Collection Of Medical Data Research Articles

COVID-19-related health utility values and changes in COVID-19 patients and the general population: a scoping review.

To summarise the diverse literature reporting the impact of COVID-19 on health utility in COVID-19 patients as well as in general populations being affected by COVID-19 control policies. A literature search up to April 2023 was conducted to identify papers reporting health utility in COVID-19 patients or in COVID-19-affected general populations. We present a narrative synthesis of the health utility values/losses of the retained studies to show the mean health utility values/losses with 95% confidence intervals. Mean utility values/losses for categories defined by medical attendance and data collection time were calculated using random-effects models. In total, 98 studies-68 studies on COVID-19 patients and 30 studies on general populations-were retained for detailed review. Mean (95% CI) health utility values were 0.83 (0.81, 0.86), 0.78 (0.73, 0.83), 0.82 (0.78, 0.86) and 0.71 (0.65, 0.78) for general populations, non-hospitalised, hospitalised and ICU patients, respectively, irrespective of the data collection time. Mean utility losses in patients and general populations ranged from 0.03 to 0.34 and from 0.02 to 0.18, respectively. This scoping review provides a summary of the health utility impact of COVID-19 and COVID-19 control policies. COVID-19-affected populations were reported to have poor health utility, while a high degree of heterogeneity was observed across studies. Population- and/or country-specific health utility is recommended for use in future economic evaluation on COVID-19-related interventions.

Prescription Sequence Symmetry Analysis (PSSA) to assess prescribing cascades: a step-by-step guide

Prescribing cascades occur when patients are prescribed medication to treat the adverse drug reaction of previously prescribed medication. Prescription sequence symmetry analysis (PSSA) can be used to assess the association between two medications in prescription or dispensing databases and thus the potential occurrence of prescribing cascades. In this article, a step-by-step guide is presented for conducting PSSA to assess prescribing cascades. We describe considerations for medication data collection and setting time periods for relevant parameters, including washout window, exposure window, continued exposure interval and blackout period. With two examples, we illustrate the impact of changes in these parameters on the strengths of associations observed. Given the impact seen, we recommend that researchers clearly specify and explain all considerations regarding medication included and time windows set when studying prescribing cascades with PSSA, and conduct subgroup and sensitivity analyses.

The future of hematopoietic stem cell transplantation using DX

The advancement of information and communication technology (ICT) is bringing significant changes to hematopoietic stem cell transplantation. Digital transformation (DX) simplifies the collection and analysis of medical data, enabling provision of medical services beyond geographical constraints through telemedicine. Convenient access to electronic medical records and vital data from wearable devices could facilitate personalized medicine, for example, by predicting of disease onset. Online consultations are effective in improving the efficiency of posttransplant follow-ups, donor recruitment, and donor screening in rural areas. Moreover, patient-reported outcomes are effective in improving treatment outcomes and patient management. The effective utilization of ICT necessitates the enhancement of information technology (IT) literacy among healthcare professionals and patients, as well as development of IT proficiency among medical personnel. DX in hematopoietic stem cell transplantation contributes to the improvement of treatment outcomes, quality of medical care, and patient convenience while introducing new possibilities for the future of healthcare.

