<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="https://med-ai.media/wp-content/plugins/seriously-simple-podcasting/templates/feed-stylesheet.xsl"?><rss version="2.0"
	 xmlns:content="http://purl.org/rss/1.0/modules/content/"
	 xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	 xmlns:dc="http://purl.org/dc/elements/1.1/"
	 xmlns:atom="http://www.w3.org/2005/Atom"
	 xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	 xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	 xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd"
	 xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0"
	 xmlns:podcast="https://podcastindex.org/namespace/1.0"
	>
		<channel>
		<title>MedAI Digest</title>
		<atom:link href="https://med-ai.media/feed/podcast/digest/" rel="self" type="application/rss+xml"/>
		<link>https://med-ai.media/archives/series/digest</link>
		<description>Daily AI medical research digest</description>
		<lastBuildDate>Tue, 14 Apr 2026 22:00:00 +0000</lastBuildDate>
		<language>en-US</language>
		<copyright>© 2026 MedAI Digest</copyright>
		<itunes:subtitle></itunes:subtitle>
		<itunes:author>MedAI Digest</itunes:author>
		<itunes:summary>Daily AI medical research digest</itunes:summary>
		<itunes:owner>
			<itunes:name>MedAI Digest</itunes:name>
			<itunes:email>biz@med-ai.ac</itunes:email>
		</itunes:owner>
		<itunes:explicit>false</itunes:explicit>
		<itunes:image href="http://med-ai.media/wp-content/uploads/2026/04/podcast-scaled.jpg"></itunes:image>
			<image>
				<url>http://med-ai.media/wp-content/uploads/2026/04/podcast-scaled.jpg</url>
				<title>MedAI Digest</title>
				<link>https://med-ai.media/archives/series/digest</link>
			</image>
		<itunes:category text="Health &amp; Fitness">
			<itunes:category text="Life Sciences"></itunes:category>
		</itunes:category>
		<itunes:category text="Education">
									<itunes:category text="Medicine"></itunes:category>
							</itunes:category>
		<googleplay:author><![CDATA[MedAI Digest]]></googleplay:author>
			<googleplay:email>biz@med-ai.ac</googleplay:email>			<googleplay:description>Daily AI medical research digest</googleplay:description>
			<googleplay:explicit>No</googleplay:explicit>
			<googleplay:image href="http://med-ai.media/wp-content/uploads/2026/04/podcast-scaled.jpg"></googleplay:image>
			<podcast:locked owner="biz@med-ai.ac">yes</podcast:locked>
		<podcast:guid>90785f5a-6205-5e14-bde7-5249e5aa1901</podcast:guid>
		
		<!-- podcast_generator="SSP by Castos/3.14.4" Seriously Simple Podcasting plugin for WordPress (https://wordpress.org/plugins/seriously-simple-podcasting/) -->
		<generator>https://wordpress.org/?v=6.9.4</generator>

<item>
	<title>AI Identifies Tumor Origins from Tissue Images with 98% Accuracy</title>
	<link>https://med-ai.media/archives/podcast/ai-identifies-tumor-origins-from-tissue-images-with-98-accuracy</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/ai-identifies-tumor-origins-from-tissue-images-with-98-accuracy</guid>
	<description><![CDATA[A new deep learning method identifies where malignant tumors originated by analyzing whole slide images with 98% accuracy, processing each image in under a minute. Original paper: Soft multiclass feature augmented deep learning to predict tumor origins using cytology or histology whole slide images. — NPJ digital medicine. 10.1038/s41746-026-02604-7 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A new deep learning method identifies where malignant tumors originated by analyzing whole slide images with 98% accuracy, processing each image in under a minute. Original paper: Soft multiclass feature augmented deep learning to predict tumor origins u]]></itunes:subtitle>
	<content:encoded><![CDATA[A new deep learning method identifies where malignant tumors originated by analyzing whole slide images with 98% accuracy, processing each image in under a minute. Original paper: Soft multiclass feature augmented deep learning to predict tumor origins using cytology or histology whole slide images. — NPJ digital medicine. 10.1038/s41746-026-02604-7 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41974822_en.mp3" length="1384512" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A new deep learning method identifies where malignant tumors originated by analyzing whole slide images with 98% accuracy, processing each image in under a minute. Original paper: Soft multiclass feature augmented deep learning to predict tumor origins using cytology or histology whole slide images. — NPJ digital medicine. 10.1038/s41746-026-02604-7 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A new deep learning method identifies where malignant tumors originated by analyzing whole slide images with 98% accuracy, processing each image in under a minute. Original paper: Soft multiclass feature augmented deep learning to predict tumor origins using cytology or histology whole slide images. — NPJ digital medicine. 10.1038/s41746-026-02604-7 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Why AI Healthcare Investment Follows Money, Not Medical Need</title>
