Research

Adherence

Automated dietary assessment using natural spoken language (COCO app) yields energy and macronutrient intake estimates that are statistically equivalent to the gold-standard multiple-pass 24-hour recall method, while significantly reducing user burden.

If you want to track your diet accurately without spending hours typing into an app, try a voice-logging tool. This study shows that speaking your meals into a smart app produces results just as accurate as a professional dietitian's interview, making it a sustainable way to monitor intake for weight management.

ModerateSupportsMEDIUM confidence
There was no significant difference in energy intake between values obtained by COCO and 24-hour recall for days when both methods were used (mean 2092, SD 1044 kcal versus mean 2030, SD 687 kcal, P=.70). There were also no significant differences between the methods for percent of energy from protein, carbohydrate, and fat (P=.27-.89)...
Salima Taylor et al. · Journal of Medical Internet Research · 2021

Why this rating

Small sample size (N=34), short duration (5 days), and reliance on self-reported data (even for the comparator).

Source

Use of Natural Spoken Language With Automated Mapping of Self-reported Food Intake to Food Composition Data for Low-Burden Real-time Dietary Assessment: Method Comparison Study

Salima Taylor et al. · Journal of Medical Internet Research · 2021

DOI 10.2196/26988

cross_sectional · n=35Cited 27×
Read the paper
DOI resolved against Crossref · corpus check 2026-06-10

This is one finding among thousands. Every one is graded and traced to its source, so you can see what the evidence actually supports. Browse the research →