From Research Gaps To Innovation Opportunities. Nlumn Nsights 2024 Vol 2. Issue 2.

Thought Leadership


Team Nlumn

We're highlighting a recent commentary in Nature Metabolism that calls out gaps in the personalized nutrition evidence base. For personalized nutrition to succeed, the health and functional outcomes that result should be better than general dietary advice. This means we need to continue evaluating individuals' biology and behavior. Read on for our thoughts on these research gaps and how they can be opportunities for your personalized nutrition business.

Big(ger) data is not always better data.

In the commentary, Dr. Guess highlights that big data may help us understand individual responses to diet and create more effective dietary interventions for individuals. You might also be excited about the learnings the data may hold, but consider your approach balanced against complexity, cost, and potential scrutiny. Dr. Guess points out that more established clinical markers may be useful in delivering advice.

Biology alone won't change behavior.

Dr. Guess correctly notes that some studies on algorithm-derived dietary advice based on biological markers don’t use the same behavior input between control and intervention groups. This is a drawback from a scientific standpoint. However, individual metabolic or genetic information alone probably won’t drive compliance. Personalizing information and behavioral inputs is what drives engagement and utilization of recommendations. The behavior inputs should align with the individual’s goals. Dr. Guess notes, “Personalizing recommendations by using algorithms driven by standard clinical markers and an individual’s behavior can be an effective way to provide recommendations at scale.

Start with the end in mind.

The commentary calls for controlled trials to truly evaluate whether better outcomes are achieved through personalized nutrition interventions. Investing in a study to support your personalized nutrition business involves several considerations.

The design selection should be based on what you are trying to evaluate. For example, suppose you are trying to demonstrate the additional value of a specific marker or measure over a conventional approach. In that case, you want to control for as many factors as possible (biology and behavior) outside of that specific addition (an efficacy trial). If you are trying to demonstrate the value of your overall offering, it is important that the integrated offering is treated as the test, and the relevant approach could be a free-living control group or baseline (an effectiveness trial).

Talk to us

Ready to get started? Have questions? Contact us for a free consultation.

Contact Us

Latest News

Latest News