Health Data Management Research Articles

Creating a Health Data Management Platform using Hadoop

Creating a Health Data Management Platform using Hadoop

Data management needs assessment for the scale-up of district health information system and introduction of routine (essential) immunization module in Bauchi State, Nigeria, 2015.

Introductionthe National Primary Health Care Development Agency, African Field Epidemiology Network, United States Centers for Disease Control and Prevention and the Bill and Melinda Gates Foundation are implementing a Routine Immunization (RI) Module as part of their Routine Health Data Management System based on the 2013 - 2015 Accountability Framework for RI in Nigeria. To inform planning and evidence-based decision making, a data management needs assessment was conducted in Bauchi state which was one of the states selected for the deployment of the DHIS2 RI module.Methodsdesk reviews were conducted, and a semi-structured questionnaire was administered in four Local Government Areas (LGAs) in Bauchi state that were selected based on the initial evaluation of the performance of all 20 Bauchi LGAs. Ganjuwa and Shira were selected as high-performing LGAs and Alkaleri and Bogoro as low-performing LGAs. Four Health Facilities (HF) were selected in each LGA based on rural or urban classification, type of HFs (private or public), security and accessibility.Resultslocal Immunization Officers (LIOs) prepare monthly reports in high-performing LGAs, and Community Health Care workers are mostly (69%) responsible for report compilation at the HFs. Shira and Alkaleri met 77% and 44% of training indicator targets, respectively, in the previous 12 months. Data recording and reporting was the type of training received the most by health facility personnel. Functioning refrigerators were in all visited LGAs, working thermometer and updated temperature monitoring charts were available in all the cold chain stores. However, no health facility reported having available computers for data-related activities.Conclusionthis assessment provided an improved understanding of the Bauchi state Routine Health Data Management System and informed the content of the state-wide scale-up.

Construction of Sports and Health Data Resources and Transformation of Teachers' Orientation Based on Web Database.

In the intelligent era, emerging information technology helps to transform the information society into an intelligent society and the educational system into a new educational ecology. Teachers must change their roles to be competent for future education and teaching as a result of social transformation, technology application, and education development. Simultaneously, figuring out how to sort sports health data and analyze students' physical health information with a low error rate is an urgent problem that needs to be solved. Data management skills are an unavoidable requirement of the current state of school physical education. Sports health information management will become easier as computer technology advances and the country places a greater emphasis on computer networks. This paper proposes a Web database-based sports health data management system. This paper can help schools understand the relationship between important factors and indicators that affect students' health in order to guide them in making timely changes to their physical education programs. Provide a reasonable sports health plan based on scientific analysis and evaluation to achieve the goal of improving students' physical quality and reducing workload.

Federated Learning for Smart Healthcare: A Survey

Recent advances in communication technologies and the Internet-of-Medical-Things (IOMT) have transformed smart healthcare enabled by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may be infeasible in realistic healthcare scenarios due to the high scalability of modern healthcare networks and growing data privacy concerns. Federated Learning (FL), as an emerging distributed collaborative AI paradigm, is particularly attractive for smart healthcare, by coordinating multiple clients (e.g., hospitals) to perform AI training without sharing raw data. Accordingly, we provide a comprehensive survey on the use of FL in smart healthcare. First, we present the recent advances in FL, the motivations, and the requirements of using FL in smart healthcare. The recent FL designs for smart healthcare are then discussed, ranging from resource-aware FL, secure and privacy-aware FL to incentive FL and personalized FL. Subsequently, we provide a state-of-the-art review on the emerging applications of FL in key healthcare domains, including health data management, remote health monitoring, medical imaging, and COVID-19 detection. Several recent FL-based smart healthcare projects are analyzed, and the key lessons learned from the survey are also highlighted. Finally, we discuss interesting research challenges and possible directions for future FL research in smart healthcare.

