Tom Jones

eHealth strategist, planner and evaluator

  • Duplicate patient records keep turning up

    Achieving accurate patients’ IDs’s a constant theme of managing EHRs. Duplicate records just won’t go away. University of Washington (UW) Medicine based in Seattle regularly reviews and improves the reliability and accuracy of its EHRs. Cleaning duplicate records is an important part of the task. 


    Its latest initiative, available from EHR Intelligence, is  with Just Associates,  a consultancy that identifies and resolves patient data integrity problems, reveals some critical lessons for Africa’s eHealth. It found that the duplicate rate was significantly higher than the 10% to 20% it usually finds. The main cause was inadequate information. Many records contained only four of six ID components. They’re last name, first name, middle name, gender, fate of birth and social security number. 


    The review identifies the source of ID issues and issues that create duplicates. This information has helped UW Medicine to develop its strategy and planning to control duplicate rates.


    There’s a long-standing ID challenge. It’s an “uphill battle to dedicate the appropriate resources.”

    Sustaining appropriate staffing levels for ID management’s a challenge. Part of the solution’s relying on ICT tools. An objective’s to using technology to improve efficiency and reduce staff time manually accessing and matching records. It means that staff can then deal directly, efficiently and successfully with awkward ID cases and records.


    A valuable lesson for Africa’s eHealth’s that EHRs alone are not enough. Extra resources are needed to ensure the value of data in EHRs. With a typical duplicate rate of 10% to 20%, any drift in ID management seems to lead to higher rates, so greatly diminished value of EHRs’ data.


  • mHealth can help to reduce hospital readmissions

    Using mHealth to improve hospital services’s a common theme in Africa’s eHealth strategies and plans. Reducing readmissions’s an important part of these initiatives. A report from MobileSmith says how three mHealth solutions can help. 


    How to Reduce Preventable Readmissions with Healthcare IT describes:


    • Efficient mHealth strategies for reducing hospital readmissions
    • Strategic use cases for prompt implementation
    • Six best practices for cost-effective apps for engaging patient and doctors. 


    Efficient mHealth should provide:


    • Relevant discharge communication
    • Family and carer engagement
    • Improved medication adherence
    • Chronic disease control.


    The six best practices are: 


    • Research and know target patient groups
    • Think big, start small, act fast, so avoid mHealth that does everything for everybody, so unlikely to be user-friendly
    • Polish user interfaces and experiences
    • Keep mHealth fresh
    • Establish secure data exchanges
    • Adopt analytics. 


    Underpinning each of these’s the core goal to empower patients. mHealth’s the bridge that healthcare can leveraging now to empower patients. It can only work with easy-to-use mHealth so patients are encouraged to become more proactive towards their health. These themes need expanding in Africa’s next wave of mHealth strategies and plans. They also need setting alongside high priority patient groups and clinical conditions.


  • Five main insights on the impact of EHRs

    While EHRs provide the most comprehensive, up-to-date patient information, more details about their impact’s needed for investment decisions. eHealth investment challenges are:


    • What benefits to they bring
    • How are they realised
    • How long does it take
    • Does their value exceed their costs.


    Spectralink describes insights into some of these in its technical brief Five ways EHRs improve healthcare delivery. It’s available from EHR Intelligence. The five generic ways are:


    • Access to critical data, anytime, anywhere
    • Improved care coordination
    • More accurate diagnostics
    • Increased work flow efficiencies and cost savings
    • Better patient participation.


    Within these five, ten benefits are identified across two groups:


    Physician workflow              

    • Accessed patient chart remotely - 74%
    • Alerted to critical lab value - 50%
    • Alerted to potential medication error - 41%
    • Reminded to provide preventative care - 39%
    • Reminded to provide care meeting clinical guidelines - 37%
    • Identified needed lab tests - 28%
    • Facilitated direct communication with patient - 25%

    Patient-related outcomes   

    • Enhanced overall patient care - 74%
    • Ordered more on-formulary medications  - 41%
    • Ordered fewer tests due to lab results availability - 29%


    Three other activities show large impacts: 


    • Note practice functions more efficiently - 79%
    • Receive lab results faster - 75%
    • Report enhances in data confidentiality - 70%. 


