Search for: All records

Abstract Our food system is complex, multifaceted, and in need of an upgrade. Population growth, climate change, and socioeconomic disparities are some of the challenges that create a systemic threat to its sustainability and capacity to address the needs of an evolving planet. The mission of the AI Institute of Next Generation Food Systems (AIFS) is to leverage the latest advances in AI to help create a more sustainable, efficient, nutritious, safe, and resilient food system. Instead of using AI in isolation, AIFS views it as the connective tissue that can bring together interconnected solutions from farm to fork. From guiding molecular breeding and building autonomous robots for precision agriculture, to predicting pathogen outbreaks and recommending personalized diets, AIFS projects aspire to pave the way for infrastructure and systems that empower practitioners to build the food system of the next generation. Workforce education, outreach, and ethical considerations related to the emergence of AI solutions in this sector are an integral part of AIFS with several collaborative activities aiming to foster an open dialogue and bringing closer students, trainees, teachers, producers, farmers, workers, policy makers, and other professionals. 

The Automated Self-Administered 24-Hour Dietary Assessment Tool (ASA24) is a free dietary recall system that outputs fewer nutrients than the Nutrition Data System for Research (NDSR). NDSR uses the Nutrition Coordinating Center (NCC) Food and Nutrient Database, both of which require a license. Manual lookup of ASA24 foods into NDSR is time-consuming but currently the only way to acquire NCC-exclusive nutrients. Using lactose as an example, we evaluated machine learning and database matching methods to estimate this NCC-exclusive nutrient from ASA24 reports. ASA24-reported foods were manually looked up into NDSR to obtain lactose estimates and split into training (n = 378) and test (n = 189) datasets. Nine machine learning models were developed to predict lactose from the nutrients common between ASA24 and the NCC database. Database matching algorithms were developed to match NCC foods to an ASA24 food using only nutrients (“Nutrient-Only”) or the nutrient and food descriptions (“Nutrient + Text”). For both methods, the lactose values were compared to the manual curation. Among machine learning models, the XGB-Regressor model performed best on held-out test data (R2 = 0.33). For the database matching method, Nutrient + Text matching yielded the best lactose estimates (R2 = 0.76), a vast improvement over the status quo of no estimate. These results suggest that computational methods can successfully estimate an NCC-exclusive nutrient for foods reported in ASA24.