Data science and its application in anesthesiology

Electronic health records have brought about vast improvement in all aspects of healthcare. ‘Anesthesia Information Management System’ is a specialized form of electronic health record system that is used to record all of the events taking place during the perioperative period, such as clinical procedures performed, physiologic changes that may happen and the medications administered. Based on anesthetic data many databases have been developed internationally for quality improvement in anesthesiology and to know the research outcomes. At an individual clinical level, big anesthesia data is not yet present, unless waveforms and continuous numerical data of intraoperative physiologic variables is recorded. Though the initiative for big data has taken up by some healthcare institutions in the health data management but our country is still far behind in this field. This editorial is aimed to highlight the necessity of this system and to draw the attention of the concerned authorities to plan provision of electronic record keeping in operating rooms.
 Key words: Electronic Health Records; Data; Data Science; Anesthesiology
 Citation: Abbasi S, Ahmed U, Khan FA. Data science and its application in anesthesiology. Anaesth. pain intensive care 2021;26(1):1–3;
 DOI: 10.35975/apic.v26i1.1757
 Received: January 11, 2022, Accepted: January 14, 2022

Assessment of Challenges and Opportunities and Identification of Approaches and Innovations in COVID-19 Pandemic Management by Different States in India: A Qualitative Approach

ObjectiveThe primary objective of the study was to compare the challenges in implementing various COVID-19-related public health strategies and activities between the selected high health index and low health index states. The secondary objective was to identify the differently managed mechanisms adopted by the health-care delivery system across the states to maintain their functioning during the COVID-19 pandemic.SettingEight states were divided into two groups; based on their health index and vulnerability index ranking—Kerala, Maharashtra, Gujarat, and Karnataka in top four (Group 1) and Delhi, Tripura, Rajasthan, and Orissa in bottom four states (Group 2).ResultsThere was lack of private sector involvement in both the groups of the states, more so in Group 2. Although transport-related issues were similar in both groups, lack of provision of vehicles for transport for carrying out various COVID and non-COVID activities seemed to be more prominent in Group 2. More obstacles related to infrastructure were observed in Group 1 states. In terms of innovations, commonalities lay in convergence of multiple departments for monitoring, contact tracing, essential supplies, and transportation. Both groups managed routine health services and fund allocation with nearly equal vigour. Major challenges faced were related to human resource, policy management, transportation, routine health services, data management, and infrastructure. HR-related challenges in top four states included confusion due to frequent change in guidelines, unclear micro-containment, and testing guidelines. Discharge guidelines and SOPs related to home isolation of slum dwellers, inter-departmental cooperation and coordination issues faced in greater proportion in top four states; issues with fund allocation for local needs were faced by the Group 2 states. Innovations implemented to meet hurdles faced during the pandemic could be categorized under heads of ‘human resource’, ‘community actions’, ‘policy management’, ‘inter-departmental coordination’, ‘use of technology and media’, and ‘fund allocations’. There was private–public partnership; use of other human resource for health-care delivery; use of technology for health-care delivery was seen in all states but more so in Group 1 states.ConclusionStates with higher health index and lower vulnerability index, i.e., Group 1 states faced fewer challenges than those in Group 2. Innovative measures taken at local level to tackle problems posed by the pandemic were unique to the situations presented to them and helped control the disease as effectively as they could.

SFTSDH: Applying Spring Security Framework With TSD-Based OAuth2 to Protect Microservice Architecture APIs

The Internet of Medical Things (IoMT) combines medical devices and applications that use network technologies to connect healthcare information systems (HIS). IoMT is reforming the medical industry by adopting information and communication technologies (ICTs). Identity verification, secure collection, and exchange of medical data are essential in health applications. In this study, we implemented a hybrid security solution to secure the collection and management of personal health data using Spring Framework (SF), Services for Sensitive Data (TSD) as a service platform, and Hyper-Text-Transfer-Protocol (HTTP (H)) security methods. The adopted solution (SFTSDH = SF + TSD + H) instigated the following security features: identity brokering, OAuth2, multifactor authentication, and access control to protect the Microservices Architecture Application Programming Interfaces (APIs), following the General Data Protection Regulation (GDPR). Moreover, we extended the adopted security solution to develop a digital infrastructure to facilitate the research and innovation work in the electronic health (eHealth) section, focusing on solution validation with theoretical evaluation and experimental testing. We used a web engineering security methodology to achieve and explain the adopted security solution. As a case study, we designed and implemented electronic coaching (eCoaching) prototype system and deployed the same in the developed infrastructure to securely record and share personal health data. Furthermore, we compared the test results with related studies qualitatively for the efficient evaluation of the implemented security solution. The SFTSDH implementation and configuration in the prototype system have effectively secured the eCoach APIs from an attack in all the considered scenarios. The eCoach prototype with the SFTSDH solution effectively sustained a load of (≈) 1000 concurrent users in the developed digital health infrastructure. In addition, we performed a qualitative comparison among the following security solutions: SF security, third-party security, and SFTSDH, where SFTSDH showed a promising outcome.

