Prediction Model of Amyotrophic Lateral Sclerosis by Deep Learning with Patient Induced Pluripotent Stem Cells

Abstract

In amyotrophic lateral sclerosis (ALS), early diagnosis is essential for both current and potential treatments. To find a supportive approach for the diagnosis, we constructed an artificial intelligence‐based prediction model of ALS using induced pluripotent stem cells (iPSCs). Images of spinal motor neurons derived from healthy control subject and ALS patient iPSCs were analyzed by a convolutional neural network, and the algorithm achieved an area under the curve of 0.97 for classifying healthy control and ALS. This prediction model by deep learning algorithm with iPSC technology could support the diagnosis and may provide proactive treatment of ALS through future prospective research. ANN NEUROL 2021;89:1226–1233

Artificial-Intelligence-Based Imaging Analysis of Stem Cells: A Systematic Scoping Review

“…Upon a demographical analysis of the collected data, the United States was the highest contributing country in this field with 9 studies out of 27 (33.3%) [ 25 , 26 , 29 , 30 , 38 , 45 , 46 , 47 , 48 ], followed by China (13.5%) [ 27 , 32 , 41 , 42 ], Japan (11.1%) [ 28 , 33 , 37 ], and Brazil [ 50 , 51 ] and Taiwan [ 32 , 40 ] (both 7.4%). Argentina [ 34 ], Finland [ 43 ], Germany [ 39 ], Italy [ 49 ], South Korea [ 36 ], and Thailand [ 44 ] each had one study each (3.7%), as shown in Figure 2 .…”

“…The number of publications studying stem cell image analysis using artificial intelligence increased throughout the years. Based on the included publications, the majority of published studies were in 2021 (seven studies) [ 25 , 26 , 27 , 28 , 29 , 30 , 31 ].…”

“…Developed using the PerkinElmer HCS system, Guo et al [ 27 ] tested the ability of the algorithm on high-content analysis to study embryo-like structures derived from several mice-induced PSC lines, TSCs and ESCs. Imamura et al [ 28 ] built an ALS prediction model using a CNN-based deep learning algorithm where 4500, 1350, and 900 images were used for training, validation, and testing, respectively. Joy et al [ 29 ] trained five different neural networks (FCRN-A, FCRN-B, U-Net, Residual U-Net, and Count-ception) to localize each cell nucleus individually in a human-induced pluripotent stem cell (hiPSC) colony, generating longitudinal measures of cell and cellular neighborhood properties.…”

Induced Pluripotent Stem Cell-Based Drug Screening by Use of Artificial Intelligence

“…The morphology of cells created from iPSCs differs depending on the cell line; however, in this study, the morphological heterogeneity among the cell lines was overcome by creating iPSCs from many patients, including 15 healthy subjects and 15 patients with ALS. Using AI technology for tasks other than image analysis using a CNN is also useful for disease evaluation of iPSCs [ 88 ]. Hidaka et al developed a machine learning algorithm from a heat diffusion equation (HDE) model and performed compound screening to suppress cell death in iPSC-derived motor neurons.…”

Artificial intelligence supports automated characterization of differentiated human pluripotent stem cells

“…In the study by Imamura et al, induced pluripotent stem cells (iPSCs) were generated from cells from healthy controls and patients with amyotrophic lateral sclerosis. The iPSCs were differentiated into motor neurons and immunostained, followed by image classification where 90 % of the cell images were correctly classified (Imamura et al, 2021). Maddah et al investigated structural toxicity of iPSC-derived hepatocytes and cardiomyocytes by treating cells with known toxic and non-toxic compounds.…”