November 21st: Digital Medicine News Picked for You

The Supreme Court made the most important decision for data science and machine learning. How will it impact digital health? Read Weekly Digital Dose!

Weekly Digital Dose
Share on
#Artificial Intelligence#Clinical Trials#Digital Health#FDA#Machine Learning

The Most Important Supreme Court Decision For Data Science and Machine Learning

The decision of the U.S. Supreme Court has given a green light to tech companies to use copyrighted material in the development of deep learning algorithms. The Rationale? This use does not directly affect the earnings of the individual articles under the copyright.

Our take: This is an important ruling, especially for companies relying on access to public and proprietary data to build mathematical models. We believe liberalisation of data access is a step in the right direction. Especially in healthcare and digital medicine, such rulings may accelerate development of next generation models, improving the global state of care. – Martin

Apple Heart Study shows a lot of promise for digital health, but cardiologists still have questions

Researchers recruited more than 400,000 participants with an Apple Watch to the study over eight months. That is an astonishingly high number for a biomedical study. About 0.5% of the participants, or just over 2,000 people, received a notification of an irregular pulse during the course of the study. Among that group, about a quarter completed the protocol of wearing a patch to monitor their heart’s rhythm for two weeks before sending it back.

Our take: A couple of interesting findings here. First, when an extra step was required – in this case returning the patch – people were less compliant to the protocol. This indicates the importance of lowering participants’ burden during clinical studies using sensor technologies. Second, the huge number of enrollees demonstrate people’s willingness to use apps and software to manage their health and that they can be powerful tools in engaging new individuals in clinical trials. – Lucy

Google scrapped the publication of 100,000 chest X-rays due to last-minute privacy problems

The incident took place in 2017 and was part of a joint project conducted with the National Institutes of Health (NIH). But it’s particularly relevant at a time when Google is moving quickly into health care and stealthily gathering medical data from millions of patients. As the search giant amasses more of these sensitive records, many privacy advocates are questioning whether it can be trusted with the information.

Our take: Remembering this failed project from 2017 is important as we consider the upcoming Project Nightingale that Google announced earlier this week. For Project Nightingale, Google is collaborating with Ascension, the largest nonprofit health system in the United States. As part of this work, Google will gain access to the medical records of more than 50 million people in 21 states. This article raises a very important question: What exactly is Google intending to use the data for? How will knowledge generated during Project Nightingale impact other project in Google’s portfolio? Or, from another perspective, what mundane commercial data in combination with health data can unlock the possibility of powerful predictions for users of Google services? The public is asking these same questions. We are also all curious about how the tech giant will handle public concern about compliance with health privacy laws and patient consents. As a result, we are seeing the decline in trust towards technological giants from their own users worldwide. – Lucy

FDA clears 2 AI applications for use in imaging studies

The FDA granted 510(k) clearance to U.K. based Ultromics for an image analysis system that automates cardiac analysis to aid in the early detection of cardiovascular disease. In addition, the FDA has approved technology from Hologic, (Mass., U.S.) that uses an AI-powered algorithm that the company contends can reduce mammography read times without compromising image quality, sensitivity or accuracy.

Our take: Demand for imaging has already outgrown the supply of qualified radiologists. This problem is likely to grow with an aging population. Thus, we should not be surprised by the recent trend of aiding (but not completely substituting) radiologists with AI solutions to attempt to increase the impact they can have with each hour worked. There are plenty of predicates that AI imaging solutions can use to follow the 510(k) route to market. The question we are all interested in is whether these technologies can meaningfully address the imbalance in need for imaging the availability of radiologists around the world. – Lucy

Janssen Leverages Wearable Technology to Reimagine Clinical Trial Design

The Janssen Pharmaceutical Companies of Johnson & Johnson announced the launch of the next evolution of digital clinical trial design with CHIEF-HF, the first-ever completely decentralized, indication-seeking clinical study. To accelerate the study and fast-track results, all contact with participants will virtual, with no in-person clinical visits required. The company is utilizing smart and wearable technologies to more quickly and efficiently gather and analyze data during activities of daily living to assess the effectiveness of canagliflozin in adults with heart failure (HF), with or without type 2 diabetes (T2D).

Our take: We are happy to see the adoption of digital technologies in this study. Heart failure is an excellent use-case for the incorporation of sensor technologies and virtual visits. This approach also allows for rapid monitoring to support compliance and data quality. We hope that in time the clinical R&D giants will develop a flexible and agile muscle necessary for successful execution of this model of clinical trials conduct. – Lucy

HealthMode News

The Association Between Perceived Electronic Health Record Usability and Professional Burnout Among US Physicians

What happens when you evaluate Electronic Health Records systems with standardized usability scale? You find out that the usability of them is worse than that of a microwave. On top of that, correlating with professionals’ burnout. The solution to this problem is not straightforward though – improving such a complex system will require a lot of effort, research and iterations. Some startups are already trying to alleviate the burden introducing a speech-to-text voice assistants, which might be an interesting step towards lifting the burden of clinician-system interaction.

Let's stay in touch

I consent to the use of my data for the purpose of receiving a weekly email. Please see our privacy policy for additional information on how we protect your data.