machine learning Archives - Page 5 of 5

Cutting through the noise of machine learning for drug discovery

While the topic of AI in drug discovery has received considerable attention in recent years, mature deployments of techniques such as machine learning in the industry remain rare.

“The chemistry domain is qualitatively different from any other problem that machine learning has exhibited real success in,” said Jason Rolfe, CTO of Variational AI (Vancouver).

For one thing, there is a relatively limited number of FDA-approved drugs. As of 2018, FDA said it had approved 19,000 prescription drugs.

A dataset involving FDA-approved drugs that have been tested in humans would be orders of magnitude smaller than the sort of datasets that underlie Generative Pre-trained Transformer 3 (GPT-3), a language model from OpenAI, an AI research company co-founded by Elon Musk.

Jason Rolfe

High-throughput screening can generate substantially larger datasets. The PubChem database, which NI…

Johnson & Johnson leaders discuss what’s possible with the Microsoft cloud deal

Johnson & Johnson Group CIO and Global Vice President of Medical Devices Larry Jones [Photo courtesy of J&J]

Two leaders from Johnson & Johnson connected with Medical Design & Outsourcing this week to discuss the medical device maker’s partnership with Microsoft, the cloud’s potential for medical devices and to offer advice for medtech engineers designing for connectivity.

In January, New Brunswick, New Jersey–based Johnson & Johnson (NYSE:JNJ) named Redmond, Washington-based Microsoft (NASDAQ:MSFT) as its preferred cloud provider for digital surgery solutions and partner on building out J&J’s digital surgery platform and internet of things (IoT) device connectivity.

Johnson & Johnson Group CIO and Global Vice President of Medical Devices Larry Jones and Office of Digital Innovation Leader Peter Schulam (who also serves as global head of medical affairs, clinical a…

Baxter touts data supporting use of machine learning for infusion pump programming

Baxter (NYSE:BAX) announced today that data shows the potential for machine learning supporting decision-making with infusion pump programming.

Deerfield, Illinois-based Baxter presented the data from a retrospective study — part of a collaboration with MedAware aimed to develop next-generation dose error reduction software — at the American Society of Health-System Pharmacists (ASHP) 2021 Midyear Clinical Meeting.

Get the full story at our sister site, Drug Delivery Business News.

The advantages of an AI/ML-enabled search engine for FDA records

(Image courtesy of the FDA)

The FDA’s exciting new list of artificial intelligence and machine learning-enabled devices highlights opportunity for improvement.

Craig Coombs and Qiang Kou, Nyquist Data

The FDA released a list of cleared or approved artificial intelligence and machine learning-enabled devices in September, documenting much of the agency’s work in the innovative area of AI/ML.

Extracting this information from the FDA’s decades-old database is labor-intensive at best — and often impossible. Despite the time spent by the FDA to make this new list, a lack of even text-based searching capability makes the list itself cumbersome and time-consuming to review.

Wouldn’t it be better if there was an AI resource that could quickly compile a list of FDA’s AI/ML clearances and approvals, allowing searches in seconds rather than hours?

Get the full story at our sister site, MassDevic…

The advantages of an AI/ML-enabled search engine for FDA records

(Image courtesy of the FDA) The FDA’s exciting new list of artificial intelligence and machine learning-enabled devices highlights opportunity for improvement.

Craig Coombs and Qiang Kou, Nyquist Data

The FDA released a list of cleared or approved artificial intelligence and machine learning-enabled devices in September, documenting much of the agency’s work in the innovative area of AI/ML.

Extracting this information from the FDA’s decades-old database is labor-intensive at best — and often impossible. Despite the time spent by the FDA to make this new list, a lack of even text-based searching capability makes the list itself cumbersome and time-consuming to review.

Wouldn’t it be better if there was an AI resource that could quickly compile a list of FDA’s AI/ML clearances and approvals, allowing searches in seconds rather than hours?

