Listen to Frank Pijpers from Centraal Bureau voor de Statistiek and University of Amsterdam presenting on "The importance of agent-based modelling for official statistics" at the BioDynaMo2021 meeting. https://youtu.be/Pv7Up1-oZhM 

The idea that Silicon Valley businesspeople are the primary drivers behind the emergence of the booming US digital health market is rarely contested in public debates, yet prominent socio-economic scholars have referred to the "entrepreneurial State" and the "hidden developmental State" as illustrations of the critical role of Governments in the early stages of technological development... 

In this viewpoint, we discuss the crucial role digital health solutions play during the coronavirus disease (COVID-19) pandemic to support public health policies. We also report on the strategies currently deployed at scale during the outbreak in Catalonia.

Most articles were published in the last two years; there was variety in telehealth terminology, and most were developed for occupational therapists, physiotherapists and speech and language therapists. Information was lacking about the assessment of telehealth use and effectiveness, barriers and limitations, the logistical management, the family’s and caregiver’s roles and the costs. 

Two of the most significant trends in health care are at cross-purposes: the boom in digital devices to prevent, diagnose, monitor and treat diseases, and the emerging recognition that environmental, economic and cultural factors are critical in affecting people’s health.

There is disagreement about the nature of the contradiction, and whether the two trends can be reconciled for the benefit of patients and the health-care system as a whole.

PerMedCoE is developing and optimising different tools for cell-level simulations, which will be the basis of the methodology to bridge HPC and personalised medicine. 

In addition to their courses and webinars, they are developing self-learning tutorials to get trained on the use of PerMedCoE tools and HPC. Check the ‘Materials’ section on their website regularly to find training you can carry out at your own pace.

In sostanza si stabilisce – credo per la prima volta – che si parla di  “intelligenza artificiale” quando l’algoritmo contempla meccanismi di machine learnig e crea un sistema che non si limita solo ad applicare le regole sofware e i parametri preimpostati (come fa invece l’algoritmo “tradizionale”) ma, al contrario, elabora costantemente nuovi criteri di inferenza tra dati e assume decisioni efficienti sulla base di tali elaborazioni, secondo un processo di apprendimento automatico. 

The ESC Working Group on e-Cardiology is organising an Online talk on "Wearable technology in cardiovascular medicine: an update" Friday 14 January 2022 from 16:00 to 17:00 CET To check the programme and register for free

Diagnostic AI has not realized its potential to improve diagnostic performance because it has not focused on supporting the diagnostic journey. Knowing the direction of the pathway in a complex environment is important, but the essential decision is determining the next step. A shift to wayfinding AI could help achieve the synergy of human intelligence and AI to achieve diagnostic excellence.

Precision medicine builds its rhetorics on a dominant understanding of ‘genetic determinism’, whilst digital phenotyping builds on the logic of ‘data fundamentalism’... Data-based approaches might facilitate epistemological and ontological redirections for the whole field of medicine, affecting knowledge production and a shifting yet again the value balance of different types of knowledge (quantifiable vs. non-quantifiable) with important consequences.

Can telemedicine be used as a reliable primary tool to identify patients with sudden sensorineural hearing loss who need urgent care but live far from treatment centers? Just a small sample size (51 patients) for this study published in JAMA Otolaryngology, but looks promising (and extra points for the clinically relevant endpoint/setting)

Working on research in digital health technologies within brain health? -> Then you might be interested in submitting your work to the Brain Health research topic in Frontiers in Digital Health! They are looking for papers tackling remote assessment, passive monitoring, and digital interventions within brain health. 🗓️ Deadline for abstracts is the 26th of December!

This year's Reith Lectures were given by AI expert Stuart Russell. He asks "how can we get it right?"

You can also read Philip Ball's piece on the issues raised in this series that forces us to confront the unknowability of the hyper-intelligent machine

Multi-site studies are hindered by differences in images acquired across multiple sites. These effects have been shown to bias comparison between sites, mask biologically meaningful associations, and even introduce spurious associations. In this work, the authors demonstrate that methods for removing site effects in mean and variance may not be sufficient for ML. This stems from the fact that such methods fail to address how correlations between measurements can vary across sites. And then they propose Correcting Covariance Batch Effects (CovBat), to remove site effects in mean, variance, and covariance.

The authors give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The resultant covariance matrices are not factor models. Based on empirical backtests, they compare the performance of these machine learning risk models to other constructions, including statistical risk models, risk models based on fundamental industry classifications, and also those utilizing multilevel clustering based industry classifications

We report on experiments with large-scale genomic datasets to show that, using game theoretic models accounting for adversarial capabilities to launch multistage attacks, most data can be effectively shared with low re-identification risk.

Security is impossible!

A deep dive into an NSO zero-click iMessage exploit: Remote Code Execution

This log4j exploit = remote code execution in basically everything Arbitrary code execution in iCloud, Twitter, Steam, CloudFlare, Amazon, Tesla, Baidu, Tencent This may well be devastating 0day RCE exploit that has ever been dropped in all of history.

