This glossary contains terms used in disease detection based on machine learning.
eccentricity
noun
deviation of a curve or orbit from circularity.
Example: A fitted linear regression across all the errors relative
to their distance (Euclidean) from the center (eccentricity) of
the screen shows no significant relationship (p-value of 0.208)
(Figure 4B), indicating that the estimation accuracy was not
systematically dependent on the eccentricity of the target.
ru: эксцентриситет
ground truth
noun
Ground truth may be seen as a conceptual term relative to the knowledge of the truth concerning a specific question. It is the ideal expected result.
Example: For the data used in this work, containing x and y coordinates,
the difference between the ground truth and the estimation.
neuropsychiatric
adj
Neuropsychiatry or Organic Psychiatry is a branch of medicine that deals with psychiatry as it relates to neurology, in an effort to understand and attribute behavior to the interaction of neurobiology and social psychology factors. Within neuropsychiatry, the mind is considered "as an emergent property of the brain", whereas other behavioral and neurological specialties might consider the two as separate entities.
Example: The approach has been used
not only as a clinical tool to detect neurological and neuropsychiatric disorders by studying the
patients’ gaze patterns, but also has been shown to be useful in everyday applications, such as analyzing the trustworthiness of phishing emails.
ru: нейропсихиатрия
phishing
noun
the fraudulent practice of sending emails purporting to be from reputable companies in order to induce individuals to reveal personal information, such as passwords and credit card numbers.
Example: The approach has been used not only as a clinical tool to detect neurological and neuropsychiatric disorders by studying the patients’ gaze patterns but also has been shown to be useful in everyday applications, such as analyzing the trustworthiness of phishing emails.
ru: фишинг
undergo
verb
go through
Example: The network undergoes 15,000 iterations (epochs) on
the training set, which lasted about 35 min.