About this Research Topic
The advent of Artificial Intelligence (AI) generated content (AIGC) has revolutionized society as it enabled the quasi-instantaneous production of multi-modal content about virtually any topic with quality standards matching that of human generated content. Trends indicate that AIGC will not only pervade but become increasingly more sophisticated and accurate.
The ideas behind AIGC can be applied to answer sleep-relevant research questions ranging from the automated ingestion of vast amounts of sleep literature to the synthesis of polysomnography (PSG)-like waveforms. By some accounts, the field of sleep is a relatively young one (indeed, REM sleep was only discovered in the 1950's) and is ideally poised for disruption. AI has already disrupted sleep medicine as it has successfully solved tasks such as automated PSG-based sleep staging and event annotation with accuracies that are indistinguishable from that of expert sleep technicians. AI-algorithms have also demonstrated their ability to detect sleep states using signals that are much more convenient to acquire compared to PSG. Diagnosis of sleep disorders that require in-lab PSG studies may be made simpler using AI methods.
The enthusiastic and welcomed application of AI to sleep medicine makes AIGC ideally suited to bring innovation to this field and pioneer applications that can be extended to other areas of sleep medicine.
The main goal of this Research Topic is to present for the first time a collection of articles that report the application of AIGC methods to precision sleep medicine. This Research Topic should ideally be established as a pioneering repository of applications that will be referred to in future communications.
- Large language models: encoding, literature summaries, fine-tuning
- Transformer Architectures
- PSG-waveform generation
- Join embedding of text information and medical records in sleep medicine
- Sleep staging generation, synthesis
Conflicts of interest: Dr. Gary N Garcia-Molina is an employee of Sleep Number Labs, CA.
Dr. Ao Li does not have conflicts of interest to declare.
The ideas behind AIGC can be applied to answer sleep-relevant research questions ranging from the automated ingestion of vast amounts of sleep literature to the synthesis of polysomnography (PSG)-like waveforms. By some accounts, the field of sleep is a relatively young one (indeed, REM sleep was only discovered in the 1950's) and is ideally poised for disruption. AI has already disrupted sleep medicine as it has successfully solved tasks such as automated PSG-based sleep staging and event annotation with accuracies that are indistinguishable from that of expert sleep technicians. AI-algorithms have also demonstrated their ability to detect sleep states using signals that are much more convenient to acquire compared to PSG. Diagnosis of sleep disorders that require in-lab PSG studies may be made simpler using AI methods.
The enthusiastic and welcomed application of AI to sleep medicine makes AIGC ideally suited to bring innovation to this field and pioneer applications that can be extended to other areas of sleep medicine.
The main goal of this Research Topic is to present for the first time a collection of articles that report the application of AIGC methods to precision sleep medicine. This Research Topic should ideally be established as a pioneering repository of applications that will be referred to in future communications.
- Large language models: encoding, literature summaries, fine-tuning
- Transformer Architectures
- PSG-waveform generation
- Join embedding of text information and medical records in sleep medicine
- Sleep staging generation, synthesis
Conflicts of interest: Dr. Gary N Garcia-Molina is an employee of Sleep Number Labs, CA.
Dr. Ao Li does not have conflicts of interest to declare.
Keywords: Generative AI, LLM, Precision Sleep Medicine, Transformer, data synthesis, PSG waveform reconstruction
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