...and follow up -> Someone has built a huge regex to cover many obfuscated versions of the log4shell payloads

Elected as Chancellor by the German Parliament today, Olaf Scholz will commence a new chapter of German politics. Karl Lauterbach (SPD), the new German Health Minister, will have to give substance to the health part of the coalition agreement, which includes a digitalisation strategy

A meta-review of 107 survey papers from natural language processing, recommender systems, computer vision, reinforcement learning, computational biology, graph learning, and more, organizing the wide range of surprisingly consistent critique into a concrete taxonomy of observed failure modes

Pharmacist-led transitions of care between hospitals, primary care clinics, and community pharmacies 

1st release: Implementation-standard Personal Health Train | The Personal Health Train set of agreements is aimed to achieve interoperablility and trust during the implementation of decentral data analysis between different parties. This first version of a PHT implementation-standard is a first step in a continuously developing implementation-standard for decentral data analysis.

In this scoping review of 70 studies addressing the intersection of dermatology and AI that were published between January 1, 2015, and November 1, 2020, most data set descriptions were inadequate for analysis and replication, disease labels did not meet the gold standard, and information on patient skin tone and race or ethnicity was often not reported. In addition, most data sets and models have not been shared publicly.

On the health system side, there is also a significant sunk cost fallacy around investments in electronic health records (EHRs). Many health systems have adopted an ‘EHR first’ approach to new technology adoption versus partnering with potentially better external solutions or building applications themselves. This is a strong enough force that sometimes even the potential that their EHR vendor might have a particular product on its future roadmap is enough of a reason for health system execs to want to wait

This website introduces a database in which scientific articles on telemedicine and digital health solutions are assessed and catalogued. Its purpose is to provide an overview of relevant telemedicine solutions and their effects. The database on the site can be searched using the criteria medical speciality, country, technology, clinical effect, patient experience and economic effect. The website serves as a platform for sharing knowledge and inspiration to hospitals and others interested in evidence based telemedicine.

The recently proposed Cures 2.0 Act in Congress calls for the FDA Commissioner to offer guidance on how to formalize regulation of decentralized trials, including how to evaluate digitally collected health data. Cures 2.0 will likely be up for consideration in Congress before year’s end.
Challenges aside, decentralized trials are here to stay, at least in some form.

Despite the recent activity involving development of some virtual-first plans, it remains unclear whether these new offerings will attract substantial interest among patients or if these plans will ultimately be niche product offerings. Furthermore, even though the virtual-first model has many potential advantages, many critical issues remain unknown, and rigorous evaluation is needed to understand the clinical benefits and risks and whether this model can deliver on the promise of maintaining health care quality and decreasing health care spending.

Indicazioni nazionali per l'erogazione di prestazioni e servizi di teleriabilitazione da parte delle professioni sanitarie

China's 5G industry has decided that things like remote surgery are no longer a priority, as it narrows its focus on profitable/sustainable use cases. 
After throwing resources at thousands of industry use cases in the past two years, the China 5G industry has abandoned most of them to narrow its focus. The big operators and vendors have concluded that most of the apps they have built are "showroom-only" that have little commercial potential in the Chinese economy. That includes high-profile use cases such as remote surgery and 5G VR online concerts, which are considered either too niche or too expensive.

This study reveals essential factors for acceptance and willingness to share personal data with digital health research repositories. Implications include the importance of being more transparent about the goals and beneficiaries of research projects using and re-using data from repositories, providing participants with greater autonomy for choosing who gets access to which parts of their data, and raising public awareness of the benefits of data sharing for research.

The Lancet and Financial Times Commission on governing health futures 2030: growing up in a digital world argues digital transformations should be considered as a key determinant of health. But the Commission also presses for a radical rethink on digital technologies, highlighting that without a precautionary, mission-oriented, and value-based approach to its governance, digital transformations will fail to bring about improvements in health for all.

The playbook of Digital Clinical Measures - A live collection of real life examples of organizations using The Playbook to make better decisions faster. From improved team communications and buy-in to refining strategies and better coordination with external partners

ESC Digital Summit - Discover the NEW tools for cardiovascular technology that will be showcased, including: Apps and wearables (mobile health), Artificial Intelligence (AI), machine learning for decision support, virtual and augmented reality (AR) and robotics. 

Deep learning's diminishing returns - Faced with computational scaling that would be economically and environmentally ruinous, we must either adapt how we do deep learning or face a future of much slower progress. Clearly, adaptation is preferable. A clever breakthrough might find a way to make deep learning more efficient or computer hardware more powerful, which would allow us to continue to use these extraordinarily flexible models. If not, the pendulum will likely swing back toward relying more on experts to identify what needs to be learned. 

MedKnowts: Unified Documentation and Information Retrieval for Electronic Health Records

MedKnowts captures structured clinical terms embedded within a free-text narrative and then links these terms to a concept-oriented, dynamic display of patient information that appears alongside a medical note. Thus, MedKnowts provides clinicians with a unified interface for writing a clinical note and exploring and navigating a patient’s medical record

Telemedicine: present and future - October 22-23 2021
Join a terrific line up of speakers discussing the present and future of telemedicine in Italy and by Italy for the world!
You still have 10 days before the deadline to submit your contribution (deadline Sept 30th) and until October the 5th to register for online attendance.

