Contact Us

Home

About us

Services

AI Excellence

case studies

publications

HEOR Certificationheor Certification

AI for Medical Writing

Contact

  • Big Data in Medicine and Artificial Intelligence: A Real World Challenge?

    Big Data in Medicine and Artificial Intelligence: A Real World Challenge?

    Artificial Intelligence (AI) refers to a computerized system that performs physical tasks, cognitive functions, solves problems, and/ or makes decisions without overt human instructions.[1] First proposed by McCarthy in 1955, the concept of AI has been applied in many health-related areas, including clinical research, hospital care, drug development, disease diagnosis, prognosis, and treatment monitoring. Advancement in the field of research has led to low-cost computational resources leading to digitalization of healthcare, innovation in daily routine examination, and improving overall quality of treatment. It has become an important element of medical diagnosis, for example, in the assessment skin lesions, detection of diabetic retinopathy, interpretation of chest X-rays, etc. In addition, AI has great value in aiding clinicians to improve quality and safety of healthcare delivery.[2]

    Over the years, big data has unknowingly been part of daily routine in the medical field as well, through clinical trials data, patients’ records, pharmaceutical research, claims data, fitness and diet apps, and various data storage platforms. Big data originated in 1997, when it became difficult to display large data sets that were stored in computers and limited the analysis of data. Doug Laney summarised the challenges of big data as the ‘3 Vs’: volume, variety, and velocity.[3]

    • ‘Volume’ refers to the quantity of the new data that is created from multiple sources, such as health records, insurance claims, transactions, sensors, etc.
    • ‘Variety’ refers to the difference in the format of Big Data from different sources, which can be structured, unstructured, semi-structured or a mixture of the three.
    • ‘Velocity’ refers to the temporal component of Big Data, in terms of creation, storage, and analysis: this can be in batches, near time, real time, streaming, retrospective, prospective, or a combination.

    There has been integration of AI and big data in the field of medicine. AI concepts such as data mining, complex statistical analysis, machine learning, and neural networks are being increasingly used for faster and more precise big data analysis in medicine.[4] This integration of AI and big data has been seen in different applications, such as mHealth (wearable devices such as smartwatches, fitness bands) and eHealth (Google fit, Apple health) applications for self-management and home care. AI also has a role in the analysis of big data originating in:

    • Electronic health records (EHRs) and electronic medical records (EMRs) for epidemiological, safety, efficacy, and patient-reported outcomes insights
    • Imaging data for precise diagnosis and treatment monitoring, especially in oncology, wherein the AI has been used for precise description of tumour biology and implementation of precision medicine for the assessment of tumour, its microenvironment, and radiomics.
    • Personal health records (PHRs) and practice management software (PMS) to improve the service, quality and costs of healthcare delivery with less medical errors.
    • Genomic sequencing like genotyping and gene expression.
    • Development and usage of wellness monitoring devices has gained popularity in improving health.[5,6]

    Though AI and big data work in synergy, often it is observed that health care systems are not fully equipped, as in the case of medical imaging, to share large amount of images. Analysis, labelling, accurate curation and clinical applications are the major challenges.[7] Repeated models with homogeneous data, lack of diversity in different populations and restricted clinical setting with poor generalizability remain the major setbacks of AI currently. The currently available AI systems, though advanced, still have a far way to go to be completely and reliably accurate enough to totally replace human intervention. There are concerns surrounding quality control, accuracy, consistency, security and privacy with AI, which mandate human intervention and participation in health-related data curation. [8]

    The analysis of big data in medicine, either through stand-alone AI protocols or with assistance of manual data curation, largely contributes to the development of real-world evidence (RWE). This offers incredible amount of data that can support regulatory drug approvals. In fact, RWE has been the basis of several approvals, such as the recent approval of Novartis’ alpelisib as the first and only treatment for PIK3CA-related overgrowth spectrum, which is considered as a rare disease.[9] This showcases the importance of RWE generation through big data curation by means of manual curation-assisted AI protocols.

    AI has a big role to play in big data curation and analysis in health care, but at the present, human intervention still cannot be completely replaced by AI. Manual curation still has an important role to play in medical big data analytics.

    Become A Certified HEOR Professional – Enrol yourself here!

