotional distress on adolescents' alcohol consumption. Method: quantitative, cross-sectional, descriptive and predictive study was conducted in 200 middle school adolescents of both sexes in Ciudad del Carmen, Campeche, Mexico; during the month of January 2018. A sociodemographic data and alcohol consumption history and the Questionnaire on Risk Factors and Protection for Drug Use was used. Results: 19.5% of the adolescents claimed to have ingested an alcoholic beverage at some time in their life and 14% in the last year. 64% present emotional discomfort, of which sadness, happiness, boredom and repetitive thoughts stand out. A positive relationship was observed (rs=.473, p=.003) and effect (p=.001, f=10.787, gl=1) of emotional distress with alcohol consumption. Conclusion: it was possible to identify that the emotional distress is associated with alcohol consumption, this as a way to mitigate that set of negative and/or positive emotions and feelings characteristics of this stage.

Objetivo: determinar a relação e o efeito do desconforto emocional no consumo de álcool dos adolescentes. Método: estudo quantitativo de corte transversal, descritivo e preditivo, junto a 200 adolescentes de ambos sexos de uma instituição pública de ensino fundamental e médio da Ciudad del Carmen, Campeche, México, durante o mês de janeiro de 2018. Foi utilizado um questionário com dados sociodemográficos e uma história de álcool e o Questionário de Fatores de Risco e de Proteção para o Consumo de Drogas. Resultados: 19,5% dos adolescentes manifestaram ter ingerido alguma bebida alcoólica em algum momento da sua vida e o 14% no último ano. 64% apresenta desconforto emocional, dos quais destaca a tristeza, alegria, tédio e pensamentos repetitivos. Observou-se uma relação positiva (rs=.473, p=.003) e efeito (p=.001, f=10,787, gl=1) do desconforto emocional com o consumo de álcool. Conclusão: foi possível identificar que o desconforto emocional está associado ao consumo de álcool, isso como uma forma de mitigar esse conjunto de emoções e sentimentos negativos e/ou positivos caraterísticos dessa etapa.

Individualized Hydrocodone Therapy Based on Phenotype, Pharmacogenetics, and Pharmacokinetic Dosing.

OBJECTIVES: (1) To quantify hydrocodone (HC) and hydromorphone (HM) metabolite pharmacokinetics with pharmacogenetics in CYP2D6 ultra-rapid metabolizer (UM), extensive metabolizer (EM), and poor metabolizer (PM) metabolizer phenotypes. (2) To develop an HC phenotype-specific dosing strategy for HC that accounts for HM production using clinical pharmacokinetics integrated with pharmacogenetics for patient safety. SETTING: In silico clinical trial simulation. PARTICIPANTS: Healthy white men and women without comorbidities or history of opioid, or any other drug or nutraceutical use, age 26.3±5.7 years (mean±SD; range, 19 to 36 y) and weight 71.9±16.8 kg (range, 50 to 108 kg). MAIN OUTCOME MEASURES: CYP2D6 phenotype-specific HC clinical pharmacokinetic parameter estimates and phenotype-specific percentages of HM formed from HC. RESULTS: PMs had lower indices of HC disposition compared with UMs and EMs. Clearance was reduced by nearly 60% and the t1/2 was increased by about 68% compared with EMs. The canonical order for HC clearance was UM>EM>PM. HC elimination mainly by the liver, represented by ke, was reduced about 70% in PM. However, HC's apparent Vd was not significantly different among UMs, EMs, and PM. The canonical order of predicted plasma HM concentrations was UM>EM>PM. For each of the CYP2D6 phenotypes, the mean predicted HM levels were within HM's therapeutic range, which indicates HC has significant phenotype-dependent pro-drug effects. CONCLUSIONS: Our results demonstrate that pharmacogenetics afford clinicians an opportunity to individualize HC dosing, while adding enhanced opportunity to account for its conversion to HM in the body.

Organ-specific microcirculatory mass transport of oxycodone in humans: clinical implications for therapeutic use.

OBJECTIVES: To begin to address the problem of heterogeneity of distribution of oxycodone (OC) in humans, we developed an organ-specific microcirculatory capillary-tissue exchange 2-compartment model for studying regional OC mass transport. MATERIALS AND METHODS: The model was developed in silico. It quantifies OC's organ-specific mass transport rates, clearances and recycling, and it considers the effects of blood flow on OC's convective and diffusive transport. RESULTS: What is new is the finding that OC undergoes local recycling at the level of organ-specific capillary-tissue exchange units in humans. Results indicate recycled OC occurs in sufficient amounts to function as a reusable source of circulating OC; which has important implications for OC dosing. Results show the brain, which is central to OC effects only receives about 8% of OC delivered to all organs via the microcirculation. This suggests that differential regulation of receptor binding, trafficking, internalization, or desensitization in the brain likely plays a dominant role in OC's central analgesic effects. DISCUSSION: Organ-specific OC mass transport kinetics provide new information for OC dosing in pain management. The model promotes patient safety in opioid prescribing because it allows predictions to be made about the relative contribution that OC recycling makes to circulating OC levels. The model indicates that pharmacologic modulation of the microcirculation may give way to site-specific delivery of opioids in the future. Our study demonstrates that translation of bench in silico research data into clinical practice, although still challenging, is feasible and can assist in OC dose regimen design for patient safety.