An empirical analysis of homicides in Mexico through Machine Learning and statistical design of experiments

Homicide is one of the most important mortality causes that has reduced the Mexican life expectancy. That is why the aim of this work is to identify some sociodemographic and economic factors that can help explain homicides in Mexico and measure their impact, assuming the current conditions prevail. To do that, several Machine Learning (ML) methods were evaluated. The C5.0 model is best suited for the data at hand. After fine-tuning the algorithm, we used the estimated model to identify the main factors that explain homicides. Among these factors, eleven were selected that can be influenced by direct changes in domestic public policy, laws and/or regulations. These were used as input in a two-level fractional factorial Statistical Design of Experiments (DOE) to estimate their main effects and possible interactions. Although several of these factors had statistically significant effects on homicide rate, the one that had the biggest and direct impact from a practical perspective, was the Rule of Law Index (RLI). In fact, if we assumed that all states had the median RLI of 0.37, implementing domestic policies and procedures to move them all to the best RLI level could significantly reduce homicide rates.

El homicidio es una de las principales causas de muerte que ha reducido la esperanza de vida de los mexicanos. El objetivo de este trabajo es identificar algunos factores sociodemográficos y económicos que puedan ayudar a explicar homicidios en México y medir su impacto, suponiendo que las condiciones actuales permanecen. Para lograrlo, comparamos diferentes métodos de Aprendizaje de Máquina (AM). Para tal fin, se encuentra que el modelo C5.0 es el más adecuado. Después de hacer una calibración final del modelo, lo utilizamos para determinar los veinticinco principales factores que explican el fenómeno de homicidios. Se seleccionan 11 factores que se consideran pueden ser influenciados directamente por cambios en políticas públicas, leyes y/o regulaciones. Estos predictores fueron utilizados como entrada en un diseño de experimentos factorial fraccionado con dos niveles para estimar los principales efectos principales e interacciones posibles. A pesar de que varios de estos factores tuvieron impactos estadísticamente significativos, el que mostró tener el mayor impacto directo desde una perspectiva práctica fue el Índice de Estado de Derecho (IED). De hecho, asumiendo que todos los estados tuvieran el valor de IED de 0.37, correspondiente a la mediana en todo el país, si se implementaran políticas y procedimientos para ubicar a todos los estados al nivel del mejor estado en términos de IED, se lograría una reducción altamente significativa en la incidencia de homicidios en México.

Production of carotenoid sarcinaxanthin by Kocuria palustris isolated from Northeastern Brazil Caatinga soil and their antioxidant and photoprotective activities

BACKGROUND This study aimed to produce carotenoids of two bacterial strains obtained and isolated from Caatinga soil in Northeastern Brazil and to evaluate their antioxidant and photoprotective activities. The morphological identification of bacteria was performed by Gram staining and molecularly confirmed through the 16S rRNA gene. The production of carotenoids was performed on two 23 factorial designs to analyze the influence of independent variables (temperature range, luminosity, agitation, spiral presence, and bacterial isolate type) for maximum carotenoid yield. The selected condition has been transferred to a bioreactor (10L). The identification of carotenoids was performed by liquid chromatography (HPLC) and mass spectrometry (LC-MS). Antioxidant activity was determined by inhibiting the bcarotene/linoleic acid system and the effectiveness as sunscreen was measured through its sun protection factor (SPF). RESULTS The results revealed that the isolates FT-7.22 and FT-5.12 were identified as Kocuria palustris; producers of a rare C50 carotenoid sarcinaxanthin. This is the first report on the production of carotenoids by this species from the Caatinga Domain. The pigment that was obtained from the Tryptic Soy Broth (TSB) medium in the best conditions of the factorial designs (increased agitation, aeration, and light exposure) exhibited a significant increase in the carotenoid production. The isolated FT-7.22 reached a higher sarcinaxanthin concentration (112,480 lg/L), and it exhibited promising antioxidant (76.53 ± 0.09%) and photoprotective activities (SPF = 9.36 ± 0.52). CONCLUSIUON This study demonstrated the ability of K. palustris to produce carotenoid sarcinaxanthin with antioxidant and photoprotective activities so that it can be applied in cosmetic formulations. How to cite: Mendes-Silva TCD, Vidal EE, de Souza RFR, et al. Production of carotenoid sarcinaxant

Application of Data Mining Technology in Risk Prediction Model for Lung Cancer / 肿瘤防治研究