     References

    1. Kaplan A, Haenlein M. Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Bus Horiz. 2019;62(1):15–25.
    2. Ahmad Z, Rahim S, Zubair M, Abdul-Ghafar J. Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosophical considerations. A comprehensive review. Diagn Pathol. 2021 Mar 17;16(1):24.
    3. Laney, D. (2001). 3D data management: controlling data volume, velocity, and variety. Meta Group. http://blogs.gartner.com/douglaney/files/2012/01/ad949-3D-Data-Management-ControllingData-Volume-Velocity-and-Variety.pdf
    4. Rahmani AM, Azhir E, Ali S, Mohammadi M, Ahmed OH, Yassin Ghafour M, Hasan Ahmed S, Hosseinzadeh M. Artificial intelligence approaches and mechanisms for big data analytics: a systematic study. PeerJ Comput Sci. 2021 Apr 14;7:e488.
    5. Yang YC, Islam SU, Noor A, Khan S, Afsar W, Nazir S. Influential Usage of Big Data and Artificial Intelligence in Healthcare. Comput Math Methods Med. 2021 Sep 6;2021:5812499
    6. Dash S, Shakyawar SK, Sharma M, Kaushik S. Big data in healthcare: management, analysis and future prospects. J Big Data 2019;6:54
    7. Willemink MJ, Koszek WA, Hardell C, Wu J, Fleischmann D, Harvey H, Folio LR, Summers RM, Rubin DL, Lungren MP. Preparing Medical Imaging Data for Machine Learning. Radiology. 2020 Apr;295(1):4-15.
    8. Wehner MR, Levandoski KA, Kulldorff M, Asgari MM. Research Techniques Made Simple: An Introduction to Use and Analysis of Big Data in Dermatology. J Invest Dermatol. 2017 Aug;137(8):e153-e158.
    9. https://www.novartis.com/news/media-releases/fda-approves-novartis-vijoice-alpelisib-first-and-only-treatment-select-patients-pik3ca-related-overgrowth-spectrum-pros

    MarksMan Healthcare

    , ,

  • How Next Generation Intelligent Data Systems are Helping in Patient Care?

    How Next Generation Intelligent Data Systems are Helping in Patient Care?

    The 90’s saw the Internet and the World Wide Web entering commercial markets as a result of major advancements in Information Technology (IT). Another huge development was later followed when mobile devices connected to the Internet became a rage in late 2000’s. Today, we’re in the middle of the next major leap, i.e. the next generation of intelligent (IT). (1)

    These leaps will not only continue having a significant impact on our personal lives, but they will also introduce new business models and product and service opportunities. The ever expanding technological progress is taking ahead the scientific knowledge, thus reducing costs and presenting the healthcare industry with innovative medical devices and procedures to diagnose, monitor and treat patients. (2)

    Big data has already transformed almost every aspect of life, including healthcare; and it’s time we implemented data-driven healthcare in our routine. Advances in data collection, storage and analytics have been accompanied by the proliferation of data; for e.g. from sensors and devices, clinical information systems and electronic health records (EHRs). Simultaneously, widespread application of data standards and interoperability is being observed, thus allowing developers to find more functions for health data. (3)

    As a result, many healthcare organizations, including pharmaceuticals, biopharmaceuticals as well as medical devices firms; are turning these recent and emerging technological advancements to good account, thereby providing innovative solutions using mobile health applications, sensor technology, data analytics, and artificial intelligence. The last decade has also witnessed the steady growth of venture capital investments stimulating medical technology (MedTech) products, especially in areas like bioinformatics and biosensors. (2)

    In addition, the volume of data produced by healthcare organizations is expanding and it is facilitating the delivery of cancer treatments, personalization of medical interventions, prediction of chronic diseases, driving behavioral changes through next-generation analytics technologies such as big data, cognitive computing and machine learning. Furthermore, artificial intelligence (AI) is constantly evolving and improving. Today, technology exists to capture data from incongruent sources and provide a real-time view of a patient’s health. All the associated technologies are evolving faster and continuously, such as mobile, cloud, analytics and the Internet of Things, to deliver solutions in advanced AI. As a result, the global predictive analytics market is expected to grow by almost 20% a year, reaching $6.5 billion by 2019.(3)

    Sensors and connected devices capturing all kinds of data are omnipresent. The worldwide market for wearable technology is expected to rise from 45 million units shipped in 2015 to more than 125 million by 2019. (4) Digital consumer devices entering regulated markets have increased in numbers, with expected FDA approvals for these products to triple in 2018 (relative to 2014 levels).(5)

