Healthcare Management

The issues of managing human capital losses have become significantly more relevant in recent years due to modern socio-economic and political circumstances. The tasks of intensifying labor productivity and increasing innovation activity are inextricably linked with the main goal facing the state – saving the population. In this regard, the assessment of implemented and planning of further measures to preserve and increase human capital is of extreme importance.

The research methods used are analysis, synthesis, generalization and classification of approaches to assessing economic losses of human capital associated with health.

Based on the literature review of scientific materials devoted to assessing economic damage to human capital associated with mortality, morbidity and disability of the population, the authors propose a classification of the main approaches to assessing economic losses. The parameters necessary for calculating economic losses of human capital are specified and the advantages and disadvantages of each approach are formulated.

Neoliberal health care reforms have been underway in OECD countries and the Russian Federation since the 1980s, with the aim of limiting the availability of medical guarantees, containing public expenditures, increasing out-of-pocket payments, and replacing public administration with market mechanisms. The reason for these reforms in OECD countries is the low efficiency of their national systems of universal health care (UHC), whose cost growth outpaces economic growth. The authors explain the low efficiency of UHC systems in OECD countries by the unprecedented favourable conditions of their formation during the so-called “golden age of capitalism” (1945–1975), when the GDP of these countries grew much faster than health expenditures. This allowed the use of high-cost solutions of the past centuries: the view of medical guarantees as final consumption of households, “Bismarckian” labour taxation, market antagonism and information asymmetry of payer and provider, insurance mechanism of payment for medical services with high administrative costs and fragmentation of resources. In contrast, the first UHC system in the world, inherited by Russia from the USSR, was extremely efficient: it guaranteed universal accessibility and free medical care at many times lower costs than in OECD countries, and suffered from a lack of resources rather than a surplus. The authors explain the high efficiency of the Soviet UHC system by the conditions of its creation in a low-income country, which required breakthrough resource-saving innovations: a view of UHC as intermediate consumption, financing by general taxes, integration of payer and provider, refusal to pay for providers’ services by centralised financing of their current activities by a linear (itemised) budget. The successful experience of the USSR allowed a number of low-income countries – e.g., Mongolia, Algeria, and Cuba – to establish UHC systems. Given these circumstances, a conscientious scientific approach demanded that the original Soviet system be scientifically studied by Western UHC systems free of ideological stereotypes, that it be funded and further developed in Russia. However, the Soviet model was consigned to oblivion in the West as “communist”, despite the fact that many of its solutions are used by market economies and/or seen as promising – for example, general tax financing, its centralisation by a “single payer” and the payer-provider integration model successfully used in the US by Kaiser Permanente Corporation since the mid-20th century. In Russia, the ineffectiveness of the Soviet model was proved by its obvious advantage – its ability to guarantee universal accessibility and free medical care in conditions of low so-called “residual” financing, which was natural for the USSR as a middle-income country with high defence expenditures. During the neoliberal dismantling of the Soviet system, its proven effective innovations were replaced by high-cost solutions from high-income countries. At the same time, Russia remained a middle-income country with high defence spending, and the government’s financing of health care is as low and “residual” as in the USSR – less than 4% of GDP. As a logical result of the Soviet low financing and dismantling of the Soviet levers of efficiency, Russia ranks last in international ratings of the efficiency of national health care systems. Today there is a global failure of neoliberal reforms. OECD countries’ health care expenditures continue to grow faster than their economies, and Russia has de facto abandoned the Soviet principles of universal access and free health care: the growth of out-of-pocket payments has taken on alarming proportions. The authors consider the innovations of the Soviet UHC system to be non-alternative for low-income countries and conclude that the scientific rationale for neoliberal health reforms is of questionable validity.

Based on the developed algorithm, methodological techniques for the formation of a corporate model of soft competencies of a medical person are presented using the example of a separate medical organization.

Aim. To systematize the methodology for forming a corporate model of soft competencies of medical personnel using the example of a separate medical organization.

Material and methods. This project was implemented in the Rehabilitation Center “Blagopoluchiye” in the Moscow Region. The main profile of activity: provision of medical services in the profile of medical rehabilitation after neurological and traumatological diseases, as well as rehabilitation after the new coronavirus infection COVID-19. The organization has 210 employees. Of these, 37 people are medical personnel. The bed fund is designed for the simultaneous stay of 100 patients. Analytical, sociological, statistical, administrative methods were used.

Results. An algorithm and methodology for constructing a corporate model of soft competencies for medical personnel has been developed.

