Skip to main content

Heidelberg develops Unsupervised AI for motor disease

Researchers at the universities of Heidelberg in Germany, and Zurich in Switzerland have developed an AI model to detect human motor impairments and determine underlying diseases.

The new software is also a test for how effective unsupervised AI behaviour analysis can be in discovering and determining complex disease states.

Conventional supervised instrumented movement analysis is time-consuming, potentially subjective, and cost-intensive. It requires prior knowledge of behaviours of interest, and typically a large amount of video frame annotation. There is scope for human annotator bias, with different annotators focusing on different behaviours, while ignoring or minimising others.

The researchers have developed uBAM ("unsupervised Behaviour Analysis and Magnification using Deep Learning"). This is a fully automatic, unsupervised diagnostic support system for behaviour analysis.

The new system can extract and classify behaviour automatically, with the ability to compare and quantify even small differences.

The system thus avoids the need for lengthy annotation.

The researchers claim their system is also more objective, avoiding user bias affecting the learning process.

An interface to the uBAM system is available for free online, together with interactive demos, at:

https://utabuechler.github.io/behaviourAnalysis/

Further reading:

Labels:

Comments

Post a Comment

Popular posts from this blog

Austria develops Smart Covid-19 Test

Austrian low power sensor firm ams AG has received funding from two Austrian Government ministries to develop a smart device to provide accurate testing for Covid-19. The hand held device is directly connected to a "medical data cloud", does not require a laboratory, and can deliver accurate test results within 15 minutes. The two Austrian Government departments funding the new device are the Federal Ministry of Climate Action, Environment, Energy, Mobility, Innovation and Technology (BMK), and the Federal Ministry for Digital and Economic Affairs (BMDW). ams has used the funds to develop a connected, smart version of a lateral flow test (LFT) device. Lateral flow tests are a standard approach for rapid point of care (PoC) testing. LFTs, which are usually analogue devices, are typically intuitive and easy to use, and are subject to strict regulatory requirements. A pregnancy strip test is a typical example of an analogue LFT device. The challenge for ams was threefold: to cre...
Post a Comment
Read more

Spain plans big boost in digital health spending

Spain is planning a big boost to spending on healthcare and digital health in next year’s budget. Public procurement also looks set to become more open and competitive. With Spain still recovering from the effects of the Coronavirus, and with subsequent waves of infection preoccupying policy makers and the healthcare establishment, the Government plans big increases in spending across the board on healthcare in the 2021 state budget. The country’s Ministry of Finance has published a note in the Official State Gazette (Boletín Oficial del Estado) that lays out the Government’s plans to increase spending and expand healthcare and digital health. These include strengthening “capacity to respond to emergencies” and “investments in science, research and innovation”. Digital healthcare is seen as critical to improving Spain’s response to future waves of the pandemic. The budget will make funds available for “improving the digitisation of health services”. The digital healthcare infrastr...
Post a Comment
Read more