Objective To establish a lung cancer risk prediction model using data mining technology and compare the performance of decision tree C5.0 and artificial neural networks in the application of risk prediction model, and to explore the value of data mining techniques in lung cancer risk prediction. Methods We collected the data of 180 patients with lung cancer and 240 patients with benign lung lesion which contained 17 variables of risk factors and clinical symptoms. Decision tree C5.0 and artificial neural networks models were established to compare the prediction performance. Results There were 420 valid samples collected in total and proportioned with the ratio of 7:3 for the training set and testing set. The accuracy, sensitivity, specificity, Youden index, positive predictive value, negative predictive value and AUC of artificial neural networks model were 65.3%, 61.7%, 73.3%, 0.350, 54.9%, 73.1% and 0.675 (95%CI: 0.628-0.720) in testing set; those of decision tree C5.0 model were 61.0%, 47.8%, 80.4%, 0.282, 35.3%, 80.6% and 0.641 (95%CI: 0.593-0.687) in testing set. Conclusion The artificial neural networks model is superior to the decision tree C5.0 model at overall performance and it has potential application value in the risk prediction of lung cancer.

Comparing performance of C5.0 decision tree and radial basis function neural network for predicting hemorrhagic transformation in patients with acute ischemic stroke / 中华疾病控制杂志

@# Objective To compare performance of C5.0 decision tree models and radial basis function(RBF) neural network in predicting the risk of hemorrhagic transformation in acute ischemic stroke. Methods Patients with acute ischemic stroke admitted to hospital were enrolled. Hemorrhagic transformation group and non-hemorrhagic transformation group were divided according to whether hemorrhagic transformation occurred within 2 weeks after admission. Retrospectively collected patients’ case information. C5.0 decision tree models and RBF neural network model were established with the ratio of 7 :3 for training set and test set, and the prediction performance of the model was compared. Results A total of 460 patients’ case information were collected and divided in 314 training set samples and 146 test set samples. Accuracy rates of the C5.0 decision tree model were 96.5% and 80.1%, sensitivities were 98.1% and 82.6%, specificities were 94.8% and 77.9%, Kappa index were 0.93 and 0.60, and AUC were 0.97 and 0.80. Accuracy rates of the neural network model were 72.6% and 74.7%, sensitivities were 87.6% and 88.4%, specificities were 56.9% and 62.3%, Kappa index were 0.45 and 0.50, and AUCs were 0.72 and 0.75. In the training set, the prediction performance of the C5.0 decision tree model was superior to the RBF neural network model. However, there was no statistical difference in the test set.Conclusion C5.0 decision tree model is better than RBF neural network model in risk prediction.

Pharmacodynamic principles and the time course of immediate drug effects

This tutorial defines the principles of the concentration - effect relationship which are the basis of pharmacodynamics. The two key parameters of pharmacodynamics are the maximum response (Emax) and the concentration producing 50% of Emax (C₅₀). The time course of effect is illustrated under the assumption that drug effects are immediately related to concentration in the central compartment e.g. plasma. The related idea of duration of drug action and its relationship to dose is shown to have a simple relationship with drug half-life.

Local radioimmunotherapy of breast cancer-bearing nude mice using anti-CEA monoclonal antibody C50 labeled with ~(131)I / 吉林大学学报(医学版)

Objective To investigate and evaluate the curative effect of radioimmunological targeting drug on nude mice bearing breast cancer. Methods The anti-CEA monoclonal antibody C50 was combined with ~ 131 I to produce radioimmunological targeting drug. 16 nude mice inoculated subcutaneously with breast cancer cell MCF-7 with tumor diameter about 0.5 cm were randomly into 4 groups(n=4): group Ⅰ, injected in part with ~ 131 I-C50 18.5 MBq; group Ⅱ, injected in part with ~ 131 I-C50 3.7 MBq; group Ⅲ, injected in part with ~ 131 I-mIgG 18.5 MBq; group Ⅳ, injected in part with C50 0.75 ?g. The size of tumor volume and inhibitory rate (IR) after treatment for six weeks were calculated and compared with the control group. Results The tumor volume and curves for tumor growth and tumor weight had significant differences between group Ⅰ and the group Ⅲ as well as group Ⅱ (P0.05). Conclusion Anti-CEA monoclonal antibody C50 labeled with radionuclide ~ 131 I could inhibit the growth of the tumor when given locally. ~ 131 I-C50 has a potential value of clinical application