    Next generation intelligent devices are creating immense opportunities for traditional healthcare as well as medical device companies. For instance, the smart contact lens has been developed by Novartis and Google to monitor glucose levels in people with diabetes. Another example is recently launched LOGIQ E10, the next generation radiology ultrasound technology by GE Healthcare. In LOGIQ E10, the digital system incorporates AI, cloud connectivity and advanced algorithms to gather and reconstruct imaging data faster; thus significantly improving image quality and giving clinicians better confidence in their diagnoses, particularly in difficult cases. (6)

    Big data can be derived from mobile medical health systems, wearable devices, and other next generation mobile communications technology and can be further used to integrate the primary medical services and improve primary healthcare quality, residents’ health index, control the growth rate of a variety of common acute and chronic diseases and increase residents’ awareness of health management and disease prevention. (7,8) Therefore, the next generation IT systems can most certainly be used into healthcare field to overcome worldwide health problems such as uneven distribution of medical resources, the growing chronic diseases, and the increasing medical expenses and can help provide patients with overall better quality of care.

    Become a Certified HEOR Professional – Enrol yourself here!

    References

    1. Glaser J, et al. The Next Generation of Intelligent Healthcare Information Technology. Convergence. Sept 15th, 2017. 
    2. Next-generation “smart” MedTech devices- Preparing for an increasingly intelligent future. Deloitte Analysis.
    3. Reily T. How data is making healthcare better. World Economic Forum.
    4. Worldwide Wearable Market Forecast to Reach 45.7 Million Units Shipped in 2015 and 126.1 Million Units in 2019, IDC.
    5. Patient Engagement: How the Colossal Clash Will Disrupt the Digital Health Landscape – Infographic.  Accenture. 
    6. Monegain B. Artificial intelligence powers GE Healthcare’s next-gen ultrasound system. March 2nd, 2018. 
    7. Li G. Big data related technologies challenges and future prospects. Inf Technol Tourism 2015; 15(3):283-285.
    8. Ma Y, et al. Big health application system based on health Internet of Things and Big Data. IEEE Access 2016; 5:7885-7897.

    Written by: Ms. Tanvi Laghate

    MarksMan Healthcare

    , ,

  • How Blockchain Technology is Likely to Change Life Science Industry?

    How Blockchain Technology is Likely to Change Life Science Industry?

    For many businesses, trade and commerce ideas are still trapped in Victorian era in spite of ever increasing IT-reliance. Whether it is a business settlement, transfer of property ownership or resolving an insurance claim, composite business processes can take days to complete and require volumes of repetitive, tedious paper-based work. All these processes, however, need mediators, such as stock exchanges, banks, government agencies or technology platforms, to serve as the trusted middle man between unknown parties and carry out record-keeping, accounting and law enforcement. These further result in unintended loss of precious time and money in creating, maintaining and dealing with mediators. To tackle such challenges, “blockchain technology”, the decentralized, distributed ledger infrastructure built around strong cryptography, is expected to support full digital transformation across the life sciences space. (1,2)

    To put it simply, blockchain is a log of transactions that is duplicated and allocated across multiple decentralized locations. It offers reliable, unbiased third party mechanisms to gauge the location of a particular data set and also the predictions about its precise transformation. (3) Recently, blockchain technology has been witnessing rapid growth, especially in the healthcare and life sciences domains; and it’s only the beginning of what’s possible. A recent IBM study- ‘how blockchains can provide new benefits for healthcare’- reports about 16% of healthcare executives are planning to implement a commercial blockchain solution at present and this number is expected to reach to 56% by 2020. (4,5)

    Creating practical, highly reliable records associated with a patient regardless of their moving through different healthcare systems is one of the biggest challenges of healthcare IT. Blockchain offers an opportunity to build a reliable place to track the changes across systems in order to attend to many of the concerns associated with data integration between proprietary systems. (3) Blockchain can be implemented across all supply chain functions, particularly proving beneficial for the life sciences supply chain; such as provenance, serialization track and trace and specialty logistics. (6)

    Depending on the requirement and types of permissions among data sharers, there can be different types of blockchains providing value to the life sciences supply chain. These types of blockchains include: Public, Permission-less Blockchains (allowing access to any user at any time), Federated, Permissioned Blockchains (accessible to users based on the rules defined by the group of entities participating in the network), and Private, Permissioned Blockchains (allowing access to users based on the permissions set by the private network). (7)

