Last Month in Healthcare AI (April 2024)

Contents: ?? 1) Prediction & Diagnosis | ??2) Treatment & Care | ?? 3) Latest Approvals | ?? 4) Generative AI | ??5) AI Assistants | ??6) Governance & Ethics

?? 1) Prediction & Diagnosis

?? Swedish researchers have developed an AI model, LARS, that detects lymphatic cancer with 90% accuracy using image analysis from over 17,000 patient scans, aimed at aiding radiologists and improving diagnostic consistency.

?? A new AI tool, VA-ResNet-50, predicts fatal heart rhythms with 80% accuracy by analyzing Holter ECGs. It successfully identified patients at risk of ventricular arrhythmia, potentially improving early detection and treatment for this deadly condition.

?? An AI tool can accurately detect pulmonary hypertension in newborns, a serious condition requiring swift treatment. Trained on ultrasound video data, the algorithm correctly diagnoses the condition with high accuracy and identifies its severity.

?? Lancaster University statisticians have developed an AI algorithm to predict hospital outbreaks, aiding in the management of diseases like COVID and MRSA. This model uses data on staff and patient movements to identify the sources of infection.

?? An NHS pilot study shows the AI tool MIA, short for?Mammography Intelligent Assessment, effectively detects early-stage breast cancers missed by specialists, promising improved early diagnosis and treatment outcomes.

?? And a new AI model called AsymMirai predicts cancer risk based on breast asymmetry, highlighting how differences between left and right breasts can indicate future health.

?? Study shows AI tool "Foresight," similar to ChatGPT but trained on NHS records, predicts future health conditions with up to 88% accuracy using US data and 68-76% using UK NHS data. Clinician-tested scenarios show a 93% alignment with Foresight's predictions, promising enhanced decision-making in healthcare.

??2) Treatment & Care

?? UCLA engineers have created an AI-assisted, bioelectric wearable patch that allows individuals with voice disorders to speak. The device attaches to the throat and converts larynx muscle movements into speech with 95% accuracy through machine learning.

?? GE HealthCare and Vanderbilt University's AI models now predict immunotherapy responses in cancer patients with 70-80% accuracy, analyzing extensive clinical data and aiming to improve targeted treatments and reduce toxicities.

?? Johnson & Johnson to enhance surgical procedures with AI in collaboration with NVIDIA, focusing on secure, real-time analysis of surgical data. This collaboration aims to improve surgical decision-making, collaboration, and education.

?? Machinify launches three AI apps to streamline the healthcare claims process, covering authorization, audit, and payment. These innovations automate requests, ensure accurate payments, and reduce administrative inefficiencies.

?? Waterlily, an AI platform developed by a former NASA data scientist, aims to predict seniors' long-term care needs, including when they'll require care, the type of facilities they might use, and their care costs.

?? Google is developing a Personal Health AI ChatBot for the Fitbit app to act as a health coach, analyzing data for personalized wellness advice. Aimed at improving user experience without diagnosing conditions, this model will launch as an experimental feature to refine based on feedback.

??3) Latest Approvals

?? GE HealthCare launches Prostate Volume Assist , an AI tool enhancing urology care by automating prostate volume measurements for faster, accurate cancer diagnosis and treatment planning.

?? GE HealthCare is also set to launch SonoSAMTrack , an AI-powered research model for ultrasound diagnostics, aiming for quicker, more precise results and streamlined development of new services.

??4) Generative AI

?? Google launched new AI tools including Vertex AI Search for Healthcare and updates to its MedLM model, aimed at improving clinical data usage and workflow efficiency for healthcare professionals.

?? NYU Langone Health developed a generative AI tool that simplifies doctors' notes from hospital visits into patient-friendly language, making them more understandable by reducing the reading level from the 11th-grade to the 6th-grade level.

?? Oracle introduce generative AI tool and related upgrades, aiming to boost care management efficiency, enhance system performance, and improve clinical analytics for healthcare stakeholders.

?? Generative AI may enhance healthcare-associated infection surveillance. Two AI-driven tools can accurately detect cases of central line-associated bloodstream infection and catheter-associated urinary tract infection.

?? A new study shows AI, specifically GPT-4, can help pinpoint brain damage from strokes by analyzing health histories & neuro exams, potentially improving care where access to scans or specialists is limited.

?? A study by NYU Langone Health found that AI, specifically ChatGPT, significantly speeds up the development of health software, such as a diabetes prevention program. By facilitating better communication between clinicians and engineers, ChatGPT reduced the design time from over 200 hours to just 40 hours.

??5) AI Assistants

?? Amwell partners with Suki to integrate an AI voice assistant into its telehealth platform, aiming to streamline administrative tasks within providers' workflows, reduce clinician burnout, and enhance care for over 90 million people across 55 health plans.

?? Symplr is working with Amazon Web Services to develop AI assistants to help automate complex workflows and mundane tasks for healthcare workers and also power chatbots to help patients find and schedule the right care.

?? China has commenced trials for an AI-powered assistant designed to aid neurosurgeons during critical procedures. The goal is to equip the AI with extensive knowledge, enabling it to serve as a virtual surgical consultant for medical professionals. It will be capable of processing various data types including MRI, ultrasound, CT scans, as well as images, text, and audio inputs.

?? A collaboration aims to enhance "Florence," a digital nurse, using generative AI and reinforcement learning . This goal is to provide personalized and accessible care to patients with chronic conditions, easing healthcare workforce shortages and improving clinical outcomes.

?? NVIDIA and Hippocratic AI collaborate to develop AI nurses, offering medical advice via video for $9/hour. Designed to supplement, not replace human nurses, these AI agents demonstrate empathy and high performance in medical tasks, potentially addressing global healthcare worker shortages.

??6) Governance & Ethics

?? A new deep learning tool tackles 'black box' AI in medical imaging, explaining diagnostic decisions, enhancing transparency in disease detection. Clinicians gain insights via 'map' of important image regions that contributed to the decision.

?? A Penn study finds AI detects depression from social media posts in white people but not Black people, highlighting potential biases in mental health AI tools and risking perpetuating racial disparities in healthcare.