Like many databases, the FDA database uses text-matching to find relevant entries. The weakness of text-matching…

FDA authorizes first machine learning-based screening device for COVID-19 biomarkers

The FDA announced that it authorized the first machine learning-based screening device for identifying COVID-19 biomarkers.

Tiger Tech Solutions’ COVID Plus Monitor received emergency use authorization (EUA) as a non-diagnostic screening device for identifying certain biomarkers that are indicative of some types of conditions, including hypercoagulation (which causes blood to clot more easily than normal), according to an FDA release.

The monitor is intended for use by trained personnel to help prevent exposure to and the spread of SARS-CoV-2, the virus causing COVID-19. The biomarkers it identifies, including other hypercoagulable conditions (like sepsis or cancer) or hyper-inflammatory states, may be indicative of infection with the virus in asymptomatic individuals over the age of five.

Tiger Tech’s monitor is designed for use following a temperature reading that does not meet criteria for fever in settings where temperature check is being…

MIT researchers tout new machine learning technique for assessing drug molecules

MIT researchers have developed a machine learning-based technique to more quickly calculate the binding affinity of a drug molecule (represented in pink) with a target protein (the circular structure). [Image courtesy of MIT News]

MIT researchers are touting a new machine-learning technique called DeepBAR that can quickly calculate the binding affinities between drug candidates and their targets.

DeepBAR produces precise calculations in a fraction of the time compared to previous, according to the researchers. They think the software could potentially accelerate drug discovery and protein engineering.

“Our method is orders of magnitude faster than before, meaning we can have drug discovery that is both efficient and reliable,” Bin Zhang, an MIT chemistry professor and a co-author of a new paper describing the technique, said in an MIT news release.

The research, which NIH partially funded, appea…

How precision drug-dosing supports individualized treatment

Photo by icon0.com from Pexels

The concept of precision drug-dosing has gained ground in recent years, given its ability to boost efficacy and curb side effects. Yet imprecise dosing regimens continue to be common for many drugs, leading to significant rates of adverse drug reactions (ADRs).

“ADRs are one of the top ten causes of death in the developed world,” said Sirj Goswami, CEO and co-founder of InsightRX. “More than two million serious ADRs occur each year, representing a cost burden of $136 billion annually. More than half of these events are preventable and are dose-related,” Goswami said.

In the following interview, Goswami shares his perspective on how precision dosing can optimize dosing in clinical trials and improve real-world drug performance. He also touches on the promise of machine learning to drive further dosing-related advances.

Drug Discovery & Development: How do yo…

Q&A: Keys to unlock data science potential for drug discovery

Image courtesy of Pexels

For all of its promise in healthcare and elsewhere, deploying artificial intelligence is frequently a challenging endeavor. “Close collaboration between data science teams, other project team members and stakeholders is essential,” said Jennifer Bradford, director of data science at Phastar, the London-headquartered contract research organization. While input from computational, statistical or medical experts could be essential to inform data science models, all stakeholders understand the requirements and are working “in sync with the project,” Branford said.

In the following interview, Bradford shares advice on how to collaborate effectively on data science projects, the impact of COVID-19 on data science in pharma and the potential for AI to accelerate R&D timelines.

What comes next after alignment between different stakeholders on data science projects is confirmed? <…

Hologic and Google Cloud team up on digital diagnostics for cervical cancer

Hologic (NSDQ:HOLX) has entered into a multi-year deal to use Google Cloud’s machine learning and deep learning technologies with its Genius digital diagnostics system, a cytology platform that uses volumetric imaging data to identify precancerous lesions and cancer cells of the cervix.

The machine learning and deep learning capabilities from Google Cloud will enable Hologic to build on its more than three decades of experience in cervical cancer screening, according to Kevin Thornal, president of Hologic’s Diagnostic Solutions division. “Enhancing our use of AI with Google Cloud’s machine learning capabilities and cloud architecture is the next natural step in this journey forward,” he said in a statement.

Genius Digital Diagnostics is CE-marked for use in Europe. It is not yet available in the U.S.

The FDA is currently overhauling how it regulates machine learning-based software for medical device applications.

In related news, Hologic recently …