A Network View of Human Ingestion and Health: Instrumental Artificial Intelligence

Humans are confronted with an increasingly complex array of ingestion substances and dietary choices that influence health and well being. However, even with strong medical evidence that clearly links ingestion strategies and heath consequences, the general public struggles to make healthoptimizing ingestion decisions. Based on our literature review, we delineate a typology of barriers to formulating health-optimizing ingestion strategies. We propose that the introduction of artificial intelligence (AI) as “decision management” (AI-DM) technology into the ingestion decision-making network would increase the likelihood of more predictable and optimized health outcomes. Also, we delineate the key informational constituencies needed to enable a comprehensive and effective AI-DM system. While no author has yet proposed AI in the particular context discussed in this paper, the theoretical and empirical literature suggests that this might be possible. We conclude by discussing areas for additional research. The Ingestion Challenge Humans are confronted with an increasingly complex array of ingestion substances (e.g., natural foods, processed foods, pharmaceuticals, recreational drugs, and toxins) and dietary choices that influence health and well being. While more scientific information about the health implications of particular substances intended for human ingestion has become available in recent years, a typical consumer’s potential to carefully analyze this disclosed information, understand possible interactions between substances, and reach individualized health-optimizing decisions may be limited by a variety of factors. For example, an individual’s cognitive capacities (as with children and Alzheimer patients) and the complexity of the decision environment are critical moderating and mediating variables (Gonzalez, Thomas, and Vanyukov 2005). Copyright © 2011, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Information for many substances may not be complete or “perfect” and may contain perceived contradictions that contribute to sub-optimized decisions. Also, a particular person’s health situation (e.g., genetic, illnesses, and health risks) and diverse contextual factors (e.g., climate and socio-economic situation) add complexity and make the decision environment dynamic. This interdisciplinary paper reviews medical, health, innovation management, legal, and artificial intelligence (AI) literature with the overarching aim of answering the following questions: Would artificial intelligence as an intervention help to optimize ingestion decisions? Could artificial intelligence be instrumental in assisting humans with complex ingestion decisions? Given our current understanding of ingestion substances and their interactions, which AI methods might deliver the most reliable assistance? Our research-framing paper describes human ingestion challenges and uses Latour’s (1991) actor network theory (ANT) lens to explore potential solutions derived from the AI literature. Substances and Interactions While many medical and health scholars have identified the various challenges associated with human ingestion, few have offered solutions. Amft and Tröster (2008) have identified dietary imbalance as a factor contributing to chronic diseases. Petot, Marling, and Sterling (1998) describe the challenges associated with optimal menu planning. Brand-Miller et al. (2009) demonstrate that dietary strategies are critical for managing health and preventing diseases. Pharmaceutical firms and researchers give scientific evidence of various drug-drug, drug-food, and drug-herb interactions and suggest drug intake coordination approaches (Abbott 2011; Bailie et al. 2004; Kuhn 2007; PDR 2008; Zucchero, Hogan, and Sommer 2004). Furthermore, interactions are often classified as either pharmacodynamic, interactions among concomitant drugs, or pharmacokinetic, interactions arising from 22 Artificial Intelligence and Smarter Living — The Conquest of Complexity: Papers from the 2011 AAAI Workshop (WS-11-07)