    While these are large increases, there’s no information about how much more efficiently, fasters of enhancing these changes were. These estimated values are important in evaluating EHRs’ impacts. 


    None of the benefits refer to increased patient access as part of Universal Health Coverage (UHC). This needs resources liberated by efficiency gains to be redeployed to communities with no or limited UHCs. Acfee reviews reveal that these seldom happens on a large scale with EHRs. It has to be linked to specific UHC initiatives. 


    Uploading information with mHealth links are in place in about two-thirds of EHRs. This offers scope for further investment. It’s an essential feature for Africa’s eHealth




  • AI and machine learning need data storage resources

    Many things come in bundles. Amit Ray, author of Mindfulness Meditation for Corporate Leadership and Management says “As more and more artificial intelligence is entering into the world, more and more emotional intelligence must enter into leadership.” It’s not enough. A report by Source Media, sponsored by Pure Storage says powerful, advanced computing and storage capacity and capabilities are needed too.

    It recognises AI’s “vast” potential. Currently, some radiology departments use it effectively to improve workloads. Progress across other clinical activities depends on extra computing and storage power for two activities, training and clinical use.

    When researchers deliver AI and machine learning techniques to clinical practice and healthcare, solutions need huge amounts of data for training models, including labelling data. It’s especially important for neural networks. These are hardware and software patterned on the way neurons work in human brains. They’re deep learning technologies often focusing on solving complex signal processing or pattern recognition problems.

    If storage’s inadequate, it can’t keep up with the workload. The result’s diminished AI. Healthcare’s typical eHealth investment model’s to buy enough computing storage infrastructure as a minimum requirement, then expand it a few years after it’s clogged up. Eventually, it’s replaced with modern solutions after a period of obsolescence.

    This doesn’t fit AI and machine learning. It has to match the computer power and storage capacity needed as AI and machine learning expands. Developers and healthcare organisations can then move beyond exploring AI’s potential and bring into full use. The, patients benefit.

    While assembling the resources needed for AI and machine learning’s challenging for Africa’ health systems, the infrastructure requirements add to the constraints. Before venturing into the AI space, it’s essential to contemplate and deal with the whole resource requirements and their affordability. 
  • Experts offer their different views on London hospital’s AI

    The AI project announcement by a major London hospital’s attracted a wide span of opinions and ideas. Building on the plan reported in eHNA, the Times has several letters on the initiative. 


    Prof Sir Robert Lechler, President of the Academy of Medical Science emphasised the requirement to have the basics in place to realise the benefits and more healthcare to lead toe fourth industrial revolution. It includes sufficient resources for collaboration with industry, academia and regulators.  He sets the goal of people’s good mental and physical health.


    Hilary Evans, CEO Alzheimer’s Research UK, sees AI as an opportunity to revolutionise dementia research. Her goal is to improve early detection and diagnosis of the progressive disease. 


    Another prof, Harold Thimbleby from Swansea University has a different view. He says more AI’s a simple theory and that much of it data is flawed. Instead, fixing bad ICT would be more cost-effective, offer increased medical value and extend across more health conditions. The effect can be dramatic. 


    Nicola Perrin, Head of Understanding Patient Data, says AI success relies in patients having confidence in how their data’s used. A constructive dialogue’s needed with the public, She evokes the alarms raised from the Facebook and Cambridge Analytic controversy.


    J Merrion Thomas, a surgeon, says the money for AI would be better spent  on earlier benefits, such as highlighting known risk factors and early diagnosis. These will save lives immediately, rather than wait for AI’s benefits.


