Toward expert-level medical question answering with large language models.

Large language models (LLMs) have shown promise in medical question answering, with Med-PaLM being the first to exceed a 'passing' score in United States Medical Licensing Examination style questions. However, challenges remain in long-form medical question answering and handling real-world workflows. Here, we present Med-PaLM 2, which bridges these gaps with a combination of base LLM improvements, medical domain fine-tuning and new strategies for improving reasoning and grounding through ensemble refinement and chain of retrieval.

Neoantigen DNA vaccines are safe, feasible, and induce neoantigen-specific immune responses in triple-negative breast cancer patients.

Background: Neoantigen vaccines can induce or enhance highly specific antitumor immune responses with minimal risk of autoimmunity. We have developed a neoantigen DNA vaccine platform capable of efficiently presenting both HLA class I and II epitopes and performed a phase 1 clinical trial in triple-negative breast cancer patients with persistent disease on surgical pathology following neoadjuvant chemotherapy, a patient population at high risk of disease recurrence.

Methods: Expressed somatic mutations were identified by tumor/normal exome sequencing and tumor RNA sequencing.

Proteins in scalp hair of preschool children.

Background: (1)Early childhood experiences have long-lasting effects on subsequent mental and physical health, education, and employment. Measurement of these effects relies on insensitive behavioral signs, subjective assessments by adult observers, neuroimaging or neurophysiological studies, or retrospective epidemiologic outcomes. Despite intensive search, the underlying mechanisms for these long-term changes in development and health status remain unknown.

Collaboration between clinicians and vision-language models in radiology report generation.

Automated radiology report generation has the potential to improve patient care and reduce the workload of radiologists. However, the path toward real-world adoption has been stymied by the challenge of evaluating the clinical quality of artificial intelligence (AI)-generated reports. We build a state-of-the-art report generation system for chest radiographs, called Flamingo-CXR, and perform an expert evaluation of AI-generated reports by engaging a panel of board-certified radiologists.

A toolbox for surfacing health equity harms and biases in large language models.

Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. We present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and conduct a large-scale empirical case study with the Med-PaLM 2 LLM.