BrainX Waves: The Newsletter of BrainX Community

September 2024: Issue 3

Sep 22, 2024

Strategies for Artificial Intelligence in Healthcare: Real-World Solutions for Reshaping Healthcare Through Artificial Intelligence and Beyond

As someone engaged in both healthcare and AI, I found this book to be a timely and insightful guide that translates AI's potential into actionable strategies for real-world healthcare challenges. The authors blend technical depth with practical application, focusing on ethical considerations and the importance of a patient-centered approach. The book is useful for both beginners and professionals, highlighting the need for collaboration between technologists and healthcare providers to ensure responsible AI integration. With practical case studies, it serves as both a roadmap and a thoughtful reflection on the future of AI in healthcare. Highly recommended for healthcare professionals, policymakers, and AI enthusiasts alike!

Review by - Dr Avneesh Khare

Learn More

Connect

BrainX Community Live! August 2024: Implementing Ambient AI Scribe in Healthcare

BrainXAI Community August 2024 Live event, explores how ambient AI scribe technology improves clinical documentation and reduces the strain of healthcare workers.

In this video,Ed Lee, MD, MPH, Chief Medical Officer, Nabla, shares their experience about implementation of Nabla’s state of the art ambient AI technology at a large health system. Ambient AI scribe improves operational efficiency by automatically recording and translating patient-physician interactions into medical records.

He addresses how healthcare systems can integrate this platform safely, addressing any privacy and data security issues. He responded to participant’s queries related to the platform's ability to improve patient care by allowing clinicians to concentrate more on patients are among the important topics of conversation.

Watch Here

Upcoming BrainX Community Live! September 2024: Generalizing AI in Healthcare applications

Click here to register

Featuring Drs. Bart Geerts & Sandeep Reddy, 25 September, 2024 11 am ET via Zoom.

Program Agenda:

– Introduction

– “How can we deal with the uniqueness of health care sites? Our approach.” Dr. Bart Geerts, CEO and Founder, Healthplus.ai

– “Translational AI in Healthcare: Moving Beyond Traditional Trials and Regulatory Hurdles.” Dr. Sandeep Reddy, Chairman, Centre for Advancement of Translational AI in Medicine, Queensland University of Technology.

– Q&A

Connect More

Datasets

RadGraph2: Tracking Findings Over Time in Radiology Reports

RadGraph2 is a dataset of 800 chest radiology reports annotated using a fine-grained entity-relationship schema, which is an expanded version of the previously introduced RadGraph dataset. RadGraph2, focuses on capturing changes in disease state and device placement over time. It introduces a hierarchical schema that organizes entities based on their relationships and show that using this hierarchy during training improves the performance of an information extraction model.

In addition to the dataset of manually labeled reports, we release more than 220,000 reports automatically annotated by our benchmark model. This model achieved an F1 micro performance of 0.88 and 0.74 on two differently sourced withheld test sets (from MIMIC-CXR-JPG and CheXpert, respectively).

ENCoDE: skin tone and clinical data from a prospective trial on acute care patients

A total of 167 skin tone variables and two temperature variables are collected per body location, excluding images, together with ten non-biometric body location images per patient and the associated electronic health record (EHR) data. The ENCoDE project is a comprehensive EHR-linked skin tone database to combat skin tone associate disparities.

The study included patients admitted to Duke University Hospital with pulse oximetry recorded up to 5 minutes prior to arterial blood gas (ABG) measurements. Skin tone was measured across sixteen body locations using administered visual scales (Fitzpatrick, Monk Skin Tone, and Von Luschan), reflectance colorimetry (Delfin SkinColorCatch), and reflectance spectrophotometry (Konica Minolta CM-700D, Variable Spectro 1). IPhone SE 2020 and Google Pixel 4 (Android) image data are available for non-biometric body locations.

More Data

Podcast

With a specialization in bioinformatics and machine learning, Dr. Rashidi is an dedicated expert in patient care, research, and education. His groundbreaking tools, such as Pitt-GPT, STNG, and MILO, are revolutionizing clinical treatment and research methodologies. Having held senior positions at Cleveland Clinic and UC Davis, he has written important textbooks, developed ground-breaking AI systems that are now extensively utilized in the sector, and advanced AI in healthcare.

Listen More