	<link>https://med-ai.media/archives/podcast/why-ai-healthcare-investment-follows-money-not-medical-need</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/why-ai-healthcare-investment-follows-money-not-medical-need</guid>
	<description><![CDATA[A comprehensive analysis of 3,807 AI health startups reveals stark geographic concentration, funding gaps, and critical underrepresentation of clinical expertise in founding teams. Original paper: Mapping AI startup investment and innovation in healthcare using a five-tier AI systems complexity framework. — NPJ digital medicine. 10.1038/s41746-026-02595-5 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A comprehensive analysis of 3,807 AI health startups reveals stark geographic concentration, funding gaps, and critical underrepresentation of clinical expertise in founding teams. Original paper: Mapping AI startup investment and innovation in healthcar]]></itunes:subtitle>
	<content:encoded><![CDATA[A comprehensive analysis of 3,807 AI health startups reveals stark geographic concentration, funding gaps, and critical underrepresentation of clinical expertise in founding teams. Original paper: Mapping AI startup investment and innovation in healthcare using a five-tier AI systems complexity framework. — NPJ digital medicine. 10.1038/s41746-026-02595-5 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41974803_en.mp3" length="1926528" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A comprehensive analysis of 3,807 AI health startups reveals stark geographic concentration, funding gaps, and critical underrepresentation of clinical expertise in founding teams. Original paper: Mapping AI startup investment and innovation in healthcare using a five-tier AI systems complexity framework. — NPJ digital medicine. 10.1038/s41746-026-02595-5 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A comprehensive analysis of 3,807 AI health startups reveals stark geographic concentration, funding gaps, and critical underrepresentation of clinical expertise in founding teams. Original paper: Mapping AI startup investment and innovation in healthcare using a five-tier AI systems complexity framework. — NPJ digital medicine. 10.1038/s41746-026-02595-5 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>AI-Augmented Learning Advances Sepsis Treatment</title>
	<link>https://med-ai.media/archives/podcast/ai-augmented-learning-advances-sepsis-treatment</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/ai-augmented-learning-advances-sepsis-treatment</guid>
	<description><![CDATA[Sepsis treatment varies widely among clinicians. MORE-CLEAR is a new framework that integrates clinical language with machine learning to recommend evidence-based sepsis treatments. Original paper: Large language model-augmented offline reinforcement learning framework for sepsis management in critical care. — NPJ digital medicine. 10.1038/s41746-026-00456-0 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[Sepsis treatment varies widely among clinicians. MORE-CLEAR is a new framework that integrates clinical language with machine learning to recommend evidence-based sepsis treatments. Original paper: Large language model-augmented offline reinforcement lea]]></itunes:subtitle>
	<content:encoded><![CDATA[Sepsis treatment varies widely among clinicians. MORE-CLEAR is a new framework that integrates clinical language with machine learning to recommend evidence-based sepsis treatments. Original paper: Large language model-augmented offline reinforcement learning framework for sepsis management in critical care. — NPJ digital medicine. 10.1038/s41746-026-00456-0 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41975229_en.mp3" length="1473216" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[Sepsis treatment varies widely among clinicians. MORE-CLEAR is a new framework that integrates clinical language with machine learning to recommend evidence-based sepsis treatments. Original paper: Large language model-augmented offline reinforcement learning framework for sepsis management in critical care. — NPJ digital medicine. 10.1038/s41746-026-00456-0 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[Sepsis treatment varies widely among clinicians. MORE-CLEAR is a new framework that integrates clinical language with machine learning to recommend evidence-based sepsis treatments. Original paper: Large language model-augmented offline reinforcement learning framework for sepsis management in critical care. — NPJ digital medicine. 10.1038/s41746-026-00456-0 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Wearable Anxiety Detection: Promising Sensors Need Clinical Proof</title>
