Generation of realistic synthetic data using multimodal neural ordinary differential equations

Individual organizations, such as hospitals, pharma companies and health insurance providers are currently limited in their ability to collect data that is fully representative of a disease population. This can in turn negatively impact the generalization ability of statistical models and scientific insights. However, sharing data across different organizations is highly restricted by legal regulations. While federated data access concepts exist, they are technically and organizationally difficult to realize. An alternative approach would be to exchange synthetic patient data instead. In this work, we introduce the Multimodal Neural Ordinary Differential Equation (MultiNODE), a hybrid, multimodal AI approach, which allows for generating highly realistic synthetic patient trajectories on a continuous time scale, hence enabling smooth interpolation and extrapolation of clinical studies. Our proposed method can integrate both static and longitudinal data and implicitly handles missing values. We demonstrate the capabilities of our approach by applying it to real patient-level data from two independent clinical studies and simulated epidemiological data of an infectious disease.

COVID-19 Crisis: What is the Role of Telehealth?

Background: The adverse outcomes of COVID-19 on the healthcare system has prompted the enactment of social distancing and self-isolation or quarantine to minimize the spread of the contagious virus. The need for social distancing and isolation has made telehealth a game-changer in the war against COVID-19. Objectives: The objectives of this study were: (1) To evaluate the current trends of using telehealth during COVID-19 pandemic, (2) To discuss regulatory and policy changes related to telehealth at the service provider level, (3) To analyze recommendations by professional organizations, and (4) To evaluate challenges and recommendations for best practices. Methods: This is a narrative review. Most current information (focused on the measures that the healthcare system has adopted to integrate telehealth in the coronavirus response measures) was obtained from peer-reviewed journals and the website of payers, pharmacies, and professional organizations. Results: Response and management of COVID-19 has seen a surge in the use of telehealth and mobile applications. Health insurance providers have reformed their payer policies to integrate telehealth in COVID-19 response. Waiving premiums, co-pays, and cost-sharing are the most common changes across the industry. For example, Cleveland Clinic has reported a 1,665% increase in the number of telemedicine visits, recording 60,000 visits in March compared to 3,400 before coronavirus. The expansion of telehealth in the era of COVID-19 has presented practical challenges stymying progress. Conclsion: Telehealth is indisputable in promoting social distance, which is a proven public health promotion intervention for curbing the spread of coronavirus.

Coverage and correlates of health insurance in the north-eastern states of India

PurposeThe paper aims to analyze the coverage of health insurance and its correlates in the north-eastern region of India.Design/methodology/approachThe study accessed the raw data of the National Family Health Survey (NFHS-4) (2015–16), which was an extensive, multiround survey conducted in a representative sample of households throughout India, which included socioeconomic, demographic and information on coverage of health insurance of any member of the household. The multivariate analysis of logistic regression was adopted to find the correlates of health insurance for all the eight (8) north-eastern states of India.FindingsThe results observed that among the north-eastern states, the coverage of health insurance was highest in Arunachal Pradesh (59%) followed by Tripura (58%), Mizoram (47%) surpassing the all India level of 27%, whereas the lowest was in Manipur (4%) followed by Nagaland (6%) and Assam (10%). The multivariate analysis of logistic regression found that the socioeconomic and demographic factors, households with a bank account and below poverty line (BPL) cardholders played a significant role in the coverage of health insurance in the north-eastern states of India.Research limitations/implicationsThe study focuses only on the coverage and correlates of health insurance. Further evaluation studies on each scheme of the social health insurance are needed for proper assessment of the health insurance schemes in the region.Practical implicationsThere has been evidence around the world (South Korea, Taiwan and Thailand) that health insurance could be a protective shield from the entrapment into poverty due to high health expenditure. The NFHS-4 put up the finding that in the north-eastern part of India, the coverage of health insurance had been low. This implied that the region could fall into poverty due to high medical expenses on health. Taking account of multiple health insurance providers, risk pooling and consolidation of health insurance providers have become the need of the hour.Originality/valueThe study is different from other studies of health insurance since it covered all the eight (8) north-eastern states of India, which are ethnically, culturally and historically distinct from the rest of India in general and within the region and states in particular and examines the impact of each of the independent variables with the dependent variables. The study has shown that the variation in health insurance coverage associated with socioeconomic and other household-level demographic attributes (although not very strong).