PROFILE OF CHARACTERISTIC, RISK FACTOR, AND CLINICAL SEVERITY OF ISCHEMIC STROKE PATIENTS

Background: Ischemic strokes account for 87% of all strokes, making them the second leading cause of disability and one of the leading causes of mortality worldwide. Using the National Institutes of Health Stroke Scale (NIHSS), the clinical severity of an ischemic stroke can be assessed. Objective: The objective of this study is to ascertain the clinical severity, risk factors, and characteristics of patients with ischemic stroke at the neurology department of RSUD Dr. Soetomo Surabaya. Methods: The participants in this descriptive observational study comprise individuals who sought medical attention at the neurology department of RSUD Dr. Soetomo between January 2019 and December 2020 due to an ischemic stroke. The observed profile comprises the following factors: age, gender, obesity, smoking status, alcohol consumption, physical inactivity, family history of vascular disease, form of infarction, dyslipidemia, hypertension, cholesterol, and diabetes. Results: In the medical record data collection of 89 ischemic stroke patients, 36 patients were excluded when they first entered the hospital. So a total of 53 ischemic stroke patients were collected. 29 (54.72%) patients are male. The age range is dominated by 48 - 62 years from 29 (54.72%) patients. 44 (83.02%) patients are Javanese. 18 (33.96%) patients had a history of smoking, 1 (1.89%) patient consumed alcohol, and 1 (1.89%) patients were inactive physically. 13 (24.53%) patients have a family history of vascular disease, 45 (84.91%) patients have hypertension, 26 (49.06%) patients have dyslipidemia, and 19 (35.85%) patients have diabetes. 34 (64.15%) patients had moderate strokes, 15 (28.30%) patients had mild strokes, 2 (3.77%) patients had moderate-severe strokes, and 2 (3.77%) patients had severe strokes according to the results of the NIHSS assessment on the first admission. Conclusion: Ischemic stroke patients were mostly in the age range of 48 – 62 years. Comorbidities such as hypertension, dyslipidemia, hypertriglyceridemia, and diabetes are present in the majority of patients. The NIHSS scoring identified moderate stroke patients as having the most frequent outcomes, followed by patients with mild stroke.

Faktor-Faktor yang Berhubungan dengan Respiratory Distress pada Bayi Baru Lahir di Ruang Perinatologi RS X Jakarta

In newborns (BBL) respiratory disorders cause apnea, respiratory failure, to cardiac arrest and cause death. This study aims to determine the factors associated with respiratory distress in newborns in the perinatology ward of X Hospital from January 2018 to December 2020. The quantitative research method used an analytical survey approach (retrospective) and cross sectional design. The population is 795 BBL and the sample is 265 BBL using purposive sampling technique. The instrument used in the study was a medical record data collection form which contained data from the variables to be taken in this study.The bivariate analysis test used is the chi square test. The results of the study 56.6% of newborns experienced respiratory distress and came from a normal placental incidence of 94.7%; birth parity 1-3 times 95.1%; did not experience gestational diabetes 97.4% and women who were not pregnant 92.8%. The results of the bivariate test showed that there were no factors related to the occurrence of Respiratory Distress in newborns in the Perinatology room at X Hospital with a p-value> 0.05.Conclusion: placental factors, parity, diseases experienced by the mother and gemelli are not related to the incidence of respiratory distress in newborns at X Hospital. It is expected that health workers will provide counseling about respiratory distress so that pregnant women understand more and can minimize the impact on the survival of the baby who was born.

The importance and added value of patient involvement in person-centred medication reviews.

