Childhood visual impairment (VI) has significant impact on the child and with far-reaching consequences for the child’s social and educational experiences and future career prospects.The VQoL_CYP and ...FVQ_CYP are validated patient-reported outcome measures (PROMs) which capture vision-related quality of life (VQoL) and functional vision (FV) and are designed for use by children and young people living with VI, to capture children’s own perspectives of the impact of VI. They are currently used as paper based questionnaires in research and routine clinic practice. However, clinicians and families would benefit from digitalising the process, allowing patients to complete questionnaires electronically with data automatically collected into a database for analysis.In collaboration with UCL computer science, through the industry exchange network, researchers at GOSH and UCL GOS Institute of Child Health developed a proof of concept app was created to deploy both instruments digitally (collectively, ‘MyEyes’), complete with a database for analysis. The web application was developed using Django with a PostgresSQL database. The mobile app was developed using Ionic.The digitalisation of the questionnaires has the potential to improve the child’s experience of self-completion. Deployment via a mobile app allows patients to complete questionnaires at sequential time-points, in-between normal clinic visits, thus providing clinicians with more information about their eye condition over time.To gain feedback on the technology, patients and families will now test the prototype mobile app. This project demonstrates how PROMs can be digitalised, supporting a more efficient collection process for important patient-generated data. This prototype could serve as an example of how other PROMs in use at the hospital could be deployed digitally.
IntroductionThe COVID-19 pandemic response has accelerated adoption of digital health technologies to support social distancing. In part, this involves repurposing technologies that were not ...originally developed for healthcare application. In the hospital setting, this includes the appropriation of ‘Off the Shelf’ (OTS) digital products that facilitate video-based clinical consultations, diagnostics and communication during ward rounds and multi-disciplinary team meetings. Such technologies were implemented within weeks at GOSH where video consultations were implemented for >90% of outpatient appointments.MethodsHere we present the findings from a Debrief-After Action Review (AAR) lasting two hours, supplemented with speculative questions on how lessons learned from the rapid deployment of one technology could inform the adoption practices of other emerging technologies.ResultsFifteen participants, who were members of a Transforming Care Links working group and interested in the impact of digital systems on patient care, contributed to the AAR. Five themes were identified from thematic analysis of this bottom-up approach: (i) Clinical: Planning and redesigning workflows with clear purpose, intent, and communication with clinical teams (ii) Technology: Infrastructure and equipment available across the team based on the needs of the workspace, with security and governance processes (iii) Capability mapping: Building core capability in a structured way across the entire team with space and time to trial out technologies as part of a progressive learning path and supported by clinical champions (iv) Benefits: Demonstrable benefits with new technology enabled ways of working based on preliminary small-scale deployments that deliver measurable value (v) Environment and Context: Context-specific workflow redesign for technology enabled interactions that consider optimum conditions of the physical environment.ConclusionThis user-centred approach identified routine training pathways, equity of access to training opportunities and equipment, a period of trialability and demonstrable benefits as enablers for the successful adoption of emerging technologies.
IntroductionThere have been several attempts to integrate touchless interactions with computer interfaces in operating theatres and interventional radiology. Whilst motivated by infection prevention ...gains, this type of technology is yet to mainstream in healthcare as depth camera are historically expensive. Here we present MotionInput supporting DirectX for desk gestures. The key idea behind this prototype project is to ‘use the tech and tools you already have’, to provide touchless interactive interfaces to existing Windows software.MethodThis proof-of-concept prototype features Visual Studio based modules that use a regular webcam (e.g., on a laptop) and open-source computer vision libraries to deliver low-latency input on Microsoft Windows 10. The functioning software prototype focuses on several image-processing algorithms, leading to desk-based gestures with in-air pen and gloved hand navigation.ResultsDiscrete hand motions are tracked via x and y coordinates. These coordinates are then mapped and processed by PyDirectInput functions to replicate movements of the mouse or press keys on the keyboard and click with the mouse. This is extended to recognition of 2 fingers that are gloved, which would apply to healthcare scenarios in which clinicians use one hand to navigate clinical applications including an electronic patient record or scan with one hand, whilst maintaining the second hand as free for other tasks. The prototype has been shown to work with UCL’s HoloRepository – an open-source project that enables 3D viewing of CT and MRI DICOM scans of the brain, lungs, chest, abdomen and kidneys.ConclusionFurther research is exploring the application of MotionInput to design touchless interactions with computer interfaces in clinical spaces. Coupled with advances in computer vision, we believe that the convenience of use and ease of access of cameras integrated into existing hardware will improve uptake and help bring gesture recognition software into the mainstream.