Development, implementation, evaluation and scaling-up of physical activity referral schemes in Germany: protocol for a study using a co-production approach

IntroductionPhysical activity referral schemes (PARSs) are recommended to promote physical activity (PA) among adults at risk of developing or with established non-communicable diseases (NCDs). In Germany, this kind of referral schemes has not yet been implemented systematically and nationwide. In this study protocol, we present the methodological design of a co-production research study aimed at establishing a PARS for adults with NCDs in German primary healthcare.Methods and analysisWe will employ a co-production approach consistently throughout the four project phases: (1) development of the PARS; (2) preparation period; (3) implementation and evaluation; (4) development of a strategic plan for scaling up the PARS to the national level as part of standard care. The first phase will additionally include a status quo analysis of the existing physical activity pathways nationwide as well as an overview of international PARS models. A pragmatic trial design will be used for evaluating the developed PARS. The co-production approach will involve relevant actors in the German healthcare system, namely, healthcare service providers (eg, physicians, exercise professionals), health insurance providers, exercise providers, patients’ representatives, experts in the development and implementation of educational concepts, and scientists from the fields of sports science and public health.Ethics and disseminationThe project has been reviewed and approved by the ethics committee of the Friedrich-Alexander-University Erlangen-Nürnberg (ethics approval number: 331_20 B). Through cooperation agreements, the stakeholders involved gave their consent to participate and were informed about the study in detail. The results of this study will be disseminated by international conference presentations and peer-reviewed publications, and if possible, a manual for the use of the PARS will be provided.

How German health insurance providers use social online networks to promote healthy lifestyles: a content analysis of Facebook® accounts

Background Social networking sites such as Facebook® can contribute to health promotion and behaviour change activities, but are currently underused for this purpose. In Germany, health insurance companies are relevant public health agencies that are responsible for health promotion, primary prevention, and health education. We intended to analyse the Facebook® accounts of health insurance providers to explore the range of prevention topics addressed, identify the communication formats used, and analyse user activity stimulated by prevention-related posts. Methods We performed a quantitative content analysis of text and picture data on Facebook® accounts (9 months in retrospect) in a cross-sectional study design. 64/159 German health insurance providers hosted a Facebook® page, 25/64 posted ≥ 10 posts/months. Among those 25, we selected 17 health insurance companies (12 public, 5 private) for analysis. All posts were categorized according to domains in the classification system that was developed for this study, and the number of likes and comments was counted. The data were analysed using descriptive statistics. Results We collected 3,763 Facebook® posts, 32% of which had a focus on prevention. The frequency of prevention-related posts varied among health insurance providers (1–25 per month). The behaviours addressed most frequently were healthy nutrition, physical activity, and stress/anxiety relief, often in combination with each other. All these topics yielded a moderate user engagement (30–120 likes, 2–10 comments per post). User engagement was highest when a competition or quiz were posted (11% of posts). The predominant communication pattern was health education, often supplemented by photos or links, or information about offline events (e.g. a public run). Some providers regularly engaged in two-side communication with users, inviting tips, stories or recipes, or responding to individual comments. Still, the interactive potential offered by Facebook® was only partly exploited. Conclusions Those few health insurace companies that regularly post content about prevention or healthy lifestyles on their Facebook® accounts comply with suggestions given for social media communication. Still, many health insurance providers fail to actively interact with wider audiences. Whether health communication on Facebook® can actually increase health literacy and lead to behaviour changes still needs to be evaluated.

Study on South Asian Diabetic Subjects on Different Attributes

Diabetes is a serious problem in today's world. Stress TTH (tension type headache) is another epidemic which is growing with a very fast pace. Diabetes is a disease of the body that prevents the metabolism of blood sugar (glucose). This increases the blood glucose to a risky level. The present study aims to analyze diabetes with the latest IoT and big data analysis techniques and its correlation with stress (TTH) on human health. Authors have tried to include age, gender, and insulin factor and its correlation with diabetes. IoT helps us to connect each other, that is, it is known a smart connecting thing (a sort of “universal global neural network” in cloud). It comprises of smart connecting machine with other machine, object, and a lot more. Big data refers to huge sets of data that are also large enough in terms of variety and velocity. Due to this, it becomes more difficult to handle, organise, store, process, and manipulate such data using traditional techniques of storage and processing. Stress especially TTH (tension type headache) is a serious problem in today's world. Now every person in this world is facing headache and stress-related problems in daily life. The authors have collected this big data and studied the people; they have studied their tension level and helped them to cure it. In this chapter, they analyze the correlation between diabetes and stressors. For the analysis, they collected sample of 30 subjects from hospitals of Delhi in random fashion who have been suffering from diabetes from their health insurance providers without disclosing any personal information (PI) or sensitive personal information (SPI) by law. To identify each case sample IDs like S1, S2, etc. has been allotted to the subjects. Sample data has been collected for following parameters: gender, age, diabetes type, insulin dependency, obesity status, CAD status, and CAN status. They have used the Tableau s/w for this analysis. Overall, an interesting observation during the research was that none of the female subjects having diabetes is below 25 years, that is, early age diabetes cases are less comparative to males subjected to the case sampling should not be impacted for age group gender biasing.