    These wide-ranging comments are just as relevant for all types of eHealth. They illustrate the engagement and commitment challenges of eHealth’s numerous stakeholders and provide valuable lessons for Africa’s health systems. eHealth never goes ahead in a straight line.

     


  • Is AI set to take off in a London hospital?

    As marches go, AI in healthcare’s still in its early stages. It may be that it’s about to make a big leap forward. The UK’s Guardian newspaper  reports that University College London Hospitals (UCLH) and the Alan Turing Institute has agreed a three-year partnership to realise AI’s benefits to healthcare on an “unprecedented scale.” Planned projects include using AI to: 


    • Improve UCLH’s A&E department’s performance, currently below 77% of patients needed urgent care treated within four hours, well below the standard set for England and stuck at 2010 levels
    • Analyse CT scans of 25,000 former smokers recruited as part of a research project
    • Automate cervical smear tests assessments. 


    A challenge is avoiding learned helplessness. It’s where health professionals become too reliant on automated instructions and abandon common sense. AI’s algorithms might be correct 99.999% times, but are rarely 100% reliable.


    Another’s sustaining rigorous data governance standards, especially privacy and confidentiality. The plan’s to apply algorithms to UCLH’s servers to avoid breaches. Private companies won’t have access. 


    A previous AI project in Engalnd’s NHS was a collaboration between London’s Royal Free Hospital and Google’s DeepMind. The Royal Free accidently gave Google access to 1.6 million records of identifiable patients.


    Alan Turing was an English computer scientist, mathematician, logician, cryptanalyst. He was highly influential in developing theoretical computer science, formalising concepts of algorithm and computation using the Turing machine. In the 1940s at Bletchley Park, he was instrumental in developing the Bombe machine to crack enemy’s complex and rapidly changing Enigma code.

     


  • US EHR solution judged not up to the job

    eHealth has risks. A report from the US Office of the Secretary of Defense, and available from EHR intelligence, highlights some of these. They provide valuable themes for Africa’s health systems to use in their EHR assessments and procurements. Is says “a partial  IOT&E [Initial Operational Test and Evaluation] was adequate to determine that MHS GENESIS was neither operationally effective nor operationally suitable.” It raises an important challenge: how could this have been established before procurement? 


    Inappropriate performance included: 


    MHS GENESIS is neither operationally effective nor operationally suitable. DOT&E recommends that the Under Secretary of Defense for Acquisition and Sustainment delay further fielding until JITC completes the IOT&E and the PMO corrects any outstanding deficiencies. Detailed recommendations are included in the main body of this report;



    • It doesn’t demonstrate enough workable functionality to manage and document patient care in 56% of the 197 tasksof performance
    • Poorly defined user roles and workflows increased the time needed for health care providers to complete daily tasks, including overtime and seeing fewer patients a day
    • Users questioned information accuracy in exchanges between external systems and MHS Genesis
    • Poor usability of 37%, on the System Usability Scale (SUS), well below the 70% threshold
    • Insufficient training
    • Inadequate help desk support
    • System unplanned downtime outages indicated that the end-to-end system and supporting network didn’t have sufficient availability to support operations at the four IOT&E locations
    • Users reported increased lag times when other IOT&E sites went live, suggesting the supporting network configuration wouldn’t support the hundreds of additional planned sites
    • Survivability is undetermined because cybersecurity testing isn’t complete. 


    This salutary experience shows the importance of rigorous assessment processes before procurement. Across the global eHealth community, it’s not the first time, and it’s not likely to be last. Africa’s health systems can afford this type of risk exposure experience. 


  • How can online health information avoid negative results?

    Type “health information” into your favourite search tool.  Then, prepare to scroll through over 2.6 million results. The negative effect of these sources on users hasn’t been examined.  A study led by Reem El Sherif at the Department of Family Medicine at McGill University in Montreal, and published in the Journal of Medical Internet Research (JMIR), aims to deal with it.

