Data Sharing Archives - Marksman Healthcare

Tokenization in Real World Evidence Studies: the Concept and its Advantages
With all stakeholders increasingly realising the value real-world evidence (RWE) studies can bring into the healthcare delivery, newer applications of RWE are being discovered with each passing day. RWE has the potential to tremendously enhance the speed of patient access to new drugs. With this background, it is absolutely essential that the quality of RWE and the real-world data (RWD) that is used to generate RWE, are of high quality. To ensure quality RWD, it is also essential to bring about transparency into the RWD collection process. Unfortunately, this is easier said than done! However, various steps have been devised to improve transparency of RWD.[1] Two most prominent ones of these are pre-registration of RWE study protocol, and tokenization.

The concept of data tokenization is not a new one, but the tokenization of health data is a fairly recent innovation. Tokenization of healthcare data is a process by which patient identifiers are de-identified through generation of a patient-specific ‘token’ that is encrypted.[2] It helps the researchers to link RWD from a patient’s previous medical history from diverse sources, and also aids tracking different active engagement across the healthcare system without any breach in the patient’s privacy.[2] Basically, all the sensitive data that can compromise a patient’s identity are replaced with unique identification symbols (tokens) that retain all the essential information, but without any compromises in the confidentiality. Tokenization can enable the access of health data without the need for decryption and re-encryption. The possibility of linking data with the use of tokens provides a more comprehensive understanding of health and health care.

Since tokens are unique patient identifiers, they can help recognize a patient who appears across multiple sources of RWD. As the tokens created are patient-specific, the nature of token remains the same across different datasets. Since tokens do not contain any protected health information (PHI) of the patient, such as name, date of birth, and social security number, tokenization can protect against patient reidentification and loss of privacy/ confidentiality. Since the tokens are consistent across different formats of RWE, tokenization also helps to prevent duplication of data while collecting for RWE generation. In other words, tokenization acts as a ‘matchmaker’ to link patient data.[3] Since blockchain technology is generally used in creating tokens, the data is secure and free of manipulation.[4]

Healthcare data tokenization has immense value from the viewpoint of all stakeholders in the healthcare industry. For clinical trial professionals, tokenization can improve study protocol design and can help in anticipating resources and support during a clinical trial. Tokenization also helps to expand follow-up data on trial participants and ensures representation of eligible participants. For healthcare providers, tokenization helps to match their patients’ clinical records accurately, enables keeping track of their patient’s clinical progress, and assists to combine healthcare data from different sources to allow new use cases.[5] For the pharmaceutical company and payers, tokenization provides immense value by helping analyse patient behaviour by tracking patient interactions with hospitals, clinics, pharmacies, laboratories, help groups, and other locations, in a completely de-identified manner. Thus, only the data relevant to the patient’s health is shared with the pharma, by keeping the patient’s personal details hidden. For the regulators, tokenization brings in an unmatched level of transparency in data, and the comprehensive data access that comes with healthcare data tokenization enables the regulators to perform appropriate and unbiased data review. Tokenization also helps data aggregators to meet regulatory compliances surrounding patient data confidentiality, such as HIPAA (Health Insurance Portability and Accountability Act) in the US. [6] Finally, patients can also benefit through tokenization of their health records. The confidentiality ensured by tokenization enables patients to securely organize, compile, share, and trade their personal medical records with relevant stakeholders.[7]

The proliferation of tokenization software and other technologies helps in obtaining a more comprehensive approach of data. The USFDA advises using common data elements to provide a standard, consistent and universal data collection format for better results when linking of patient data is done. Maintaining the data integrity is a must as it may impact the overall scenario. The common issues can be redundant data, inconsistencies across data, privacy and data security. The integrity of data should be assessed for the compatibility and interoperability of data systems and the results produced must be consistent and repeatable, so that relevant data is obtained accurately.[8] Tokenization has the potential to improve the data integrity and enhance the quality of RWE studies.

With the increasing stress by multiple stakeholders on data security and patient privacy, and increasing awareness about the importance of RWD transparency, and considering the unique advantages brought about by blockchain technology, healthcare tokenization has the potential to become a multibillion-dollar industry in the near future.

Become A Certified HEOR Professional – Enrol yourself here!

