ModernDoctor.AI

A new AI algorithm called STORK-A developed by researchers at Weill Cornell Medicine shows promise for predicting the chromosomal health of in vitro fertilized embryos without invasive testing. The algorithm analyzes microscope images of embryos along with data such as maternal age and embryo scoring, achieving about 70% accuracy in identifying normal and abnormal chromosomal counts, a condition known as aneuploidy, which can lead to failed pregnancies. This non-invasive method could significantly reduce the need for costly and invasive procedures like preimplantation genetic testing (PGT-A), aiming to enhance IVF success rates. The research is still in its early stages, and further clinical trials will be necessary before it can be widely adopted Read more: https://lnkd.in/g-84f4GQ

Engineers at the University of Houston have developed an AI tool that reveals how international air travel influences the global spread of COVID-19, with findings published in Nature. The team, led by associate professor Hien Van Nguyen, identified Western Europe, the Middle East, and North America as major regions driving transmission due to high international flight traffic. Using a model called Dynamic Weighted GraphSAGE, which analyzes complex networks like global flight patterns over time and space, they conducted a perturbation analysis to assess the sensitivity of disease spread to different flight connections. This allowed them to recommend targeted flight reductions in key regions, particularly Western Europe, which could minimize pandemic spread with less disruption to human mobility. Although developed in response to COVID-19, the tool is intended to aid policymakers in managing air travel during future pandemics. Researchers from the Houston Methodist Research Institute also contributed to the study. Read more: https://lnkd.in/gdZgvEjn

A Stanford University study, published in JAMA Network Open, compared layperson satisfaction with AI-generated medical advice versus clinician responses. Using GPT models, researchers found AI responses, enhanced with prompt engineering, received significantly higher satisfaction scores (3.96) than clinician responses (3.05). AI responses, especially in cardiology, were longer and rated more satisfying, though empathy and information quality were highest in endocrinology questions. Despite these results, the study noted limitations, emphasizing the need for broader research on AI's role in patient communication across medical settings. Read more: https://lnkd.in/gDaKvreg #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare

Microsoft announced new healthcare data and AI tools designed to streamline administrative tasks and accelerate AI application development for health systems. These tools include a medical imaging model collection, a healthcare agent service, and an AI-powered documentation solution for nurses. The aim is to reduce clinician burnout by saving time spent on administrative work, such as documentation, which consumes up to 41% of nurses' time. Microsoft also introduced open-source AI models capable of analyzing diverse data types, such as medical images and clinical records, enhancing capabilities for health organizations. The new tools build on Microsoft's broader efforts to lead in healthcare AI, following previous initiatives like its acquisition of Nuance Communications and the integration of AI solutions into its Azure platform. Many of these tools are in preview and will undergo validation before broader release. Read more: https://lnkd.in/eKJC8k5g

Researchers have developed a flexible AI model, referred to as "ChatGPT-like," capable of performing a variety of diagnostic tasks across 19 cancer types, including detecting cancer cells, identifying tumor origins, and predicting genetic mutations linked to treatment responses. This model, called Clinical Histopathology Imaging Evaluation Foundation (CHIEF), was trained on millions of pathology images using self-supervised learning, allowing it to recognize patterns and adapt to a broad range of tissues. Tested on over 32 independent datasets from 24 hospitals, CHIEF has outperformed prior AI systems in cancer diagnosis and prognosis. While promising, further development is needed, especially in rare cancers and pre-cancerous conditions, to ensure its clinical application and improve outcomes for patients globally. Read more https://lnkd.in/gMjdUDGx

The WHO held a global technical meeting in September 2024 to explore the use of AI in traditional medicine, hosted at the All India Institute of Ayurveda. The event brought together 60 participants from 15 countries to discuss topics like equitable access, intellectual property, capacity building, and the development of a global library for traditional medicine. The meeting also addressed the role of AI in advancing traditional knowledge, highlighting its potential impact on healthcare and sustainable development. A WHO technical brief on AI in traditional medicine is set to launch in October 2024. Read more: https://lnkd.in/gaRwW8fA #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare

AI-assisted technology is increasingly being integrated into obstetrics and gynecology to improve clinical outcomes, from predicting delivery modes to enhancing cervical cancer risk assessments. Despite its transformative potential, there is a notable gap in AI applications for menopausal women, primarily due to insufficient data. Dr. Melissa Wong from Cedars-Sinai Medical Center emphasized the need for improved data to harness AI for menopause care, while also highlighting the importance of clinician involvement in AI development to enhance patient care and avoid bias. Current AI tools are already influencing diagnostic practices, often unnoticed by clinicians, by prioritizing urgent cases in imaging and providing contextual analysis in cervical cytology. However, advancing AI in menopause care requires more granular data and a redesign of electronic health records to capture detailed menopause-related symptoms and experiences. Read the full article: https://lnkd.in/gmivCYs4 #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare

Heart failure during pregnancy is a serious but often overlooked condition, as its symptoms can be mistaken for normal pregnancy discomforts.   A Mayo Clinic study presented at the European Society of Cardiology Congress found that an AI-enabled digital stethoscope significantly improved the detection of heart failure in pregnant women, identifying twice as many cases compared to standard care. Conducted in Nigeria, the trial revealed that this AI tool was 12 times more likely to detect a specific type of heart failure called peripartum cardiomyopathy at an early stage. The study highlights the potential of AI in improving maternal health outcomes, especially in regions with high rates of pregnancy-related heart failure. Read the full article: https://lnkd.in/dA9z2rhj #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare

A recent poll reveals that Americans hold ambivalent views on the role of artificial intelligence (AI) in healthcare. While there is optimism about AI's potential to enhance medical diagnoses and streamline operations, concerns persist regarding its reliability, privacy risks, and the possible erosion of the human element in patient care. Many respondents express a cautious optimism, hoping for balanced integration where AI supports but does not replace human expertise. Overall, the public's mixed feelings reflect a broader debate about technology's role in sensitive areas like health care. Read the full article:https://lnkd.in/dwbRhRD3 #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare

Researchers at the NIH have developed an AI tool called LORIS that uses routine clinical data to predict cancer patients' responses to immune checkpoint inhibitors. The study, published in Nature Cancer, shows the model's accuracy in predicting patient outcomes and survival. LORIS uses common clinical features like age, cancer type, blood test results, and tumor mutational burden. Larger studies are needed to validate LORIS, which aims to guide immunotherapy decisions and improve patient care. Read the full article: https://lnkd.in/egcaD7Xq #health  #healthai  #healthcare  #ai  #artificialintelligence  #healthnews  #ModerndoctorAI  #AIinHealthcare #DigitalHealth #HealthcareInnovation #MedTech #HealthTech #AIHealthcare #HealthIT #HealthTechNews #AIandHealthcare