BACKGROUND: Most artificial intelligence tools used to estimate nutritional content rely on image input. However, whether large language models (LLMs) can accurately predict nutritional values based solely on text descriptions of foods consumed remains unknown. If effective, this approach could enable simpler dietary monitoring without the need for photographs. METHODS: We used 24-hour dietary recalls from adolescents aged 12-19 years in the National Health and Nutrition Examination Survey (NHANES). An open-source quantized LLM was prompted using a 10-shot, chain-of-thought approach to estimate energy and five macronutrients based solely on text strings listing foods and their quantities. We then applied parameter-efficient fine-tuning (PEFT) to evaluate whether predictive accuracy improved. NHANES-calculated values served as the ground truth for energy, proteins, carbohydrates, total sugar, dietary fiber and total fat. RESULTS: In a pooled dataset of 11,281 adolescents (49.9% male, mean age 15.4 years), the vanilla LLM yielded poor predictions. The mean absolute error (MAE) was 652.08 for energy and the Lin's CCC <0.46 across endpoints. In contrast, the fine-tuned model performed substantially better, with energy MAEs ranging from 171.34 to 190.90 across subsets, and Lin's CCC exceeding 0.89 for all outcomes. CONCLUSIONS: When prompted using a chain-of-thought approach and fine-tuned with PEFT, open-source LLMs exposed solely to text input can accurately predict energy and macronutrient values from 24-hour dietary recalls. This approach holds promise for low-burden, text-based dietary monitoring tools.

TechWatch editor Emily McDaid meets with Sensum's Ben Bland to discuss how the start-up is translating human emotion into quantifiable data for the auto industry. Sensum is on the bleeding edge of empathic technology – technology that aims to understand human emotions. The company uses artificial intelligence (AI) to make sense of human-centric data. "We don't make a wearable," said Ben Bland, CTO of Sensum. "We provide physiological and emotional data insights that can be captured with a wide array of sensor technology. "We can use data from heart-rate monitors, technology that monitors palms, facial expression recognition and voice analysis." "The skin on your hands has an evolutionary hangover.

In the year leading up to Sandra Bland's arrest, she uploaded a series of videos to YouTube, recorded on her cell phone, called "Sandy Speaks." In the first of the series, made on Jan. 15, 2015, Bland expressed her wish to educate black youth about how to interact with law enforcement, believing that children were the key to a more peaceful, unprejudiced future. "With the police brutality, all the things that have been going on in the news," Bland says, curlers in her hair, "a lot of people have been making noise and expressing their opinions about how they feel. Somewhere along the way we've forgotten about the kids. I want to get some dialogue started with them ... Why not educate them on interacting with the people who are really important to our survival?"