Tom Jones

eHealth strategist, planner and evaluator

  • Can Africa adopt a modern MPI?

    Paper patient administration and medical records can be unreliable in sustaining patient identification. Overcoming their limitations needs a sound Master Patient Index (MPI) and effective patient identification as a foundation for dependable eHealth. A white paper from Verato, an MPI vendor, describes a way to do it.

    A thesis in The Future of Healthcare Depends on a New Architecture for Patient Identity Interoperability has five components:

    • Healthcare will involve extensive co-ordination across the full care continuum
    • The ability to access patient information is the cornerstone of co-ordination
    • Resolving patient identities across disparate systems and enterprises is critical to accessing information
    • Current MPI technologies can’t resolve patient identities consistently enough or well enough to support emerging information needs
    • MPIs patient identity resolution technology must support the new needs as part of a highly accurate, national patient identity resolution service.

    Africa’s health systems can apply these criteria to their strategic and procurement choices. They apply to all types of eHealth, not just EHRs. It’s a core requirement for improving healthcare efficiency. It supports a shift from point-in-time service towards effective healthcare co-ordination too.

    Three themes are needed for effective access to patient information: 

    •  Agreed rules and policies for sharing patient data
    • Standardised access protocols and content in EMRs and EHRs
    • Patient identity matching.

    A unique national patient ID number is seen as supporting these. But Verato sees this as logistically

    Impossible, politically untenable because of privacy implications and would not help link people to pre-existing medical records. Relying on basic demographic identifiers such as name, address, birthdate, gender, phone, email, and social security numbers aren’t a solution because they’re prone to error when patients register at receptions and can change over time. About 8 to 12% of people may have more than one identity in any given hospital system, with actual medical histories spread randomly across them.

    MPI matching techniques was invented in 1969, and obsolete. Verato sees the solution as a pre-built, cloud-based, nationwide MPI that healthcare organisations  can plug into. It can avoid the need for extensive algorithm tuning, data standardisation, data governance, data cleansing, or data stewardship. It can help to achieve better compliance with data standards. 

    As Africa’s eHealth moves on, the concept can be assessed as an investment option. If it’s not, then an option to deal with the limitations of conventional MPIs may be needed.

  • Limited IOp’s a drag on benefits

    For several years, health informaticians and other eHealth’s ICT experts have recognised the link for effective Interoperability (IOp) and eHealth benefits. Now, US finance executives have added to the case for more IOp.

    A US Healthcare Financial Management Association (HFMA) survey of 117 financial executives identified their views. It found an increasing need for an increased IOp priority, slightly up to from 68% in 2015 to over 70%. Almost a quarter, 24%, said their organisations can’t share data effectively with other providers and payers.

    Their views extended to external and internal IOp. Both are seen as a combined, upcoming primary focus of healthcare providers. Three drivers are:

    • Current shortcomings
    • Anticipated future need
    • Increasing demand for access to numerous data sources.

    While the survey may not have revealed much that’s new about IOp, it’s a valuable reminder that progress is slow. For Africa’s health systems, it confirms the long timescales needed to reach high IOp levels. If it’s taking the rich US health systems so long, Africa’s can’t expect rapid results. Slow, steady and sustained seem to be their IOp plan.

  • Top ten algorithms that can help healthcare

    As algorithms become more prevalent in eHealth, it’s important to have a clear development path for their use. Two core principles are:

    • No single algorithm works best for every problem
    • A learning a target function (f) maps input variables (X) to an output variable (Y), so: Y = f(X), used for predictive modelling.

    An article by James Lee in Towards Data Science sets out ten top algorithms. They’re: 

    • Linear regression, a long-standing techniques from some 200 years ago, but a good starting point
    • Logistic regression, suitable for binary classification problems and their two class values
    • Linear discriminant analysis, where prediction rely on calculating a discriminate value for each class and making a prediction for the class with the largest value
    • Classification and regression trees represented by a binary tree
    • Naive Bayes, a simple, powerful algorithm for predictive modelling using two types of probabilities, one of each class, the other the conditional probability for each class given each x value
    • K-Nearest Neighbours (KNN), a simple and effective algorithm, where predictions are derived from  new data points by searching  entire data sets for the K most similar instances, the neighbours, and summarizing output variables for those K instances
    • Learning Vector Quantisation (LVQ), a KNN relative, and an artificial neural network algorithm enabling choices of the number of instances to hang onto, learning precisely what the instances should look like
    • Support Vector Machines (SPV) are possibly one of the most popular, using a hyperplane to separate points in input variables spaces by their class, either class 0 or class 1
    • Bagging and Random Forest (BBR), another popular algorithm, called Bootstrap Aggregation or bagging, and can estimate quantities from data samples
    • Boosting and AdaBoost, an ensemble technique aiming to create strong classifiers from several weak classifiers by building a model from training data then creating a second model that attempts to correct the errors from the first model.