Physical Characteristics of Type 1 and 2 Diabetic Subjects

The Delhi and NCR healthcare systems are rapidly registering electronic health records, diagnostic information available electronically. Furthermore, clinical analysis is rapidly advancing—large quantities of information are examined and new insights are part of the analysis of this technology—and experienced as big data. It provides tools for storing, managing, studying, and assimilating large amounts of robust, structured, and unstructured data generated by existing medical organizations. Recently, data analysis data have been used to help provide care and diagnose disease. In the current era, systems need connected devices, people, time, places, and networks that are fully integrated on the internet (IoT). The internet has become new in developing health monitoring systems. Diabetes is defined as a group of metabolic disorders affecting human health worldwide. Extensive research (diagnosis, path physiology, treatment, etc.) produces a great deal of data on all aspects of diabetes. The main purpose of this chapter is to provide a detailed analysis of healthcare using large amounts of data and analysis. From the Hospitals of Delhi and NCR, a sample of 30 subjects has been collected in random fashion, who have been suffering from diabetes from their health insurance providers without disclosing any personal information (PI) or sensitive personal information (SPI) by law. The present study aimed to analyse diabetes with the latest IoT and big data analysis techniques and its correlation with stress (TTH) on human health. Authors have tried to include age, gender, and insulin factor and its correlation with diabetes. Overall, in conclusion, TTH cases increase with age in case of males and do not follow the pattern of diabetes variation with age while in the case of female TTH pattern variation (i.e., increasing trend up to age of 60 then decreasing).

Cyber-physical Threat Detection Platform Designed for Healthcare Systems

Hospitals are responsible for delivering healthcare services to patients in need. These services are large and complex and get affected by multiple interacting actors, such as doctors, nurses, patients, citizens, medical suppliers, health insurance providers. Lately, hospitals around the world are one of the main targets when it comes to terrorist attacks, the cyber realm being the principal source. The healthcare sector is particularly vulnerable due to heavy involvement in patient personal and health information, time constraints, and complex day-to-day operations. In addition to cyber-threats, physical threats are increasingly growing and even healthcare facilities are not immune to them. Malicious intended people created cyber threatening attacks with the purpose to systematically collect evidence against the healthcare system, to advocate for the end of such attacks, and to endanger people's lives or to use the stolen personal data for bad intended actions. Henceforth it is necessary to build a platform that will get alerts and incidents at a fast pace in real-time to prevent any casualties at low cost. SAFECARE project aims to offer protection to hospitals and increase the compliance for the European regulations and security regarding ethics and privacy for health services. This paper presents a solution that will enhance security in hospitals. The primary platform will be built based on a BTMS (Building Threat Monitoring System) where events, incidents, and alerts will be transmitted by sensors from hospital rooms in real-time. Several scenarios were thought to simulate different types of attacks against hospitals and according to the scenarios, various prototypes will be built for assuring the security of the personal and patients from various hospitals.

Results from an Epidemiological Follow-Up Survey on Home Artificial Nutrition in Switzerland from 2010 to 2015

<b><i>Background:</i></b> Home artificial nutrition (HAN) is an established treatment for malnourished patients. Since July 2012, the costs for oral nutrition supplements (ONS) are covered by the compulsory health insurance providers in Switzerland if the patient has a medical indication based on the Swiss Society for Clinical Nutrition guidelines. Therefore, the purpose of our study was to analyse the development of HAN, including ONS, before and after July 2012. <b><i>Methods:</i></b> We obtained the retrospective and anonymized data from the Swiss association for joint tasks of health insurers (SVK), who registered patients on HAN. Since not all health insurers are working with SVK, this retrospective study recorded nearly 65% of all new patients on HAN in Switzerland from January 1, 2010, to December 31, 2015. <b><i>Results:</i></b> A total of 33,410 patients (49.1% men and 50.9% women) with a mean BMI of 21.3 ± 4.5 kg/m² and mean age of 68.9 ± 17.8 years were recorded. The number of patient cases on ONS increased from 808 cases in 2010 to 18,538 cases in 2015, while patient cases on home enteral nutrition (HEN) and home parenteral nutrition (HPN) remained approximately the same. The relative distribution of type of HAN changed from 26.2% cases on ONS, 68.7% cases on HEN and 5.1% cases on HPN in 2010 to 86.1% cases on ONS, 12.8% cases on HEN, and 1.1% cases on HPN in 2015. Treatment duration decreased for ONS from 698 ± 637 days to 171 ± 274 days, for HEN from 416 ± 553 days to 262 ± 459 days, and for HPN from 96 ± 206 days to 72 ± 123 days. Mean costs per patient decreased for ONS from 1,330 CHF in 2010 to 606 CHF in 2015. Total costs for HAN increased from 16,895,373 CHF in 2010 to 32,868,361 CHF in 2015. <b><i>Conclusion:</i></b> Our epidemiological follow-up study showed an immense increase in number of patients on HAN in Switzerland after July 2012. Due to shorter therapy duration and reduced mean costs per patient, total costs were only doubled while the number of patients increased 7-fold.