Table 2.

Abbreviations and definitions

N/A	Algorithm	A set of defined step-by-step instructions. Can be very simple or very complex.
AI	Artificial intelligence	Not well defined. Broadly described as making a machine behave in ways that would be called “intelligent” if seen by a human.
ANN	Artificial neural network	A highly abstracted and simplified model compared to the human brain, used in machine learning. A set of units receives input data, performs computations on them, and passes them to the next layer of units. The final layer represents the answer to the problem.
N/A	Black box	The calculations performed by some deep learning systems between input and output are not easy (and potentially impossible) for humans to understand.
CNN	Convolutional neural network	In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery.
CPU	Central processing unit	The part of a computer in which operations are controlled and executed.
DL	Deep learning	A specific sub-field of deep learning. It is a process by which a neural network becomes sensitive to progressively more abstract patterns. Hundreds of successive layers of data representations are learned automatically through exposure to training data.
EMR	Electronic medical record	An electronic record of health-related information on an individual that can be created, gathered, managed, and consulted by authorized clinicians and staff within one health care organization.
ESA	Embryo selection algorithm	Any number of morphokinetic parameters that have been linked to an embryo’s viability are combined, for example; the appearance and disappearance of pronuclei and nuclei at each cell stage, the length of time between early cytokinesis and initiation of blastulation, reabsorption of fragments, direct cleavage of cells within embryos from one to three cells, and reverse cleavage.
GPU	Graphics processing unit	A specialized electronic circuit designed to rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device.
ML	Machine learning	Algorithms that find patterns in data without explicit instructions. ML is a single contributing entity for AI technology.
PGT-A	Pre-implantation testing-aneuploidy	A set of techniques used on the embryo prior to transfer to the mother’s uterus with the aim of studying any possible chromosomal and/or genetic abnormalities.
PPV	Positive predictive value	The post-test probability of being affected after a positive test.
SL	Supervised learning	A type of machine learning where the algorithm compares its outputs with the correct outputs during training.
N/A	Test dataset	The sample of data used to provide an unbiased evaluation of a final model fit on the training dataset.
N/A	Training dataset	The sample of data used to fit the model. The actual dataset that we use to train the model (weights and biases in the case of Neural Network). The model sees and learns from this data.
TL	Transfer learning	A technique in machine learning where the algorithm learns one task, and build on that knowledge while learning a different, but related, task. Transfer learning is an alternative approach to help mitigate the large, manually annotated data sets needed for training an AI.
N/A	Validation dataset	The sample of data used to provide an unbiased evaluation of a model fit on the training dataset while tuning model hyperparameters. The evaluation becomes more biased as skill on the validation dataset is incorporated into the model configuration.