References
1. Patorno E, Schneeweiss S, Wang SV. Transparency in real-world evidence (RWE) studies to build confidence for decision-making: reporting RWE research in diabetes. Diabetes Obes Metab. 2020 Apr;22 Suppl 3(Suppl 3):45-59.
2. Weng I. Linking RWE to Clinical Trials. 2022. https://www.komodohealth.com/insights/linking-rwe-to-clinical-trials
3. Dagenais S, Russo L, Madsen A, Webster J, Becnel L. Use of Real-World Evidence to Drive Drug Development Strategy and Inform Clinical Trial Design. Clin Pharmacol Ther. 2022;111(1):77-89.
4. Scheuer E. Blockchain solves healthcare data obstacles. https://healthmanagement.org/c/hospital/issuearticle/blockchain-solves-healthcare-data-obstacles
5. Healthcare Data Tokenization. https://risk.lexisnexis.com/healthcare/healthcare-tokenization
6. Pezold A. HIPAA compliance requirements and tokenization. https://www.tokenex.com/blog/hipaa-compliance-and-tokenization .
7. Dimitrov DV. Blockchain Applications for Healthcare Data Management. Healthc Inform Res. 2019 Jan;25(1):51-56.
8. Trial Tokenization: Building A Bridge Between Clinical Trial Data And Real-World Data. E-Book. July 13, 2021.
MarksMan Healthcare

May 31, 2022

Data Privacy, Data Sharing, Real World Evidence
Federated Data Networks (FDNs): Enhancing the Quality of RWE Research
Real-World Data (RWD), from which Real-World Evidence (RWE) is generated, has the unique capability of depicting real-world outcomes. RWD can also reduce timelines for research and development, and generate profound insights into the disease process. However, RWD from a single source often suffers from bias relating to equipment, lack of phenotypic diversity, limited training models, and diverse cohorts. RWD are also scattered and structured in diverse formats, which makes it difficult to unlock its full value. Furthermore, health data are personal, highly sensitive, and subject to data privacy rights and regulations.[1] As a result of these barriers, new methods are needed to enable unlocking the full potential of RWD, and Federated Data Networks (FDNs) are one such attempt.

FDNs are a string of decentralized, interrelated nodes that allow data to be challenged and analysed by the other nodes in the network, without the data leaving the parent node.[1] The member nodes involved in FDNs are governed by a common framework which allows harmonized standards and tools for data access. Each member node is semi-independent as they can make decisions on ceding data access. Since the shared data are masked, blocked or anonymized, the member nodes have limited idea on the identity of the data contained in the other nodes; as a result, data ownership is maintained. The algorithms are trained collaboratively without data exchange by study models called federated learning. Thus, FDNs provide safe data mining with regulated access to diverse data, without crossing the legal barriers.

In contrast to data sharing, data transfer, or data pooling, FDN is simply data visiting, and applying or modifying the results on the existing guidelines and practice.[1] To illustrate, consider two persons in a phone call: here, ideas are shared without sharing their identities, billing address etc. Similarly, FDNs involve sharing of only mathematical values and metadata sets, without sharing confidential patient identity. An example of FDN is the TIES (Text Information Extraction System) Cancer Research Network (TCRN). This FDN has 4 active nodes that search across 5.8 million cases and 2.5 million patients assess cohorts with rare phenotypes.[2]

FDNs can create huge impact on the stakeholders such as physicians, hospitals, insurance companies, researchers and patients. With the surge in digital health devices, the federated model assures good training options for the physicians and hospitals. FDNs are useful in disease classification, mortality forecasting, and predicting treatment outcomes. Proven applications of FDNs include prognosis of stroke prevention, improving patient pathways in cancer, coronary artery disease, classification of EEG recordings, brain tumor classification, breast density classification, multi-disease chest X-ray classification, adverse drug reaction prediction, recognition of human activity and emotion, and prediction of oxygen requirements in COVID patients.[3,4] A federated approach using diverse datasets from different institutions had a 98.3% accuracy in COVID-19 detection, 95.4% accuracy in recognizing human activity and emotions, and 97.7% accuracy in mortality prediction.[3]

In clinical research, FDNs serve to potentiate protocol optimization, patient selection, and adverse effect monitoring. It also facilitates translational research. Federated approach paves way to research on rare disease where the incidence rates and data sets are very low. FDNs reduce the time and resources by identifying the target patients rapidly for recruitment in clinical trials. Also, FDNs aid disease surveillance process by pooling data from different geographies.[5] For the manufacturers, FDNs facilitate continuous product validation and improvement.