Background: The iSIMPATHY (implementing Stimulating Innovation in the Management of Polypharmacy and Adherence Through the Years) team is conducting person-centred medication reviews using a 7-step review tool focusing on ‘what matters to you’1.
 iSIMPATHY is an EU-funded partnership between Scotland, Ireland and Northern Ireland. One of the main drivers for change is the WHO 3rd global patient safety challenge, Medication Without Harm which aims to reduce severe avoidable medication-related harm by 50% globally in the next 5 years, with one of the key action areas being polypharmacy2. To date over 1400 person-centred medication reviews have been conducted with patients in Northern Ireland. These reviews aim to reduce inappropriate polypharmacy, promote adherence and health literacy and provide patient education.
 Personal and Public Involvement (PPI) feedback was sought prior to the project starting and patient engagement has continued throughout.
 Method: Structured, person-centred medication reviews were conducted in acute medical wards in a secondary care setting in Northern Ireland. Priority was given to those on 10 or more medicines or a high risk medicine, over 50 and resident in a care home or approaching end of life. Data were collected for a cohort of 66 patients who consented to an iSIMPATHY review. Data were analysed to determine the interventions made due to patient involvement in the review as compared with interventions which could be made by completing a kardex (medicine list) review only.
 Results: An average of 9.3 interventions were made per patient, significance was graded using the Eadon system, with 4.4% graded 3 (significant but does not lead to an improvement in patient care), 88.9% graded 4 (significant and results in an improvement in standard of care) and 6.7% graded 5 (very significant and prevents major organ failure or an adverse reaction of similar importance). Interventions included checking and requesting laboratory tests, omitted medicines started, adjustments made for allergy, frailty, renal or liver impairment and identification of adverse drug reactions. Importantly, 88% (n=58) of patients had an intervention made because the medication review was discussed with them. This resulted in 38% additional interventions and included 22% of grade 5 interventions.
 The themes of additional interventions were: adherence and inhaler education (19%), identification of unmet/unknown health need and symptom control (15%), community support services (15%), lifestyle (12%), reduction and stopping unnecessary/inappropriate medicines (10%), identification of important additional information (10%), sick day rules (8%), self-care (7%) and referral to other services (5%).
 Conclusion: Patient involvement in their medication review leads to the identification of new and unmet needs, allows for the provision of counselling on medicines, adherence and lifestyle and prompts discussion and action on the deprescribing of inappropriate and unnecessary medicines. These additional interventions are clinically significant for the patient.
 Next steps: Medication reviews and data collection continues with the aim of scale and spread. For results and learning opportunities search https://www.isimpathy.eu/.
 
 https://www.isimpathy.eu/
 Medication Safety in Polypharmacy Technical Report, World Health Organisation 2019.
 
 https://www.who.int/initiatives/medication-without-harm
 
 Eadon, H. Assessing the quality of ward pharmacists’ interventions. Int. J. Pharm. Pract 1992, 1, 145–147
 

COST-EFFECTIVENESS ANALYSIS OF TREATMENT IN GASTROESOPHAGEAL REFLUX DISEASE INPATIENT PATIENTS IN BANDUNG, INDONESIA

Objective: This study aimed to analyze the cost-effectiveness of the GERD treatment management strategy for class II inpatient patients at a police hospital in Bandung, Indonesia.
 Methods: This study was retrospective, using medical record data collection techniques for 103 patients of the Social Security Administrator for Health (Badan Penyelenggara Jaminan Sosial, BPJS), from January 2017 to July 2019. The pharmacoeconomic method was Cost-Effectiveness Analysis. The medicines being compared were omeprazole injection and pantoprazole injection. The outcome parameter was the length of stay (LOS). The perspective was a hospital with a direct cost component. This study uses a 5% discounting rate due to differences in years.
 Results: The results showed that the patient majority was female (76%) and the largest age group was>40 y (53%). There was a significant difference in LOS and total cost between omeprazole and pantoprazole (p-value<0.050) using the Mann-Whitney test. The cost-effectiveness ratio showed that omeprazole has a higher value than pantoprazole.
 Conclusion: Therapy using pantoprazole was more cost-effective than omeprazole.

Dual blockchain-based data sharing mechanism with privacy protection for medical internet of things

In the period of big data, the Medical Internet of Things (MIoT) serves as a critical technology for modern medical data collection. Through medical devices and sensors, it enables real-time collection of a large amount of patients' physiological parameters and health data. However, these data are often generated in a high-speed, large-scale, and diverse manner, requiring integration with traditional medical systems, which further exacerbates the phenomenon of scattered and heterogeneous medical data. Additionally, the privacy and security requirements for the devices and sensor data involved in the MIoT are more stringent. Therefore, when designing a medical data sharing mechanism, the data privacy protection capability of the mechanism must be fully considered. This paper proposes an alliance chain medical data sharing mechanism based on a dual-chain structure to achieve secure sharing of medical data among entities such as medical institutions, research institutions, and cloud privacy centers, and at the same time provide privacy protection functions to achieve a balanced combination of privacy protection capability and data accessibility of medical data. First, a knowledge technology based on ciphertext policy attribute encryption with zero-knowledge concise non-interactive argumentation is used, combined with the data sharing structure of the federation chain, to ensure the integrity and privacy-protecting capability of medical data. Second, the approach employs certificate-based signing and proxy re-encryption technology, ensuring that entities can decrypt and verify medical data at the cloud privacy center using this methodology, consequently addressing the confidentiality concerns surrounding medical data. Third, an efficient and secure key identity-based encryption protocol is used to ensure the legitimacy of user identity and improve the security of medical data. Finally, the theoretical and practical performance analysis proves that the mechanism is feasible and efficient compared with other existing mechanisms.

