• Hospitals
  • 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 levelsAnalyse CT scans of 25,000 former smokers recruited as part of a research projectAutomate 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.

     

  • Robot Tug to help aid nurses in hospitals

    The field of robotics is making great leaps in health care today.  Take for example, Tug, the robot nurse. The aim of this robot is to improve patient care in hospitals by doing the mundane tasks like hauling food, linens, specimens and medications around the facility. This enables the healthcare workers to focus on other relevant duties and patient care.

    Appearance wise, Tug does not look like a typical humanoid robot. Instead, it looks like an oven that has wheels.  Staff begin the day by uploading activities that they would like Tug to do and then it wheels itself around the hospital performing those duties. It is programmed in such a way that employees can change the order of the tasks based on urgency.

    Tug navigates a facility using dozens of lasers therefore it is able to make quick decisions such as stopping when a person is in the way. It can carry up to a 1000 pounds on its back which can also be swapped with different models to meet other needs besides medical deliveries and food.

    This is a great use case for the overburdened, understaffed hospitals in Africa – a robot to aid nurses and health workers with their daily activities.  Will we being seeing Tug in African hospitals soon?

  • e-Hospital portals can improve hospitals

    The world we live in has seen a revolution of digitisation in mobile phones, banks and the internet are examples.  People want to avoid or reduce the time they spend doing things manually, and would rather opt for using the latest technology.

    An e-Hospital portal is an example. It’s a project introduced by the government of India. An aim's to use technology to empower people and help them connect to areas of health.

    e-Hospital enables the public to book outpatient appointments, view diagnostic reports, check the availability of blood, lab reports and pay their fees. Using this type of eHealth offers quicker access, remote diagnosis and faster medical prescriptions. Time taken to receive treatment or see a medical expert is expected to be reduced considerably.

    Services provided by an e-Hospital portal maximises the contribution of existing healthcare professionals. It enables networks of nurses and doctors to achieve more efficient treatment and monitoring.

    The large scale of the project offers an insight for Africa’s eHealth strategies. Planning directly for national coverage can offer bigger scale benefits, even where, as in India, roll out's phased.

  • Voice recognition reduces Tanzania's patient waiting times

    Patients at the Muhimbili National Hospital in Dar es Salaam no longer have to endure long waiting times for their radiology results.  This is thanks to a new technology installation in the department.  Voice recognition or speech recognition technology is now being used to encode doctors notes on patients so that they can easily be transferred to the radiology department. 

    With this new technology, Tanzanian medical professionals are able to dictate into their computers, in the normal course of speaking and have the speech engine recognise what the clinician wants, and then apply the commands or structured words, respectively, to obtain a radiology report for a patient.  There has been some concern around the effect of speech accents on the technology, but this has posed no problems since implementing it at the hospital.  

    The speech engine is also capable of showing the cardiology report template populated with the name of the patient and other demographic data. By dictating the cardiology report narrative, the computer recognises the narrative context and intent and condenses a complete, correct, and structured document.

    This translates to shorter waiting times for patients, greater operational efficiency within the hospital and reduced workload on medical staff who are required to take notes of patient examinations and consultations.  The technology, which uses natural language processing, is constantly learning speech behaviour through repetitive exposure to terms and complex algorithms that organise speech patterns into recognisable behaviour. 

    This bold technology implementation in Tanzania could be a useful pilot for overburdened health care systems in Africa hoping to achieve the same benefits.

  • A portal doesn’t improve US hospital outcomes

    As the internet and web have spread across healthcare, portals have been seen as an essential link between patients and clinical teams. It seems they don’t make any difference to hospital outcomes. A study at Mayo Clinic Hospital, Jacksonville, published in the Journal of the American Medical Informatics Association (JAMIA), found the 30-day re-admissions, inpatient mortality and 30-day mortality rates were virtually the same for hospital patients who used portals without prompting and those who didn’t have accounts to use them. The 30-day rates were adjusted for Lengths of Stay (LOS).