    One of the most intricate challenges of the life sciences supply chain is the ability to effectively track the origin of a product (or therapy) from raw materials to the finished product. Blockchain is an ideal solution to this problem, given that no single organization is responsible for provenance. Additionally, in order to eliminate counterfeit and diverted products thereby contributing to increased patient safety, blockchains can be helpful with serialization capabilities for the recall process. Recall notification, once injected into the blockchain, can generate communication and alert messages to all affected parties (manufacturers, distributors, dispensers and eventually patients). Moreover, blockchain together with technologies like IIoT (Industrial Internet of Things) can provide documentation of storage temperatures at every point in a product’s journey, thus generating solutions for specialty logistics. (7)

    In near future, approximately 30 percent of life sciences companies are planning to employ blockchain, thus opening new business opportunities and addressing past challenges. Blockchain tools in supply chain applications know no bounds for life sciences companies, given the necessity for specialized medicines and therapies. (7)

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. The Voyage of Discovery: Blockchain for Pharmaceuticals and Medical Devices. IEEE. April, 2017.
    2. Blockchain: A Catalyst for the Next Wave of Progress in Life Sciences. Cognizant. June, 2017.
    3. Bean R, et al. How Blockchain Is Impacting Healthcare And Life Sciences Today. April, 2018.
    4. Frazeer H. How blockchains can provide new benefits for healthcare. February, 2017.
    5. Marr B. This Is Why Blockchains Will Transform Healthcare. November, 2017.
    6. Guenther C.  Transforming life sciences with blockchain. February, 2018.
    7. In blockchain we trust: Transforming the life sciences supply chain. Accenture Life Sciences.

    MarksMan Healthcare

    ,

  • How to Encourage Healthcare Data Sharing?

    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

    , , , , ,

  • How Data Analytics Utilisation Can Direct Population Health Programs?

    How Data Analytics Utilisation Can Direct Population Health Programs?

    An excellent population health management approach considers multiple aspects of health, such as sufficiency of medical care, public health interventions, social and physical environments and related services, genetics, and individual behavior. (1) Data from multiple sources can be used to conduct population health management programs and to assess their value. In addition to these diverse data, data from big population health programs are driven by huge volume, high speed, and incoherent data flows. (2)

    Population health programs improve health by catering to individuals with unmet medical needs as well as taking actions to close these gaps; thereby encouraging quality in health care that focuses on getting the right care to the right patient at the right time. (3,4) Given the extensive potential of population health management, its execution may require maximum utilisation of big data sources existing across the healthcare and other social systems. (5)

    Advanced data analytics, when used appropriately, has the potential to improve patient care in the health care system. With the shift in healthcare towards outcome and value-based initiative, analysis of existing data to determine the most efficient practices can enable cost reduction and improvement in population health. With more and more healthcare systems becoming data-reliant, insights regarding health of population along with data on high-risk individuals can be understood with the help of data analytics. With this knowledge, the health systems can more competently assign resources thus maximising revenue, population health and, most importantly, patient care. (6)

    The ongoing big data utilisation by population health programs is capable to get even bigger in time to come. Multiple data types are usually used to manage such programs. Clinical data includes information on engaging health management programs as well as data on health risks collected via survey-based health assessments. External data sources describing characteristics of home life, neighbourhood, and the local supply and quality of health care can provide understanding of the origin of social or physical environment. Yet, other survey data can be helpful in assessing health-related quality of life (HRQoL) and insurance arrangements, perceptions of access to care, and the quality of care received. (2)

    Delivering practical insights to help providers get an understanding of chronic diseases as well as tracking the success of practice transformation processes are two main driving forces while developing big data analytics infrastructure and reporting during population health programs. It is imperative to optimize electronic health records (EHRs) to collect some data elements in a more standardized way, and to emphasize on executing data governance programs that account for currently unstructured data as well as data that to be structured better. (7)

    Implementing a robust framework of good governance will help providers and payers to move towards desired clinical and financial improvements in the near future. The management of population health programs has proven beneficial with recent advancements in big data; especially, when big data is successfully leveraged to execute a comprehensive program. Additionally, data generated from these programs have been used to routinely monitor program performance and to conduct in-depth program evaluations. Further advancements in technology will certainly improve population health and social service programs through the use of big data. (2,7)

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. Kindig D, et al. What is population health? Am J Public Health. 2003; 93:383.
    2. Wells ST, et al. Leveraging big data in population health management. Big Data Analytics. 2016; 1:1.
    3. Chen EH, et al. Improving population health through team-based panel management: comment on “Electronic medical record reminders and panel management to improve primary care of elderly patients”. Arch Intern Med. 2011; 171:1558–9
    4. Clancy CM. What is Health Care Quality and Who Decides. Committee on Finance Subcommittee on Health Care United States Senate, Agency for Health Care Research and Quality, U.S. Department of Health and Human Services. 2009.
    5. Hartman C. Healthcare’s growing data opportunity. Leveraging clinical intelligence to elevate population health management strategies. Health Manag Technol. 2014; 35:24.
    6. How healthcare analytics improves patient care. 
    7. Bresnick J. Population Health is Top Data Analytics Challenge for Providers, Payers. HealthIT Analytics. 

