{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:52:52Z","timestamp":1772041972977,"version":"3.50.1"},"reference-count":68,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The detrimental consequences of stress highlight the need for precise stress detection, as this offers a window for timely intervention. However, both objective and subjective measurements suffer from validity limitations. Contactless sensing technologies using machine learning methods present a potential alternative and could be used to estimate stress from externally visible physiological changes, such as emotional facial expressions. Although previous studies were able to classify stress from emotional expressions with accuracies of up to 88.32%, most works employed a classification approach and relied on data from contexts where stress was induced. Therefore, the primary aim of the present study was to clarify whether stress can be detected from facial expressions of six basic emotions (anxiety, anger, disgust, sadness, joy, love) and relaxation using a prediction approach.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>To attain this goal, we analyzed video recordings of facial emotional expressions collected from n = 69 participants in a secondary analysis of a dataset from an interventional study. We aimed to explore associations with stress (assessed by the PSS-10 and a one-item stress measure).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Comparing two regression machine learning models [Random Forest (RF) and XGBoost], we found that facial emotional expressions were promising indicators of stress scores, with model fit being best when data from all six emotional facial expressions was used to train the model (one-item stress measure: MSE (XGB) = 2.31, MAE (XGB) = 1.32, MSE (RF) = 3.86, MAE (RF) = 1.69; PSS-10: MSE (XGB) = 25.65, MAE (XGB) = 4.16, MSE (RF) = 26.32, MAE (RF) = 4.14). XGBoost showed to be more reliable for prediction, with lower error for both training and test data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The findings provide further evidence that non-invasive video recordings can complement standard objective and subjective markers of stress.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2025.1578917","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:42:29Z","timestamp":1745991749000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Stress can be detected during emotion-evoking smartphone use: a pilot study using machine learning"],"prefix":"10.3389","volume":"7","author":[{"given":"Lydia Helene","family":"Rupp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Misha","family":"Sadeghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lena","family":"Schindler-Gmelch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie","family":"Keinert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bjoern M.","family":"Eskofier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Berking","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"key":"B1","volume-title":"Stress, Appraisal, and Coping","author":"Lazarus","year":"1984"},{"key":"B2","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.ynstr.2016.11.001","article-title":"The trier social stress test: principles and practice","volume":"6","author":"Allen","year":"2017","journal-title":"Neurobiol Stress"},{"key":"B3","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.psyneuen.2019.02.021","article-title":"Stress and inflammation \u2013 the need to address the gap in the transition between acute and chronic stress effects","volume":"105","author":"Rohleder","year":"2019","journal-title":"Psychoneuroendocrinology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"385","DOI":"10.2307\/2136404","article-title":"A global measure of perceived stress","volume":"24","author":"Cohen","year":"1983","journal-title":"J Health Soc Behav"},{"key":"B5","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1002\/ejsp.2420150303","article-title":"Methods of coping with social desirability bias: a review","volume":"15","author":"Nederhof","year":"1985","journal-title":"Eur J Soc Psychol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1086\/269326","article-title":"Measuring extreme response style","volume":"56","author":"Greenleaf","year":"1992","journal-title":"Public Opin Q"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1016\/j.psyneuen.2009.06.011","article-title":"Assessing salivary cortisol in large-scale, epidemiological research","volume":"34","author":"Adam","year":"2009","journal-title":"Psychoneuroendocrinology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.psyneuen.2008.10.026","article-title":"Salivary cortisol as a biomarker in stress research","volume":"34","author":"Hellhammer","year":"2009","journal-title":"Psychoneuroendocrinology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1016\/j.psyneuen.2015.10.010","article-title":"Assessment of the cortisol awakening response: expert consensus guidelines","volume":"63","author":"Stalder","year":"2016","journal-title":"Psychoneuroendocrinology"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3432220","article-title":"Evaluating the reproducibility of physiological stress detection models","volume":"4","author":"Mishra","year":"2020","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1159\/000119004","article-title":"The \u2018trier social stress test\u2019 \u2013 a tool for investigating psychobiological stress responses in a laboratory setting","volume":"28","author":"Kirschbaum","year":"1993","journal-title":"Neuropsychobiology"},{"key":"B12","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1186\/s40814-023-01386-z","article-title":"Evaluating the feasibility and exploring the efficacy of an emotion-based approach-avoidance modification