Conclusion. The proposed methodological techniques for constructing a corporate model of soft competencies of medical personnel based on the developed algorithm are quite simple and can be implemented in a medical organization without the involvement of consulting companies.

The article examines the history of medical tourism in the world: from thermal springs to modern high-tech medicine. The author draws attention to the problems of functioning and development of medical tourism, as well as possible ways to solve them. The main events contributing to the promotion of medical tourism on the international market are listed. The issues of interaction between participants of medical tourism are considered.

Theoretical research methods were used to write the article, and publications in scientific journals dealing with the topic of medical tourism were used as material.

Aim of the study was to create and test a methodology for expert assessment of cases of treatment of patients with peptic ulcer disease, which would allow predicting the further course of the disease. Diagnostic coefficients according to A. Wald and informative coefficients according to S. Kulbak were used as methods.

Aim – to develop a time-saving technology that allows to increase the productivity of both the development and study of clinical practice guidelines, to eliminate systemic defects in the clinical algorithms, to facilitate understanding, study and assimilation of algorithms and, on this basis, to offer a more advanced methodology for the development of clinical practice guidelines in the interests of practicing physicians.

Material and methods. In Russia, the DRAKON graphical medical language was created, designed to develop clinical algorithms in the form of ergonomic drawings (DRAKON-charts). Detailed information about the DRAKON medical language is given in the textbook ‘‘Clinical algorithmic medicine. Algorithms for diagnosis and treatment in the DRAKON medical language”. To increase the productivity of clinical guidelines developers, an automated workplace for the algorithm developer has been created. With these tools, 20 professional clinical algorithms of high accuracy have been developed and demonstrated in various fields of medicine: respiratory therapy, neurology and phthisiology.

Results. The time-saving technology has been developed that allows increasing the productivity of both the development and study of clinical practice guidelines. The technology contains the DRAKON medical language and the automated workplace for the doctor-developer of clinical practice guidelines (the DRAKON-builder program). The workplace serves not only for development, but also for study of the DRAKON language, and for the analysis of the algorithms created.

On the website of the Russian Ministry of Health, in the section “Rubricator of clinical practice guidelines”, systemic defects in the clinical algorithms were revealed. To eliminate the shortcomings, the method for developing clinical practice guidelines based on the DRAKON medical language is proposed. The concept of “medical algorithmic system” is introduced and a real algorithmic system containing 9 clinical algorithms is demonstrated. Its name is “Respiratory therapy for respiratory failure associated with COVID-19”. The use of the medical algorithmic system in the development of clinical practice guidelines is shown.

Conclusion. The time-saving technology based on the DRAKON medical language has been created, which makes it possible to increase the productivity of both the development and study of clinical practice guidelines. Clinical guidelines containing ergonomic algorithms of high accuracy acquire a new quality: they become ergonomic, convenient for studying, assimilating, analyzing, errors searching, checking and certifying. As a result, difficulties in implementing clinical guidelines in medical practice are eliminated or weakened.

Importance. The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow.

Objectives. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle.

Evidence review. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores.

Findings. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most [27 (63%)] focused on cardiovascular diseases and diabetes. Most [35 (81%)] were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19 and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45 vs 29%).

Conclusions and relevance. The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms’ quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Key points

Question. Which machine learning (ML) predictive algorithms have been implemented in primary care, and what evidence is publicly available for supporting their quality?

Findings. In this systematic review of 43 predictive ML algorithms in primary care from scientific literature and the registration databases of the US Food and Drug Administration and Conformité Européene, there was limited publicly available evidence across all artificial intelligence life cycle phases from development to implementation. While the development phase (phase 2) was most frequently reported, most predictive ML algorithms did not meet half of the predefined requirements of the Dutch artificial intelligence predictive algorithm guideline.

Meaning. Findings of this study underscore the urgent need to facilitate transparent and consistent reporting of the quality criteria in literature, which could build trust among end users and facilitate large-scale implementation.

The article discusses the problem of effective use by attending physicians of modern knowledge in the field of clinical laboratory diagnostics (CLD). It is proposed to change the order of interaction between attending physicians and doctors of CLD, increasing the active role of the latter in the diagnostic process. In particular, priority in the appointment of laboratory tests should be given to doctors of CLD. It is also necessary to give the opportunity to CLD doctors to prescribe additional laboratory tests if obtained results do not provide a clear diagnostic picture. The results of laboratory tests should be accompanied by a clinical laboratory report. The proposed changes will significantly improve the quality of the treatment and diagnostic process.