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.
Ontology highlight
ABSTRACT: Background
Self-monitoring food intake is a cornerstone of national recommendations for health, but existing apps for this purpose are burdensome for users and researchers, which limits use.Objective
We developed and pilot tested a new app (COCO Nutritionist) that combines speech understanding technology with technologies for mapping foods to appropriate food composition codes in national databases, for lower-burden and automated nutritional analysis of self-reported dietary intake.Methods
COCO was compared with the multiple-pass, interviewer-administered 24-hour recall method for assessment of energy intake. COCO was used for 5 consecutive days, and 24-hour dietary recalls were obtained for two of the days. Participants were 35 women and men with a mean age of 28 (range 20-58) years and mean BMI of 24 (range 17-48) kg/m2.Results
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), and no trend in energy intake obtained with COCO over the entire 5-day study period (P=.19).Conclusions
This first demonstration of a dietary assessment method using natural spoken language to map reported foods to food composition codes demonstrates a promising new approach to automate assessments of dietary intake.
SUBMITTER: Taylor S
PROVIDER: S-EPMC8691405 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Studies of patients with acquired cognitive deficits following brain damage and studies using contemporary neuroimaging techniques form two distinct streams of research on the neural basis of cognition. In this study, we combine high-quality structural neuroimaging analysis techniques and extensive behavioural assessment of patients with persistent acquired language deficits to study the neural basis of language. Our results reveal two major divisions within the language system-meaning versus form and recognition versus production-and their instantiation in the brain. Phonological form deficits are associated with lesions in peri-Sylvian regions, whereas semantic production and recognition deficits are associated with damage to the left anterior temporal lobe and white matter connectivity with frontal cortex, respectively. These findings provide a novel synthesis of traditional and contemporary views of the cognitive and neural architecture of language processing, emphasizing dual routes for speech processing and convergence of white matter tracts for semantic control and/or integration.
| S-EPMC4400840 | biostudies-literature
Project description:Aphasia is an acquired disorder caused by damage, most commonly due to stroke, to brain regions involved in speech and language. While language impairment is the defining symptom of aphasia, the co-occurrence of non-language cognitive deficits and their importance in predicting rehabilitation and recovery outcomes is well documented. However, people with aphasia (PWA) are rarely tested on higher-order cognitive functions, making it difficult for studies to associate these functions with a consistent lesion correlate. Broca's area is a particular brain region of interest that has long been implicated in speech and language production. Contrary to classic models of speech and language, cumulative evidence shows that Broca's area and surrounding regions in the left inferior frontal cortex (LIFC) are involved in, but not specific to, speech production. In this study we aimed to explore the brain-behaviour relationships between tests of cognitive skill and language abilities in thirty-six adults with long-term speech production deficits caused by post-stroke aphasia. Our findings suggest that non-linguistic cognitive functions, namely executive functions and verbal working memory, explain more of the behavioural variance in PWA than classical language models imply. Additionally, lesions to the LIFC, including Broca's area, were associated with non-linguistic executive (dys)function, suggesting that lesions to this area are associated with non-language-specific higher-order cognitive deficits in aphasia. Whether executive (dys)function - and its neural correlate in Broca's area - contributes directly to PWA's language production deficits or simply co-occurs with it, adding to communication difficulties, remains unclear. These findings support contemporary models of speech production that place language processing within the context of domain-general perception, action and conceptual knowledge. An understanding of the covariance between language and non-language deficits and their underlying neural correlates will inform better targeted aphasia treatment and outcomes.
| S-EPMC10275719 | biostudies-literature
Project description:Reading involves transforming arbitrary visual symbols into sounds and meanings. This study interrogated the neural representations in ventral occipitotemporal cortex (vOT) that support this transformation process. Twenty-four adults learned to read 2 sets of 24 novel words that shared phonemes and semantic categories but were written in different artificial orthographies. Following 2 wk of training, participants read the trained words while neural activity was measured with functional MRI. Representational similarity analysis on item pairs from the same orthography revealed that right vOT and posterior regions of left vOT were sensitive to basic visual similarity. Left vOT encoded letter identity and representations became more invariant to position along a posterior-to-anterior hierarchy. Item pairs that shared sounds or meanings, but were written in different orthographies with no letters in common, evoked similar neural patterns in anterior left vOT. These results reveal a hierarchical, posterior-to-anterior gradient in vOT, in which representations of letters become increasingly invariant to position and are transformed to convey spoken language information.
