Articles from rubric: «Decision support systems»
-
2020 № 4 Algorithm for forming a suspicion of a new coronavirus infection based on the analysis of symptoms for use in medical decision support systems
The course of the COVID‑19 pandemic imposes a significant burden on healthcare systems, including on primary care,
when it is necessary to correctly suspect and determine further management. The symptoms non-specificity and the manifestations versatility of the COVID‑19 impose difficulties in identifying suspicions. To improve the definition of COVID‑19 symptom checkers and medical decision support systems (MDSS) can potentially be useful. They can give recommendations for determining the disease management.
The scientific analysis shows the manifestations versatility and the occurrence frequency COVID‑19. We structured the manifestations by occurrence frequency, classified them as “large” and “small”. The rules for their interaction were determined to calculate the level of suspicion for COVID‑19. Recommendations on patient management tactics were developed for each level of suspicion. NLP models were trained to identify the symptoms of COVID‑19 in the unstructured texts of electronic health records. The accuracy of the models on the F-measure metric ranged from 84.6% to 96.0%. Thus, a COVID‑19 prediction method was developed, which can be used in symptom checkers and MDSS to help doctors determine COVID‑19 and support tactical actions. -
2020 № 4 Non-infectious diseases information system for pre-military evaluation of the risk
The article describes a conceptual approach to automating the algorithm for pre-hospital assessment of risk factors
for non-communicable diseases in order to detect diseases early and monitor them later. The presented information system will allow calculating risk factors for non-communicable diseases, providing dynamic monitoring, and creating a unified register of pre-medical examinations. The information system is developed on the basis of a previously developed algorithm for pre-medical assessment of the risk of non-communicable diseases [4], and allows preliminary identification of risk factors for non-communicable diseases among the General population without conducting expensive analyses and without involving highly qualified medical professionals. -
2020 № 3 Improving the quality of dispensary medical examination of the population in an outpatient clinic based on the use of information technologies
Introduction. A special feature of the adult population’s dispensary medical examination (DME) is the wide range of new tasks for the primary health care system. DME leads to an increase in the number of patients subject to dispensary follow up (DFU), an increase in the load on specialists of outpatient hospitals. Thus, it is necessary to search for and implement new tools in the practice of outpatient hospitals that improve the quality of preventive medicine and ensure that doctors make informed and
timely decisions. Information technologies are offered as such a tool. Material and methods of study. This article uses methods of descriptive statistics and programming. The source material for the development of software modules was the materials of questionnaires and clinical and instrumental examination of patients, statistical reports on DME, DFU of patients in need at the district outpatient hospital from 2013 to 2018. The technical task and development of the algorithm for programming were performed by the authors. Comprehensive monitoring of risk factors for non-communicable diseases among those who have undergone DME was carried out using the program module “Screening of modifiable risk factors for major chronic non-communicable human diseases”, integrated with the MIS (medical information system of the institution). On this basis, the database “Monitoring of risk factors for chronic diseases among the population of the territory covered by the district outpatient hospital” was created. Improving the quality and increasing the coverage of the population with dispensary follow up was carried out using a software module developed for this purpose, integrated with the institution’s MIS. Results and discussion. A continuous comprehensive monitoring of non-communicated diseases risk factors has been organized, and their structure and changes over a 6-year period have been described. The proposed efficiency coefficient indicates positive changes in the work of the medical network to reduce the impact of risk factors on health. It was found that the most modifiable risk factors include “Low physical activity”, “Eating disorders”, and “Hyperglycemia”. DME leads to an increase in the number of patients who need DFU, an increase in the load on the primary health care network. The use of a software module in the practice of the institution to improve the quality and coverage of those in need of DFU contributes to positive changes in this section of work, facilitates the work of healthcare providers. Expanding the range of information technologies used in the work of outpatient hospitals contributes to improving the quality of decisions taken in the prevention of public health disorders by doctors working in conditions of increased workload. Conclusion. DME statistics indicate an increase in the burden on specialists of outpatient hospitals due to the increase in the detection of patients, the need to perform work to eliminate risk factors for non-communicable diseases, and an increase in the number of people subject to dispensary follow up. The work of specialists of outpatient hospitals to eliminate the impact of modifiable risk factors of non-communicable diseases should be carried out on the basis of their comprehensive monitoring. In these conditions, there is a need to expand the range of information technologies used in the preventive work of institutions providing primary health care, aimed at improving the quality of work in this section, creating new working conditions for healthcare providers. These results of using the proposed IT‑tools in integration with the operated MIS allow to improve the quality of preventive work in an outpatient facility, demonstrate the emergence of new tools for doctors that contribute for informed and timely medical decision-making. -
2020 № 3 Making diagnostic decisions with the help of neural networks for disorders of the functioning of the gastrointestinal tract caused by the influence of parasites
The possibilities of using the processing and analysis method in medical research using an artificial neural network to improve the accuracy of diagnosing diseases of the gastrointestinal tract due to the influence of various parasites are considered.
