Monday, October 12, 2026

Ultra-Processed Foods and Mental Health: The Emerging Evidence

Emerging evidence links ultra-processed food consumption with adverse mental-health outcomes, highlighting the importance of addressing food environments and dietary quality as part of a broader public-health approach to mental well-being 

Mental health is increasingly recognised as a major component of population health, yet its relationship with food environments remains comparatively underexplored. In 2023, an estimated 1.2 billion people were living with a mental disorder, with anxiety and depressive disorders being the most common conditions. The latest World Health Organization (WHO) estimates indicate that mental disorders accounted for 157 million disability-adjusted life years (DALYs) in 2021, equivalent to 5.2 percent of global DALYs; depressive and anxiety disorders alone contributed 56.7 million and 42.8 million, respectively. At the same time, dietary exposure to ultra-processed foods (UPFs) has expanded substantially across many populations. This convergence is drawing growing scientific attention to the relationship between highly processed diets and mental health. 

UPFs are products formulated largely from food-derived substances and additives, often designed for convenience, palatability, affordability and extended shelf life.

UPFs are products formulated largely from food-derived substances and additives, often designed for convenience, palatability, affordability and extended shelf life. They include packaged snacks, confectionery, sugar-sweetened beverages, instant noodles, many ready-to-eat meals and processed meat products. Under the NOVA classification, their defining characteristic is the nature and purpose of industrial processing rather than simply their nutrient composition. This distinction matters because UPFs constitute a heterogeneous category, and the nutritional and health implications of individual products can differ greatly.

A Changing Global Food Environment

The expansion of UPFs is increasingly evident across different regions and stages of nutrition transition. A systematic review of 99 studies involving 1.38 million participants found considerable international variation in UPF consumption. The United States and the United Kingdom recorded some of the highest dietary contributions, generally exceeding 50 percent of total energy intake in several population groups, while estimates in countries such as Italy were much lower. A broader synthesis of global sales and consumption trends has also documented a substantial expansion in the volume and variety of UPFs available worldwide, although the pace and extent of this transition vary considerably across countries and regions. The evidence base remains geographically uneven. A 2024 systematic review restricted to nationally representative samples identified 55 studies covering 32 countries, but also found wide variation in UPF intake by country, urbanisation, income and food insecurity, underscoring the need for more representative evidence across diverse food-system contexts.

This gap is increasingly important as packaged and convenience foods become more accessible in countries undergoing rapid urbanisation and dietary transition. The changing food environment is not simply altering the nutrient composition of diets; it is also changing how food is purchased, prepared and consumed. Time constraints, food prices, marketing, convenience and increasing availability of packaged products can collectively shift diets away from traditional dietary patterns towards greater reliance on commercially formulated foods.

Emerging Evidence on Mental Health

The evidence linking UPFs with mental health is no longer limited to small observational studies. A 2022 systematic review and meta-analysis covering 17 observational studies and approximately 385,500 participants found that greater UPF consumption was associated with higher odds of depressive symptoms, anxiety symptoms and common mental-disorder symptoms. A dose-response meta-analysis involving 26 studies and 260,385 participants from 12 countries also reported an association between greater UPF consumption and depression, although the evidence for anxiety was less consistent.

The evidence linking UPFs with mental health is no longer limited to small observational studies.

In a population-based cohort of 183,474 participants followed for an average of 13.1 years, 5,453 participants developed depression and 6,763 developed anxiety. Those in the highest quartile of UPF consumption had a higher risk of incident depression than those in the lowest quartile, with hazard ratios varying according to how UPF exposure was measured. A 2024 analysis of the NutriNet-Brasil cohort, involving 15,960 adults, similarly found that each 10-percentage-point increase in dietary energy from UPFs was associated with a 10% higher hazard of incident depressive symptoms.

The 2024 umbrella review of 45 pooled analyses involving almost 9.9 million participants found that greater UPF exposure was associated with prevalent anxiety, common mental disorders, incident depressive outcomes and adverse sleep outcomes. The authors classified the evidence for anxiety and common mental disorders as convincing according to their predefined evidence framework, and the evidence for depressive outcomes as highly suggestive. Several mechanisms may plausibly connect high UPF consumption with mental health. UPF-heavy diets can contain more refined carbohydrates, added sugars, saturated fats and sodium, while providing less fibre and dietary diversity. Such dietary patterns may contribute to metabolic dysfunction and chronic low-grade inflammation, pathways that have been implicated in depression and other mental disorders.