CrowdMed-II: a blockchain-based framework for efficient consent management in health data sharing

The healthcare industry faces serious problems with health data. Firstly, health data is fragmented and its quality needs to be improved. Data fragmentation means that it is difficult to integrate the patient data stored by multiple health service providers. The quality of these heterogeneous data also needs to be improved for better utilization. Secondly, data sharing among patients, healthcare service providers and medical researchers is inadequate. Thirdly, while sharing health data, patients’ right to privacy must be protected, and patients should have authority over who can access their data. In traditional health data sharing system, because of centralized management, data can easily be stolen, manipulated. These systems also ignore patient’s authority and privacy. Researchers have proposed some blockchain-based health data sharing solutions where blockchain is used for consensus management. Blockchain enables multiple parties who do not fully trust each other to exchange their data. However, the practice of smart contracts supporting these solutions has not been studied in detail. We propose CrowdMed-II, a health data management framework based on blockchain, which could address the above-mentioned problems of health data. We study the design of major smart contracts in our framework and propose two smart contract structures. We also introduce a novel search contract for searching patients in the framework. We evaluate their efficiency based on the execution costs on Ethereum. Our design improves on those previously proposed, lowering the computational costs of the framework. This allows the framework to operate at scale and is more feasible for widespread adoption.

Data Management in Healthcare Research as a Guarantee of its Quality

Today, in times of outbreaks of epidemics such as the Zika virus and COVID-19, health systems around the globe face an urgent need to respond quickly to overcome their spread and prevent the re-infection of humanity. Among the solutions was the World Health Organization’s call for immediate, rapid, and, most importantly, open dissemination of medical research data. Although data sharing benefits science and society, there is a range of ethical, legal, cultural, financial, and technical barriers to the dissemination and reuse of medical research data today. Therefore, the quality of data, namely the possibility of their easy search, availability, compatibility, and reusability, is considered relevant in developing data infrastructure in healthcare. Consequently, there is an urgent need to develop an appropriate research data management system in the healthcare system. The aim is to study the efficiency of data management in the healthcare system. This goal is proposed to be achieved in the following sequence: to consider the essence of the concept of research data management; to conduct a bibliometric study of the concept of data management in the medical fields of knowledge, to analyze the frequency of publications on the issue of data management of medical research, indexed by the Scopus database. The object of research is the healthcare sector. The subject is the determinants of the impact of proper management of medical research data on the healthcare sector. The terminological maps of term relationships were constructed using the VOSviewer visualization tool. The study found that 8% of all data management research was conducted in the medical fields of knowledge. The study found an upward trend in the number of health data management publications with the highest growth rate in 2019 and 2020. Analysis of terminology clusters revealed that the keywords «Big Data», «Machine Learning», «Data Collection», «Data Quality», «Data Sharing», «Data Reuse», «COVID-19», and «Blockchain» have the highest number of mentions in publications and strong connection with other publications. Thus, we justified the importance of developing a coherent program and strategic plans for managing research data in the health care system. The results of the study can be used to support decision-making on future opportunities to effectively influence the development of access to medical research data, as well as to ensure the improvement of the quality and confidentiality of research data in the health system.