	<link>https://med-ai.media/archives/podcast/wearable-anxiety-detection-promising-sensors-need-clinical-proof</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/wearable-anxiety-detection-promising-sensors-need-clinical-proof</guid>
	<description><![CDATA[Wearable heart rhythm sensors show potential for objective anxiety monitoring, but most studies lack the rigor needed for clinical adoption. Original paper: Wearable ECG and PPG for anxiety detection: a translational digital medicine perspective. — NPJ digital medicine. 10.1038/s41746-026-02620-7 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[Wearable heart rhythm sensors show potential for objective anxiety monitoring, but most studies lack the rigor needed for clinical adoption. Original paper: Wearable ECG and PPG for anxiety detection: a translational digital medicine perspective. — NPJ d]]></itunes:subtitle>
	<content:encoded><![CDATA[Wearable heart rhythm sensors show potential for objective anxiety monitoring, but most studies lack the rigor needed for clinical adoption. Original paper: Wearable ECG and PPG for anxiety detection: a translational digital medicine perspective. — NPJ digital medicine. 10.1038/s41746-026-02620-7 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41975050_en.mp3" length="2100288" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[Wearable heart rhythm sensors show potential for objective anxiety monitoring, but most studies lack the rigor needed for clinical adoption. Original paper: Wearable ECG and PPG for anxiety detection: a translational digital medicine perspective. — NPJ digital medicine. 10.1038/s41746-026-02620-7 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[Wearable heart rhythm sensors show potential for objective anxiety monitoring, but most studies lack the rigor needed for clinical adoption. Original paper: Wearable ECG and PPG for anxiety detection: a translational digital medicine perspective. — NPJ digital medicine. 10.1038/s41746-026-02620-7 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Reading Pain in the Face: AI Detects Headache Intensity From Facial Expressions</title>
	<link>https://med-ai.media/archives/podcast/reading-pain-in-the-face-ai-detects-headache-intensity-from-facial-expressions</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/reading-pain-in-the-face-ai-detects-headache-intensity-from-facial-expressions</guid>
	<description><![CDATA[Researchers developed an AI model that estimates headache pain intensity from facial expressions, offering an objective, nonverbal pain assessment method for clinical monitoring. Original paper: An exploratory study of headache pain intensity using facial expressions and APEX frames. — NPJ digital medicine. 10.1038/s41746-026-02617-2 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[Researchers developed an AI model that estimates headache pain intensity from facial expressions, offering an objective, nonverbal pain assessment method for clinical monitoring. Original paper: An exploratory study of headache pain intensity using facia]]></itunes:subtitle>
	<content:encoded><![CDATA[Researchers developed an AI model that estimates headache pain intensity from facial expressions, offering an objective, nonverbal pain assessment method for clinical monitoring. Original paper: An exploratory study of headache pain intensity using facial expressions and APEX frames. — NPJ digital medicine. 10.1038/s41746-026-02617-2 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41974887_en.mp3" length="1354656" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[Researchers developed an AI model that estimates headache pain intensity from facial expressions, offering an objective, nonverbal pain assessment method for clinical monitoring. Original paper: An exploratory study of headache pain intensity using facial expressions and APEX frames. — NPJ digital medicine. 10.1038/s41746-026-02617-2 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[Researchers developed an AI model that estimates headache pain intensity from facial expressions, offering an objective, nonverbal pain assessment method for clinical monitoring. Original paper: An exploratory study of headache pain intensity using facial expressions and APEX frames. — NPJ digital medicine. 10.1038/s41746-026-02617-2 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Climate Factors Drive Vector-Borne Disease in Bangladesh: Machine Learning Reveals Prevention Opportunities</title>