Анализ требований к конфиденциальности и обмену данными цифрового здравоохранения

The article provides answers to immediate questions associated with the state regulation of confidentiality of information and exchange of data in the era of digital healthcare. The institute of medical confidentiality which originated in the ancient world is still evolving throughout the development of medical law. In the current era of global digitalization, however, the issues related to data confidentiality have become more relevant than ever. With all the modern technologies and digital health care platforms on the rise, new challenges associated with protection of these patients are emerging. To ensure the reliable protection of patient’s personal and medical information, doctors and medical institutions have to meet data security standards. It becomes vital to develop effective strategies and mechanisms to prevent unauthorized access and data leakage due to a larger volume of electronic medical records and digital data exchange. Strict rules and standards regulating collection, storage and transfer of medical data belong to a key aspect in this area. The Russian Federation is making great efforts to create the legislation which could protect the rights of patients and made medical establishments to follow the high standards of confidentiality, and to develop technical aids that provide data encryption and protection against hacker attacks.

Safety culture and patient safety outcomes in developing countries: A narrative review

The effects of medical errors on patients are increasingly becoming a public concern. It is estimated that 10% and 20% of persons receiving healthcare in developed and developing economies, respectively, are harmed, but a majority of these errors are preventable. The purpose of this paper is to summarise the current literature on the level of patient safety culture awareness and practice, predictors of patient safety culture, and the link between patient safety culture and patient outcomes in developing countries. A systematic search for literature from the following data bases, ScienceDirect, PubMed, JSTOR, ProQuest, Taylor & Francis Online, and Emerald Insight was carried out. Consistent with the inclusion criteria and study objectives, 23 published articles were included in this review. We found that patient safety culture awareness and practice in developing countries is low and still evolving. High predictors of patient safety culture include teamwork, communication, work environment and provider job satisfaction. Low predictors include a non-punitive response to errors, handoffs, transitions and transfers, staffing, and blameless reporting systems. We found that improved patient safety culture results in better patient outcomes. However, there is limited evidence on patient safety culture and patient outcomes in African countries, which hinder evidence-based practice aimed at promoting better health outcomes of patients. Stakeholders must ensure enhanced medical data collection and preservation of comprehensive incidence reporting systems and strategies to improve patient safety and health outcomes.

Insights of Validating Death Certificates through Clinical Autopsies

Background: With decreasing autopsy numbers, the cause of death listed in the death certificate is only based on an external inspection, which is increasingly criticized as insufficient. This investigation analyses 447 death certificates from the archives of the University Hospital of Koeln, Germany and their corresponding autopsy reports from the Institute of Pathology. Methods: For this analysis, quality assurance protocols, death certificates, clinical/autopsy notes, and final autopsy reports were used. Cases were categorized: 1. in four validation classes (Goldman criteria, identifying unknown diseases with therapeutic relevance as cause of death); 2) in four nosological causal chains (WHO ICD10; type: linear/ divergent/ convergent/ complex). Results: Differences in diagnoses between death certificate and autopsy report occurred in 32% (143/447 cases). In 7%, only the autopsy identified the cause of death (Goldman, type 2a). Nosological causal chains were established in 21% (linear/divergent) vs 28% (convergent/complex). Myocardial infarct, septicemia and cardiac insufficiency caused death in more than two thirds of cases. Diabetes and obesity did not play a major role as cause of death. Conclusion: Autopsies are highly advisable if death occurs within 48 hrs. of admission and as sudden death in the hospital setting. Regular interdisciplinary autopsy conferences are important for quality control, assessing cases of the convergent/ complex type. The position of an autopsy commissioner as mediator between relatives, clinicians and pathologists seems recommendable in a hospital setting. While an electronic patient file is still controversial, medical data collection as source of information in emergencies by the patient’s medical practitioner seems advantageous.