    Selecting algorithms in eHealth uses, four questions need answering, what’s:

    • The size, quality, and nature of the data
    • The available computational time
    • The urgency of the task
    • The data to be used for.

    The answers aren’t easy to find. Lee points out that experienced data scientist can’t tell which algorithm’s best before trying different ones. It seems that Africa’s eHealth needs time to ponder these before settling on a preferred short list.

  • Ghana will have a national telemedicine service next year

    Pilotitis become a phenomenon a few years ago as scaling-up eHealth pilots became too challenging. Good scale-up news is the recent  telemedicine initiative by Ghana Health Service and The Novartis Foundation, They’ve announced the successful integration and scale-up of a telemedicine service. National coverage’s planned for 2019. 

    The 24-hour telemedicine service uses mHealth for community health workers to consult specialist health professionals at teleconsultation centres on a range of health topics, including emergencies. It builds from the telemedicine pilot started in 2011 in the Ashanti Region’s Amansie West District.

    An important lesson for other African countries’s the timescale. Seven years may seem like a long time, but eHealth does take time to come to fruition. Over the period, telemedicine has encountered some specific changes. mHealth opportunities have replaced conventional conferencing technology, now obsolete and looking a bit clumsy and chunky.

    Ghana may have set a standard for other African countries to follow. It represents a considerable technological achievement in modernising and transforming healthcare. 

  • mHealth to drive Cote d’Ivoire's immunisation project

    Like falling snow, announcements at the World Economic Forum come thick and fast. Taking place in Davos Switzerland, Thursday 25th, 2018, one of the world’s leading telecommunications operators, Orange SA and the Vaccine Alliance Gavi announced a partnership with Côte d’Ivoire’s Ministry of Health to boost immunisation rates in the countries’ regions and districts with the lowest vaccine coverage.

    A report in Ventures Africa says it’s a joint US$ 5.47m five-year project. Half the money’s from the Gavi Matching Fund, a mechanism financed by the Bill & Melinda Gates Foundation to motivate and provide incentives for private sector investment in immunisation. It builds from Gavi’s longstanding role in the country starting form 2001, Gavi supported Côte d’ Ivoire in introducing eleven vaccines.

    It all fits with the M-Vaccin Côte d’ Ivoire initiative. It uses Orange mobile technology to inform parents about the importance of vaccination. Sending text and voice messages in local languages and targeting messages about keeping immunisation sessions are standard themes. Reminders of their children’s schedules and dates are the main goals.

    The initiative should be transferrable to all African countries. It’ll be good to see vaccination rates above 95% soon.

  • Analytics offers expanding opportunities for better health

    EHRs alone are no longer enough. Their rich source of data alongside other readily available data such as social media sources, can improve EHRs cost and benefit curves. A whitepaper from Insight, available from Health IT Analytics sets out a way to do it. As Africa’s health systems move their programmes for EHRs forward, they need to run analytics in parallel to maximise benefits for all types of stakeholders. 

    Achieving Success in the Big Data Analytics Era With Microsoft SQL Server says healthcare

    faces new realities about clinical care and business processes, with patient satisfaction scores, performance metrics and risk-based arrangements becoming routine. It’s switching decision on short-term expediency to using data make the choices for raising quality, improving populations’ health and lowering costs.

    Many healthcare organisations are unprepared, even though almost 75% of hospitals’ chief financial officers say EHRs are insufficiently sophisticated enough for complex risk modelling needed to improve performance One solution’s Microsoft SQL Server.

    It’s a database engine plus a full suite of components, resources, connections and community that supports organisations’ entire data platforms. It can help to analyse historical data and reveal current performance and trends that need addressing. Examples are avoiding patient harm, closing healthcare gaps and preventing duplicated or unnecessary services.

    Its set of services includes: 

    • Reporting,  to create interactive reports
    • Analysis,  to mine and manipulate  data for actionable insights
    • Integration, streamlining Extraction, Transformation and Load (ETL) processes
    • R, to develop and deploy applications to enhance data assets’ usefulness and  reduce the time to insight.