	<link>https://med-ai.media/archives/podcast/climate-factors-drive-vector-borne-disease-in-bangladesh-machine-learning-reveals-prevention-opportunities</link>
	<pubDate>Tue, 14 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/archives/podcast/climate-factors-drive-vector-borne-disease-in-bangladesh-machine-learning-reveals-prevention-opportunities</guid>
	<description><![CDATA[A new analysis of vector-borne diseases across Bangladesh reveals that temperature is the strongest climate predictor of disease spread, suggesting that climate-informed early warning systems could significantly improve outbreak prevention and control. Original paper: Spatiotemporal patterns of climate-sensitive vector-borne diseases in Bangladesh: leveraging machine learning and spatial regression for intervention strategies. — BMC medicine. 10.1186/s12916-026-04857-1 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A new analysis of vector-borne diseases across Bangladesh reveals that temperature is the strongest climate predictor of disease spread, suggesting that climate-informed early warning systems could significantly improve outbreak prevention and control. O]]></itunes:subtitle>
	<content:encoded><![CDATA[A new analysis of vector-borne diseases across Bangladesh reveals that temperature is the strongest climate predictor of disease spread, suggesting that climate-informed early warning systems could significantly improve outbreak prevention and control. Original paper: Spatiotemporal patterns of climate-sensitive vector-borne diseases in Bangladesh: leveraging machine learning and spatial regression for intervention strategies. — BMC medicine. 10.1186/s12916-026-04857-1 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41975424_en.mp3" length="1485216" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A new analysis of vector-borne diseases across Bangladesh reveals that temperature is the strongest climate predictor of disease spread, suggesting that climate-informed early warning systems could significantly improve outbreak prevention and control. Original paper: Spatiotemporal patterns of climate-sensitive vector-borne diseases in Bangladesh: leveraging machine learning and spatial regression for intervention strategies. — BMC medicine. 10.1186/s12916-026-04857-1 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A new analysis of vector-borne diseases across Bangladesh reveals that temperature is the strongest climate predictor of disease spread, suggesting that climate-informed early warning systems could significantly improve outbreak prevention and control. Original paper: Spatiotemporal patterns of climate-sensitive vector-borne diseases in Bangladesh: leveraging machine learning and spatial regression for intervention strategies. — BMC medicine. 10.1186/s12916-026-04857-1 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Regulatory Clearance ≠ Clinical Benefit: The State of AI-Enabled ICU Devices</title>
	<link>https://med-ai.media/archives/podcast/regulatory-clearance-%e2%89%a0-clinical-benefit-the-state-of-ai-enabled-icu-devices</link>
	<pubDate>Sun, 12 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/?post_type=podcast&amp;p=4590</guid>
	<description><![CDATA[A systematic review of 36 commercially available AI-enabled medical devices designed for intensive care reveals a fragmented regulatory landscape across the US and EU—with a critical gap between regulatory clearance and proven clinical utility. Original paper: The landscape of artificial intelligence-enabled medical devices in the EU and the US intended for intensive care units. — NPJ digital medicine. 10.1038/s41746-026-02609-2 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A systematic review of 36 commercially available AI-enabled medical devices designed for intensive care reveals a fragmented regulatory landscape across the US and EU—with a critical gap between regulatory clearance and proven clinical utility. Original ]]></itunes:subtitle>