Symptoms and diseases associated with the influence of the main parasites in the gastrointestinal tract are highlighted. Based on
this information, the implementation on the NeuroPro network emulator is carried out. The results of disease progression based
on selected symptoms using a neural network are presented. For a specific disease, significant input parameters of the network
are determined. -
2020 № 2 Informatization in public health: from standards to expert systems
According to the updated requirements of the Ministry of Health of Russia, the main document regulating the treatment and diagnostic process are clinical recommendations. The guidelines for clinical recommendations, based on the results of randomized trials, determine the doctor’s actions when making a diagnosis, and choosing a rational treatment. However, the rudimentary format for the placement of information on paper significantly limits their operation. The capabilities of IT technologies allow integrating clinical recommendations into the structure of expert systems. On the example of the expert system “Treatment of chronic heart failure” the possibilities and prospects of informatization of the diagnostic process are presented.
-
2020 № 2 Multimodal data analysis, “Human” and “Machine” approaches difference, social problematics of biomedical data collection and turnover
Artificial intelligence technologies based physicians decision support systems is an important step of healthcare digital transformation. Despite of neuronet algorithms implementation into analytical systems benefits there are questions that have to be solved for digital healthcare successful launch. In addition to knowledge expert level for systems development and privacy warranties work with professional medical society and general public is essential for psychological and social barriers overcoming during transmission to digital economics.
-
2020 № 1 Life cycle of decision support systems as medical technologies
Decision support systems (DSS) in medicine can be classified into reference and intellectual, and the latter, in turn, into
modeling and imitating human reasoning. Modeling systems are based on formalized expert knowledge, and imitating ones are
based on models built by various multidimensional data analysis methods. DSS should be considered as medical technologies,
therefore, after their development, assessing of analytical (technical) and clinical validity should follow, regardless of current
national regulatory documents. Clinical validation have to be based on principles of evidence based medicine and demonstrate
superiority, non-inferiority or equivalence to routine practice. Then a clinical and economic analysis can be carried out in order
to justify the economic feasibility of DSS, and later health technology assessment can be performed. -
2020 № 1 Automation of the activities of the multidisciplinary rehabilitation team through the ICF WIZARD software package
The article discusses the possibilities of forming a rehabilitation diagnosis using the categories of the directory codes
of the International Classification of Functioning, Disability and Health (ICF) using the ICF WIZARD information system. The possibilities of using the ICF WIZARD information system and its scope are also considered. -
2020 № 1 Decision support services for the diagnosis and treatment of diseases and their practical application on the example of ckd 5d
The article clarifies the concept of DSS, shows the trend of development of new services in medicine. The article
describes the developed DSS‑service for issuing recommendations for the treatment and diagnostic process on the example of
complications in patients on permanent hemodialysis, in particular, correction of anemia. The information and logical architecture
of the service, the rating and trigger models used, the underlying knowledge base, and their relationship are described.
Based on the theory of decision-making, the principle of making recommendations is shown. Examples of integration of the
service with various information systems and other data sources are given. The analysis of the results of the implementation
of the DSS service for the correction of anemia in patients with CKD5D in the Nephrology and hemodialysis departments of
the medical clinical company Nefrosovet in integration with the information and analytical system for managing treatment and
diagnostic processes Maximus. -
2019 № 4 Knowledge-based diagnostic system for orphan diseases development
The paper discusses the problems of early diagnosis of rare hereditary origin diseases in children, presents a brief description of previously created systems aimed at providing support for physician assistance in diagnosis. The prototype of an expert diagnostic system is presented, the knowledge which combines bibliographic data on clinical cases, the coefficients of modality of signs (based on expert evaluations) and certainty factors for manifestation and severity of signs over four age periods. Such an approach to the formation of a knowledge base allows improving the quality of differential diagnosis of a rare pathology at an early age in order to start treatment on time to prevent the development of pathological manifestations caused by the accumulation of macromolecules in organs and tissues.
-
2019 № 3 Сloud decision support service for diagnosis in gastroenterology
The decision support service for diagnosis in gastroenterology was developed on a medical portal of the IACPaaS cloud platform. The general principles of development and the concept architecture of intelligent service, developed information and software components are described. The possibilities of diagnosis and differential diagnosis of diseases on the medical portal are presented.
-
2019 № 2 Medical data usage to create medical decision support systems
-
2019 № 2 Practical use of the database of glycemic indices for the calculation of the glycemic load of foods in computerized programs for assessing actual nutrition
-
2019 № 1 Automated system of bacterioscopic diagnosis of tuberculosis
The article describes the scheme of work and requirements for software and hardware complex for automated bacterioscopic diagnosis of tuberculosis. The basic functionality of the hardware of such an automated system and the required capabilities provided by its software are listed. The stages of automated analysis of digital microscopic images of sputum stained by the method of Ziehl-Nielsen are presented. Own algorithms and mathematical models which can be included in such hardware software complex are presented.