Left Ventricle Contouring in Cardiac Images in the Internet of Medical Things via Deep Reinforcement Learning

Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. The internet of medical things (IoMT) and artificial intelligence (AI) for efficient medical data collection and analysis have been deemed effective approaches to remote and automatic diagnosis. In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agents movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agents landing spot (or coordinate of its initial position on a cardiac image). We further propose an alternative approach for generating the landing spot based on interventricular septum detection, which is more efficient since no extra effort in data preprocessing and model training are involved. The experiment results show that the coordinates of the generated landing spots with both of the two approaches are sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model and its improved version, even with limited training set.

Exploring the interest of medical students in global health in South Korea: Does taking a global health course matter?

BackgroundPrioritizing global health is important for positive health outcomes. Doctors play a pivotal role in addressing health issues that they need to recognize the importance of global health practice. However, medical education in global health is still in its early stages in many countries, including South Korea.MethodsThis study is a quantitative cross-sectional study. Medical students were recruited from all 40 Korean medical schools and data collection was conducted in 2021. Stratified proportional quota sampling was employed as the sampling method. The study examined medical students’ interest in global health as the dependent variable. Independent variables included whether individuals had taken global health courses as part of their medical curriculum, while covariates included student background and institutional factors. Logistic regression was used to determine if taking a global health class was associated with global health interests.ResultsThe study included 2450 participants and almost 32% of medical students (n = 781) were interested in global health. Taking global health classes in school was associated with a higher likelihood of developing an interest in global health (OR: 1.29, 95% CI: 1.00-1.67). The likelihood of being interested in global health decreased across the academic year (OR: 0.70, 95% CI: 0.53–0.94). Individuals in graduate entry programs were associated with an interest in global health (OR: 1.32, 95% CI: 1.01–1.72).ConclusionThis study provides the first comprehensive nationwide assessment of medical students’ perspectives on global health education in South Korea. The findings underscore the importance of early and sustained exposure to global health topics in medical education in fostering interest in global health. These results can serve as valuable evidence for medical educators seeking to integrate global health education into their curricula.

A 5G-Enabled and Self-Powered Sensor Data Management Scheme for the Smart Medical Platform System

With the rapid development of information technology and the Internet, the advent of 5G era, combined with the self-powered sensors technology of the Internet of things, can meet the needs of the rapid popularization of intelligent devices and intelligent terminals. With the national economic growth and the continuous development of high-tech industry, the people’s demand for medical services and medical construction is gradually increasing. In order to improve the medical speed, treatment efficiency and treatment success rate of the medical platform, the intelligent medical system has become a system platform widely used in major hospitals. Based on 5G development and self-powered sensors development, this paper studies the construction of intelligent medical platform and system data management. We analyze the development of 5G and the application status of self-powered sensors in the medical field, and briefly describe the defects and problems existing in the intelligent medical system. Use 5G network propagation speed to optimize and improve the intelligent medical system, manage the system data information in the big data environment, and build an information integration platform. In the medical information data collection, the intelligent self-powered sensors technology is used to expand the retrieval range and improve the accuracy and reliability of the system. A set of intelligent medical data retrieval system is designed by using artificial intelligence algorithm and 5G communication technology to realize and optimize the function of patient service on the medical platform. Finally, the data management of medical platform is studied under the data security mechanism. Combined with advanced self-powered sensors technology, the purpose of dynamically monitoring patients’ heart rate and body test data is realized, and the information is transmitted to the medical management platform to help doctors and nurses analyze and diagnose. The results show that 5G technology and intelligent self-powered sensors technology play a good role in promoting the establishment of intelligent medical platform, and improve the overall accuracy and reliability of medical system.