    MarksMan Healthcare

    , , , ,

  • How Integration of Multiple Data Sources can Improve Patient Insights?

    How Integration of Multiple Data Sources can Improve Patient Insights?

    There are humungous quantities of data existing in healthcare; data from all kinds of sources, such as clinical, patient, payer, R&D, pharmacy as well as revolutionary technologies that are being quickly embraced, for e.g. data from wearable devices. According to a report by International Data Corporation (IDC), (1) the volume of healthcare data which was observed to be around 153 exabytes in 2013 is estimated to reach around 2,314 exabytes in the year 2020. Therefore, integrating data from all types of diverse sources and clinical systems is a fundamental challenge for any healthcare entity in order to enhance patient care and performance indicators. (2)

    It’s obvious that these huge amounts of health data are essential for betterment of both the cost as well as the quality aspects of care. Also, analyses of these data can provide significant insights for patients and researchers. However, methods to merge data from multiple formats and sources ranging across various systems used within clinics are still unclear. Data quality and accessibility provided by these systems can vary to a great extent. The healthcare industry has been traditionally observed to embrace new technologies; however, it lags behind while handling data, particularly data sharing and integration. To add to the practical challenges of data integration processes, compliance and capability to join forces with all the healthcare stakeholders also faces problems. As a consequence, data collection, storage, integration, and analysis make up for complicated processes. (2)

    There are some specific underlying concerns surrounding multiple, un-integrated data sources, viz. lack of broad view into enterprise-wide data as well as data standardization and governance, and matching patients to care events. Lack of broad view can impose challenges resulting in time consuming and expensive procedures during development of meaningful internal and external reports, like quality and patient safety regulatory and accreditation reporting. It may also hamper efforts to identify and prioritize opportunities to reduce costs, while improving care and patient experience. Lack of data standardization and governance can hamper performance of important analytics owing to multiple data sources, definitions and terms. Last but not the least, it is crucial to match patients accurately to their respective care events across multiple sites of care, which can be a complicated process. (3,4)

    There is no doubt that the Healthcare systems undoubtedly require effective data integration tools and greater level of flexibility when handling data, typically from multiple sources. The standards implemented in many countries recently have been intended for healthcare data integration and unification. For instance, in the USA the Health Information Technology (HITECH) Act (5) offers incentive payments to health care providers implementing certified EHR technology while showing meaningful use of that technology. HIPAA standards provide healthcare data protection; while HL7 standards allow clinical and administrative data communication between software applications used by various healthcare providers. (6)

    In order to gain patient insights, integration of data from multiple sources can prove to be beneficial. One way to facilitate data integration can be incorporating data warehouses [enterprise data warehouses (EDWs)], which can facilitate easy data mining in case of faster, major data initiatives. These methods can pull in and push out data with just one interface. Furthermore, data governance policies focusing on data standardization, advances in data reporting and further education and communication need to be in place in order to make changes in how data is to be collected, defined, and consumed. By integrating health data with financial and cost data to track patient encounters across multiple care locations and information systems, it is easier for health systems to compare patient quality and cost, i.e. comprehending the exact process of ‘value’ delivery. This insight is the difference between surviving and thriving in the new value based purchasing environment. (4)

    Clinical data integration from multiple sources can provide a wide-ranging perspective across care delivery systems. Health systems can easily carry out reporting while employing quality improvement initiatives, such as analytical care variation and measuring implementation of evidence-based guidelines. (4)

    To sum it all up, multiple data integration can obviously facilitate electronic exchange of information, while also reducing the costs and intricacies of building interfaces between different systems; thus proving valuable patient insights. The foundation of the healthcare industry’s data-sharing conundrum is data interoperability. Genuinely integrated systems must be easily understood by users, i.e. these systems must be able to exchange data and consequently put it forward through inclusive and user friendly interface.

    Become an Certified HEOR Professional – Enrol yourself here!

    References 

    1. Corbin K. How CIOs can prepare for healthcare ‘data tsunami’. December, 2014.
    2. Healthcare data integration: How to combine data from multiple sources. 
    3. Managing the integrity of patient identity in health information exchange. American Health Information Management Association. 2009. 
    4. Turning Data from Five Different EHR Vendors into Actionable Insights. Health Catalyst.
    5. Health Information Technology (HITECH Act). 2009. 
    6. Summary of the HIPAA Privacy Rule. 