ISOMERISM will be presented at the opening session of the event!

"Patient apprehensions about the use of artificial intelligence in healthcare.
patients have multiple concerns, including concerns related to the safety of AI, threats to patient choice, potential increases in healthcare costs, data-source bias, and data security. ...Patient acceptance of AI is contingent on mitigating these possible harms"

The 2021 IMIA Yearbook of medical informatics is out! An open access review of the most important issues and research of the year

AI in radiology: "Thirty four (94%) of 36 AI systems evaluated in these studies were less accurate than a single radiologist, and all were less accurate than consensus of two or more radiologists. Five smaller studies (1086 women, 520 cancers) at high risk of bias and low generalisability to the clinical context reported that all five evaluated AI systems (as standalone to replace radiologist or as a reader aid) were more accurate than a single radiologist reading a test set in the laboratory. In three studies, AI used for triage screened out 53%, 45%, and 50% of women at low risk but also 10%, 4%, and 0% of cancers detected by radiologists."

NEJM: "After a substantial investment in information technology, providing digital health care is technically feasible. But patients and physicians can’t reap the benefits because payers don’t know how to pay for new digital health options."

New pivot in Alphabet's healthcare engagement strategy: Google is dismantling its health division, Insider has learned, as its chief Dr. David Feinberg departs the company.

Digital Technologies and Data Science as Health Enablers: An Outline of Appealing Promises and Compelling Ethical, Legal, and Social Challenges - The running theme to this article is the underlying tension between the promises of digital health and its many challenges, which is heightened by the contrasting pace of scientific progress and the timed responses provided by law and ethics. Digital applications can prove to be valuable allies for human skills in medicine and public health. Similarly, ethics and the law can be interpreted and perceived as more than obstacles, but also promoters of fairness, inclusiveness, creativity and innovation in health.

Report on the regulatory strategies of European DPAs for 2021-2022 - The report contains links to and translated summaries of 15 DPAs’ strategic documents from DPAs in France, Portugal, Belgium, Norway, Sweden, Ireland, Bulgaria, Denmark, Finland, Latvia, Lithuania, Luxembourg and Germany. The analysis also includes documents published by the European Data Protection Board (EDPB) and the European Data Protection Supervisor (EDPS). These documents complement or replace the ones that were included in our 2020 report.

In silico saturation mutagenesis of cancer genes. - We propose that the mutations observed in thousands of tumours—natural experiments testing their oncogenic potential replicated across individuals and tissues—can be exploited to solve this problem. From these mutations, features that describe the mechanism of tumorigenesis of each cancer gene and tissue may be computed and used to build machine learning models that encapsulate these mechanisms.

Great opportunity!
Clinical validation of artificial intelligence (AI) solutions for treatment and care - deadline Sept 21st 2021. Get in touch if you are interested!

PhysiCell has released version 1.9.0 that includes community developed intracellular model support by ODE models, Boolean networks, and dynamic flux balance... and a model builder GUI to make it more widely usable!

When we look at Life Sciences and Medicine, the picture is blurred: there is a clear case for molecular simulations, but much less clarity for single-cell system biology, and even less for system physiology.  In Silico Medicine, intended as the clinical and industrial application of computational biomedicine methods, is in my opinion at the present far from making a clear case for being and HPC Scientific domain.

September 28-29, 2021, online research seminar "Multi-disciplinary care for older people".

Swetaly University Collaboration is a project that aims to strengthen the academic relations between Sweden and Italy on AI and ageing.

Call for papers by Medical Engineering & Physics, deadline September the 30th:
This special issue is specifically dedicated to machine learning as an enabler of medical technology. Manuscripts describing well-developed translation of machine learning applications into medical practice are encouraged. Pharmacology, genomics, proteomics, epidemiology and pure data mining will be considered out of scope. Fitness monitoring will be considered only with clear clinical / healthcare implications.

October 2021 - Upcoming National conference of the Italian Society of Telemedicine and eHealth. 

The results show that the evidence available to support the claims made by the health apps analysed is often unavailable or of questionable quality. The article concludes with X=number specific actions that should be taken to improve the quality of evidence available for health apps and thus protect individuals and groups from harm.

PLOS Digital Health publishes boundary-breaking research that uses digital tools, technologies, and data to advance every aspect of health care.

Questions?
Contact digitalhealth@plos.org

European University Institute - The State of the Union 2021

Programme
Streaming

"European Health Data Space" public consultation.
Your contribution can help provide important insights, opinions and evidence to support the impact assessment accompanying the EHDS proposal on the problems to be tackled, the policy options to be considered and their likely impacts

Inception impact assessment of the "European Health Data Space"

The European Commission is coordinating a common European response  to the coronavirus outbreak. They are taking resolute action to reinforce our public health sectors and mitigate the socio-economic impact in the European Union

Abilitate le procedure a distanza in telemedicina. Ma come si inseriscono nei processi di cura? Centrale il concetto di co-operabilità