Pinned
Check out our new podcast, The Digital Pulse. In the latest episode, host @BenMazer talks with algorithmic bias pioneer @oziadias.
creators.spotify.com/pod/profile/np…
npj Digital Medicine
3,459 posts
npj Digital Medicine
@npjDigitalMed
Open access @NaturePortfolio journal for the #DigitalMedicine community, publishing research, reviews & comments. Tag us & tweet your work with @npjDigitalMed.
- There are over 7000 rare diseases. Due to clinicians’ limited experience with such diseases and the heterogeneity of clinical presentations, 70% of individuals remain undiagnosed. Can deep learning help close the gap? nature.com/articles/s4174…
- This study develops a generative clinical LLM using 277 billion words of text and up to 20 billion parameters. The model improves biomedical natural language processing, generates synthetic clinical text, and passed Turing test in writing clinical notes. nature.com/articles/s4174…
- This study developed an open-source tool using a LLM to extract important medical information from clinical text, focusing on decompensated #LiverCirrhosis. The tool identified liver cirrhosis from free text with 100% sensitivity and 96% specificity, and showed strong results
- Foundation models (FMs) such as #ChatGPT have the potential to revolutionize healthcare. But what's hype and what's real? This review from a team in @StanfordMed includes 84 clinical FMs + proposes an evaluation framework better suited to assess value. nature.com/articles/s4174…
- In this perspective, @Berci & @EricTopol discuss the regulation of GPT-4 & generative #ArtificialIntelligence in medicine... balancing the exciting + transformative potential, but ensuring safety, maintaining ethical standards, & protecting privacy. nature.com/articles/s4174…
- It is important to ensure #digitalhealth does not accelerate #healthdisparities. @SafiyaMD et al. from @nyugrossman present this framework inc. key digital determinants of health, from individual to societal, to understand the impact on health #equity. nature.com/articles/s4174…
- This article introduces ETHOS, an AI tool that uses advanced #MachineLearning to predict future health outcomes based on patient records, without needing labelled data or model tuning. This tool can simulate different treatment options, helping improve patient care & reduce
- We are delighted to welcome @girish_nadkarni to the #npjDigitalMed Editorial Team. Girish brings a wealth of #DigitalHealth and #Nephrology expertise to our Editorial Board Member team. go.nature.com/3HA8CbD
- How are #LLMs in healthcare evaluated by humans? This article identifies gaps in current methods such as reliability & generalizability. To improve these evaluations, the authors propose the QUEST framework, which focuses on assessing LLMs based on five principles: information
- Matching patients to #ClinicalTrials is usually complex and time-consuming, often leaving patients unaware of potential treatment options. This study presents a custom fine-tuned language model that uses real-world patient data to automate trial matching, showing performance
- Your weekend read editorial: Discussing the importance of shifting the focus towards clinically relevant outcomes, when adopting #ArtificialIntelligence tools, the ecosystem required for AI to succeed in health, & the human aspect of #healthcare. nature.com/articles/s4174…
- To help surgeons learn faster, it's important to give them real-time feedback during surgery, but this is hard to study because there's so much information to analyze. This study by an interdisciplinary team @AjhungMD @AnimaAnandkumar @CedarsSinai @Caltech uses AI to analyze
- Are large language models (LLMs) safe for use in medicine? In this study led by @OmiyeTofunmi & @RoxanaDaneshjou, the authors found that four different LLMs had outputs that perpetuated false race-based medicine. nature.com/articles/s4174…