	<content:encoded><![CDATA[A systematic review of 36 commercially available AI-enabled medical devices designed for intensive care reveals a fragmented regulatory landscape across the US and EU—with a critical gap between regulatory clearance and proven clinical utility. Original paper: The landscape of artificial intelligence-enabled medical devices in the EU and the US intended for intensive care units. — NPJ digital medicine. 10.1038/s41746-026-02609-2 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41963517_en.mp3" length="1596768" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A systematic review of 36 commercially available AI-enabled medical devices designed for intensive care reveals a fragmented regulatory landscape across the US and EU—with a critical gap between regulatory clearance and proven clinical utility. Original paper: The landscape of artificial intelligence-enabled medical devices in the EU and the US intended for intensive care units. — NPJ digital medicine. 10.1038/s41746-026-02609-2 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A systematic review of 36 commercially available AI-enabled medical devices designed for intensive care reveals a fragmented regulatory landscape across the US and EU—with a critical gap between regulatory clearance and proven clinical utility. Original paper: The landscape of artificial intelligence-enabled medical devices in the EU and the US intended for intensive care units. — NPJ digital medicine. 10.1038/s41746-026-02609-2 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>Can Multiagent AI Committees Improve Fairness in Liver Transplant Selection?</title>
	<link>https://med-ai.media/archives/podcast/can-multiagent-ai-committees-improve-fairness-in-liver-transplant-selection</link>
	<pubDate>Sun, 12 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/?post_type=podcast&amp;p=4603</guid>
	<description><![CDATA[A multiagent AI system with four specialized language models successfully simulated a transplant selection committee, achieving 92% accuracy in survival prediction while demonstrating fairness across patient demographics. Original paper: A multiagent large language model-based system to simulate the liver transplant selection committee: a retrospective cohort study. — The Lancet. Digital health. 10.1016/j.landig.2025.100966 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A multiagent AI system with four specialized language models successfully simulated a transplant selection committee, achieving 92% accuracy in survival prediction while demonstrating fairness across patient demographics. Original paper: A multiagent lar]]></itunes:subtitle>
	<content:encoded><![CDATA[A multiagent AI system with four specialized language models successfully simulated a transplant selection committee, achieving 92% accuracy in survival prediction while demonstrating fairness across patient demographics. Original paper: A multiagent large language model-based system to simulate the liver transplant selection committee: a retrospective cohort study. — The Lancet. Digital health. 10.1016/j.landig.2025.100966 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41951492_en-1.mp3" length="1528704" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A multiagent AI system with four specialized language models successfully simulated a transplant selection committee, achieving 92% accuracy in survival prediction while demonstrating fairness across patient demographics. Original paper: A multiagent large language model-based system to simulate the liver transplant selection committee: a retrospective cohort study. — The Lancet. Digital health. 10.1016/j.landig.2025.100966 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A multiagent AI system with four specialized language models successfully simulated a transplant selection committee, achieving 92% accuracy in survival prediction while demonstrating fairness across patient demographics. Original paper: A multiagent large language model-based system to simulate the liver transplant selection committee: a retrospective cohort study. — The Lancet. Digital health. 10.1016/j.landig.2025.100966 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>APOE Genotype Reveals Personalized Dementia Risk Thresholds in Lewy Body Disease</title>
	<link>https://med-ai.media/archives/podcast/apoe-genotype-reveals-personalized-dementia-risk-thresholds-in-lewy-body-disease</link>
	<pubDate>Sun, 12 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/?post_type=podcast&amp;p=4616</guid>
	<description><![CDATA[A landmark post-mortem study of 399 brains reveals that APOE genotype fundamentally shapes individual dementia risk thresholds in Lewy body disease, with major implications for patient stratification and personalized treatment. Original paper: Quantitative pathology and APOE genotype reveal dementia risk and progression in Lewy body disease. — Brain : a journal of neurology. 10.1093/brain/awag114 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[A landmark post-mortem study of 399 brains reveals that APOE genotype fundamentally shapes individual dementia risk thresholds in Lewy body disease, with major implications for patient stratification and personalized treatment. Original paper: Quantitati]]></itunes:subtitle>