To ensure data privacy, FDNs work in line with various regulatory provisions such as General Data Protection Regulation (GDPR) of Europe, Data Protection Act (DPA) of UK, Health Insurance Portability and Accountability Act (HIPAA) of the United States, California Consumer Privacy Act (CCPA), CDSCO of India, Personal Information Protection Law (PIPL), Cybersecurity Law (CSL), and Data Security Law (DSL) of China and the On Personal Data (OPD) of Russia.[6]

Despite their utility in data networking, FDNs face certain challenges in creating robust RWE. Insufficient and inconsistent data, uneven data quality, bias, and lack of data standardization are some of the factors that can lead to inconsistent conclusions. Cloud-based data, which is crucial to develop FDNs, are not enabled by all health care institutions. Practically speaking, debugging and optimizing FDNs is strenuous, because the hardware and networking differs on various sites which makes the learning algorithms diverse.[7] Another important challenge is the discrepancy in research grant funding. Larger hospitals may contribute to more datasets and may expect more research grant funds. However funding should be more towards the value of these contributions than to the size of datasets. That said, the main problem is in the accurate scaling of the value of these contributions.[7]

The success of FDNs lies with the strong and consistent governance coupled with open lines of communication among partners. Also, an approach involving incentives can boost the quality and quantity of data contributions among the member nodes. With these steps, FDNs can significantly increase the external validity and enhance the robustness and quality of RWD and the resulting RWE, without the need to centralize datasets, thereby realizing the promise of precision medicine.

Become A Certified HEOR Professional – Enrol yourself here!

References
1. Hallock H et al. Federated networks for distributed analysis of health data. Frontiers in Public Health. 2021;9.
2. Jacobson R et al. A federated network for translational cancer research using clinical data and biospecimens. Cancer Research. 2015;75(24):5194-5201.
3. Prayitno et al. A systematic review of federated learning in the healthcare area: from the perspective of data properties and applications. Applied Sciences. 2021;11(23):11191.
4. Joshi M et al. Federated learning for healthcare domain – pipeline, applications and challenges. ACM Transactions on Computing for Healthcare. 2022. https://dl.acm.org/doi/10.1145/3533708
5. Au F. Aggregated data or federated data: is one better than the other? https://blog.orionhealth.com/aggregated-data-or-federated-data-is-one-better-than-the-other/
6. The best of both worlds: benefits of applying AI/ML in a federated data network. https://www.bcplatforms.com/the-best-of-both-worlds-benefits-of-applying-ai-ml-in-a-federated-data-network/
7. Ng D et al. Federated learning: a collaborative effort to achieve better medical imaging models for individual sites that have small labelled datasets. Quantitative Imaging in Medicine and Surgery. 2021;11(2):852-857.
MarksMan Healthcare

May 28, 2022

Data Analytics, Data Curation, Data Privacy, Data Sharing, Real World Evidence
How to Encourage Healthcare Data Sharing?
Last few years have seen data as well as data exchange emerging as the new currency in healthcare. Data sharing is a powerful force that is transforming conventional relationships in the healthcare marketplace as the global healthcare platform moves from being volume-based to quality-based. (1) Around 30% of the stored global data is generated within the healthcare industry. Also, a single patient normally generates about 80 MB of data every year in the form of imaging and electronic medical records (EMRs). The abundance of such data has substantial clinical, financial as well as operational value for the healthcare industry. (2) Moreover, such data could enable new value pathways, which would be worth more than $300 billion annually in reduced costs alone. (3)

However, at present, the essential value of these data has not been recognized to the fullest by the industry. Also, this value is realized only when the raw data is converted into knowledge that would lead the change in practice. It is also explained by more inclusive data sharing and insights from within the hospital or healthcare organization, health insurance partners and community stakeholders; and most importantly, by tailored partnering with individual patients to better understand chronic conditions, enhance adherence and compliance, boost self-care, and avoid costlier treatments at costlier sites of care within the hospital’s overall population base.²

