Search

Neurodegenerative diseases affect a large part of the population in the world and also in Mexico, deteriorating gradually the quality of patients’ life. Therefore, it is important to diagnose them with a high degree of reliability. In order to solve it, various computational methods have been applied in the analysis of biomarkers of human gait. In this study, we propose employing the automatic model selection and hyperparameter optimization method that has not been addressed before for this problem. Our results showed highly competitive percentages of correctly classified instances when discriminating binary and multiclass sets of neurodegenerative diseases: Parkinson’s disease, Huntington’s disease, and Spinocerebellar ataxias.

The COVID-19 pandemic has generated the need to evolve health services to reduce the risk of contagion and promote a collaborative environment even remotely. Advances in Industry 4.0, including the internet of things, mobile networks, cloud computing, and artificial intelligence make Health 4.0 possible to connect patients with healthcare professionals. Hence, the focus of this work is analyzing the potentiality, and challenges of state-of-the-art Health 4.0 applications to face the COVID-19 pandemic including augmented environments, diagnosis of the virus, forecasts, medical robotics, and remote clinical services. It is concluded that Health 4.0 can be applied in the prevention of contagion, improve diagnosis, promote virtual learning environments, and offer remote services. However, there are still ethical, technical, security, and legal challenges to be addressed. Additionally, more imaging datasets for COVID-19 detection need to be made available to the scientific community. Working in the areas of opportunity will help to address the new normal. Likewise, Health 4.0 can be applied not only in the COVID-19 pandemic, but also in future global viruses and natural disasters.

Foliar disease is common problem in plants; it appears as an abnormal change in the plant’s characteristics, such as the presence of lesions and discolorations, among others. These problems may be related to plant growth, which causes a decrease in crop production, impacting the agricultural economy. The causes of leaf damage can be variable, such as bacteria, viruses, nutritional deficiencies, or even consequences of climate change. Motivated to find a solution for this problem, we aim that using image processing and machine learning algorithms (MLA), these symptomatic characteristics of the leaf can be used to classify diseases. Then, contributions of this research are (i) the use of image processing methods in the feature extraction (characteristics), and (ii) the combination of assembled algorithms with deep learning to classify foliar features of Valencia orange (Citrus Sinensis) tree leaves. Combining these two classification approaches, we get optimal rates in binary datasets and highly competitive percentages in multiclass sets. This, using a database of images of three types of foliar damage of local plants. Result of combination of these two classification strategies is an exceptional reliable alternative for leaf damage identification of orange and other citrus plants.

Multiple myeloma (MM) is a hematological malignancy characterized by the clonal proliferation of pathogenic CD138+ plasma cells (PPCs) in bone marrow (BM). Recent years have seen a significant increase in the treatment options for MM; however, most patients who achieve complete the response ultimately relapse. The earlier detection of tumor-related clonal DNA would thus be very beneficial for patients with MM and would enable timely therapeutic interventions to improve outcomes. Liquid biopsy of “cell-free DNA” (cfDNA) as a minimally invasive approach might be more effective than BM aspiration not only for the diagnosis but also for the detection of early recurrence. Most studies thus far have addressed the comparative quantification of patient-specific biomarkers in cfDNA with PPCs and BM samples, which have shown good correlations. However, there are limitations to this approach, such as the difficulty in obtaining enough circulating free tumor DNA to achieve sufficient sensitivity for the assessment of minimal residual disease. Herein, we summarize current data on methodologies to characterize MM, and we present evidence that targeted capture hybridization DNA sequencing (tchDNA-Seq) can provide robust biomarkers in cfDNA, including immunoglobulin (IG) rearrangements. We also show that detection can be improved by prior purification of the cfDNA. Overall, liquid biopsies of cfDNA to monitor IG rearrangements have the potential to provide important diagnostic, prognostic, and predictive information in patients with MM.