IntroductionPopulation health and wellbeing is a priority in the UK, with new initiatives that empower children to live healthier lives. Excess weight has also been associated to worse outcomes ...during the COVID-19 pandemic period, complicated by reduced activity within the confinements of a home environment and coupled by increased screen time with remote classroom practices. As a result, children and young people now interact with computer interfaces in their home environment for education, gaming and healthcare purposes for prolonged periods and in new ways.MethodThere is a growing interest in Natural User Interfaces (NUIs) that use natural hand and body gestures to interact with computers. Advances to these technologies mean that they are now more accurate, easier to use and instead of requiring expensive depth cameras, can be operated using simple webcams. In this study, OpenCV library is used to track user movement by calculating the pixel difference between two frames and create a catalogue of exercises. We use PyTorch exercise recognition model to check the status of the user every 8 frames. These are recognised by using Convolutional Neural Networks (CNNs) with static training from datasets and offer users the option to create personalised exercises.ResultWe present University College London’s (UCL) Motion- Input supporting DirectX: Gestures for at-home exercises. This exercise module can recognise six repetitious static exercises, such as running on the spot, squatting, cycling on an exercise bike, and rowing on a rowing machine using a webcam. This is intended for integrated exercise triggers during gaming in place of a handheld control panel (i.e., jumping to trigger commands), remote coaching for fitness and bespoke treatment plans for physical rehabilitation.ConclusionWebcam-based computer vision exercise catalogues using everyday devices like webcams, hold the potential to encourage healthier and more active behaviours during screen-based activities.
IntroductionThe Internet of Things (IoT) has emerged as a disruptive technology with potential to revolutionise healthcare by collecting and communicating healthcare data from the home. This could ...enable health-related data to be remotely monitored for paediatric patients with long-term conditions. However, to anchor trust in new and remote digital care approaches, this requires involving patients as part of the design and evaluation process.MethodMembers of the Great Ormond Street Hospital for Children’s (GOSH) Young Persons’ Advisory Group for research (YPAG), who typically have lived experiences of healthcare, were invited to a one-hour design workshop, to discuss common indicators of falling unwell, followed by imagining scenarios for intelligent everyday items in the home to help monitor wellness. Qualitative contributions were collected on a collaborative platform as micronarratives of 250 characters or less, anonymously, and voluntarily, and analysed for emergent themes.Results22 YPAG members, aged 10–21 years of age, contributed 51 comments on 3 behavioural indicators of falling unwell (i) pronounced lethargy (ii) feeling antisocial and (iii) reduced appetite. Correspondingly, intelligent home devices to track wellness were described as: (i) smart appliances: fridges to track changes in eating habits, (ii) smart garments: smart shoes, beds, and fabrics to track movement and clinical markers (iii) smart behavioural nudges: smart bottles that encourage good hydration (iv) digital biomarkers: smart nail clippers, tissues, and combs to track nutrient deficiencies and (v) smart sensors integrated into medical devices: inhalers, spirometers, and stethoscopes.ConclusionIn this exploratory workshop we ideate with the YPAG on whether data from intelligent everyday items in the home has potential to monitor wellness in the future. We recommend that future research in this growing field includes children and young people and that forums such as GOSH’s YPAG are positioned well to deliberate the future of smart-home remote monitoring.
IntroductionImagine entering an operating theatre or developing clinical skills in empathy and communication through Virtual Reality. To enhance the experience of learning, novel methods using VR ...have been researched and simulated for clinicians. This is because some aspects of clinical training, like conducting procedures and effective team communication focus on ‘learning by doing’ which is difficult to recreate remotely. Here we present a proof-of-concept prototype of a 360°-video editor that augments 360° videos with media to create a mixed reality learning experience.MethodAn editor was built inside Unity to augment 360°-videos of real-world scenarios in healthcare with interactive data. Unity is a cross-platform games engine used to create two-dimension, three-dimension, virtual reality, and augmented reality games, as well as video players to play panoramic 360°-videos. The video player is attached to a Render Texture and a Skybox material that provides the spherical surface for the 360°-video achieving an immersive experience.ResultsThe editor comprises two software packages, one for the trainer, another for the learner. As a unique feature, we introduce clickable Hotspots. This enables users to annotate the 360° film by tagging specific artefacts in the environment and create a place-based interaction. These Hotspots are anchored to a position and can display text and images, and form part of a novel branched timeline of nested data. The intention being the trainer would create the film and annotate the environment with interactive media. This would then be available to the learner, who would use the player to view a bespoke teaching package.ConclusionSituated Cognition 360 Editor 2021 envisages trainers creating interactive 360°-video learning experiences using real life scenarios in healthcare. Future steps involve user experience evaluations, co-design and development of new learner interactions that deliver low cost, remote and easily deployed healthcare education through immersive learning environments.