-
2019 № 1 Prediction of development of inflammatory complications in patients with an urolithiasis in the postoperative period
It is developed diagnostically – the prognostic way of assessment of risk of development of inflammatory complications
of the postoperative period in patients with an urolithiasis based on results of prospektivny inspection of 1240 patients. When carrying out the multiple-factor analysis the following markers influencing development of complications in the postoperative period were revealed: SOE, LII level, index of an albumin, expressiveness of a proteinuria and leukocyturia, existence of signs of system inflammatory reaction, violation of an urodinamika and hydronephrosis. Points which during conducting diagnostic testings summarized were appropriated to these signs. On the basis of an original way the computer program having high diagnostic value is created. -
2019 № 1 Capabilities of «Big Data» technologies in medicine
The article is devoted to the study of the peculiarities of using the «Big Data» technology in medicine. The scope of this
technology has been analyzed in detail. On the example of the history of development and experience the «Big Data» technology in Europe and Russia and early diagnostics of oncological diseases by compiling genomic databases, that include the genetic information of each individual patient, its advantages, and disclosed opportunities for treatment are determined. Special attention is paid to the prospects of the development of «Big Data» technology in medicine and healthcare. The potential of analytical technologies in the epidemiological surveillance was also noted. -
2019 № 1 Medical Decision Support System for Ultrasound Protocol Formation
A clinical decision support system is proposed, which allows forming an ultrasound protocol. The descriptive part of
the protocol is formed by the doctor by selecting from a database the ready-made phrases and sentences, which correspond to many features of the studied organ. The system recommends a conclusion based on a set of features using the decision rule. The doctor has the ability to adjust the study protocol in the system. As an example the formation of an ultrasound protocol for the liver is considered. The developed system has been successfully used for more than two years in various medical institutions in Russia. -
2018 № itm Means of intellectual data analysis and support of decision-making in diagnostics and treatment of drug-dependent
Early detection of the drug used by the patient is essential In the diagnosis and treatment of drug addicts. There are specific symptoms of drug use, according to which it is determined that the patient used before the laboratory tests. The use of methods of data mining allows you to identify the characteristic signs of using several drugs and establish previously unexplored symptoms for new drugs, identify typical and atypical patients. In the work, the patterns between the narcotic drugs used and the symptoms are mathematically described using associative rules. Algorithms Apriori, Close and the MClose algorithm proposed by the authors are used to find these rules. The MClose algorithm finds the most significant strict associative rules (rules with reliability 1). The article presents a proposal on expert pre-pro- cessing of melon, which allows to significantly reduce the number of generated associative rules and improve the quality of their interpretation. The developed methods and means is aimed at diagnosing and supporting decision-making in the treatment of drug addicts.
-
2018 № itm The possibility of using Google’s services for adoption of management decisions in organization of emergency medical aid
Not achievement of the indicative indicators reflecting development of emergency medical care testifies to need of the analysis of the reasons and acceptance of the administrative decisions directed to its improvement. The growing popularity of e-applications in medicine, the active application programs and application among patients, the high prevalence of medical communities in social networks – on the one hand, and the lack of a developed system of support of managerial decision-making in the health sector, on the other, raises the question about the use of existing Internet services in the activities of medical organizations for managerial decision-making. The purpose of the study was to identify the possibilities of using Google services for management decisions aimed at improving the organization of emergency medical care. The sociological method included an online study of the opinion of legal representatives of children on emergency medical care using Google services. The analy- sis revealed a number of problems in the organization of emergency medical care for children, causing limited availability of primary health care in emergency form for children, the solution of which requires operational management decisions. The results of using Google services in solving these problems can be used by the heads of medical organizations and health authorities
-
2018 № 2 Decision Support System for Choosing Correction Tactics of Internal Carotid Arteries Stenosis
Along with the medical systems development there is an important task on creation of medical decision support systems (DSS), in particular, capable of predicting the probability of postoperative complications. Computer methods of data analysis make it possible to successfully use both classical methods of applied statistics and modern heuristic procedures for identifying latent (hidden) knowledge in patients’ databases with subsequent construction of predictive models. The article describes the DSS, which automates the prediction of complications probability in the surgical treatment of internal carotid arteries stenoses by carotid endarterectomy and angiostentiation methods basing on the clinical parameters of the patient’s condition before treatment and the technological parameters of the operative intervention. The DSS is based on such classification methods as classification trees and neural networks, the training sample for the classification is the database of patients, who have been treated, with the information of complications presence or absence availiable. Studies, preceding the DSS development were implemented in the STATISTICA package environment. The entrance into program is automated. At the user’s require, the patient data, needed for the calculation is imported into the prediction program module of complications probability from the Excel table. Also, at the user’s request, the prediction results can be saved in the source table.