    As analytics becomes more routine, Africa’s health systems will need both skills and tools to benefit from them. Insight offers a tool. Health systems will have to invest in the skills too.


  • HELINA wants papers for its October conference

    In the lead up to its conference in Nairobi on 1 to 5 October 2018, Health Informatics in Africa (HELINA) has released its timetable for its call for papers. It’s:

    • Paper submission deadline: 30 April, using the online system
    • Notification of paper acceptance: 15 July
    • Papers ready for publication: 15th September.

    Submissions have to comply with the Uniform Requirements for Manuscripts to Biomedical Journals. There’s a help line for support.

    The main conference themes are:

    • National and regional eHealth strategies and policies
    • Interoperability
    • Quality, continuous quality improvement and using health data and systems
    • Human capacity building for eHealth
    • Applying technology in supply chain management
    • Sustainable ICT solutions for health service delivery
    • Technology-enabled health financing.

    There’s a host of other topics too:

    • Health facility management information systems
    • PHR information systems
    • HIE
    • IoT and wearables
    • Point of care information management solutions
    • Health informatics standards
    • Mobile health
    • Health financing information management
    • Healthcare research informatics
    • Health systems M&E
    • Decision support systems for low resource settings
    • Biomedical devices integration
    • Medical imaging and radiology information systems
    • Laboratory information systems
    • Pharmacy management information systems
    • Data mining and Big Data analytics
    • AI and machine learning.

    This considerable, attractive array offers a strategic profile for Africa’s health systems. It’d be goo to see cyber-security added.

  • ISfTeH International Conference prepares to set sail

    Organising conferences is seldom plain sailing. ISfTeH hopes its’ event will be. This year's ISfTeH International Conference theme’s eHealth2018 - Health Communities Facing Cyber Transformation event. It’s aboard a cruise ship on the Baltic Sea between Helsinki, Finland and Stockholm, Sweden, on 15 to 17 March 2018.The Finnish Society of Telemedicine and the organiser.

    Presenters include representatives from:


  • Cisco’s umbrella can help deal with cyber-attacks

    Simple, open, automated and effective: these are the four cornerstones of Cisco Umbrella set out in its solution brief. Cisco sees its value in dealing with the complexity, range and reach of eHealth services. It’s continuously expanding, along with its cyber-security requirements and gaps. Available from Health IT Security, the brief sets out its functions as: 

    • Covering gaps without any hardware to install or software to manually update
    • Protecting any device and every port without configuration changes or latency
    • Extending existing protection and incident response data through integrations
    • Protecting all devices, locations, and users on and off networks
    • Predicting threats before they happen by learning where attacks are staged
    • Blocking malicious domains and IPs before connections are established
    • Stopping threats before they reach networks and endpoints
    • Identifying infected devices faster and preventing data exfiltration.

    Cisco recognises that cyber-security isn’t an absolute, 100% state. Its goals are to maximise prevention and achieve early, effective responses to cyber-attacks.  This is realistic, and offers an option for Africa’s eHealth.

  • EHRs can be more efficient, with better quality

    Better efficiency and quality are two main eHealth benefit groups. They don’t stand alone. Benefits in one group can lead to benefits in the other. Imprivata  emphasises two lessons in its white paper, available from EHR Intelligence.  Saving time, improving care Two lessons to remember when integrating a new EHR sees efficiency gains liberating resources for better quality. 

    Its proposition’s that clinicians can waste 13 seconds waiting unnecessarily with the time they log into EHRs. Aggregating these across all clinicians’ logins can create a valuable chunk of their time, about 13,000 hours a week for a typical hospital. On this scale, clinicians’’ time, can be redeployed to improving health care quality. This simple arithmetic looks appealing, but it’s consistent with an EHR challenge of redeploying each clinician’s small time savings and efficiency gains. It’s an essential, but not an easy activity. 

    Three important findings from a study by American EHR illustrate the difficulties:

    • 42% of professionals who found it difficult to improve efficiency with EHRs
    • 72% found it difficult to decrease workload with EHRs
    • 54% said EHRs increased total operating costs.

    These confirm the need for eHealth to be highly usable. It’s a prerequisite for benefit realisation. 

    Imprivata suggests early types of EHRs incorporate these constraints. Modern versions can overcome them, and more benefits will result. It points Africa’s health systems to the need to test the efficiency and performance of EHRs that they’re considering in their procurements. Better EHRs offer better benefits. It looks encouraging for Africa’s healthcare.