Smartpathk: a platform for teaching glomerulopathies using machine learning

Ana Paula da Silva Mendes,Vinícius Ponte Machado,Luiz Claudio Demes da Mata Sousa,Francisco Jair de Oliveira Neres,Antonio Gilberto Borges Coelho,Adalberto Socorro da Silva,Keylla Maria de Sá Urtiga Aita,Nayze Lucena Sangreman Aldeman,Semíramis Jamil Hadad do Monte

doi:10.1186/s12909-021-02680-1

Abstract

BackgroundWith 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.ResultsAn 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.ConclusionThis artificial intelligence system can assist in teaching renal pathology to increase the training capacity of new medical professionals in this area.

Highlights

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
This is because renal biopsy is an old and low-risk procedure, it requires the presence of a pathologist with specialized training in nephrolopathology and a complex laboratory structure in terms of microscopy, which enhances the differences in access to professional training
Using the tool SmartPathk was developed as a complementary remote tool in the teaching-learning process for pathology teachers and their students

Summary

Introduction

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 Practical areas, such as pathology, have made traditional teaching based on conventional microscopy more flexible through the synergies of computational tools and image digitization, to improve teaching-learning and to offer alternatives to repetitive and exhaustive histopathological analyzes. The formation of the nephropathologist takes time, requiring extensive analytical training due to the structural richness of the glomerulus and the glomerular filtration barrier, a complex structure formed by three layers—the vascular endothelium, the glomerular basement membrane, and the podocytes with their spaced podocyte processes (pedicels) that need to be carefully evaluated It requires the analysis of extra glomerular structures such as renal vessels, interstices, and tubules, as well as access to clinical and laboratory data for the pathological diagnosis of glomerular disease [6,7,8]

Objectives

Methods

Results

Discussion

Conclusion