What happened in health care technology this week – and why it’s important.
Electrochemical Test Measures Antibiotic Resistance
Medgadget writer Conn Hastings reported on work from researchers at Washington State University who have developed an electrochemical test that can rapidly identify antibiotic-resistant bacteria in patient samples. The technology can provide a result in less than 90 minutes and is based on measuring the bacteria’s electrochemical activity after they are exposed to antibiotics. The data reveal the metabolism and respiration of the bacteria. If they are still happily metabolizing after exposure to an antibiotic, they are considered resistant to it. By providing a rapid answer to the question of antibiotic resistance, the method could be beneficial for clinicians in prescribing the most appropriate antibiotic for their patients.
Why it’s important – In the age of antibiotic-resistant bacteria, prescribing the correct antibiotic is becoming critical. If a clinician gets it wrong, the treatment won’t work, and misused antibiotics could even contribute to new resistant forms of bacteria. Instead of looking for the growth of a culture, they look for metabolism, and that is basically what they’re detecting by the movement of these electrons so that it can happen in much shorter time spans compared to a conventional culture-based assay.
Scientists discover an antibody that can protect people against several coronaviruses
An article in Rifnote online by Mansur Shaheen describes research at the University of North Carolina – Chapel Hill (UNC) and Duke University, in Durham, where scientists have identified an antibody that can protect people from COVID-19, its variants, and other types of coronaviruses. The antibody, DH1047, works by binding to the virus’s cells and neutralizing them, preventing them from replicating.
Why it’s important – This antibody has the potential to be a therapeutic for the current epidemic. It could also be available for future outbreaks, if or when other coronaviruses jump from their natural animal hosts to humans. The findings provide a template for the rational design of universal vaccine strategies that are variant-proof and provide broad protection from known and emerging coronaviruses.
Google is taking sign-ups for Relate, a voice assistant that recognizes impaired speech
As reported in The Verge, Google launched a beta app that people with speech impairments can use as a voice assistant while contributing to a multiyear research effort to improve Google’s speech recognition. The goal is to make Google Assistant, as well as other features that use speech to text and speech to speech, more inclusive of users with neurological conditions that affect their speech.
The new app is called Project Relate, and volunteers can sign up at g.co/ProjectRelate. To be eligible to participate, volunteers need to be 18 or older and “have difficulty being understood by others.” They’ll also need a Google account and an Android phone using OS 8 or later. For now, it’s only available to English speakers in the US, Canada, Australia, and New Zealand. They’ll be tasked with recording 500 phrases, which should take between 30 to 90 minutes to record. Here’s a short video showcasing the project:
Why it’s important – Other Google apps like Translate and Assistant haven’t been very accessible for people with conditions like ALS, traumatic brain injury (TBI), or Parkinson’s disease. The hope is that the Project Relate data will help people with speech impairments when having conversations or when using voice commands for home assistant devices.
Nvidia unveils new healthcare offerings at GTC Fall 2021
Graphics processing unit technology developer Nvidia introduced a new healthcare artificial intelligence (AI) computing platform, as well as a new relationship with MD Anderson Cancer Center, at this week’s GPU Technology Conference (GTC) Fall 2021. Eric Ridley reported on these topics in his article on AuntMinnie.com. Clara Holoscan is designed to provide the computational infrastructure to enable medical device developers to build applications that process multimodality sensor data, run physics-based models, accelerate AI inferencing, and render high-quality graphics in real-time, according to the vendor. It provides scalable, end-to-end processing of streaming data for medical devices.
Nvidia is now also partnering with MD Anderson Cancer Center on cancer-focused AI initiatives. Several radiology AI initiatives are underway, including new AI models aimed at early detection of pancreatic cancer — a leading cause of cancer deaths that’s often identified only after it has metastasized. Other AI initiatives underway at MD Anderson include image-contouring models for planning of radiotherapy treatments and MRI-assisted radiosurgery, as well as an algorithm that analyzes post-treatment prostate MRI studies to assess the quality of radiation delivery.
Why it’s important – As I highlighted in a previous post, Nvidia continues to grow its footprint in health care through partnerships like the one with M.D. Anderson Cancer Center. They’re leveraging their strengths in AI and machine learning to create a robust platform for researchers to increase the variability of their sample datasets, which in turn boosts the model’s accuracy and generalizability.