Is there a room for autonomous medical diagnosis?

Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy inprimary care offices

With an eye to AI and autonomous diagnosis

In Digital medicine you'll find the article on an artificial intelligence-based  diagnostic of diabetic retinopathy. It's the first AI system approved by FDA last April, and represents the begining of new aids for medical decision making. Therefore, there is a room for supporting decision making with AI, but maybe one day autonomous diagnosis could be the issue, who knows.

The prespecified sensitivity end point agreed with the FDA was 85.0% and this was met with a point estimate of primary sensitivity of 87.2%. However, the confidence intervals of this estimate were 81.8–91.2% (that is, spanned the superiority end point). The study also employed an intention-to-screen protocol; however, 40 participants successfully enrolled in the study were excluded from analysis as their images were subsequently found to be insufficient quality to be graded by the image reading center. The authors attempt to address this by considering a worst-case scenario where all such images are incorrectly graded and repeating the analysis. In this approach the sensitivity would
be 80.7% (76.7–84.2%).

 Although deep learning will not be a panacea, it has huge potential in many clinical areas where high dimensional data is mapped to a simple classification and for which datasets are potentially stable over extended periods. As such, it will be incumbent on healthcare professionals to become more familiar with this and other AI technologies in the coming years to ensure that they are used appropriately.

Alice Francis - Coco Baca Bum Bum

The uselessness of current hospital rankings

Personalized Hospital Ratings — Transparency for the Internet Age

Eric Topol said in a tweet: It's high time to transcend hospital ratings and move to indvidualized ratings of hospitals. He refers to an NEJM article that supports personalized hospital ratings like the Rand ones.

As currently constructed, the weighting systems that underlie overall hospital performance ratings are expressions of the values, preferences, and tastes of their creators. Why not ask patients what’s important to them instead?

It makes sense.

PS. FT life of a song

The paucity of public information about medical devices

The need for transparency of clinical evidence for medical devices in Europe

Last year EU approved a new law for assessing safety and efficacy of medical devices. Unfortunately, it comes late and it is not enough to solve current situation of lack of information on evidence. An article in Lancet explains precisely what should be done to increase the transparency of information on medical devices.All the details in this list:

 A small task force of regulators and invited stakeholders has recommended what information should be included in the summaries of safety and clinical performance and which components of the Eudamed database need to be open to public access. Those recommendations are now under revision. The European Commission has been delegated authority to translate them into further legislation, but it has indicated that it does not consider that to be a priority. Any member of the public or any organisation with an interest in these issues should therefore make representations now to the European Commission. The medical device regulations will take effect from 2020.

The time is now.