• Informatics
  • What does eHealth have to do for radiology services?

    Radiologists are in short supply.  Radiology workloads and demand are rising. A report from Digital Health explores the opportunities to use AI and Radiology Information Systems (RIS) in the UK’s NHS to fill the gap. It identifies essential requirements for national eHealth too.

    Two solutions are proposed, both needing RIS: 

    Sharing reporting workloads across healthcare organisations

    Using AI to automate some of the clinical workload.

    Current images and workflow sharing relies on  an Image Exchange Portal run by Sectra. It’s fast, but seems it needs replacing to meet radiologists’ needs of: 

    Knowing when an image is there for reviewA single system that displays their own images and other clinicians’ images for individual patientsAccess to each patient’s reporting history and images needed for full and useful reports.

    This needs a specific organisational structure, a lesson for Africa’s health systems. In the days before England’s National Programme for IT (NPfIT) was abandoned, radiology information could be shared across each of England’s five NPfIT regions.

    Since then, smaller geographic consortia have emerged to procure Picture Archiving and Communications Systems (PACS) and RIS from single vendors. It achieves lower costs, smoother, more efficient workflows and makes their sharing easier. Patients, radiologists and organisations outside these consortia don’t benefit.

    Vendor-neutral standards are the solution. Two, Soliton and Wellbeing Software, provide solutions share radiology reporting across several sites with different RIS vendors. Their impacts are constrained because there isn’t a single or unified procurement organisation.

    Is RIS becoming obsolete? EPRs and PACS may be able to deal with scheduling and remote reporting. Some radiologists see it differently. They may be increasingly dependent on RIS.

    AI may be a solution too. It’s already dealing with some basic reporting. Wellbeing has a platform for  an AI algorithm to report directly into its RIS. 

    Agfa uses the term Augmented Imaging (AI). It’s exploring the potential for its AI to automate some administrative tasks. Algorithms are already available to detect TB on chest X-rays. Partnering’s already in place with hospitals and research institutes that need Agfa’s workflow engine to develop their own algorithms. 

    Lessons for Africa’s eHealth are clear. Radiology needs its own eHealth engagement, strategy, plans and procurement.

  • GIS software helps optimise health efforts

    Graphic information systems (GIS) software could change the way countries tackle public healthcare issues. GIS helps capture, store, combine, analyse and display aggregated data from censuses and national health information systems and then overlays this data onto regional maps.  This visual representation of data then allows departments of health and ministries to better manage resources and plan accordingly. 

    A great advantage of using GIS technology in healthcare application is the spatial dependency of health related factors.  Several countries and organisations have already started to invest in GIS programmes.  In the United States, the Centre for Disease Control (CDC) launched its 500 Cities Project, which aims to provide geographic data on the distribution of chronic disease risk factors.  In South Africa, the South African National Aids Council (SANAC) launched the Focus for Impact Project, which aims to identify populations most at risk in areas most severely affected by HIV and TB. 

    The hope is that by better visualising and understanding the geographic distribution of health variables, health departments and planners will be able to plan public health interventions more effectively.  GIS software helps with this by answering 2 key questions; 

    Where are the high burden areas? – by overlaying routine health data on geographical regionsWhy is it a high burden area? – by profiling epidemiology and associated risks using secondary data and community dialogue 

    This in turn allows health departments and health planners to identify; 

    Who is at risk in this high burden area?What interventions can help reduce this burden? 

    To improve the overall health of our communities, access to these kinds of services is vital.  Further investment into GIS programmes could reveal other beneficial use cases for the healthcare industry, improve overall efficiency and better manage the cost burden of the healthcare system.

  • Can Africa adopt a modern master patient index?

    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 continuumThe ability to access patient information is the cornerstone of co-ordinationResolving patient identities across disparate systems and enterprises is critical to accessing informationCurrent MPI technologies can’t resolve patient identities consistently enough or well enough to support emerging information needsMPIs 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 dataStandardised access protocols and content in EMRs and EHRsPatient 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.

