Articles with tag: «machine learning»
-
2023 № 4 Medical datasets for machine learning: fundamental principles of standartization and systematization.
Backgraund: Active implementation of artificial intelligence technologies in the healthcare in recent years promotes increasing amount of medical data for the development of machine learning models, including radiology and instrumental diagnostics data. To solve various problems of digital medical technologies, new datasets are being created through machine learning algorithms, therefore, the problems of their systematization and standardization, storage, access, rational and safe use become actual.
A i m : development of an approach to systematization and standardization of information about datasets to represent, store, apply and optimize the use of datasets and ensure the safety and transparency of the development and testing of medical devices using artificial intelligence.
M a t e r i a l s a n d m e t h o d s : analysis of own and international experience in the creation and use of medical datasets, medical reference books searching and analysis, registry structure development and justification, scientific publications search with the keywords “datasets”, “registry of medical data”, placed in the databases of the RSCI, Scopus, Web of Science.
R e s u l t s . The register of medical instrumental diagnostics datasets structure has been developed in accordance with stages of datasets lifecycle: 7 parameters at the initiation stage, 8 – at the planning stage, 70 – dataset card, 1 – version change, 14 – at the use stage, total – 100 parameters. We propose datasets classification according to the purpose of their creation, a classification of data verification methods, as well as the principles of forming names for standardization and datasets presentation clarity. In addition, the main features of the organization of maintaining this registry are highlighted: management, data quality, confidentiality and security.
C o n c l u s i o n s . For the first time, an original technology of medical datasets for instrumental diagnostics structuring and systematization is proposed. It is based on the developed terminology and principles of information classification. This makes it possible to standardize the structure of information about datasets for machine learning, and ensures the storage centralization. It also allows to get quick access to all information about the dataset, and ensure transparency, reliability and reproducibility of artificial intelligence developments. Creating a registry makes it possible to quickly form visual data libraries. This allows a wide range of researchers, developers and companies to choose data sets for their tasks. This approach ensures their widespread use, resource optimization and contributes to the rapid
development and implementation of artificial intelligence. -
2023 № 4 Medical datasets for machine learning: fundamental principles of standartization and systematization.
Backgraund: Active implementation of artificial intelligence technologies in the healthcare in recent years promotes increasing amount of medical data for the development of machine learning models, including radiology and instrumental diagnostics data. To solve various problems of digital medical technologies, new datasets are being created through machine learning algorithms, therefore, the problems of their systematization and standardization, storage, access, rational and safe use become actual.
A i m : development of an approach to systematization and standardization of information about datasets to represent, store, apply and optimize the use of datasets and ensure the safety and transparency of the development and testing of medical devices using artificial intelligence.
M a t e r i a l s a n d m e t h o d s : analysis of own and international experience in the creation and use of medical datasets, medical reference books searching and analysis, registry structure development and justification, scientific publications search with the keywords “datasets”, “registry of medical data”, placed in the databases of the RSCI, Scopus, Web of Science.
R e s u l t s . The register of medical instrumental diagnostics datasets structure has been developed in accordance with stages of datasets lifecycle: 7 parameters at the initiation stage, 8 – at the planning stage, 70 – dataset card, 1 – version change, 14 – at the use stage, total – 100 parameters. We propose datasets classification according to the purpose of their creation, a classification of data verification methods, as well as the principles of forming names for standardization and datasets presentation clarity. In addition, the main features of the organization of maintaining this registry are highlighted: management, data quality, confidentiality and security.
C o n c l u s i o n s . For the first time, an original technology of medical datasets for instrumental diagnostics structuring and systematization is proposed. It is based on the developed terminology and principles of information classification. This makes it possible to standardize the structure of information about datasets for machine learning, and ensures the storage centralization. It also allows to get quick access to all information about the dataset, and ensure transparency, reliability and reproducibility of artificial intelligence developments. Creating a registry makes it possible to quickly form visual data libraries. This allows a wide range of researchers, developers and companies to choose data sets for their tasks. This approach ensures their widespread use, resource optimization and contributes to the rapid
development and implementation of artificial intelligence. -
2023 № 6 Experience in the application of artificial intelligence technologies for the development of preventive health care on the example of the Kirov region.
Healthcare is one of the priority sectors for the practical application of artificial intelligence (AI) systems. In 2018, in the Kirov region, it was decided to launch its own regional project for the implementation of AI technologies in order to gain practical experience and understand the features, advantages and barriers to the use of AI. Improvement of preventive medicine was chosen as a priority direction.
The Russian predictive analytics platform Webiomed was chosen as the base software product. The project implementation included 3 stages: pilot testing in 2019–2020, commercial operation in the “second opinion” mode in 2021–2022. and implementation in the digital assistant mode, launched in 2023. As a result of the implementation of the 1st and 2nd stages of the project, it was possible to prove that the main advantage of AI in the analysis of big medical data is the autonomous and high accuracy of interpretation of the information available in it. An AI system for independently extracting the data necessary for analysis from electronic medical records, comparing them with data from past periods, assessing the dynamics of changes in health indicators, and identifying the emergence of dangerous trends and risk factors. Together, this allows the formation of the so-called “digital profiles” of patients, which in turn are a valuable resource for supporting management and clinical decision-making. -
2022 № 2 Predicting the development of hypertension using machine learning models in the remote cardiomonitoring subsystem
One of the tasks of personalized medicine is to build a new organizational model for providing medical care to patients, based on the selection of individual medical, diagnostic and preventive agents that are optimally suitable for the peculiarities of the body.
Modern artificial intelligence methods allow you to solve problems of this type.
Purpose. The aim of the study is to construct and apply predictive logistic regression models and decision tree using machine learning techniques to identify patients at high risk of hypertension without the need for invasive clinical procedures.
Materials and methods. A formed data set consisting of 395 patient records of Voronezh City Clinical Clinic No. 1 is used. Each record contains patient parameters: patient sex; patient age; body mass index; waist circumference; hip circumference; tobacco smoking status; alcohol use status; systolic pressure; diastolic pressure. Machine learning methods are used to build prognostic models.
Results. Two models for predicting the development of hypertension are constructed, characterized by high indicators of classification accuracy: a logistic regression model designed to calculate the patient’s individual risk (accuracy 96%), and a decision tree model designed to predict the patient’s possible disease with hypertension and explain the reasons why this disease can occur (accuracy 94%).
Findings. The expediency of using machine learning methods in constructing prognostic models for assessing the state of patients is shown, the possibility of creating a recommendation block based on the obtained models in the remote cardiomonitoring subsystem is indicated.