Impact Of COVID-19 Pandemic Era 2020 on Rashtriya Bal Swasthya Karyakram (RBSK) - National Child Health Program in India-A Cross-Sectional Comparative Research Study

In India because of the elevated birth rate and Brobdingnagian population (globally next to china) Rashtriya Bal Swasthya Karyakram (RBSK) (National Child Health program) is a significant measure by the Government of India, quite vital for public health care provision systems for reducing mortality in children (to achieve SDG goal), particularly within the current COVID-19 pandemic era throughout which most of the essential maternal- kid RCH (Reproductive and Child Health) health services were disrupted globally as well as in India. One of the researchers is a medical doctor who felt that the performance of RBSK during COVID-19 must be investigated to know the status of implementation of services during the pandemic crisis to alert policymakers if there is a disruption of these vital health services due to ongoing pandemic so that proper and timely action should be taken to rectify disruption if any during as well as after pandemic. This analysis study was done to supply significant information to the scientific community and decision-makers with concrete information analysis from authorized HMIS (Health Management data system) of Government - MoHFW (Ministry of Health and Family Welfare)) to provide the COVID-19 impact on RBSK services by public health care facilities across thirty-six states and UTs of India. This novel cross sectional research study revealed that COVID-19 period 2020 had a less number of Male/Female children identified with Disease (6 month to 18 years) screened by RBSK services mobile health teams at Govt and Govt aided schools and Anganwadi centre under RBSK services in India on an all India cumulative basis. This is clearly due to less number of screenings done during the COVID-19 era. The prevalence of Male/Female children identified with Disease (6 month to 18 years) / 1000 screened were 23.49, 31.18 and 29.72 for males and 22.37, 30.27 and 29.31 for females during 2018-2019-2020 respectively, is reduced during COVID-19 era is a good sign.

Nouvelles influences pour la nosographie psychiatrique

It seems legitimate to wonder about the influence that digital technologies could have on the unstable field of psychiatric classifications. For example, passive data collection is a form of monitoring that seems to promote dimensional approaches, more able to represent global trends or breaks than categorial classification based on symptomatology. The enthusiasm around these technologies needs to be recontextualized, and a realistic short-term development could lead to a form of digital assistance, requiring the development of a new type of therapeutic education: personal health data management.

Report on the Third International Workshop on Semantic Web Meets Health Data Management (SWH 2020)

Creating a holistic view of patient data comes with many challenges but also brings many benefits for disease prediction, prevention, diagnosis, and treatment. Especially in the COVID-19 era, this is more important than ever before. The third International Workshop on Semantic Web Meets Health Data Management (SWH) was aimed at bringing together an interdisciplinary audience who was interested in the fields of Semantic Web, data management, and health informatics. The workshop goal was to discuss the challenges in healthcare data management and to propose new solutions for the next generation of data-driven healthcare systems. In this article, we summarize the outcomes of the workshop, and we present a number of key observations and research directions that emerged from presentations.

From Real-world Individuals' Data to National Health Indicators: Multiphase Pilot Study in Gabon.

BackgroundAchieving health goals requires informed decision-making supported by transparent, reliable, and relevant health information. This helps decision makers, such as health managers, to better understand the functioning of their health system and improve their ability to respond quickly to health demands. To achieve this, the health system needs to be supported by a digitized decision-making information system. In Sub-Saharan African countries, inadequate digital infrastructure, including limited internet connectivity and insufficient access to appropriate computer software, makes it difficult to collect, process, and analyze data for health statistics. The processing of data is done manually in this case; however, this situation affects the quality of the health statistics produced and compromises the quality of health intervention choices in these countries.ObjectiveThis study aimed to describe the conceptual approach of a data production and dissemination platform model proposed and implemented in Gabon. More precisely, it aimed to present the approach applied for the multidimensional analysis of the data production and dissemination process in the existing information system and present the results of an evaluation of the proposed model implemented in a real context.MethodsThe research was carried out in 3 phases. First, a platform was designed and developed based on the examination of the various data production and indicator generation procedures. Then, the platform was implemented in chosen health facilities in Gabon. Finally, a platform evaluation was carried out with actual end users.ResultsA total of 14 users with 12 years of average experience in health data management were interviewed. The results show that the use of the proposed model significantly improved the completeness, timeliness, and accuracy of data compared with the traditional system (93% vs 12%, P<.001; 96% vs 18%, P<.001; and 100% vs 18%, P<.001; respectively).ConclusionsThe proposed model contributes significantly to the improvement of health data quality in Gabon.

A Methodology for an Auto-Generated and Auto-Maintained HL7 FHIR OWL Ontology for Health Data Management.

