AI Medical Compendium Journal:
Proceedings of the National Academy of Sciences of the United States of America

Showing 11 to 20 of 332 articles

Evaluating interdisciplinary research: Disparate outcomes for topic and knowledge base.

Proceedings of the National Academy of Sciences of the United States of America
Interdisciplinary research is essential for addressing complex global challenges, but there are concerns that scientific institutions like journals select against it. Prior work has focused largely on how interdisciplinarity relates to outcomes for p...

Existential risk narratives about AI do not distract from its immediate harms.

Proceedings of the National Academy of Sciences of the United States of America
There is broad consensus that AI presents risks, but considerable disagreement about the nature of those risks. These differing viewpoints can be understood as distinct narratives, each offering a specific interpretation of AI's potential dangers. On...

The fruit fly, , as a microrobotics platform.

Proceedings of the National Academy of Sciences of the United States of America
Engineering small autonomous agents capable of operating in the microscale environment remains a key challenge, with current systems still evolving. Our study explores the fruit fly, , a classic model system in biology and a species adept at microsca...

An integrated AI knowledge graph framework of bacterial enzymology and metabolism.

Proceedings of the National Academy of Sciences of the United States of America
The study of bacterial metabolism holds immense significance for improving human health and advancing agricultural practices. The prospective applications of genomically encoded bacterial metabolism present a compelling opportunity, particularly in t...

Bridging the human-AI knowledge gap through concept discovery and transfer in AlphaZero.

Proceedings of the National Academy of Sciences of the United States of America
AI systems have attained superhuman performance across various domains. If the hidden knowledge encoded in these highly capable systems can be leveraged, human knowledge and performance can be advanced. Yet, this internal knowledge is difficult to ex...

Structure of activity in multiregion recurrent neural networks.

Proceedings of the National Academy of Sciences of the United States of America
Neural circuits comprise multiple interconnected regions, each with complex dynamics. The interplay between local and global activity is thought to underlie computational flexibility, yet the structure of multiregion neural activity and its origins i...

A general framework for interpretable neural learning based on local information-theoretic goal functions.

Proceedings of the National Academy of Sciences of the United States of America
Despite the impressive performance of biological and artificial networks, an intuitive understanding of how their local learning dynamics contribute to network-level task solutions remains a challenge to this date. Efforts to bring learning to a more...

Logic-based machine learning predicts how escitalopram attenuates cardiomyocyte hypertrophy.

Proceedings of the National Academy of Sciences of the United States of America
Cardiomyocyte hypertrophy is a key clinical predictor of heart failure. High-throughput and AI-driven screens have the potential to identify drugs and downstream pathways that modulate cardiomyocyte hypertrophy. Here, we developed LogiRx, a logic-bas...

A spectral machine learning approach to derive central aortic pressure waveforms from a brachial cuff.

Proceedings of the National Academy of Sciences of the United States of America
Analyzing cardiac pulse waveforms offers valuable insights into heart health and cardiovascular disease risk, although obtaining the more informative measurements from the central aorta remains challenging due to their invasive nature and limited non...

Deep learning to quantify the pace of brain aging in relation to neurocognitive changes.

Proceedings of the National Academy of Sciences of the United States of America
Brain age (BA), distinct from chronological age (CA), can be estimated from MRIs to evaluate neuroanatomic aging in cognitively normal (CN) individuals. BA, however, is a cross-sectional measure that summarizes cumulative neuroanatomic aging since bi...