| S-EPMC6731646 | biostudies-literature
Project description:Aim of Study: The use of weighed food diaries in nutritional studies provides a powerful method to quantify food and nutrient intakes. Yet, mapping these records onto food composition tables (FCTs) is a challenging, time-consuming and error-prone process. Experts make this effort manually and no automation has been previously proposed. Our study aimed to assess automated approaches to map food items onto FCTs. Methods: We used food diaries (~170,000 records pertaining to 4,200 unique food items) from the DiOGenes randomized clinical trial. We attempted to map these items onto six FCTs available from the EuroFIR resource. Two approaches were tested: the first was based solely on food name similarity (fuzzy matching). The second used a machine learning approach (C5.0 classifier) combining both fuzzy matching and food energy. We tested mapping food items using their original names and also an English-translation. Top matching pairs were reviewed manually to derive performance metrics: precision (the percentage of correctly mapped items) and recall (percentage of mapped items). Results: The simpler approach: fuzzy matching, provided very good performance. Under a relaxed threshold (score > 50%), this approach enabled to remap 99.49% of the items with a precision of 88.75%. With a slightly more stringent threshold (score > 63%), the precision could be significantly improved to 96.81% while keeping a recall rate > 95% (i.e., only 5% of the queried items would not be mapped). The machine learning approach did not lead to any improvements compared to the fuzzy matching. However, it could increase substantially the recall rate for food items without any clear equivalent in the FCTs (+7 and +20% when mapping items using their original or English-translated names). Our approaches have been implemented as R packages and are freely available from GitHub. Conclusion: This study is the first to provide automated approaches for large-scale food item mapping onto FCTs. We demonstrate that both high precision and recall can be achieved. Our solutions can be used with any FCT and do not require any programming background. These methodologies and findings are useful to any small or large nutritional study (observational as well as interventional).
| S-EPMC5954085 | biostudies-literature
Project description:The role of taste perception, its relationship with oral microbiota composition, and their putative link with eating habits and food intake were the focus of the present study. A sample of 59 reportedly healthy adults (27 male, 32 female; age: 23.3 ± 2.6 years) were recruited for the study and taste thresholds for basic tastes, food intake, and oral microbiota composition were evaluated. Differences in taste perception were associated with different habitual food consumption (i.e., frequency) and actual intake. Subjects who were orally hyposensitive to salty taste reported consuming more bakery and salty baked products, saturated-fat-rich products, and soft drinks than hypersensitive subjects. Subjects hyposensitive to sweet taste reported consuming more frequently sweets and desserts than the hypersensitive group. Moreover, subjects hypersensitive to bitter taste showed higher total energy and carbohydrate intakes compared to those who perceived the solution as less bitter. Some bacterial taxa on tongue dorsum were associated with gustatory functions and with vegetable-rich (e.g., Prevotella) or protein/fat-rich diets (e.g., Clostridia). Future studies will be pivotal to confirm the hypothesis and the potential exploitation of oral microbiome as biomarker of long-term consumption of healthy or unhealthy diets.
| S-EPMC6567015 | biostudies-literature
Project description:The quality and quantity of food intake affect body weight, but little is known about the genetics of such human dietary intake patterns in relation to the genetics of BMI. We aimed to estimate the heritability of dietary intake patterns and genetic correlation with BMI in participants of the Erasmus Rucphen Family study. The study included 1,690 individuals (42 % men; age range, 19-92), of whom 41.4 % were overweight and 15.9 % were obese. Self-report questionnaires were used to assess the number of days (0-7) on which participants consumed vegetables, fruit, fruit juice, fish, unhealthy snacks, fastfood, and soft drinks. Principal component analysis was applied to examine the correlations between the questionnaire items and to generate dietary intake pattern scores. Heritability and the shared genetic and shared non-genetic (environmental) correlations were estimated using the family structure of the cohort. Principal component analysis suggested that the questionnaire items could be grouped in a healthy and unhealthy dietary intake pattern, explaining 22 and 18 % of the phenotypic variance, respectively. The dietary intake patterns had a heritability of 0.32 for the healthy and 0.27 for the unhealthy pattern. Genetic correlations between the dietary intake patterns and BMI were not significant, but we found a significant environmental correlation between the unhealthy dietary intake pattern and BMI. Specific dietary intake patterns are associated with the risk of obesity and are heritable traits. The genetic factors that determine specific dietary intake patterns do not significantly overlap with the genetic factors that determine BMI.