The process of maintenance of an underlying semantic model that supports data management and addresses the interoperability challenges in the domain of telemedicine and integrated care is not a trivial task when performed manually. We present a methodology that leverages the provided serializations of the Health Level Seven International (HL7) Fast Health Interoperability Resources (FHIR) specification to generate a fully functional OWL ontology along with the semantic provisions for maintaining functionality upon future changes of the standard. The developed software makes a complete conversion of the HL7 FHIR Resources along with their properties and their semantics and restrictions. It covers all FHIR data types (primitive and complex) along with all defined resource types. It can operate to build an ontology from scratch or to update an existing ontology, providing the semantics that are needed, to preserve information described using previous versions of the standard. All the results based on the latest version of HL7 FHIR as a Web Ontology Language (OWL-DL) ontology are publicly available for reuse and extension.

Magnetic Resonance Imaging Sequence Identification Using a Metadata Learning Approach.

Despite the wide application of the magnetic resonance imaging (MRI) technique, there are no widely used standards on naming and describing MRI sequences. The absence of consistent naming conventions presents a major challenge in automating image processing since most MRI software require a priori knowledge of the type of the MRI sequences to be processed. This issue becomes increasingly critical with the current efforts toward open-sharing of MRI data in the neuroscience community. This manuscript reports an MRI sequence detection method using imaging metadata and a supervised machine learning technique. Three datasets from the Brain Center for Ontario Data Exploration (Brain-CODE) data platform, each involving MRI data from multiple research institutes, are used to build and test our model. The preliminary results show that a random forest model can be trained to accurately identify MRI sequence types, and to recognize MRI scans that do not belong to any of the known sequence types. Therefore the proposed approach can be used to automate processing of MRI data that involves a large number of variations in sequence names, and to help standardize sequence naming in ongoing data collections. This study highlights the potential of the machine learning approaches in helping manage health data.

학생들의 학업 및 운동스트레스와 건강상태의 관련성에 관한 연구

The purpose of this study is to identify the effects of lifestyle, study stress and training stress on health status, and provide fundamental data for health management of university students majoring in physical education. In this study, 149 students participated and they were surveyed demographic characteristics, lifestyle, Maslach burnout inventory (student stress inventory), training stress inventory, and Mibyeong index. Height and weight were measured for calculating BMI. For statistical analysis, Student t-test, ANOVA test, chi-square test, correlation analysis, and multinominal logistic regression test has been used. There were differences between Mibyeong groups according to digestion status, smoking for female students and quality of sleeping for both male and female students. Study stress and training stress also affected to health status. Cynicism among study stress categories and all categories among training stress showed differences between sex. Correlation analysis and logistics regression analysis was used to estimate related factors of health status after adjusting for sex and age. Based on logistics regression analysis, quality of sleeping affected to Mibyeong 1 group and quality of sleeping, smoking and digestion status affected to Mibyeong 2 group. Among training stress category, dissatisfaction with game result and skills and lack of leisure time were affected to both Mibyeong 1 and 2 group. This study suggests that lifestyle, study stress and training stress might be significantly associated with university students majoring in physical education. Through managing those influence factors, health status of students could be improved.

Measurements of public trust in the health system: mapping the evidence

IntroductionPublic trust in the health system is essential to control the Covid-19 pandemic. It can influence the extent to which interventions to combat a pandemic are accepted by citizens. The objective of this review was to map the evidence of measurements of the concept of public trust in the health system with a focus on health system institutions.MethodsWe performed a systematic literature search in the databases Web of Science and Embase in March 2020. Quantitative studies measuring trust on a system level with regard to healthcare were eligible if they addressed the general public and were published in English or German. We excluded studies that measured trust on an interpersonal level, in a single health profession, or a single treatment. We extracted data to map the characteristics of measurements.ResultsOf initially 7137 identified articles, 87 studies were included in the mapping. In 58 (67%) of the studies, trust was the outcome variable. Most studies (69%) measured the level of trust with single items, 27 studies (31%) used scales or indices to measure the concept of trust. Of these, 12 studies measured healthcare system trust, 7 trust in government and political institutions, 4 trust in healthcare organisations, 3 trust in health insurances, and 1 trust in health data management institutions. Most common domains of trust in the healthcare system refer to policies, quality of services, communication and provision of information, relationships with providers and their expertise, and quality of cooperation between providers. Theoretical dimensions of the concept of trust include fidelity, competency, trustworthiness, integrity and global trust.ConclusionsFew quantitative studies examine dimensions of public trust on a health system level. Future country-specific research on the concept of public trust may support the understanding of context-specific determinants for the tailoring of interventions to promote trust in health systems.Key messages Public trust is an important aspect for controlling a pandemic, as it is a precondition for accepting interventions, such as vaccination programmes.Country-specific research may promote the understanding of public trust and the tailoring of interventions to increase health system trust.