    MarksMan Healthcare

    , , , , , ,

  • Best Practices for Protecting Privacy While Conducting Big Data Analytics

    Best Practices for Protecting Privacy While Conducting Big Data Analytics

    The concept of “Big Data” is #trending today, which is characterized by types of data sources with huge quantities, high speed and broad diversity of information. Healthcare industries are trying to apply Big Data analytics to reform data into a workable platform in order to generate information that would help making better and faster clinical decisions, such as reduced readmissions, scaling down hospital-associated illnesses, identifying and eliminating waste, improved clinician workflow etc. Government and the private sectors are taking in Big Data to enable better, quicker and more valuable care delivery to people. (1)

    With rising discussions about Big Data, artificial intelligence, and related techniques in health care, the need for the appropriate and more importantly, ethical use of these methods is becoming increasingly relevant. (1) Privacy and confidentiality associate closely with each other. Data privacy talks about the rights of individuals to maintain control over their own health information; while confidentiality is the responsibility of entities handed over with those data to maintain privacy. (2) Concerns of data privacy and confidentiality hamper their scope, proper storage, accessibility, and propagation, particularly in case of highly sensitive or personal data. The ever expanding scope of data collection, storage and analysis (3,4), further add to the risk of data privacy infringements. (5,6) In addition, data anonymity does not ensure against individuals’ identity subsequently through the joining of data sets and re-identification, (7) data manipulation and discrimination, (8) or other inappropriate ways of data uses. (9) Therefore, protected management of patient data is necessary, since healthcare clouds link large amounts of data from disparate networks. (10)

    There are several factors of privacy and security that must be taken into consideration while using Big Data analytics for healthcare. For instance, although it has the potential to provide an understanding on the huge volumes of heterogeneous data, challenges arise with respect to potential security and privacy breaches; which, as a result, hinder the process of appropriately accessing the value held within the data. (11)

    Big Data platform must embrace multiple layers of security for data at rest and the data in flight. All communications between data sources, data consumers and the Big Data warehouse should be encrypted to provide security to the data. There are some methods that can be applied to ensure data security in Big Data analytics. A traditional method to prevent the confidential information disclosure by de-identifying, i.e. rejecting any information that can identify the patient, either by removing specific identifiers of the patient or by the second statistical method, where the patient verifies himself that enough identifiers are deleted. The traditional method can be enhanced with the help of concepts like k-anonymity, l-diversity and t-closeness. Moreover, hybrid execution model ensures confidentiality and privacy in cloud computing by utilizing public clouds only in case of non-sensitive data and computation classified as public; i.e., when the organization declares no privacy and confidentiality risk in exporting the data and performing computation on it using public clouds. While it uses private cloud in case of sensitive, private data and computation, some techniques do apply identity-based anonymization. However, due to increased complexity as well as several limitations, these models need to undergo further research and tests as they are getting more difficult to interpret and less reliable. (12)

    Patient data security and privacy are crucial in driving the healthcare transformation. With Big Data in healthcare becoming more omnipresent with cloud computing, the host companies will be more reluctant to share massive healthcare data for centralized processing. Hence, distributed processing across different clouds and pulling up on cumulative intelligence is foreseen.

    The extreme sensitivity of healthcare data makes their confidentiality and integrity crucial. Therefore, in healthcare, Big Data security is fundamental. Additionally, to provide the best care, healthcare providers must have quick, but secure, access to a patient’s medical history. Security solutions should ensure protecting analytics and securing Big Data frameworks. Laying out the right technical foundation is a precondition for successful data analysis.

    Become an Certified HEOR Professional – Enrol yourself here!

