Formal representation of the features and feature space of medical diagnostic data

Рузибаев, О.Б.

Рақамли технологияларнинг назарий ва амалий масалалари · 2026-yil

Annotatsiya

This article analyzes the medical diagnosis process from a data perspective and describes an approach to formally representing a mixed-type feature space describing a patient's condition. The formation of medical data from various sources, such as clinical observations, laboratory tests, instrumental examinations, medical images, genetic data, and anamnesis, as well as their measurement scales, reliability levels, and time-varying properties are analyzed. The impact of distinguishing nominal and numerical features, accounting for missing values based on reliability masks, class imbalance, and taking into account time-dependent features on the quality of the diagnostic model is highlighted. The informativeness of medical features, criteria for their selection, and principles for preserving clinical semantics are also analyzed.

Maqola ma’lumotlari
MualliflarРузибаев, О.Б.
JurnalРақамли технологияларнинг назарий ва амалий масалалари
Nashr sanasi2026-08-02
Jild9
Son3
Betlar25-29
TilRus
DOI10.62132/ijdt.v9i3.395

Kalit so‘zlar

признак, медицинское изображение, утечка целевой переменной (target leakage), глубокие нейронные сети, фенотипический, чувствительность (sensitivity), специфичность (specificity), feature, medical images, target leakage, deep neural networks, phenotypic features, sensitivity, specificity

Ilmiy soha

Рақамли технологияларнинг назарий ва амалий масалалари jurnalidan boshqa maqolalar

Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar