natural language processing Archives - Medical Design Sourcing

How syncing wearables with AI chatbots can accelerate recovery time

Smart integration of AI chatbots and data collected by wearable devices can help patients and health care providers respond to early signs of illness.

By Nate MacLeitch, QuickBlox

[Illustration by Kudryavtsev via Stock.Adobe.com]

More effective public health and medical interventions could save 1.2 million lives per year, according to the Organization for Economic Cooperation and Development (OECD).

But the healthcare industry isn’t solely responsible. There is usually a gap between identifying an illness and seeking medical attention. Even when a patient feels unwell, they often don’t know the best path of care and may avoid medical support because they minimize their symptoms, lack physical access to local healthcare, worry about healthcare costs, or simply don’t have a doctor.

Wearable medical devices can bridge this gap by monitoring vital signs — often remotely — to determine irregular behavi…

NLP in drug discovery and the quest for the ‘right’ research elements

[Kishore Newton/Adobe Stock]

In drug discovery and development, data sources are as diverse as they are plentiful. There are comprehensive databases brimming with molecular targets, cellular processes, genomic sequences, proteomic profiles, and metabolite patterns that shed light on disease pathways. Data possibilities in the patient care realm are similarly vast, spanning electronic medical records, imaging datasets, and even patient-reported outcomes and adverse events reported on social media. The biomedical research site PubMed has tens of millions of research articles and studies.

Yet, it’s easier to drown in such turbulent data volumes than it is to swim. Various estimates over the past decade have projected that 80% of healthcare data are unstructured. “There’s a huge amount of information that’s not standardized,” said Jane Reed, director of life sciences with Linguamatics, an IQVIA company.…

Decode deaths with BERT to improve medical device safety and design

Michelle Wu is the founder and CEO of Nyquist Data. [Photo courtesy of Nyquist Data]

By Qiang Kou and Michelle Wu, Nyquist Data

A recent study shows that the number of death events in the FDA’s MAUDE (Manufacturer and User Facility Device Experience) database has been vastly underestimated because many are not reported as deaths.

Lalani et al. manually reviewed 290,141 MAUDE reports and found that around 17% of the death events had been misclassified. That means the patient died, but the event was labeled as having “no consequences or impact to patient.”

The manual review requires expertise in different medical specialties and is too time-consuming to process millions of added reports. This problem can be viewed as a binary classification problem. And we can fine-tune the BERT model to solve it.

What is BERT?

BERT stands for Bidirectional Encoder Representations from Transformers. Rec…

Google unveils AI-powered Care Studio Conditions to make sense of patient records

Google Health’s new Care Studio feature, Conditions [Screenshot courtesy of Google]Google Health previewed a new Care Studio feature called Conditions to make electronic health records more accessible and useful for clinicians treating patients.

Powered by artificial intelligence, Conditions can interpret and organize clinical notes stored across different systems for different purposes by different health care professionals.

‘When it comes to writing notes, clinicians use different abbreviations or acronyms depending on their personal preference, what health system they’re a part of, their region and other factors.” Paul Muret VP and GM of Google Health’s Care Studio, wrote yesterday in a blog post. “All of this has made it difficult to synthesize clinical data — until now.”

Get the full story at our sister site, Medical Design & Outsourcing.

Google unveils AI-powered Care Studio Conditions to make sense of patient records

Google Health’s new Care Studio feature, Conditions [Screenshot courtesy of Google]

Google Health previewed a new Care Studio feature called Conditions to make electronic health records more accessible and useful for clinicians treating patients.

Powered by artificial intelligence, Conditions can interpret and organize clinical notes stored across different systems for different purposes by different health care professionals.

‘When it comes to writing notes, clinicians use different abbreviations or acronyms depending on their personal preference, what health system they’re a part of, their region and other factors.” Paul Muret VP and GM of Google Health’s Care Studio, wrote yesterday in a blog post. “All of this has made it difficult to synthesize clinical data — until now.”

Conditions uses natural language processing to understand the notes, rank conditions b…

The role of natural language processing in advancing disease research

Image courtesy of Markus Spiske/Pexels

In any area of disease research, a deep understanding of recent and future trends surrounding a particular condition is crucial to the drug discovery process. But with the volume of scientific literature increasing all the time, it is difficult to manually sift through all the existing information and correlate data in such a way to produce meaningful direction. This predicament can lead to the misallocation of resources on research in areas that are less likely to yield promising treatments.

By analyzing all literature related to a specific condition or disease, researchers can better identify which areas will likely lead to a breakthrough. Natural language processing (NLP) uses a combination of linguistics, artificial intelligence, and computer science to understand text in the same way as people. Researchers can use NLP in trend analysis to determine the rate at whic…

What’s driving the natural language processing revolution in pharma and life sciences

Image courtesy of Pixabay

Pharmaceutical and life sciences companies are faced with a constant stream of new data flowing into often siloed information systems. About 80% of that information exists in unstructured text that is difficult to extract and use, despite its paramount importance in driving clinical and commercial outcomes.

As a result, these organizations find themselves increasingly overwhelmed with volumes of inaccessible data. At the same time, researchers and data scientists lack effective search tools to find the right information in this “big data” tsunami, causing them to miss opportunities to enhance patient safety, improve clinical trial design, identify previously undetected biomarkers and better understand the voice of the customer.

To overcome the limitations of time-consuming, manual searches through mountains of data, pharma and life sciences companies are looking to artificial…