RESUMO
Purpose: Determination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies. Approach: A deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline. Results: The best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume. Discussion: The lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level. Conclusions: This work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies.
RESUMO
OBJECTIVE: To investigate whether oral lipid-lowering drugs (OLL) are used in line with the Mexican Official Regulation (NOM)-015-SSA-1994 for preventing, treating, and monitoring diabetes mellitus 2 (DM2) patients. DESIGN: Observational, descriptive study. SETTING: Primary care. Unit of Family Medicine (UMF) No. 80 of the Mexican Social Security Institute. PARTICIPANTS: 332 patients diagnosed with DM2, taking pharmacological treatment and with recent laboratory studies. MAIN MEASUREMENTS: Age, body mass index (BMI), years of evolution of diabetes, type of medication and OLL dose, time taking OLL, glucose, total cholesterol, and triglycerides. The patients were divided into 2 groups on the basis of the BMI: group 1 with BMI<27; group 2 >=27. In addition, each group was sub-divided by the type of medication. RESULTS: Glibenclamide was the OLL most prescribed (52% in both groups). In group 1 there were significant intra-group differences between patient's age and years of evolution of diabetes, whereas in group 2 only the metformin sub-group was associated with lower glucose concentrations and higher concentrations of triglycerides than in the other sub-groups. All patients had deficient glucaemia control. CONCLUSIONS: The data show that OLL treatment for DM2 patients varied from the NOM. Unification of criteria in primary care for the prescription pattern and the use of OLL for better metabolic control of this kind of patient were recommended.