Identification of People with Diabetes Treatment through Lipids Profile Using Machine Learning Algorithms

Diabetes incidence has been a problem, because according with the World Health Organization and the International Diabetes Federation, the number of people with this disease is increasing very fast all over the world. Diabetic treatment is important to prevent the development of several complications, also lipid profile monitoring is important. For that reason the aim of this work is the implementation of machine learning algorithms that are able to classify cases, that corresponds to patients diagnosed with diabetes that have diabetes treatment, and controls that refers to subjects who do not have diabetes treatment but some of them have diabetes, bases on lipids profile levels. Logistic regression, K-nearest neighbor, decision trees and random forest were implemented, all of them were evaluated with accuracy, sensitivity, specificity and AUC-ROC curve metrics. Artificial neural network obtain an acurracy of 0.685 and an AUC value of 0.750, logistic regression achieve an accuracy of 0.729 and an AUC value of 0.795, K-nearest neighbor gets an accuracy of 0.669 and an AUC value of 0.709, on the other hand, decision tree reached an accuracy pg 0.691 and a AUC value of 0.683, finally random forest achieve an accuracy of 0.704 and an AUC curve of 0.776. The performance of all models was statistically significant, but the best performance model for this problem corresponds to logistic regression.

Ab initio study of the reactions of Ga(2P, 2S, and 2P) with methane

The interactions of Ga(2P:4s(2)4p1, 2S:4s(2)5s1, and 2P:4s(2)5p1) with CH4 is studied by means of Hartree-Fock self-consistent-field (SCF) calculations using relativistic effective core potentials and multiconfigurational-SCF plus multireference variational and perturbational on second-order Möller-Plesset configuration interaction calculations. The Ga atom 2P(4s(2)5p1) state can spontaneously insert into the CH4. In this interaction the 4 2A potential energy surface is initially attractive and becomes repulsive only after meeting with the 3 2A surface, adiabatically linked with the Ga(2S:4s(2)5s1) + CH4 fragments. The Ga atom 2S(4s(2)5s1) excited state inserts in the C-H bond. In this interaction the 3 2A potential energy surface initially attractive, becomes repulsive after meet the 2 2A' surface linked with the Ga(2P:4s(2)4p1) + CH4 fragments. The two 2A curves (2 2A and X 2A) derived from the interaction of Ga(2P:4s(2)4p1) atoms with methane molecules are initially repulsive. The 2 2A curve after an avoided crossing with the 3 2A curve goes smoothly down and reaches a minimum: after this point, it shows an energy barrier. The top of this barrier is located below the energy value of the Ga(2S:4s(2)5s1) + CH4 fragments. After this energy top the 2 2A curve goes down to meet the X 2A curve. The 2 2A curve becomes repulsive after the avoided crossing with the X 2A curve. The X 2A curve becomes attractive only after its avoided crossing with the 2 2A curve. The lowest-lying X 2A potential leads to the HGaCH3 X 2A intermediate molecule. This intermediate molecule, diabatically correlated with the Ga(2S:4s(2)5s1) + CH4 fragments, which lie 6 kcal/mol, above the ground-state reactants, the dissociation channels of this intermediate molecule leading to the GaH + CH3 and H + GaCH3 products. These products are reached from the HGaCH3 intermediate without activation barriers. The work results suggest that Ga atom in the first excited state in gas-phase methane molecules could produce better quality a-C:H thin films through CH3 radicals, as well as gallium carbide materials.