    References 

    1. Balthazar P, et al. Protecting Your Patients’ Interests in the Era of Big Data, Artificial Intelligence, and Predictive Analytics.  J Am Coll Radiol 2018; 15(3 Pt B):580-586.
    2. Centers for Disease Control and Prevention. Emergency preparedness for older adults; HIPAA, privacy and confidentiality. Available at:
    3. Mittelstadt BD, et al. The ethics of big data: current and foreseeable issues in biomedical contexts. Sci Eng Ethics 2016; 22:303-41.
    4. Nunan D, et al. Market research and the ethics of big data. Int J Mark Res 2013; 55:505-20.
    5. Andrejevic M. The big data divide. Int J Commun 2014;8:17.
    6. Puschmann C, Burgess J. Metaphors of big data. Int J Commun 2014;8:20.
    7. Choudhury S, et al. Big data, open science and the brain: lessons learned from genomics. Front Hum Neurosci 2014; 8:239
    8. Crawford K. The hidden biases in big data. Harvard Business Review. Available at: https://hbr.org/2013/04/the-hidden-biases-in-big-data.
    9. Tene O, et al. Big data for all: privacy and user control in the age of analytics. Nw J Tech Intell Prop 2012; 11:xxvii.
    10. Patil HK, e al. Big data security and privacy issues in healthcare. Nanthealth: Dallas, US. 
    11. [11] Rao S, et al. Security solutions for big data analytics in healthcare. Second International Conference on Advances in Computing and Communication Engineering – IEEE, 2015. 
    12. Abouelmehdi K, et al. Big data security and privacy in healthcare: A Review. Procedia Computer Science 2017; 113:73-80.

    MarksMan Healthcare

    , , ,

  • Forecasting the Analytics Landscape to Anticipate Future Patient Requirements

    Forecasting the Analytics Landscape to Anticipate Future Patient Requirements

    There is heaps-full of data existing in the healthcare domain that has been generated historically, by means of record keeping, compliance & regulatory requirements, and patient care. (1) The current trend suggests faster digitization of this large amount of data, known as ‘Big Data’, that have been stored as hard copies over time. Big Data can facilitate a wide range of medical and healthcare functions, such as clinical decision support, disease surveillance, and population health management; with primary goals of providing better quality of healthcare delivery as well as reducing the costs. (2,3)

    Big data are often identified by 5V’s in terms of Volume, Velocity, Variety, Value, and Veracity. The patient data collected often amount to peta or zeta bytes in volume. The speed and rate at which data is received from the patients explains the velocity. The miscellaneous data sets classified as the structured, semi-structured and unstructured data sets like clinical reports, EHRs, and radiological images represent variety; whereas veracity is when the true and reliable data sets with accessible and genuine data are provided. The collected data are transformed to provide meaningful understanding, thus explaining their significance in 5V’s. (4)

    While multiple discussions on healthcare data are focusing excessively on probable risks and misuses of the data, there are also enormous profits from extending healthcare data usage. A whole host of use cases are available to prove the widespread value being created by data analytics, across all stakeholders of the healthcare system, including patients, healthcare professionals and providers, payers, researchers, biopharmaceuticals and medical device companies, and regulatory authorities. Patient and healthcare associations in the past, while discussing the big data applications, have focused on the potential risks linked to exploitation of personal health records (such as predictions of individual or family health risks). Progressively, however, patients are accepting the countless benefits of data analytics, while still being vigilant about possible risks linked to data misuse. (5)

    Data analytics, in conjunction with latest technologies, can help healthcare providers expand care pathways and services “beyond their walls”. For example, new measurement devices (such as wearable, ingestible or implantable sensors) can convey data that will prompt a provider to determine patient crisis. For instance, a provider can foresee and avert any complications like diabetic foot and evade amputation by monitoring vital signs in diabetic patients. In psychiatric or neurological patients, accurate supervision of a combination of indicators can provide better certainty of a crisis. Growing number of continuous monitoring services that rely remarkably on connected objects and data analytics are already altering care paradigm for chronic patients. Examples of these include Bioserenity solutions for epilepsy, Ginger.io for chronic conditions, several congestive heart failure programs being undertaken worldwide, or Diabeo for individualized insulin dosing.(5)

    As we can see, data analytics has the potential to put together predictive models and categorize patients based on the probable/future healthcare risk they might carry, in order to modify treatment protocols to their profile. These models are crucial in deciding the success of disease management programs. With increasing digital technologies, life sciences and healthcare are on the verge of a revolution. Continuous improvement in the global and quick analysis methods, initiated with genome sequencing, along with the increasing digitization of vast information, now creates substantial quantity of data. The exploitation and analysis of these big data create new prospects, while also helping address technological, scientific and medical challenges.

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. Raghupathi W. Data Mining in Health Care. In: Kudyba S, editor. Healthcare Informatics: Improving Efficiency and Productivity. 2010. pp. 211–223.
    2. Burghard C. Big Data and Analytics Key to Accountable Care Success. 2012.
    3. Fernandes L, O’Connor M, Weaver V. J AHIMA. 2012. Big data, bigger outcomes; pp. 38–42.
    4. Sahoo PK, et al. Analyzing Healthcare Big Data With Prediction for Future Health Condition. IEEE 2017; 4:9786-9799.
    5. Unlocking the full potential of data analytics for the benefit of all. Healthcare Data Institute. November, 2015. 

