Shania Kennedy

A machine learning-based approach could flag individuals at high risk for lung cancer by analyzing DNA fragments found in blood, which may improve screening uptake.

Using a newly developed symptom atlas, a deep brain stimulation algorithm could optimize personalized treatments for Parkinson’s disease.

A machine learning approach using wearable data, EHRs and ecological momentary assessment information outperformed existing spine surgery outcome prediction tools.

An interpretable machine learning model improved clinicians’ performance in reading electroencephalography charts, boosting accuracy from 47% to 71%.

Six new data dashboards will track cancer, care access and SDOH across South Carolina’s 46 counties in an effort to advance population health.

Researchers from Vanderbilt University Medical Center (VUMC) have been awarded a five-year, $4.2 million grant from the National Heart, Lung, and Blood Institute, part of the National Institutes of Health (NIH), to validate an AI tool capable of measuring skin...

Deloitte’s 2024 consumer healthcare survey found that adoption of GenAI for health reasons has progressed little in the last year due to consumers’ distrust.

Healthcare generates a wealth of data, much of which is captured in provider notes and patient EHRs. In recent decades, healthcare organizations have begun not only to see the value of this information but also to use it to pursue key goals, such as improved outcomes. However, data availability...

A deep reinforcement learning model designed to tailor adaptive treatment schedules could double the time to progression for prostate cancer patients.

Bard and GPT-4 enhanced the readability of pathology reports while maintaining high medical accuracy, which could help explain findings to patients.

An AI tool developed by Mass General Brigham researchers has revealed that changes in muscle mass and fat quality over the course of immunotherapy are associated with poorer outcomes for patients with advanced non-small cell lung cancer (NSCLC), according to a...

A convolutional neural network successfully flagged 95% of breast cancer patients with axillary metastasis, demonstrating potential to reduce unnecessary biopsies.

The artificial intelligence-driven EXPRESSO model uses genomic data, epigenetics and other information to identify risk genes for autoimmune disease.

Potential use cases for AI in healthcare continue to grow as the technology rapidly advances. However, the potential for AI to enhance clinical decision support, chronic disease management and population health efforts has been checked by concerns over pitfalls like model bias and fairness. In an...

The American Academy of Sleep Medicine recently examined the potential and challenges of integrating artificial intelligence in clinical care.

New machine learning framework reveals that almost 15% of opioid use disorder patients discontinued recommended buprenorphine treatment prematurely.

Artificial intelligence is set to transform healthcare, bolstering both administrative and clinical workflows across the care continuum. As these technologies have rapidly advanced over the years, the pros and cons of AI use have become more apparent, leading to mixed perceptions of the tools...

As generative AI continues to proliferate in healthcare, investigations into potential use cases and how these tools can be deployed in clinical settings are becoming more prevalent. Listen to the full podcast to hear more details. And don’t forget to subscribe on iTunes, Spotify, or Google...

Healthcare leaders came together this week virtually for the 2024 Workgroup for Electronic Data Interchange (WEDI) Spring Conference to explore trends, standards, lessons learned and best practices for data exchange in healthcare. In addition to conversations about prior authorization and...

Researchers from Stony Brook University, Stanford University and the University of Pennsylvania have developed an AI-based system to track rates of depression and anxiety using data from social media posts, according to a recent study published in npj Digital...