Exploration of remote management and an intelligent platform for in-hospital respiratory therapy

The construction of an intelligent remote management platform for respiratory therapy, utilizing artificial intelligence (AI) and the electronic medical record system (EMR), has significant potential to improve the management of respiratory therapy in critically ill patients. This platform includes the development of a dedicated respiratory therapy EMR, the integration of data from multiple mechanical ventilators from different vendors and models, and the utilization of AI-assisted analysis to understand the pathophysiology of respiratory diseases and the complex physiological factors that influence specific interventions, thereby supporting diagnosis, treatment guidance, and prognosis prediction. In addtion, a network will be established to provide seamless connectivity between hospitals and wards. The resulting platform enables the collection of medical device data from multiple points within the hospital, real-time data analysis, and timely alarms, thereby facilitating remote data access, centralization of information, and standardization of data. As a result, the platform enables efficient intra-hospital and inter-hospital doctor-patient management. Despite the benefits offered by this platform, certain challenges need to be addressed, including ensuring data privacy and security, as well as managing the financial and human resources required for its implementation and maintenance. Furthermore, continuous optimization of the platform is crucial, and the clinical use of the platform requires appropriate professional training.

Transgender People's Experiences Sharing Information With Clinicians: A Focus Group-Based Qualitative Study.

Investigating transgender people's experiences sharing health information in clinical encounters may yield insights for family medicine clinicians. This was a qualitative study using a community-based participatory research approach and interpretive description methodology. Seven qualitative focus groups were conducted with 30 transgender adults living in North America. We used purposive sampling to ensure diversity. The focus groups were transcribed verbatim, and 2 investigators independently reviewed and coded each transcript, then they mutually reviewed the transcripts, reconciled their coding, and summarized the codes into themes. Themes were reviewed with community members, participants, and uninvolved clinically oriented investigators for member checking and peer debriefing. Four themes were noted: (1) transgender people often perceive clinicians' questions as voyeuristic, stigmatizing, or self-protective; (2) patients describe being pathologized, denied or given substandard care, or harmed when clinicians learned they are transgender; (3) transgender people frequently choose between risking stigma when sharing information and risking ineffective clinical problem solving if clinicians do not have all the information about their medical histories; (4) improving the safety of transgender people is difficult in the context of contemporary medical systems. Transgender people often must choose between stigma and potentially suboptimal care. Improvements in medical culture, policies, procedures, and data collection tools are necessary to improve the quality and safety of clinical care for transgender people. Institutional and systems changes may be required to safely and effectively implement sexual orientation and gender identity (SOGI) data collection in clinical settings.

Prevalence of Insomnia among Medical Staff during the Epidemic Prevention and Control: A Perspective on Health Behavior

Objectives: In this study, we investigated the sleep status of medical personnel in selected regions of China during the pandemic years of 2020 to 2022; we also considered their health behavior (HB). Methods: We used a random sampling method to select medical personnel for data collection in Shandong Province and its surrounding areas. For assessment instruments we used the General Situation Questionnaire, Pittsburgh Sleep Quality Index Inventory (PSQI), Self-Assessment Scale for Anxiety (SAS), and Self-Assessment Scale for Depression (SDS). Results: A total of 621 medical personnel participated, with a mean PSQI score of 11.37±3.79. The overall detection rate of insomnia was 88.73%, with 16.79% indicating severe insomnia. The primary sleep disorder among medical staff was daytime dysfunction, followed by difficulty falling asleep, poor sleep quality, and sleep efficiency. Various factors including age, education, position/title, abnormal menstruation, working age, income, night shift, and work intensity significantly influenced sleep quality. Advanced age, higher education, higher position/title, abnormal menstruation, working night shift, and higher work intensity emerged as risk factors; having longer working years was protective. Income was a compound factor affecting sleep. Conclusion: Increasing attention to the sleep situation of medical personnel is crucial, as these factors may impact their HB.