	<content:encoded><![CDATA[A landmark post-mortem study of 399 brains reveals that APOE genotype fundamentally shapes individual dementia risk thresholds in Lewy body disease, with major implications for patient stratification and personalized treatment. Original paper: Quantitative pathology and APOE genotype reveal dementia risk and progression in Lewy body disease. — Brain : a journal of neurology. 10.1093/brain/awag114 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41889331_en-6.mp3" length="1636128" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[A landmark post-mortem study of 399 brains reveals that APOE genotype fundamentally shapes individual dementia risk thresholds in Lewy body disease, with major implications for patient stratification and personalized treatment. Original paper: Quantitative pathology and APOE genotype reveal dementia risk and progression in Lewy body disease. — Brain : a journal of neurology. 10.1093/brain/awag114 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[A landmark post-mortem study of 399 brains reveals that APOE genotype fundamentally shapes individual dementia risk thresholds in Lewy body disease, with major implications for patient stratification and personalized treatment. Original paper: Quantitative pathology and APOE genotype reveal dementia risk and progression in Lewy body disease. — Brain : a journal of neurology. 10.1093/brain/awag114 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>

<item>
	<title>ChatGPT-5 Generates Clinically Relevant Psychiatric Cases—But Safety Framing Lags Behind</title>
	<link>https://med-ai.media/archives/podcast/chatgpt-5-generates-clinically-relevant-psychiatric-cases-but-safety-framing-lags-behind</link>
	<pubDate>Sun, 12 Apr 2026 13:00:00 +0000</pubDate>
	<dc:creator><![CDATA[MedAI Digest]]></dc:creator>
	<guid isPermaLink="false">https://med-ai.media/?post_type=podcast&amp;p=4629</guid>
	<description><![CDATA[Artificial intelligence can generate clinically relevant psychiatric case vignettes for medical education, but substantial gaps in safety framing and protective factors require expert modification before classroom deployment. Original paper: Evaluation of artificial intelligence-generated vignettes depicting patient chatbot use in psychiatric contexts. — NPJ digital medicine. 10.1038/s41746-026-02605-6 📄 Read the article]]></description>
	<itunes:subtitle><![CDATA[Artificial intelligence can generate clinically relevant psychiatric case vignettes for medical education, but substantial gaps in safety framing and protective factors require expert modification before classroom deployment. Original paper: Evaluation o]]></itunes:subtitle>
	<content:encoded><![CDATA[Artificial intelligence can generate clinically relevant psychiatric case vignettes for medical education, but substantial gaps in safety framing and protective factors require expert modification before classroom deployment. Original paper: Evaluation of artificial intelligence-generated vignettes depicting patient chatbot use in psychiatric contexts. — NPJ digital medicine. 10.1038/s41746-026-02605-6 📄 Read the article]]></content:encoded>
	<enclosure url="https://med-ai.media/wp-content/uploads/2026/04/41946953_en-1.mp3" length="1587840" type="audio/mpeg"></enclosure>
	<itunes:summary><![CDATA[Artificial intelligence can generate clinically relevant psychiatric case vignettes for medical education, but substantial gaps in safety framing and protective factors require expert modification before classroom deployment. Original paper: Evaluation of artificial intelligence-generated vignettes depicting patient chatbot use in psychiatric contexts. — NPJ digital medicine. 10.1038/s41746-026-02605-6 📄 Read the article]]></itunes:summary>
	<itunes:explicit>false</itunes:explicit>
	<itunes:block>no</itunes:block>
	<itunes:duration>0:00</itunes:duration>
	<itunes:author><![CDATA[MedAI Digest]]></itunes:author>	<googleplay:description><![CDATA[Artificial intelligence can generate clinically relevant psychiatric case vignettes for medical education, but substantial gaps in safety framing and protective factors require expert modification before classroom deployment. Original paper: Evaluation of artificial intelligence-generated vignettes depicting patient chatbot use in psychiatric contexts. — NPJ digital medicine. 10.1038/s41746-026-02605-6 📄 Read the article]]></googleplay:description>
	<googleplay:explicit>No</googleplay:explicit>
	<googleplay:block>no</googleplay:block>
</item>
	</channel>
</rss>
