Smartpathk: a platform for teaching glomerulopathies using machine learning.

BACKGROUND: With the emergence of the new coronavirus pandemic (COVID-19), distance learning, especially that mediated by information and digital communication technologies, has been adopted in all areas of knowledge and at all levels, including medical education. Imminently practical areas, such as pathology, have made traditional teaching based on conventional microscopy more flexible through the synergies of computational tools and image digitization, not only to improve teaching-learning but also to offer alternatives to repetitive and exhaustive histopathological analyzes. In this context, machine learning algorithms capable of recognizing histological patterns in kidney biopsy slides have been developed and validated with a view to building computational models capable of accurately identifying renal pathologies. In practice, the use of such algorithms can contribute to the universalization of teaching, allowing quality training even in regions where there is a lack of good nephropathologists. The purpose of this work is to describe and test the functionality of SmartPathk, a tool to support teaching of glomerulopathies using machine learning. The training for knowledge acquisition was performed automatically by machine learning methods using the J48 algorithm to create a computational model of an appropriate decision tree. RESULTS: An intelligent system, SmartPathk, was developed as a complementary remote tool in the teaching-learning process for pathology teachers and their students (undergraduate and graduate students), showing 89,47% accuracy using machine learning algorithms based on decision trees. CONCLUSION: This artificial intelligence system can assist in teaching renal pathology to increase the training capacity of new medical professionals in this area.

Familial lecithin-cholesterol acyltransferase deficiency: If so rare, why so frequent in the state of Piauí, northeastern Brazil?

Lecithin-cholesterol acyltransferase (LCAT), an enzyme that participates in lipoprotein metabolism, plays an important role in cholesterol homeostasis. Mutations in the LCAT gene can cause two rare genetic disorders: familial LCAT deficiency (FLD), which is characterized by corneal opacities, normocytic anemia, dyslipidemia, and proteinuria progressing to chronic renal failure, and fish-eye disease (FED), which causes dyslipidemia and progressive corneal opacities. Herein, we report six suspected cases of FLD in the backlands of Piauí, located in northeast Brazil. A genetic diagnosis was performed in index cases. Among these, a further investigation was performed to identify new cases in the families. In addition, molecular analyses were performed to verify the levels of consanguinity within families and the existence of a genetic relationship between them. All six index cases were confirmed as FLD with an identical mutation (c.803G > A, p.R268H). The genetic investigation confirmed another 7 new cases of FLD, 52 heterozygous and 6 individuals without mutations. The rate of consanguinity revealed that marriages within the family did not contribute to the high number of FLD cases within the restricted region. The elders of each family (patriarchs and matriarchs) were subjected to a kinship analysis and were more genetically related to each other than the control group. Bayesian analysis was implemented to confirm the hypothesis of connectivity among patriarchs and matriarchs and indicated that they were genetically more related to each other than would be randomly expected, thus suggesting the occurrence of a possible founder effect in these families.

pHLA3D: Updating the database of predicted three-dimensional structures of HLA with HLA-DR, HLA-DQ and HLA-DP molecules.

To improve the availability of three-dimensional (3D) structures of HLA molecules, we created the pHLA3D database. In its first version, we modeled and published 106 3D structures of HLA class I molecules from the HLA-A, HLA-B, and HLA-C loci. This paper presents an update of this database, providing more 127 3D structures of HLA class II molecules (41 DR, 42 DQ, and 44 DP), predicted via homology modeling with MODELLER and SWISS-MODEL. These new 3D structures of HLA class II molecules are now freely available at pHLA3D (www.phla3d.com.br) for immunologists and other researchers working with HLA molecules.

EpViX: A cloud-based tool for epitope reactivity analysis and epitope virtual crossmatching to identify low immunologic risk donors for sensitized recipients.

One of the challenges facing solid organ transplantation programs globally is the identification of low immunological risk donors for sensitized recipients by HLA allele genotype. Because recognition of donor HLA alleles by host antibodies is at the core of organ rejection, the objective of this work was to develop a new version of the EpHLA software, named EpViX, which uses an HLAMatchmaker algorithm and performs automated epitope virtual crossmatching at the initiation of the organ donation process. EpViX is a free, web-based application developed for use over the internet on a tablet, smartphone or computer. This program was developed using the Ruby programming language and the Ruby-on-Rails framework. To improve the user experience, the EpViX software interface was developed based on the best human­computer interface practices. To simplify epitope analysis and virtual crossmatching, the program was integrated with important available web-based resources, such as OPTN, IMGT/HLA and the International HLA Epitope Registry. We successfully developed a program that allows people to work collaboratively and effectively during the donation process by accurately predicting negative crossmatches, saving time and other resources.