Marzyeh Ghassemi

Sep 23, 2024 | nature.com | Elaine O. Nsoesie |Marzyeh Ghassemi

The proliferation of artificial intelligence (AI) algorithms for public use has led to many creative healthcare applications, some with the potential to create or worsen health inequities. Here, we argue that similar to prescription medicine labels, AI algorithms should be accompanied by a responsible use label. The proliferation of generative AI models has garnered public interest and creative healthcare and clinical applications.

Sep 12, 2024 | jamanetwork.com | Nigam H. Shah |Michael Pfeffer |Marzyeh Ghassemi

Rakers et al8 conducted a much-needed systematic review of the availability of evidence for artificial intelligence prediction algorithms (AIPAs) in primary care. Their review found 43 such prediction algorithms, of which 25 were commercially available. For all reviewed AIPAs, the least evidence was available for the data preparation phase followed closely by the impact assessment phase.

Aug 27, 2024 | nature.com | Marzyeh Ghassemi

Cancer screening, diagnosis and care stand to benefit greatly from advances in artificial intelligence (AI). Researchers, developers and deployers must ensure that applications of AI avoid known racial and gender biases to advance health care for all.

Jun 10, 2024 | cell.com | Moritz Gerstung |David C Liu |Marzyeh Ghassemi |James Zou

Experts discuss the challenges and opportunities of using artificial intelligence (AI) to study the evolution of cancer cells and their microenvironment, improve diagnosis, predict treatment response, and ensure responsible implementation in the clinic.

Nov 19, 2023 | nature.com | Marzyeh Ghassemi

If mistakes are made in clinical settings, patients suffer. Artificial intelligence (AI) generally — and large language models specifically — are increasingly used in health settings, but the way that physicians use AI tools in this high-stakes environment depends on how information is delivered. AI toolmakers have a responsibility to present information in a way that minimizes harm.