The First Saint Petersburg Regional Inflammatory Bowel Diseases Registry on the Basis of the Regional Health Information System: Principles of Functioning, Testing Results, Plan of Development

Aim: to present the principles of functioning of the regional registry of inflammatory bowel disease (IBD) patients in Saint Petersburg on the basis of the City Health Information System (Saint Petersburg IBD Registry).Key points. The Saint Petersburg IBD Registry consists of General Statistical Module and Clinical Module. The General Statistical Module is intended to analyze the prevalence of ulcerative colitis and Crohn's disease, the number of patient visits to medical institutions; to assess the burden on the healthcare system, demographic characteristics, routing and mortality for the whole region. The Clinical Module allows to assess the IBD features in prospective observation. The register case report form is integrated into the patient's status in the Medical Information System of the medical institution. Saint Petersburg IBD Registry operates on the basis of the Saint Petersburg Medical Center of Information and Analysis within the framework of the Regional Medical Data Collection System of the Russian state information system “Regional Fragment of the Unified State Information System in the Healthcare Branch”. The accumulation of prospective data in the Clinical Module continues, which in the near future will make it possible to test and configure the automated analytical block of the registry.Conclusion. The functioning of the Saint Petersburg IBD Registry allows to achieve following primary goals within region: assessment of the epidemiological features of IBD in Saint Petersburg; dynamic assessment of the disease features; assessment and planning of health care resources required to provide care to IBD patients; improvement of approaches to the treatment taking into account the specifics of the region; assessment of the effectiveness and tolerability of specific treatment including biologics.

Data Mining for Heart Disease Prediction Based on Echocardiogram and Electrocardiogram Data

Traditional methods of detecting cardiac illness are often problematic in the medical field. The doctor must next study and interpret the findings of the patient's medical record received from the electrocardiogram and echocardiogram. These tasks often take a long time and require patience. The use of computational technology in medicine, especially the study of cardiac disease, is not new. Scientists are continuously striving for the most reliable method of diagnosing a patient's cardiac illness, particularly when an integrated system is constructed. The study attempted to propose an alternative for identifying cardiac illness using a supervised learning technique, namely the multi-layer perceptron (MLP). The study started with the collection of patient medical record data, which yielded up to 534 data points, followed by pre-processing and transformation to provide up to 324 data points suitable to be employed by learning algorithms. The last step is to create a heart disease classification model with distinct activation functions using MLP. The degree of classification accuracy, k-fold cross-validation, and bootstrap are all used to test the model. According to the findings of the study, MLP with the Tanh activation function is a more accurate prediction model than logistics and Relu. The classification accuracy level (CA) for MLP with Tanh and k-fold cross-validation is 0.788 in a data-sharing situation, while it is 0.672 with Bootstrap. MLP using the Tanh activation function is the best model based on the CA level and the AUC value, with values of 0.832 (k-fold cross-validation) and 0.857 (bootstrap).

Update of the federal governmental statistical surveillance form № 3-DOZ “Data on patient doses from medical X-ray examinations”. Perquisites for the update

Analysis of levels of exposure of public of the Russian Federation by sources of ionizing exposure is one of main parts of the activities conducted by the Federal Service for Surveillance on Consumer Rights Protection and Human Wellbeing. Data on the doses of public of the Russian Federation from medical exposure on facility, regional and federal levels is collected using the form of federal governmental statistical surveillance № 3-DOZ “Data on patient doses from medical X-ray examinations”, that is active since 2000. For the last 20 years there were no significant updates of the form № 3-DOZ. According to the decision of the Board of the Rospotrebnadzor from 11.09.2020, a complex program on update and modernization of form № 3-DOZ was initiated, that has resulted in the approvement of new form № 3-DOZ by the order of Rosstat № 880. The form has been significantly changed to reflect the modern condition of X-ray diagnostics in the Russian Federation. The aim of the current study was to analyze main components of medical exposure dose data collection system that required update and modernization. The study was performed based on the results of assessment of the forms № 3-DOZ from different medical facilities and regions in 2015-2020. The results of the study allowed developing main approaches to the update of the form № 3-DOZ that were implemented in a new edition of the form.