IntroductionComputer vision could be a valuable tool in medicine to track objects during a procedure. In an operating theatre computer vision could be used to track and monitor the use of surgical ...equipment, examples could be the scanning of trays pre and post operation to check instruments into and out of the operating theatre. The aim of this project was to create a system that utilises computer vision to identify surgical equipment. To discover the limitations of object detection systems, and the time required to train a model.MethodAs part of a joint collaboration between GOSH and UCL computer science (CS) through the industry exchange network programme, CS students developed a platform for computer vision for reliable detection of surgical instruments using standard over-the-counter digital video and mobile phone cameras, in conjunction with an Object Detection model developed using Google’s TensorFlow Object Detection API. The desktop client application was built using PyQT. The client application sends individual frames to a cloud-hosted web service that handles the detection of objects and was built in Python providing a ‘real time’ object detection interface.ResultsUsing two similar surgical objects, curved and straight forceps, the team developed a system that accurately identified the instruments (>99% accuracy). The system could track items use and monitor the number of time an object as used and for how long. The training of models for object detection was however, lengthy and required a significant number of photographs to achieve a high accuracy of recognition.ConclusionA model was developed and trained to recognise surgical instruments. The prospect of tracking objects in healthcare is exciting however the data required to train a model, and current camera capabilities, are limiting factors in the use of computer vision and further work is required.
IntroductionIndoor navigation in hospitals can be challenging for all visitors, and even more so for patients with sight or hearing impairment. The aim of this project was to develop a mobile ...application to aid navigation for GOSH patients with sight or hearing impairments.MethodAs part of a joint collaboration between GOSH and UCL computer science (CS) through the industry exchange network programme, CS students developed a navigational tool using GOSH DRIVE as a mapped model environment. The user’s location is determined using Aruba Meridian Bluetooth beacons and a mobile phone. The mobile application was build using the Meridian SDK provide by Aruba Meridian. App content such as maps, place markers and routes, were generated using the Meridian Editor and communicated to the app using Meridian APIs. The Meridian Editor and API are hosted on Google Cloud Services. A Google Firebase Real time Database stores user location data as communicated by the app to a NoSQL database.ResultsThe application developed connected with Aruba Bluetooth beacons, which are installed across parts of the hospital and provide accurate positioning of users on each floor to within 1 meter. To aid navigation for visitors with sight impairment the app was linked to the haptic device BuruNavi. This device vibrates to give the illusion of a person being pulled in a particular direction. The app allows patients to select their destination by voice command or touch with directions displayed visually, accompanied by audio cues and BuruNavi. The data from the Bluetooth beacons provides information on the most frequently used routes, this can inform design of space to facilitate.ConclusionA prototype navigation app to support patients with sight or hearing impairments was developed. This app has the potential to make a real difference in the ability of patients to navigate the hospital.
IntroductionGOSH DRIVE is a flexible workspace often used for events such as seminars, workshops and hackathons. Currently visitor management is completed using physical records. It would be ...beneficial if this process could be digitised. The goal of this visitor management app is to increase the efficiency of the sign in procedure for visitors.MethodAs part of a joint collaboration between GOSH and UCL computer science (CS) through the industry exchange network programme, CS students devised a platform for easy tracking of visitors to a specific area, using GOSH DRIVE as a model. The application employs a 3-tier, presentation, logic and data, software architecture pattern. The presentation tier consists of a mobile application and web app. The mobile application was developed in Ionic4, an open source, cross-platform toolkit for developing mobile apps that uses standard web technologies; HTML, CSS and JavaScript. The web app make use of Bootstrap to create fully responsive web pages. The logic tier containing the application’s functional business logic was built in Express.js and consists of the RESTful APIs used to access the data. The data tier comprises of a MySQL database to store events details, status and booked visitors, visitor details and visitors currently signed in.ResultsThe app for visitors to sign in and out of the building, alongside the web based admin panel allows staff members to view, modify or export the data from the database. The app and web based user interface give the staff at DRIVE an easier way of accessing and manipulating data from events. The app also has the capacity to generate a register of all persons in the building in case of emergency evacuations.ConclusionThe app and website developed facilitates visitor management and could be used in other parts of the trust to replace physical records.
BackgroundModern technology could be implemented to enhance clinical training. GOSH is a hospital specialising in the treatment of rare childhood diseases that can be hard to diagnose and treat. To ...support training of medical students to understand more about rare diseases we devised a game to support learning.MethodAs part of a joint collaboration between GOSH and UCL computer science (CS) through the industry exchange network programme, CS students devised a game with the aim of correctly diagnosing a virtual patient by asking the least amount of questions. This application employs a three-tier, presentation, logic and data, software architecture pattern. The presentation tier consists of a mobile application developed in Ionic4, an open source, cross-platform toolkit for developing mobile and desktop apps that uses standard web technologies; HTML, CSS and JavaScript. The logic tier, which contains the application’s functional business logic, was built in Node.js and consists of the RESTful APIs the mobile app uses to access the data. The data tier comprises of a PostgresSQL database to store user details and answers, patient cases and questions.ResultsTrainee doctors are provided with simple demographic details and the reason for the medical assessment. The player can then request results of standard examinations such as blood test, x-ray, MRI etc. The game ends when the player selects the diagnose button and submits an answer, following which the correct diagnosis is revealed, with information about the condition. A working proof of principle was developed which could be expanded to include person, department or organisation specific leader boards as part of future development.ConclusionAn application to allow gamified medical learning on mobile devices for rare paediatric conditions has been developed with potential for expansion across a range of clinical settings and services.