Implications for Food and Health policy

The emerging evidence expands the UPF debate beyond obesity and metabolic disease. Food environments are increasingly recognised as important determinants of dietary behaviour and health, with food availability, affordability, accessibility and marketing shaping dietary choices. This does not imply that all processed foods carry equivalent risks, nor does the current evidence justify attributing mental disorders to UPF consumption alone. It does, however, strengthen the case for policies that improve access to healthy, nutritious foods while addressing food environments and marketing practices that promote foods high in free sugars, saturated fats and sodium.

Food environments are increasingly recognised as important determinants of dietary behaviour and health.

Large prospective datasets from Europe and other high-income settings have generated much of the current evidence, while comparable longitudinal evidence remains scarce across South Asia, Africa and parts of Latin America. This is particularly significant for countries experiencing rapid nutrition transition, where traditional dietary patterns coexist with expanding markets for packaged foods. A study of 1,030 adolescents aged 12-16 years from private and government schools in Delhi found that UPFs contributed an average of 16.2 percent of total energy intake, demonstrating a notable level of exposure among Indian adolescents.

Recent evidence among adolescents has revealed UPF consumption alongside psychological and sleep outcomes. For India, stronger longitudinal evidence is needed to examine the relationship between dietary processing, food affordability, dietary quality and mental-health outcomes across different age and socioeconomic groups. Such research would help determine whether associations observed predominantly in European and other high-income populations are replicated within India's distinct nutritional, cultural and food-system context.

For India, stronger longitudinal evidence is needed to examine the relationship between dietary processing, food affordability, dietary quality and mental-health outcomes across different age and socioeconomic groups.

The emerging UPF-mental health literature therefore adds an important dimension to the global food-policy debate. The evidence is sufficiently consistent to warrant greater scientific and policy attention, but the causal pathways remain incompletely understood. Moving beyond an obesity-centred understanding of UPFs towards a broader ‘food-health-mental health framework’ can help integrate dietary quality, food environments and mental well-being into public-health policy.

 

This is only for your information, kindly take the advice of your doctor for food, medicines, exercises and so on.   

 

Labels: , , , , , ,

AI helps neurologists distinguish epilepsy from functional seizures

 Similar symptoms can complicate seizure diagnosis, prompting researchers to test whether AI can identify useful clues in routine medical notes before confirmatory monitoring.

   Study: Early epilepsy detection from electronic health records with large language models. 

 In a recent study published in the journal npj Digital Medicine, researchers describe the development and validation of “EpiScreen”, a novel artificial intelligence (AI) system designed to distinguish epilepsy from psychogenic non-epileptic seizures (PNES) using clinical notes from routinely documented electronic health records (EHRs).

The retrospective, two-institution study used 13,633 patient records to assess whether fine-tuned large language models (LLMs) could accurately differentiate epilepsy from PNES.

EpiScreen outperformed the comparison models, achieving an area under the receiver operating characteristic curve (AUC) of up to 0.992 in within-institution testing and 0.980 in cross-institutional testing. AUC measures a model’s ability to distinguish between the two conditions across different classification thresholds.

In a retrospective case-review assessment, EpiScreen improved clinicians’ classification accuracy, supporting its potential in future epilepsy screening applications.

Background

Epilepsy is clinically defined as a chronic neurological disorder characterized by recurring, unprovoked seizures. Seizures arise from sudden, abnormal electrical discharges in the brain, with public health records estimating that approximately 50 million individuals live with the condition globally.

Epilepsy’s diagnosis can be complicated by PNES, also termed functional or dissociative seizures. These involve paroxysmal events (sudden, temporary seizure-like episodes) that resemble epileptic seizures but are not caused by epileptic electrical activity.