Next-generation sequencing (NGS) has greatly improved our ability to detect the genomic aberrations occurring in multiple myeloma (MM); however, its transfer to routine clinical labs and its validation in clinical trials remains to be established. We designed a capture-based NGS targeted panel to identify, in a single assay, known genetic alterations for the prognostic stratification of MM. The NGS panel was designed for the simultaneous study of single nucleotide and copy number variations, insertions and deletions, chromosomal translocations and V(D)J rearrangements. The panel was validated using a cohort of 149 MM patients enrolled in the GEM2012MENOS65 clinical trial. The results showed great global accuracy, with positive and negative predictive values close to 90% when compared with available data from fluorescence in situ hybridization and whole-exome sequencing. While the treatments used in the clinical trial showed high efficacy, patients defined as high-risk by the panel had shorter progression-free survival (p = 0.0015). As expected, the mutational status of TP53 was significant in predicting patient outcomes (p = 0.021). The NGS panel also efficiently detected clonal IGH rearrangements in 81% of patients. In conclusion, molecular karyotyping using a targeted NGS panel can identify relevant prognostic chromosomal abnormalities and translocations for the clinical management of MM patients., The study was supported by the Accelerator Grant: next steps: Early detection and intervention: Understanding the mechanisms of transformation and hidden resistance of incurable hematological malignancies, grants from Instituto de Salud Carlos III PI15/01484 and CRIS Foundation 2020/0063 and 2021/0088.

Misantla, is a city located in the state of Veracruz, Mexico. It is located in the mountainous region of the central zone of the state and is a region of warm-humid-regular climate, it has a great ecosystem with great diversity of species. Here the arthropods play an important role in the ecosystem. The arachnids are chelated arthropods and represent one of the largest classes of invertebrates that exist within the classification of animals. Most spider venoms do not harm people by being too weak, and can cause a sharp or stabbing pain, such as a bee sting. However, in cases of severe bites, the surrounding skin can die within a few hours. The reason for the project is the detection of accidents caused by arachnid bites, especially among children in the Misantla region, who are often severely damaged by the venom of a spider bite. It is worth mentioning that there are very few studies devoted to the analysis of the detection of any arachnid worldwide. And, in the country, it is not known, until today, a work of investigation whose objective has been; to identify the bite of a spider, as well as of its species and to suggest at the moment of the bite, some center of specialties to be treated. The importance of environmental intelligence within this study is related to the fact that it is currently in charge of solving this type of problems related to daily life, and with the correct functioning of the implementation of Deep Learning techniques for the detection process, to obtain a classification with the best precision and with a minimum margin of error. For all the above reasons, it is necessary to implement an intelligent application for the citizens of the city of Misantla. Citizens would then have more information about possible arachnid accidents and which medical facilities to go to before an accident occurs.

As the number of elderly people increases, it is a necessity for smart cities to take care of elder special needs. As people age, the likelihood of accidents increases because of their motor skills decrease over time, this risk is not only latent when they live alone but also exists within the nursing homes. Because of this, constant care for older adults is a necessity for smart cities, this may not always be possible due to the lack of family members who can care for the elder or in the case of the nursing homes, the staff may not be enough to care for all adults. This leaves the need for systems that can constantly monitor older adults and respond and alert automatically in the event of accidents. In order to find a means to improve the quality of life of older adults who may suffer accidents, in this chapter it is presented an algorithm based on neural networks for the automatic fall detection of older adults in nursing homes. The implemented model was trained and tested on a database of video images containing fall situations.

The incorporation of an intelligent drone that replaces one of the main tasks of farmers, direct visual inspection in order to reduce future damage to citrus production generated by bird pests, where the use of a convolutional neuronal network will serve to extract characteristics and generate a classification model capable of distinguishing between healthy tree foliage from that which is not and which consequently presents some type of pest produced by birds taking into account the coloration of the leaves, as well as, extracting the coloration of the leaves that present diseases, with the aim of optimizing and improving the activities immersed in the cultivation of citrus fruits. In addition, to reduce the damage of bird pests, which will significantly increase productivity in the agricultural sector annually, therefore, through the implementation of unmanned aerial vehicles, provide visual recognition to reduce the indirect effects generated by the type of pests and with this, optimize the activities and techniques involved in citrus cultivation.