    Two goals are:

    • Describe negative outcomes in primary care
    • Identify potential preventive strategies from users, health practitioners and health librarians.

    It found three types of interdependent negative outcomes:

    • Internal, such as increased worrying
    • Interpersonal, such as a tension in patient-clinician relationships
    • Service-related, such as postponing clinical encounters.

    The study links them as:




    Three types of strategies were identified that aim to reduce these negative outcomes. They were:

    • Providing users with reliable information
    • Educating users on how to assess websites that provide health information
    • Helping users to present and discuss their online information with health professionals, their social networks or librarians.

    These are integrated too:

    Librarians have a core role in minimising negative outcomes. Responsible for providing reliable health information and advocating the advantages of using health websites, they’re well positioned to implement the preventive strategies. Their work with users and health practitioners can integrate them with users’ health information–seeking and ensure the reliability of the information they find and use. Improving health literacy can lead to fewer internal tensions. Librarians can also develop discussions with health practitioners, leading to fewer interpersonal tensions. Their third contribution’s helping users to find relevant information so they can make better health and health care decisions, leading to fewer service-related tensions.

    While this might seem a bit obvious, the researchers identified two barriers that needed overcoming. One’s a lack of awareness of available health librarian services. The other’s a lack of access to health librarians by the public. A possible solution is to train community librarians working in public facilities, such as libraries, on how to provide health information services.

    Africa’s health systems should consider these additional costs of online health information. Without these resources, their investments in online health information may not realise the benefits requires of them, so an inadequate return.




  • GE sells its healthcare Value-Based Care Division to Veritas for >$1b

    In a shake-up to the health ICT supply side, an announcement by GE says it’s selling its:

    • Enterprise Financial Management, Revenue-Cycle, Centricity Business
    • Ambulatory Care Management, Centricity Practice Solution
    • Workforce Management, formerly API Healthcare.

    The buyer, Veritas Capital takes it on for $1.05b in a cash-will-do-nicely deal. It’s Veritas Capital is a leading, global private equity firm that invests in companies that provide essential products and services. Technology and technology-enabled solutions are its main service range. Governments and commercial organisations are its main customers.

    They extend across aerospace, defence, healthcare, national security, communications, energy, education and government services. It’s Veritas business model seeks to create value by strategically transforming companies that it invests in.

    GE says Veritas is ideal to provide the focus and investment needed to take GE’s former services to the next level of scale and performance. The former GE team  sees the switch as an opportunity to revitalise its product portfolio and pursue complementary acquisitions. The intended result’s better for patients, providers and payers services

    These big outfits seldom see Africa’s health systems as fruitful markets. Affordability’s a constraint. Will Veritas take a different view?


  • AlienVault insider’s guide to cyber-security incident response can help

    Preventing cyber-security breaches is a top priority. On its own, it’s not enough. Cyber-criminals are at least one step ahead, so sound preparation for an incident response’s vital.  A book from Alien Vault can help. It's an Insider’s Guide to Incident Response in one eBook! 


    It provides a detailed insight into the fundamental strategies of efficient and effective incident response that security teams need. The goal should be to do more with less to deal with the rapidly changing cyber-threats. The guide deals with: 


    • Arming and aiming an incident response team
    • Incident response processes and procedures
    • Types of cyber-security incidents
    • Incident response tools
    • Incident response training


    Combating cyber-threats needs teams with a strong mental constitution.  Techniques are needed too. The guide sets out how to build an incident response plan and develop a team that has the right tools and training.


    Observe, Orient, Decide and Act (OODA) loop’s the core methodology.  It’s a cycle developed by military strategist and United States Air Force Colonel John Boyd. He used it to help to prepare for combat operations processes. It’s now applied to understand commercial activities. 


    Benjamin Franklin, the 18th century polymath promoted the original concept. “By failing to prepare, you are preparing to fail.” It applies to eHealth too.