Since epilepsy and PNES have different underlying mechanisms and management needs, timely differentiation and accurate diagnoses are critical for appropriate care. Misdiagnosis remains common, with prior studies indicating that 20%–30% of patients

Prolonged inpatient video-electroencephalography (vEEG) is the diagnostic gold standard for distinguishing epileptic seizures from PNES. The method records synchronized brain waves alongside behavioral data. But vEEG is costly and time-consuming, often costing over US$15,000 per admission in the United States, with reported wait times of 8 to 12 weeks that vary across healthcare systems.

Beyond direct expenses, diagnostic delays can lead to unnecessary treatment and delay appropriate care. Researchers are investigating whether routinely collected clinical notes can support earlier screening for both conditions.

Routine clinical notes contain extensive diagnostic signals, but seizure semiology (the symptoms, signs, and sequence of a seizure-like event) overlaps considerably across disorders. Earlier narrative-based approaches have shown limited diagnostic performance.

About the study

The researchers adapted existing LLMs to address this diagnostic bottleneck and differentiate between epilepsy and PNES using only unstructured clinical narratives.

The system was named “EpiScreen” and was trained and evaluated using a collated dataset comprising 3,451 records from the Beth Israel Deaconess Medical Center’s Medical Information Mart for Intensive Care IV (MIMIC-IV) database and 10,182 records from the University of Minnesota (UMN) Clinical Data Repository. Labels reflected clinicians’ final documented diagnoses, and we processed notes to approximate information available before diagnosis. Patients with coexisting epilepsy and PNES were excluded.

EpiScreen was developed by instruction fine-tuning open-source LLMs, including Qwen-2.5-32B, DeepSeek-R1-32B, Llama-3.3-70B, and Med42-70B, using Quantized Low-Rank Adaptation (QLoRA). This method reduces the memory and training demands of adapting large models.

To explain the model, the study used sentence-level Integrated Gradients (IG), a mathematical technique that computes attribution scores to highlight the sentences most influential in the algorithm’s decisions across 11 predefined clinical feature categories.

Finally, the study conducted a retrospective clinician-AI assessment in which four medical teams (six neurology residents and two senior attending physicians) evaluated 300 MIMIC-IV test cases. Each pair reached decisions by consensus.

Study findings

EpiScreen consistently outperformed conventional supervised baselines, including ClinicalBERT, achieving AUCs of 0.891 on MIMIC-IV and 0.976 on UMN for its Med42-based variant. Qwen- and DeepSeek-based variants reached 0.992 on UMN.

Cross-institutional evaluations also outperformed the comparison models, with the best AUCs reaching 0.875 on MIMIC-IV and 0.980 on UMN. These evaluations tested models on records from institutions that did not supply their training data.

In the clinician assessment, standalone EpiScreen achieved 81.0% diagnostic accuracy, compared with unaided senior attendings (81.7%) and unaided neurology residents (76.3%–79.3%). These differences were not statistically significant. Providing clinicians with AI predictions and sentence attributions improved resident-group accuracy to 87.7%–89.0% and attending accuracy to 89.3%. The largest improvement among the reported group accuracies was about 12.7 percentage points.

Finally, error-pattern analyses showed that AI assistance reduced resident Group A’s false negatives (missed epilepsy cases) from 36 to 14, while the attending pair reduced false positives from 37 to 19.

Not all diagnostic labels were vEEG-confirmed, but sensitivity analyses in confirmed cases supported the findings. Documentation bias remains possible, and other seizure mimics, including syncope and sleep disorders, were not evaluated.

Conclusions

The findings support further evaluation of EpiScreen as a neurological decision-support tool. The authors suggest using it during or after neurology referral, before confirmatory vEEG, to support earlier assessment and help clinicians prioritize urgent monitoring. The authors propose reduced diagnostic delays, costs, and unnecessary antiseizure medication exposure, but these remain benefits rather than measured outcomes.

Future investigations must prioritize prospective, real-time trials to confirm how this collaborative AI system performs in real-world clinical settings using minimally curated notes. EpiScreen is intended to support clinical judgment alongside definitive testing.

 

This is only for your information, kindly take the advice of your doctor for food, medicines, exercises and so on.   

 

Labels: ,