  • 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 problemA 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 pointLogistic regression, suitable for binary classification problems and their two class valuesLinear discriminant analysis, where prediction rely on calculating a discriminate value for each class and making a prediction for the class with the largest valueClassification and regression trees represented by a binary treeNaive 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 valueK-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 instancesLearning 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 likeSupport 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 1Bagging and Random Forest (BBR), another popular algorithm, called Bootstrap Aggregation or bagging, and can estimate quantities from data samplesBoosting 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 dataThe available computational timeThe urgency of the taskThe 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.

  • Patient ID architecture needs an overhaul

    As eHealth expands its reach across more health and healthcare activities, each health system needs a more reliable Master Patient Index (MPI). Three activities are limited without it: 

    Co-ordination across the healthcare continuum and locatonsAccessing patient informationResolving patient identities across disparate systems and enterprises. 

    These need patient ID architecture needs to switch away from episodic modes. A whitepaper from        

    Verato, a cloud-based platform that matches identities, sets out how. It’s based on three components:

    Agreed business rules and policies for sharing patient dataStandardised EMR access protocols andPatient identity matching. 

    Significant progress on Interoperability (IOp) for data sharing rules and Health Level Seven (HL7) provide a foundation. What’s needed now's a set of Unique Patient Identifiers (UPI) so data sharing unambiguously refers to each patient. Easy to say, and Verato acknowledges the logistical and politically constraints. 

    Using demographic identifiers, such as names, addresses, birthdates, genders, phone numbers, email addresses and social security numbers, to identify individuals and their EMRs are error-prone when captured at receptions. They change over time too. Between 8 and 12% of people have more than one identity across healthcare organisations. Their medical histories are spread randomly across these different IDs. These duplicates are one of healthcare’s most intractable challenges.

    Current MPIs were created in the late 1990s and broadly deployed over the last ten years. They use probabilistic matching algorithms that compare all demographic attributes to decide if there are enough similarities to make a match. Common changes, such as maiden names, old addresses, second home addresses, misspellings, default entries twins, junior and senior ambiguities, and hyphenated names aren’t detected. 

    Verato’s approach uses pre-populated, pre-mastered and continuously-updated demographic data

    spanning countries’ populations. It referential matching that leverages the pre-mastered database as an answer key to match and link identities. This isn’t enough in eHealth’s changing and expanding world.

    Verato also aims to deal with:

    Adding new ICT by using standard Application Programming Interfaces (API)Automating existing MPI technologies stewardship, discovering missed duplicates and validating identities at registrationSupporting EHR consolidation where connections MPIs can’t reconcile patients’ data in other EHRsSupport HIE. 

    For Africa’s eHealth, these are valuable steps forward. It emphasises the need for better civil registration too, a long-standing challenge.

  • Dell offers better access to imaging data

    Modern eHealth can provide mountains of clinical data. Storing and accessing it effortlessly in real-time’s an increasing challenge. A whitepaper from Dell EMC, available from EHR Intelligence, describes a way to do it. 

    Key Strategic Technolgies (sic) to Improve Access to Clinical Data promotes two principles for PACS. One’s that storage infrastructure shouldn’t need redesigning every time new data’s added. The other’s to have a Vendor Neutral Archive (VNA).

    Affording a fully-fledged solution can be a challenge for Africa’s tight eHealth finances. Dell EMC proposes a phased approach that supports future VNA deployment. It is flexible enough to support a wide range of performance demands such as data analytics, expansion into private, hybrid, or public clouds and changing clinical workflows.

    It’ll need Africa’s eHealth programmes to partner with infrastructure development vendors who can: 

    Scale local architecture without downtimeMaintain daily performanceReduce or eliminate future migration burden.

    These will help to achieve several objectives that improve healthcare quality:

    Integrate imaging with other eHealthEnable doctors to taking clinical decisions using the most pertinent, complete, accurate and timely patient data. 

