Early diagnosis of ADHD and treatment could significantly improve the quality of life and functioning. Recently, machine learning methods have improved the accuracy and efficiency of the ADHD diagnosis process. However, the cost of the equipment and trained staff required by the existing methods are generally huge. Therefore, we introduce the video-based frame-level action recognition network to ADHD diagnosis for the first time. We also record a real multi-modal ADHD dataset and extract three action classes from the video modality for ADHD diagnosis. The whole process data have been reported to CNTW-NHS Foundation Trust, which would be reviewed by medical consultants/professionals and will be made public in due course.

Objective: To report imaging protocol and scheduling variance in routine care of glioblastoma patients in order to demonstrate challenges of integrating deep-learning models in glioblastoma care pathways. Additionally, to understand the most common imaging studies and image contrasts to inform the development of potentially robust deep-learning models. Methods: MR imaging data were analysed from a random sample of five patients from the prospective cohort across five participating sites of the ZGBM consortium. Reported clinical and treatment data alongside DICOM header information were analysed to understand treatment pathway imaging schedules. Results: All sites perform all structural imaging at every stage in the pathway except for the presurgical study, where in some sites only contrast-enhanced T1-weighted imaging is performed. Diffusion MRI is the most common non-structural imaging type, performed at every site. Conclusion: The imaging protocol and scheduling varies across the UK, making it challenging to develop machine-learning models that could perform robustly at other centres. Structural imaging is performed most consistently across all centres. Advances in knowledge: Successful translation of deep-learning models will likely be based on structural post-treatment imaging unless there is significant effort made to standardise non-structural or peri-operative imaging protocols and schedules.

Background: Electronic Health Records hold detailed longitudinal information about each patient's health status and general clinical history, a large portion of which is stored within the unstructured text. Existing approaches focus mostly on structured data and a subset of single-domain outcomes. We explore how temporal modelling of patients from free text and structured data, using deep generative transformers can be used to forecast a wide range of future disorders, substances, procedures or findings. Methods: We present Foresight, a novel transformer-based pipeline that uses named entity recognition and linking tools to convert document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events such as disorders, substances, procedures and findings. We processed the entire free-text portion from three different hospital datasets totalling 811336 patients covering both physical and mental health. Findings: On tests in two UK hospitals (King's College Hospital, South London and Maudsley) and the US MIMIC-III dataset precision@10 0.68, 0.76 and 0.88 was achieved for forecasting the next disorder in a patient timeline, while precision@10 of 0.80, 0.81 and 0.91 was achieved for forecasting the next biomedical concept. Foresight was also validated on 34 synthetic patient timelines by five clinicians and achieved relevancy of 97% for the top forecasted candidate disorder. As a generative model, it can forecast follow-on biomedical concepts for as many steps as required. Interpretation: Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials and clinical research to study the progression of disorders, simulate interventions and counterfactuals, and educational purposes.

The latest Digital Health News Industry round up includes details on a name change, a robotic surgical systems installation and the launch of digital pre-op assessments for one trust. The Midlands Partnership NHS Foundation Trust has selected Agilisys to develop a business intelligence strategy to enhance the trust's data and analytics capabilities. As a result, the trust will have a single business intelligence tool that can be used across the whole of Midlands Partnership NHS Foundation Trust (MPFT). Previously this information was used by just the Business Intelligence Team but by making it available trust-wide, regardless of skill-level, it will support massive growth in the trust's data warehouse. In turn, this will support MPFT's ambitions for HIMSS 7. The two organisations are now working together on delivering a roadmap that informs the trust's decisions on migrating its data to the cloud.

Guy's and St Thomas' NHS Foundation Trust has added a fourth surgical robot to to its collection in a bid to speed up cancer operations delayed by the pandemic. The new addition joins three 4th generation da Vinci surgical systems from manufacturer Intuitive which the trust already owns and with four machines, the trust now has the largest robotic programme in the UK currently. The new robot, which is on loan until the end of the year, will operate on NHS patients from the private floors of the Cancer Centre at Guy's as part of a collaboration with private healthcare provider, HCA Healthcare UK. The new delivery will help to clear a backlog of surgical procedures and it is also hoped it will lead to improved patient outcomes. The use of robots in surgery leads to increased operative precision which can mean less pain for patients, smaller scars and reduced hospital stays post-surgery.

AIMed UK 2020 virtual summit took place early on. In the opening keynote session: Deployment of artificial intelligence (AI) in the UK and across the world, Professor Neil Sebire, Chief Research Information Officer at the Great Ormond Street Hospital for Children National Health Service (NHS) Foundation Trust talked about some of the considerations healthcare organization need to have as they plan to deploy AI tools at scale. Professor Sebire said healthcare organization ought to think about what is required, in terms of infrastructure, when it comes to dealing with healthcare data. Often, it's great to have talks focusing on electronic health records (EHRs) but these data warehouses do not facilitate utilization. What the healthcare system needs is a place which not only keeps all the data but also permits algorithm development; planning the deployment and scaling of AI, and everything else.

Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of Information Extraction (IE) technologies to enable clinical analysis. We present the open source Medical Concept Annotation Toolkit (MedCAT) that provides: a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; b) a feature-rich annotation interface for customizing and training IE models; and c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performance in extracting UMLS concepts from open datasets ( F1 0.467-0.791 vs 0.384-0.691). Further real-world validation demonstrates SNOMED-CT extraction at 3 large London hospitals with self-supervised training over ~8.8B words from ~17M clinical records and further fine-tuning with ~6K clinician annotated examples. We show strong transferability ( F1 >0.94) between hospitals, datasets and concept types indicating cross-domain EHR-agnostic utility for accelerated clinical and research use cases.

Artificial intelligence has the potential to be deeply disruptive across the healthcare sector, especially in cutting down administrative waste, streamlining billing, and improving patient matching and population health management. Tech giants like Amazon, Google and Intel are leveraging their hefty AI capabilities as they move into healthcare, and providers and payers become more open to the technology. However, AI's value add in diagnostics, a realm dogged with variability, is unproven though much-hyped among investors and the public. University Hospitals Birmingham NHS researchers vetted more than 20,500 articles published between 2012 and 2019, but only ended up including 1% of them in their meta-analysis. The included studies spanned breast cancer, orthopaedic trauma, respiratory disease, cardiology, facial surgery and more. Of the 82 articles researchers looked at, only 25 validated the AI models externally by using medical images from a different population, and just 14 directly compared clinician and AI diagnostic abilities side by side.

A British regulatory organization has found that the National Health Service violated data privacy laws when it shared patient records with Google's DeepMind artificial intelligence startup. In a statement announcing its findings, the Information Commissioner's Office said the Royal Free NHS Foundation Trust did not comply with the Data Protection Act when it provided partial records for more than 1.6 million patients to DeepMind. The data was originally provided to help bolster DeepMind's Streams app and improve detection of acute kidney injury and other medical problems. However, the Information Commissioner's Office found that the Foundation Trust should have taken additional measures to inform patients about the data use. In its release, commissioner Elizabeth Denham said Streams and DeepMind's work had clear benefits, but the Trust should have been clearer about the amount of data it needed and the reasons it wanted patient data.