| S-EPMC3898132 | biostudies-literature
Project description:Most studies of food-related parenting practices, parental meal involvement, and adolescent dietary intake have focused on maternal influences; studies of paternal influences, particularly among marginalized groups, are lacking. This study examined lower-income, Latino fathers' food parenting practices and involvement in planning meals, buying/preparing foods, and family meal frequency, separately and in combination, to identify relationships with adolescent food intake. Baseline data were used from Latino adolescents (10-14 years, n = 191, 49% boys) participating with their fathers in a community-based overweight/obesity prevention intervention. Fathers reported sociodemographic characteristics. Adolescents reported frequency of fathers' food parenting practices, fathers' food/meal involvement, and family meals and participated in 24 h dietary recalls. The analysis included regression models using GLM (generalized linear mixed model) and PLM (post GLM processing) procedures. Most fathers were married, employed full-time, and had annual incomes below USD 50,000. Favorable fathers' food parenting practices were associated with adolescent intake of more fruit and vegetables and fewer sugar-sweetened beverages, sweets/salty snacks, and less fast food (p < 0.05 or p < 0.01). No independent effects of family meal frequency or fathers' food/meal involvement were observed on adolescent dietary outcomes. Additional analyses showed favorable food parenting practices in combination with frequent family meals were associated with adolescents having a higher intake of fruit (p = 0.011). Latino fathers can have an important positive influence on adolescent dietary intake.
| S-EPMC8346089 | biostudies-literature
Project description:This study aimed to investigate whether there was any difference in eating pattern, abnormal eating behaviour, obesity and the number of food addiction symptoms according to food addiction presence. A total sample of 851 healthy subjects living in Ankara (n = 360 male, n = 491 female) aged 19-65 years were included in this cross-sectional survey. Data on demographic information, 24-hour dietary recalls, Yale Food Addiction Scale (YFAS), Eating Attitudes Test-26 (EAT-26), and anthropometric measurements were collected through face-to-face interviews. Overall, 11.4% of participants were identified as "food addicted" (F: 13.0%; M: 9.2%). Subjects meeting criteria for 'food addiction' had higher body mass index (35.1% were obese and 3.1% were underweight), compared to subjects without food addiction (13.1% were obese and 10.2% were underweight) (p<0.05). Abnormal eating attitudes estimated with EAT-26 were determined as 45.5% in males, 37.5% in females and 40.2% in total, among subjects with food addiction. Daily energy, protein and fat intakes were significantly higher in food addicted females, compared to non-addicted females (p<0.05). Participants with food addiction reported significantly more problems with foods, which contain high amounts of fat and sugar, compared to the participants without food addiction. Food addiction behaviour should be considered as a part of efforts towards reducing food related problems involving obesity.
| S-EPMC5909892 | biostudies-literature
Project description:There is limited research describing associations between food insecurity and dietary intake.To examine differences in dietary intake by food security status among a nationally representative sample of children and adolescents in the USA.The sample included 5136 children, ages 2-15 years, from the National Nutrition and Health Examination Survey, 2007-2010. Propensity score weighting was used to improve covariate balance between food-secure and food-insecure (marginal, low or very low food security) participants. Multivariate measurement error models were used to model usual intake of various dietary components and assess differences by food security status.Initial analyses using multivariate measurement error models determined there were no differences between food-insecure and food-secure children across several dietary components. In sensitivity analyses, children experiencing very low food security consumed fewer whole grains and more solid fats and added sugars compared with their food-secure counterparts. Some of these differences were attenuated after propensity score weighting, although intake of whole grains and added sugars remained significantly different.Food insecurity was largely not associated with dietary intake among 2-15-year-old US children, although some differences were observed comparing food-secure children to those experiencing very low food security.
| S-EPMC4675681 | biostudies-other
Project description:The Prosodic Parallelism hypothesis claims adjacent prosodic categories to prefer identical branching of internal adjacent constituents. According to Wiese and Speyer (2015), this preference implies feet contained in the same phonological phrase to display either binary or unary branching, but not different types of branching. The seemingly free schwa-zero alternations at the end of some words in German make it possible to test this hypothesis. The hypothesis was successfully tested by conducting a corpus study which used large-scale bodies of written German. As some open questions remain, and as it is unclear whether Prosodic Parallelism is valid for the spoken modality as well, the present study extends this inquiry to spoken German. As in the previous study, the results of a corpus analysis recruiting a variety of linguistic constructions are presented. The Prosodic Parallelism hypothesis can be demonstrated to be valid for spoken German as well as for written German. The paper thus contributes to the question whether prosodic preferences are similar between the spoken and written modes of a language. Some consequences of the results for the production of language are discussed.
| S-EPMC5069292 | biostudies-literature