Approaches to Sampling for Quality Control of Artificial Intelligence in Biomedical Research.

Sovrem Tekhnologii Med

Deputy Director for Research; Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health care Department, 24/1 Petrovka St., Moscow, 127051, Russia; Professor, Department of Information and Internet Technologies; First Moscow State Medical University named after I.M. Sechenov (Sechenov University), 8/2 Trubetskaya St., Moscow, 119991, Russia.

Published: July 2023

Unlabelled: is to evaluate the efficacy of approaches to sampling during periodic quality control of the artificial intelligence (AI) results in biomedical practice.

Materials And Methods: The approaches to sampling based on point statistical estimation, statistical hypothesis testing, employing ready-made statistical tables, as well as options of the approaches presented in GOST R ISO 2859-1-2007 "Statistical methods. Sampling procedures for inspection by attributes" have been analyzed. We have considered variants of sampling of different sizes for general populations from 1000 to 100,000 studies.The analysis of the approaches to sampling was carried out as part of an experiment on the use of innovative technologies in computer vision for the analysis of medical images and their further application in the healthcare system of Moscow (Russia).

Results: Ready-made tables have specific statistical input data, which does not make them a universal option for biomedical research. Point statistical estimation helps to calculate a sample based on given statistical parameters with a certain confidence interval. This approach is promising in the case when only a type I error is important for the researcher, and a type II error is not a priority. Using the approach based on statistical hypothesis testing makes it possible to take account of type I and II errors based on the given statistical parameters. The application of GOST R ISO 2859-1-2007 for sampling allows using ready-made values depending on the given statistical parameters.When evaluating the efficacy of the studied approaches, it was found that for our purposes, the optimal number of studies during AI quality control for the analysis of medical images is 80 items. This meets the requirements of representativeness, balance of the risks to the consumer and the AI service provider, as well as optimization of labor costs of employees involved in the process of quality control of the AI results.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10306966PMC
http://dx.doi.org/10.17691/stm2023.15.2.02DOI Listing

Publication Analysis

Top Keywords

approaches sampling
16
quality control
16
based statistical
12
statistical
9
control artificial
8
artificial intelligence
8
intelligence biomedical
8
point statistical
8
statistical estimation
8
statistical hypothesis
8

Similar Publications

A comparative approach on the prophylactic impact of fermented beverages on acute ulcerative colitis in mouse model.

Pol J Vet Sci

December 2024

Department of Pathology, Faculty of Veterinary Medicine, Burdur Mehmet Akif Ersoy University, Burdur, 15030, İstiklal Campus, Burdur, Turkey.

Acute ulcerative colitis is an inflammatory disease of the colon that is becoming increasingly prevalent. Yet, a growing body of evidence supports the efficacy of dietary interventions in preventing acute ulcerative colitis. Fermented beverages have been the focus of research in humans and animals for several years due to their potential to influence overall health functions with an emphasis on gut health.

View Article and Find Full Text PDF

Gene Polymorphisms in Greek Primary Breast Cancer Patients.

Front Biosci (Schol Ed)

December 2024

Institute for Health and Sport, Victoria University, Melbourne, VIC 3030, Australia.

Background: Breast cancer is a heterogeneous disease with distinct clinical subtypes, categorized by hormone receptor status, which exhibits different prognoses and requires personalized treatment approaches. These subtypes included luminal A and luminal B, which have different prognoses. Breast cancer development and progression involve many factors, including interferon-gamma ().

View Article and Find Full Text PDF

Background: Contamination with crude oil and hydrocarbons has become a global threat. Such threats have urged us to invent solutions to deal with this dilemma. However, chemical treatment comes with limited benefits.

View Article and Find Full Text PDF

The origin of life on Earth remains one of the most perplexing challenges in biochemistry. While numerous bottom-up experiments under prebiotic conditions have provided valuable insights into the spontaneous chemical genesis of life, there remains a significant gap in the theoretical understanding of the complex reaction processes involved. In this study, we propose a novel approach using a roto-translationally invariant potential (RTIP) formulated with pristine Cartesian coordinates to facilitate the simulation of chemical reactions.

View Article and Find Full Text PDF

Family Functioning, Anxiety and Depression in Chinese Higher Vocational School Students: A Network Analysis.

Psychol Res Behav Manag

December 2024

Department of Psychiatry, Sleep Medical Center, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China.

Purpose: Network analysis is a statistical method that explores the complex interrelationships among variables by representing them as nodes and edges in a network structure. This study aimed to examine the interconnections between family functioning, anxiety, and depression among vocational school students through network analysis approach.

Participants And Methods: A sample of 2728 higher vocational school students participated in a survey utilizing the Family APGAR Index Questionnaire (APGAR), Generalized Anxiety Disorder Scale (GAD-7), and Patient Health Questionnaire (PHQ-9).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!