    MarksMan Healthcare

    , , ,

  • Importance of Tapping Payer’s Data to Document the Effect of a New Therapy

    Importance of Tapping Payer’s Data to Document the Effect of a New Therapy

    Traditionally, the pharmaceutical industry has always been dependent upon the ‘push’ strategy for successful market access for products. The drug approval process, involving submission of data on efficacy, safety, and tolerability to the regulatory agencies, used to be simple; which ended with the drug being marketed to the targeted physicians and dispensed by pharmacies post approval. Thus, this whole process involved a limited set of stakeholders, viz. physicians, regulatory agencies, and pharmacies. Conversely, over the years, the market access landscape has evolved primarily due to two factors: (1)

    1. Rising healthcare costs owing to an increasing prevalence of chronic diseases, growing geriatric population, and higher prices of new therapies
    2. Competitive pricing and reimbursement environment

    This has further led to the emergence of a new and diverse set of stakeholders over the years, i.e. the ‘Payer’(s), increasing the complexity of drug access to the market in general, and to patients in particular. Payer exercises the greatest degree of control over pricing and reimbursement for any new drug, and will continue to dominate the market access scenario to ensure successful market access. (2,3)

    Pharmaceutical advancements are increasingly conflicting as countries attempt to accommodate healthcare costs via different tools. New criteria for recognizing unique drugs and differences among those within the same therapeutic area or concerning the same molecule are being introduced, even though ‘price’ remains the main driver. (4) There is a surge of criticism towards the increasing prices of drugs that adds growing pressure on pharma companies and manufactures to limit future price increases, and eventually on payers to be more cost-effective in their approach to setting budgets and managing costs. (5) Global pharma operations need to keep up with the pace of these changes to approach pharma tendering as a strategy that spans pricing and commercialization.

    In order to document the effect of a new therapy in the real world, pharma companies are trying to justify prices by tapping payer’s data. Payers encourage pharma to collect post-launch evidence of product performance in the real world, thus turning it in pharma’s favor. This can help verify a price agreement or even clarify uncertainties about the clinical and/or safety outcomes outlined at registration. (6)

    The successful market access will involve collaborative team work between sales and marketing departments. The strategy itself should be well equipped to respond to market evolution and also, to accommodate all known interactions. There is no ‘one-size-fits-all’ solution. The challenges in the market will constantly vary as per the product, therapy area and the setting in which the treatment will be used.i,vi

    Payers are increasingly focusing on “real-world” outcomes to form their decisions, encouraging new policies to be formed, in order to assimilate evidence from different sources. These policies prioritize the evidence that goes beyond information collected during clinical development in randomized controlled trials (RCTs), required by regulatory authorities for marketing approval. ‘Administrative data’- that normally use retrospective or real-time patient data – are an example of the real world data sources, as they are collected primarily for reimbursement, but contain some clinical diagnosis and procedure use with detailed information on charges. Retrospective analyses (longitudinal and cross-sectional) of clinical and economic outcomes at patient, group, or population levels can be performed with the help of claims databases. Such analyses can be performed in short time and at low costs. (7)

    In conclusion, payer data from real-world such as claims data can most certainly impact the sound coverage, payment, and reimbursement decisions. It is critical that payers recognize – a) the benefits, limitations, and methodological challenges in using these data, and b) the need to carefully consider the costs and benefits of different forms of data collection in different situations.

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. Kumar A, et al. Pharmaceutical market access in emerging markets: concepts, components, and future. Journal of Market Access & Health Policy 2014; 2:10.3402/jmahp.v2.25302.
    2. McClearn C, et al. Big pharma’s market access mission. Deloitte University Press; 2013.
    3. Arx RV, et al. Leveraging success factors for market access in the life sciences industry. Capgemini Consulting and Cegedim dendrite; 2009.
    4. Skinner JS. The costly paradox of healthcare technology. September, 2013. 
    5. Pharmaceutical pricing and market access 2017.
    6. Wechsier J. Measuring the value of prescription drugs. Pharmaceutical Executive 2017; 37(5).
    7. Garrison LP Jr. Using real-world data for coverage and payment decisions: The ISPOR Real-World Data Task Force Report. Value Health 2007; 10(5):326-225.

    MarksMan Healthcare

    , , , , , , , ,