• Home
  • Search
  • ПРИМЕНЕНИЕ СИНТЕТИЧЕСКИХ ОБРАЗОВ ДЛЯ РЕШЕНИЯ ЗАДАЧИ КЛАССИФИКАЦИИ НА ПРИМЕРЕ ДИАГНОСТИКИ РАКА ЛЕГКОГО
  • https://doi.org/10.15690/vramn73296-104-936Copy DOI Icon

ПРИМЕНЕНИЕ СИНТЕТИЧЕСКИХ ОБРАЗОВ ДЛЯ РЕШЕНИЯ ЗАДАЧИ КЛАССИФИКАЦИИ НА ПРИМЕРЕ ДИАГНОСТИКИ РАКА ЛЕГКОГО

  • May 10, 2018
  • Гундырев Иван Анатольевич +3 more
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Background: From a mathematical point of view, the problems of medical diagnostics are the tasks of data classification. It is important to understand how significant distortions can contribute to the result of classification errors in the collection of primary diagnostic information, in particular, the results of biochemical tests. Aims: Determination of the dependence of the prediction result on the variability of the primary diagnostic information on the example of the model classifier. Materials and methods : The case-control study enrolled patients who were divided into 2 groups: the main (diagnosed with lung cancer, n=200) and the control group (conditionally healthy, n=500). Questioning and biochemical saliva study was performed in all participants. Patients of the main group and the comparison group were hospitalized for surgical treatment, after which carried out the histological verification of the diagnosis. The biochemical composition of saliva is determined spectrophotometrically. Based on the data obtained, a model classifier for the diagnosis of lung cancer (a random forest) has been constructed. In each parameter underlying the classifier, deviations were made in the specified range (±1–5%, ±5–10%, ±10–15%), creating synthetic images. Then, the results of the classification were evaluated by the cross-validation method. Results: The basic diagnostic characteristics of the model classifier are determined (sensitivity ― 72.5%, specificity ― 86.0%). As the deviations of synthetic images from the baseline increase, diagnostic characteristics deteriorate with the general classification. However, the result of a confident classification, on the contrary, gives higher values (sensitivity ― 81.8%, specificity ― 93.1%). In case of a confident classification, similar images that fall into different classes according to the classification results are deleted, whereas in the case of a general classification, they are taken into account. The difference between methods of classification is associated with the presence of images on which the classifier gives the result of belonging to the class in the range of 0.45–0.55. Therefore, it is necessary to introduce a third class into the classifier, the so-called gray zone (0.4–0.6), since the probability of making an erroneous diagnosis in this area is significantly increased. Conclusions: The obtained results allow to conclude that the measurement error in the range (±1–15%) does not significantly affect the quality of the classification.

Similar Papers
  • Video Transcripts

Analysis of Clinical and Radiologic factors associated with follow up Lung RADS score and lung cancer diagnosis in a low-intermediate risk lung cancer screening population

  • Oct 03, 2022
  • Underline Science Inc.
  • Flaminio Pavesi
  • Research Article
  • Citations4

Value of liquid-based cytology of brushing specimens obtained via fiberoptic bronchoscopy for the diagnosis of lung cancer

  • Jun 01, 2015
  • Chinese journal of oncology
  • Huiqin Guo +5
  • Research Article

Analysis of typical cases on clinical application of autofluorescence bronchoscopy

  • May 20, 2010
  • Chinese Journal of Asthma
  • Jingjing Yan +2
  • Front Matter

Informing Patient Surveillance for the Growing Number of Survivors of Lung Cancer

  • Feb 22, 2022
  • Journal of Thoracic Oncology
  • Kevin Ten Haaf
  • Research Article

PCN44 NATIONAL TRENDS IN ADMISSION AND IN-HOSPITAL MORTALITY OF PATIENTS WITH LUNG CANCER IN THE UNITED STATES, 2012-2016

  • May 01, 2020
  • Value in Health
  • T Yan +3
  • Research Article
  • Citations2

Role of Nanoformulations in the Treatment of Lung Cancer.

  • Feb 01, 2025
  • Recent patents on nanotechnology
  • Parijat Pandey +9
  • Research Article

Clinical siginficanie of combined detection of serum tumor markers for lung cancer

  • Aug 25, 2017
  • Central Plains Medical Journal
  • Yanlu Chen +2
  • Research Article

The clinical value of combined detection of serum tumor makers in the diagnosis of lung cancer

  • Apr 10, 2011
  • Central Plains Medical Journal
  • Ronghua Zhang +2
  • Research Article

Clinecal Applications of PET in Lung Cancer

  • Mar 01, 2004
  • 核子醫學雜誌
  • Ching-Yee Oliver Wong +2
  • Research Article
  • Citations32

Pulmonary Embolism, Myocardial Infarction, and Ischemic Stroke in Lung Cancer Patients: Results from a Longitudinal Study

  • Jun 27, 2013
  • Lung
  • Myrthe P P Van Herk-Sukel +6
  • Research Article

Clinical value of detection of tumor markers in bronchoalveolar lavage fluid and serum in the diagnosis of lung cancer

  • May 25, 2019
  • Beibei Jin
  • Research Article
  • Citations6

Diagnosis and prediction of lung cancer through different classification techniques with tumor markers

  • May 01, 2009
  • Chinese Journal of Industrial Hygiene and Occupational Diseases
  • Guang-Jin Nie +3
  • Research Article
  • Citations6

Recent Progress and Challenges in Clinical Translation of Nanomedicines in Diagnosis and Treatment of Lung Cancer.

  • Jan 01, 2024
  • Current Drug Targets
  • Bhavna Yadav +4
  • Research Article

Diagnostic value of endobronchial ultrasound-guided transbronchial needle aspiration vs. mediastinoscopy in lung cancers and mediastinal masses

  • Sep 08, 2017
  • Chinese journal of experimental surgery
  • Qiang Chen +6
  • Research Article

Scoping the Problem

  • Jan 01, 2021
  • Acta Medica Philippina
  • Joven Jeremius Q Tanchuco
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.