    Interpreting the results needs to incorporate the limitations of the portal. It has no specific features for communication between patients and healthcare teams. It only includes admission notes, operative notes, consultations and laboratory studies in real time. Daily progress notes can’t be viewed, and there’s a 72-hour delay in viewing radiology and pathology reports. There’s no educational material about patient-specific diseases and processes.

    Patients with portal accounts seem to drop their access on admission. About 44% of patients who had a portal account when they were admitted, but fewer than half, about 21%, accessed it when they were inpatients. Other studies have found similar results, such as 34% and 23%. For tertiary services, the rates were 25% and 16%.

     of registered users accessed their account.22 The lack of features designed specifically for inpatient use was previously emphasised in a systematic review.14 Consequently, several medical centres designed hospital-specific applications aimed at improving the use and usability of inpatient portals.23–25 In a realistic review, Roberts indicated that patient participation with inpatient health information technology (including patient portals) can be augmented by interactive learning focused on information sharing, self-assessment and feedback, tailored education, user-centred design, and user support. Outpatients with severe diseases use portals more frequently. 

    Patients who access portals have better outcomes for some chronic conditions such as: 

    ·             Diabetes, with lower haemoglobin (HbA1c) after 6 months

    ·             Hypertension, with improved blood pressure control at 12 months)

    ·             Depression management, with increased medication adherence

    ·             Preventative care, such as up-to-date immunisations and mammograms. 

    Portals can have benefits. African health systems need to be explicit about what their portals can achieve and ensure that these are maximised.

  • eHealth for consultations can reduce hospital waiting times

    It’s inevitable that appointments with hospital specialists have waiting times. eHealth that provides online consultations can reduce them. A report in the New England Journal of Medicine (NEJM) Catalyst says NYC Health + Hospitals, an integrated healthcare system of hospitals, neighbourhood health centres, long-term care, nursing homes, and home care, has built an eConsult services that improves access to specialty care and reduces patients’ waiting times.

    It offers fast review of clinic referrals for specialists to provide clinical guidance to some referring providers. The initial pilot found 30% of referrals were either appropriate for management by the referring provider or needed extra work before patients were seen by specialists. Transforming these clinical and working practices has three lessons that Africa’s health systems can consider for their eHealth strategies and plans: 

    1.     Learn the unique needs and limitations of health systems’ referral processes so eConsult’s aligned specific needs

    2.     Specialty clinics must prepare for an appropriate eConsult workflow by designating a specialist reviewer who can triage each referral and allocate resources for patient communications and scheduling

    3.     Specialty providers must collaborate on the best care plan each patient and set clear expectations on communications and shared management. 

    The greatest waiting time reduction was a pilot clinics third next available appointments dropping from 37 days to eight days in the first six months, about an 80% improvement. Achieving an equivalent for Africa’s health systems can improve productivity and liberate some of their overstretched healthcare resources for redeployment to other patients, and minimise costly journeys for patients and save them time.

    Los Angeles County Department of Health Services provides acute and rehabilitative services with 19 integrated health centres. Fierce Healthcare has reported that its eConsult service achieved similar benefits. About 25% of patients resolve their health issues without visiting specialists.

  • India’s NH adds another eHealth centre to its services

    Remote communities are challenging for all health systems. Solutions can rest with high level operators, not just community services.

    Narayana Health Group (NH), a successful healthcare provider in India, runs several prestigious facilities and services in and around West Bengal. They include Rabindranath Tagore International Institute of Cardiac Science in Mukundapur, Kolkata and Narayana Superspeciality Hospital in Guwahati and another in Howrah. It’s not surprising that it’s launched its fourth eHealth Centre in West Bengal at Tikiapara in Howrah. A report in the Echo of India says the initiative’s in association with Rebecca Belilious Charitable Dispensary, a Samaritan Help Mission project. The goal’s to make primary healthcare and diagnostic facilities accessible to people living in Howrah’s remote communities where access to quality healthcare, specialist consultations and diagnoses aren’t available.

    NH’s initiative includes telemedicine and cloud services. These help to overcome connectivity, electrical supplies and sourcing medical team challenges of rural areas. These are longstanding challenges caused by a lack of medical resources and poor infrastructure. The eHealth Centre will overcome these because it relies on self-sustained infrastructure and robust healthcare services using remote access through cloud technology.