Data is the basis for healthcare and medical research, therefore data sharing expedites the progress of research. Data sharing in research is widely discussed in the literature. Conversely, there are seemingly no evidence-based incentives that promote data sharing. In order to fully utilize the power of data and data sharing, providers, payers, and purchasers must be willing to work together to share cost and quality data across the entire healthcare system; instead of treating data as an exclusive asset. Patients routinely receive care and services from different providers, health systems, and health plans. In such instances, health data may not be consistent; which can create gaps in coverage leading to uneven, uncoordinated care of poor quality and high costs.¹

Furthermore, in spite of numerous benefits, such as addressing emergencies on the global public health platform, data sharing is still not a common research practice. For example, the severe acute respiratory syndrome (SARS) disease was controlled within only 4 months after its appearance by a WHO-coordinated effort, which focused on extensive data sharing. Nevertheless, several studies have demonstrated as low rates of data sharing as 4.5% [as seen in the British Medical Journal (BMJ)] in the field of health care. The global spending on health and medical research is 85% of the total expenditure, out of which an estimated $170 billion is lost every year, leading to questions about the authenticity of scientific knowledge. Open data sharing should be vital to understand the source of ever expanding base of scientific knowledge. Open data will most certainly reduce waste in case of time, costs, and patient burden; eventually strengthening scientific knowledge by guaranteeing research integrity. (4)

The increasing gap between healthcare costs and outcomes can be attributed to poor management of research insights, poor usage of available evidence, and poor capture of care experience as well as valuable data, all leading to lost opportunities as well as resources, and potential harm to patients. To bridge this gap, the research and operational arms of healthcare can be used effectively to effectively harness data and encourage data sharing. (5)

Many approaches can be applied to encourage data sharing. While organisations are likely to favour an ‘opt-out’ model, expecting an opt-in approach based on active patient consent to be impractical that might yield low participation rate, patients must be conversant about the projected uses and benefits of sharing their data for research; which will generate awareness in data sharing and reduce the number of patients opting out. (6)

Another approach that can possibly boost data sharing would be the use of incentives. A recent systematic review has identified strategies that would facilitate data sharing practices among researchers. These strategies include the introduction to data systems, such as electronic laboratory notebooks and databases for data deposition in order to integrate a credit system through data linkage; group collaborations to use data attribution as an incentive; association among groups by means of workshops and agendas for data sharing; implementation of data sharing policies; and campaigns to promote data sharing. These strategies emphasize on the need of rewards to increase the rate of data sharing and the only form of incentive that has been successfully used is via data attribution and advertising on websites. Therefore, studies assessing the attribution efficacy and advertising as a form of credit are crucial. (4)

There are innumerable benefits of openness in research, such as verification of research findings, progress in health and medicine, increase in new insights as well as in research value, reduction in research waste, and promotion of transparency in research findings. However, there’s a lack of evidence-based incentives for researchers that hinders data sharing even in today’s evidence-based world. We have tried to suggest ways to encourage data sharing through the use of incentives. Using strategies like implementation of data systems can be adopted even by journals to use as reward for promoting reproducible and sharable research. (4,7)

Become an Certified HEOR Professional – Enrol yourself here!

References
1. Steele G. The culture of data sharing has to change. September, 2016.
2. Huesch MD, Mosher TJ. Using it of losing it? The case of data scientists inside healthcare. May, 2017.
3. Kayyali B, Knott D, Van Kuiken S. The big-data revolution in US healthcare: Accelerating value and innovation. McKinsey. April, 2013.
4. Rowhani-Farid A, Allen M, Barnett AG, et al. What incentives increase data sharing in health and medical research? A systematic review. Research Integrity and Peer Review 2017; 2:4.
5. Lee CH, Yoon H-J. Medical big data: promise and challenges. Kidney Research and Clinical Practice 2017; 36(1):3-11.
6. New JP, Leather D, Bakerly ND, et al. Putting patients in control of data from electronic health records. BMJ 2018; 360:j5554
7. Ioannidis JA, Khoury MJ. Assessing value in biomedical research: The PQRST of appraisal and reward. JAMA 2014; 312(5):483–4.
Written by: Ms. Tanvi Laghate
MarksMan Healthcare

January 31, 2019

Big Data, Data Privacy, Data Sharing, Database Studies, Electronic Medical Records, RWE

Tokenization in Real World Evidence Studies: the Concept and its Advantages

Federated Data Networks (FDNs): Enhancing the Quality of RWE Research

How to Encourage Healthcare Data Sharing?