Machine learning for stem cell differentiation and proliferation classification on electrical impedance spectroscopy

Abstract

Electrical impedance spectroscopy (EIS) measurements on cells is a proven method to assess stem cell proliferation and differentiation. Cell regenerative medicine (CRM) is an emerging field where the need to develop and deploy stem cell assessment techniques is paramount as experimental treatments reach pre-clinical and clinical stages. However, EIS measurements on cells is a method requiring extensive post-processing and analysis. As a contribution to address this concern, we developed three machine learning models for three different stem cell lines able to classify the measured data as proliferation or differentiation laying the stone for future studies on using machine learning to profile EIS measurements on stem cells spectra.

AI‐organoid integrated systems for biomedical studies and applications

“…If ML could predict the expected results from different samples during the early stages of organoid differentiation, it could guide experimental planning and execution, thus greatly improving the quality and reliability of organoid sources. Moreover, generating an experimentally relevant synthetic ground‐truth dataset of organoid differentiation and functionality will allow for benchmarking and identifying best‐performing differentiation approaches and culturing conditions 97,132,135 . Recently, we applied the function of feature importance to rank the features to determine the most effective growth factors and small molecules for cardiac differentiation and vascularization in the hPSC‐derived cardiac organoids 136 .…”

Classification of cardiac differentiation outcome, percentage of cardiomyocytes on day 10 of differentiation, for hydrogel‐encapsulated hiPSCs

“…Mehrian et al [ 11 ] predicted the population doubling time of cells in human mesenchymal stromal cell expansion using random forest models, which had significantly better performance than theoretical estimates. Cunha et al [ 12 ] assessed the differentiation and proliferation of stem cells using artificial neural networks, and Schmidt‐heck et al [ 13 ] implemented support vector machines and random forest models to predict the performance of a bioreactor producing human liver cells.…”

Non-destructive characterization of bone mineral content by machine learning-assisted electrochemical impedance spectroscopy

“…Machine learning has emerged as an effective and accurate method to understand complex biological phenomena, especially human diseases and injuries ( Yu et al, 2018 ; Liang et al, 2019 ; Tekkesin, 2019 ; Peng et al, 2021 ). Several studies have used various machine learning approaches to develop equivalent circuit models from EIS data ( Tripathi and Maktedar, 2016 ; Cunha et al, 2019 ; Babaeiyazdi et al, 2021 ), but the application of machine learning in diagnosing the degree of bone health has not been attempted. The workflow presented in this study consisted of four main steps—an EIS impedance measurement, equivalent circuit modeling and data fitting, principal component analysis, and machine learning analysis—to gradually build up a bone composition detection strategy with the purpose of automatically formulating multiple impedimetric parameters into a recognition machine that determines the bone mineral content.…”