Using Requirements for Health Data Organization and Management

Digital health technologies and their data potentially offer significant opportunities for health management, with both individuals and health research. The research includes pharmaceutical trials, medical studies, public health programs, pandemic response, and health product evaluation. Having organized and updated health data generated by a consumer or home digital health devices combined with medical records from other sources enables these opportunities. This article discusses a practical approach to organizing and managing these data with standards and requirements. The organization includes a data management framework where requirements can be specified. The article is not an in-depth study of existing public health systems or medical record systems. The objective is to consider a practical strategy to develop these requirements with both the medical, engineering and regular communities.

A Solution for Medical Information Management

Abstract Nowadays, the amount of data that is being generated by medical devices has exponentially increased. The aim of this paper is to develop an integrated health data management tool, that aggregates data from various sources, which are in various formats. With the aid of artificial intelligence (AI), this data will be processed and will help healthcare professionals be aware of the improvements that could make the healthcare system be more preventive, predictive and personalized. This paper introduces an integrated medical information management system – that intends to manage medical activities in hospitals, clinics and laboratories and describes its development and future directions of improvement. Furthermore, it presents a smart analysis tool that can generate both statistical data, but also infer additional information from the medical records based on natural language processing (NLP), image processing and machine learning. The novelty of the system is that it gives an overview of the patients’ medical record, statistical analysis, examinations results and interpretations. Furthermore, the system is trying to predict the evolution of a disease, based on previous medical records.

Establishing evidence-based decision-making mechanism in a health eco-system and its linkages with health service coverage in 25 high-priority districts of Uttar Pradesh, India

BackgroundAchievement of successful health outcomes depends on evidence-based programming and implementation of effective health interventions. Routine Health Management Information System is one of the most valuable data sets to support evidence-based programming, however, evidence on systemic use of routine monitoring data for problem-solving and improving health outcomes remain negligible. We attempt to understand the effects of systematic evidence-based review mechanism on improving health outcomes in Uttar Pradesh, India.MethodsData comes from decision-tracking system and routine health management information system for period Nov-2017 to Mar-2019 covering 6963 health facilities across 25 high-priority districts of the state. Decision-tracking data captured pattern of decisions taken, actions planned and completed, while the latter one provided information on service coverage outcomes over time. Three service coverage indicators, namely, pregnant women receiving 4 or more times ANC and haemoglobin testing during pregnancy, delivered at the health facility, and receive post-partum care within 48 h of delivery were used as outcomes. Univariate and bivariate analyses were conducted.ResultsTotal 412 decisions were taken during the study reference period and a majority were related to ante-natal care services (31%) followed by delivery (16%) and post-natal services (16%). About 21% decisions-taken were focused on improving data quality. By 1 year, 67% of actions planned based on these decisions were completed, 26% were in progress, and the remaining 7% were not completed. We found that, over a year, districts witnessing > 20 percentage-point increase in outcomes were also the districts with significantly higher action completion rates (> 80%) compared to the districts with < 10 percentage-point increase in outcomes having completion of action plans around 50–70%.ConclusionsFindings revealed a significantly higher improvement in coverage outcomes among the districts which used routine health management data to conduct monthly review meetings and had high actions completion rates. A data-based review-mechanisms could specifically identify programmatic gaps in service delivery leading to strategic decision making by district authorities to bridge the programmatic gaps. Going forward, establishing systematic evidence-based review platforms can be an important strategy to improve health outcomes and promote the use of routine health monitoring system data in any setting.