    There are NH lessons for Africa’s health systems. Integrating eHealth as part of health system expansion may offer better opportunities that stand-alone eHealth programmes. eHealth is, after all, one of healthcare’s resources.

  • Four apps for ER doctors

    Emergency Rooms (ER) are busy. mHealth that eases workload and makes ER doctors’ working lives better are worth it. In Med Page Today, Dr Iltifat Husain has identified four that help.

    GoodRx for Doctors, described by Dr Husain as “fantastic … for helping your patients be compliant with their prescriptions,” it included a bookmark to find medications prescribed frequently but may be unaffordable for patients. An equivalent for Africa’s health systems would be well received by communities.

    OrthoFlow was developed by UK orthopaedic surgeons and doctors working in Accident and Emergency. Dr Husain says it’s “A great fracture management app that essentially puts an orthopedic surgeon in your pocket.” It helps with fracture management and understanding essential features of fractures, such as how much displacement needs changed management.

    STD Tx Guide, developed by the US Center for Disease Control and Prevention (CDC) provides alternative antibiotic regimes for patients allergic to penicillin (PCN). The app was updated recently to include new guidelines.

    Gout Diagnosis avoids tapping red or painful joints. Dr Joshua Steinberg took a validated study on gout diagnosis and created an app. He’s a bit of an appthusisast. They’re all available from iTunes.

    Africa’s mHealth plans could include investment programmes in ER services. These would have to be in parallel with investment in mHealth for citizens and communities.

  • Four ways hospitals should respond to data breaches

    A quick and simple set of steps to guide a data breach are in a slideshow in Health Data Management. The overall goals are to plan to minimise damage and react constructively. It suggests that the day after, hospitals should react, respond, transform and sustain. Advice is don’t report a breach until you understand where it’s from, what its goal was and which part of the infrastructure was compromised.

    The four steps include:

    React: understand what happened and collect and preserve evidence, detect a stop further damage and look for previous, unidentified attacksRespond: deal with security gaps and concerns and add new, effective defencesImprove: develop organisation’s cyber-security priority, attitude and behaviour  and redefine securitySustain: monitor constantly and support a dedicated security team led by a Chief Information Security Officer.

    It’s a simple checklist that CEOs and managers in Africa’s hospital and other health services can keep in their draw labelled What to do in the Event of a Security Breach.

  • South Africa introduces electronic bed management system

    A number of hospitals in the Steve Biko Academic Cluster in Tshwane, Gauteng, South Africa have reduced patient waiting times by at least two hours using a new Electronic Bed Management System (eBMS). It was introduced by the provisional Department of Health as part of their healthcare modernisation initiative. Gauteng hospitals manage an average of 27.7 million patients annually, and often experience bed shortages. To address this, the department piloted eBMS at Steve Biko Academic Hospital earlier this year, says an article in allAfrica.

    The eBMS allows medical staff to identify the location of available beds, so improve patient movement and management. Using innovative cloud-based technology, eBMS hospital staff can view current bed availability in their hospital on large display screens or over the Internet on their mobile device or PC. 

    The pilot phase was successful, so a decision was made to roll it out across the cluster., and hospital staff and management have commended eBMS. Hospital personnel use the information to make both long and short term decisions that have led shorter patient waiting times and better ward and staff utilisation. 

    "Management is using eBMS to make reallocation decisions about ward beds. We have split not frequently used wards to move beds to a ward that is always busy. Having had the system in place since early January, Kalafong has already seen a two hour reduction in their casualty waiting times," said Dr Htwe, clinical manager at Kalafong Hospital. "We are so excited about being able to view available beds across the cluster. This increases transparency which helps us improve patient care," added Dr Htwe.

    The Gauteng Emergency Medical Services uses eBMS too, including when transporting patients to hospitals. It leads to better coordination of it services.

    MEC for Health, Ms Qedani Mahlangu said introducing BMS was part of initiatives by the Department to use technology to improve healthcare. She anticipates that eBMSwill be fully implemented across the province by the end of 2016.