    Can this find a place in Africa’s eHealth strategy? The principles fit all types of clinical data.

  • Managing high risk populations’ health needs better information

    Successful population health management need health organisations to learn and know how to manage risks, outcomes, utilisation and well-being of high and increasing risk communities. Components Necessary for Managing High-Risk Population, a report from Cerner, available from EHR Intelligence, sets out ways that organisations can use information to manage people’s care as part of health risks cohorts and identify opportunities to reduce avoidable costs.

    The report says about 5% of the population are high risk. Another 20% are grouped as rising risk. Globally, these health risks are increasing. In a report, on global health risks, WHO says “Health risks are in transition: populations are ageing owing to successes against infectious diseases; at the same time, patterns of physical activity and food, alcohol and tobacco consumption are changing. Low- and middle-income countries now face a double burden of increasing chronic, non-communicable conditions, as well as the communicable diseases that traditionally affect the poor. Understanding the role of these risk factors is important for developing clear and effective strategies for improving global health.”

    Cerner’s report focuses on care management requirements and patients. The principles apply to health promotion and illness prevention too. Selecting the right people for care management plans is essential to improve their health and enable healthcare to cost outcomes. Cerner proposes three components:

    Risk stratification strategiesHealth IT needs for managing high-risk populationsChoosing the right care management approach.

    These are supported by six eHealth requirements.

    Longitudinal healthcare recordsChronic condition and wellness registries for patient cohortsCare management and co-ordination systemsLongitudinal plansData analytics and modellingReferral management system. 

    Linked to information on social determinants of health, some of this approach can support health interventions in high risk communities in low and middle income countries. It could include local data and predictive analytics to identify changes communities’ behaviour, and needs and demands for healthcare and related services such as education and social care.

  • What to expect in the next computing wave?

    Computing technology’s transient. Benjamin Franklin, a USA Founder Father, said “Nothing can be said to be certain, except death and taxes.” For computing services, obsolescence is too. Strategies need to estimate and assess what might be coming next, or the strategies can become obsolete too. Just because it’s obsolete doesn’t mean it’s worthless. Obsolete is just out of date, not used, not available. Provided it’s supported, there’s no need to chuck it in the bin. But, there’s still a need to keep up to date to take advantage of new opportunities offered by new computing technology services and techniques. Striking the right balance has considerable affordability issues for Africa’s eHealth.

    Muneeb Ali, co-founder of Blockstack, a new decentralised internet service, has set how he sees the next computing wave coming towards us. His post on Medium builds on the past, its trajectory and its obsolescence. Mainframes of the 1960s and 1970s were a centralised model with a single machine serving an entire building. Dumb terminals sent compute-jobs to the mainframe. Then, desktops of the 1980s and 1990s lead a big shift away from mainframes, with computers in people’s homes and owning the physical machine, the software and their data. Then along came the cloud.

    Data centres with huge resources are the new mainframes. Laptops are just screens to access compute-jobs in the cloud where data is stored. Their role has reverted to dumb terminals. Ali sees the next wave of computing as a “massive shift away from cloud computing.” It will overcome its two major problems:

    Cloud users don’t own their own dataRemote servers are security holes.

    Decentralised systems like Bitcoin provide explicit control of digital assets to end-users and remove the need to trust any third-party servers and infrastructure. At the Blockstart Summit in July 2017 Naval Ravikant, co-founder of AngelList, US website for start-ups, said “The arc of the internet is now bending towards decentralization.”Ali sees it having a big economic, social and political impact larger than desktops and cloud.

    It will include data silo unbundling, with data ownership and power to monetise the data shifting from large companies to users. Cloud storage providers will become dumb drives, storing users’ encrypted and suppliers struggling to differentiate from each other because they’ll all provide a similar basic storage service. Running secure, personal cloud servers will become easy as using current cloud services.

    Publishing source code for software will become almost a requirement for security reasons. Running closed-source black box magic software will be seen as a security risk.

    Cryptocurrency tokens, tradable goods such as coins, points, certificates and company shares, are often used to raise funds in crowd sales. As assets and equity, their protocols could be as common as software licenses and terms-of-service agreements for cloud services. Having an appropriate token can provide access to software in decentralised computing.

    Expanded human capacity is needed to underpin this new computing wave. Cyber-security engineers, cryptographers, and distributed systems engineers will be in high demand. Local universities and colleges will need to help to increase their supply.

  • England’s NHS spending on a digital academy

    Developing eHealth leaders is an essential component of successful eHealth. NHS England has announced it’s creating the NHS Digital Academy. Its goal’s to train and develop informatics capabilities for Chief Information Officers (CIO) and Chief Clinical Information Officers (CCIO). The one year programme’ll provide specialist ICT training and development support to 300 senior clinicians and health managers.

    It implements the recommendation in a report from the National Advisory Group on Health  Information Technology  in England, lead by its chair, Prof Robert Wachter, chair of University of California, San Francisco  Department of Medicine. The report identified a shortage of CCIO and CIO professionals who can advance eHealth transformation. Harnessing the Power of Health Information Technology to Improve Care in England proposed spending of £42m, about US$55m, €46m, to strengthen and expand CCIOs’ capacity, especially in informatics, and health ICT professionals. It’s about 1% of the England’s £4.2b eHealth plan. It’s about 0.04% of NHS England’s total spending.

    NHS Digital Academy will have three main partners in the initiative, Imperial College London, the University of Edinburgh and Harvard Medical School. Part of the programme’s remit’s to support the development of vibrant professional societies for clinician and non-clinician informaticians, informatics researchers, programme evaluators and system optimisers. It’ll be mainly online, with some residential events.

    eHealth success needs many other leaders across the whole reach of programmes. It seems that their development needs are not part of this initiative. NHS England already has its Leadership Academy.

    Can Africa’s health systems start a journey towards this? Several Universities across Africa already provide health informatics degrees. Several Africans attend the Master’s in e-Health Management course at Rome Business School, supported by Acfee, which also provides Future eHealth Leaders events, including pre-conference workshops at this year’s eHealthAFRO 2017. While modest compared to NHS England’s initiatives, these combine into a start-point for eHealth leadership capacity.

  • Call for Papers - six days to go

    Sharing eHealth experiences and research finding’s essential to progress. These are the main goals of the Health Informatics South Africa (HISA) Call for Papers (CfP) for its conference at eHealthAFRO 2017 on 2 to 4 October 2017 in Johannesburg. It’s hosted by the South African Health Informatics Association (SAHIA). The CfP has four topics. They are:

    eHealth Strategy, governance and regulationeHealth impact through routine health informationCyber-security related to eHealth applicationseHealth systems related to public health and surveillance. 

    Papers on other relevant eHealth topics may be considered. Will extra papers include health informatics developments and research on eHealth futures, such as AI and health analytics?

    The timetable is: 

    Full papers submitted to South African Computer Journal (SACJ), complying with SACJ’s submission guidelines, by Monday 28 August 2017    Notification of paper acceptance on Friday, 15 September 2017Final author registration by Friday, 22 September 2017Final paper due Friday, 29 September.

    A special SACJ edition will published presented papers. They’ll comply with SACJ’s editorial process, so at the end of the submission form, comments to the editor should include “HISA Conference paper.”

    eHealthAFRO 2017 brings together researchers and practitioners active in health informatics. At least one author should register for eHealthAFRO and present the paper at the HISA Conference for the paper to be eligible for SACJ publication. SACJ charges ZAR6,000 for publication costs for accepted papers, but authors with no funding can apply for this to be waived.

    Prof Nicky Mostert-Phipps is the contact for submissions. She is a software development lecturer at the Nelson Mandela Metropolitan University Faculty of Engineering’s Built Environment and Information Technology, and can provide more information about HISA’s conference and preparing and submitting papers.