training (eAAMT) in the context of perceived stress in an adult sample\u2014protocol of a parallel randomized controlled pilot study","volume":"9","author":"Keinert","year":"2023","journal-title":"Pilot Feasibility Stud"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e3384","DOI":"10.1002\/smi.3384","article-title":"Disgust-based approach-avoidance modification training for individuals suffering from elevated stress: a randomized controlled pilot study","volume":"40","author":"Streit","year":"2024","journal-title":"Stress Health"},{"key":"B14","doi-asserted-by":"publisher","first-page":"100187","DOI":"10.1016\/j.cpnec.2023.100187","article-title":"You look stressed: a pilot study on facial action unit activity in the context of psychosocial stress","volume":"15","author":"Blasberg","year":"2023","journal-title":"Compr Psychoneuroendocrinol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.biopsych.2006.08.016","article-title":"Facial expressions of emotion reveal neuroendocrine and cardiovascular stress responses","volume":"61","author":"Lerner","year":"2007","journal-title":"Biol Psychiatry"},{"key":"B16","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/BF02884836","article-title":"Negative emotions and acute physiological responses to stress","volume":"21","author":"Feldman","year":"1999","journal-title":"Ann Behav Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/s41811-024-00218-z","article-title":"An anger-based approach-avoidance modification training targeting dysfunctional beliefs in adults with elevated stress \u2013 results from a randomized controlled pilot study","volume":"17","author":"Keinert","year":"2024","journal-title":"J Cogn Ther"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e50324","DOI":"10.2196\/50324","article-title":"Sadness-based approach-avoidance modification training for subjective stress in adults: pilot randomized controlled trial","volume":"7","author":"Rupp","year":"2023","journal-title":"JMIR Form Res"},{"key":"B19","first-page":"256","article-title":"Facial expression recognition system for stress detection with deep learning","author":"Almeida","year":"2021"},{"key":"B20","first-page":"B172","article-title":"Optical computer recognition of facial expressions associated with stress induced by performance demands","volume":"76","author":"Dinges","year":"2005","journal-title":"Aviat Space Environ Med"},{"key":"B21","first-page":"5961","article-title":"Detecting emotional stress from facial expressions for driving safety","author":"Gao","year":"2014"},{"key":"B22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.bspc.2016.06.020","article-title":"Stress and anxiety detection using facial cues from videos","volume":"31","author":"Giannakakis","year":"2017","journal-title":"Biomed Signal Process Control"},{"key":"B23","first-page":"728","article-title":"Automatic stress detection evaluating models of facial action units","author":"Giannakakis","year":"2020"},{"key":"B24","first-page":"3711","article-title":"Extraction of facial features as indicators of stress and anxiety","author":"Pediaditis","year":"2015"},{"key":"B25","first-page":"1","article-title":"Towards independent stress detection: a dependent model using facial action units","author":"Viegas","year":"2018"},{"key":"B26","first-page":"430","article-title":"Detecting negative emotional stress based on facial expression in real time","author":"Zhang","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"5552","DOI":"10.3390\/s20195552","article-title":"Video-based stress detection through deep learning","volume":"20","author":"Zhang","year":"2020","journal-title":"Sensors"},{"key":"B28","doi-asserted-by":"publisher","first-page":"106753","DOI":"10.1016\/j.psyneuen.2023.106753","article-title":"Video-based measurement of subjective, observable and biological stress responses","volume":"160","author":"Drimalla","year":"2024","journal-title":"Psychoneuroendocrinology"},{"key":"B29","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1093\/oso\/9780195169157.003.0014","article-title":"Observer-based measurement of facial expression with the facial action coding system","volume-title":"Handbook of Emotion Elicitation and Assessment","author":"Cohn","year":"2007"},{"key":"B30","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1037\/npe0000028","article-title":"Automated facial coding: validation of basic emotions and FACS AUs in FaceReader","volume":"7","author":"Lewinski","year":"2014","journal-title":"J Neurosci Psychol Econ"},{"key":"B31","first-page":"59","article-title":"Openface 2.0: facial behavior analysis toolkit","author":"Baltrusaitis","year":"2018"},{"key":"B32","doi-asserted-by":"publisher","first-page":"277","DOI":"10.3233\/VES-1999-9405","article-title":"Surface height effects on postural control: a hypothesis for a stiffness strategy for stance","volume":"9","author":"Carpenter","year":"1999","journal-title":"J Vestib Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1037\/a0024211","article-title":"Aversive life events enhance human freezing responses","volume":"141","author":"Hagenaars","year":"2012","journal-title":"J Exp Psychol Gen"},{"key":"B34","doi-asserted-by":"publisher","first-page":"105417","DOI":"10.1016\/j.psyneuen.2021.105417","article-title":"Human defensive freezing: associations with hair cortisol and trait anxiety","volume":"133","author":"Hashemi","year":"2021","journal-title":"Psychoneuroendocrinology"},{"key":"B35","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3389\/fnbeh.2014.00237","article-title":"Individual differences in bodily freezing predict emotional biases in decision making","volume":"8","author":"Ly","year":"2014","journal-title":"Front Behav Neurosci"},{"key":"B36","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/1471-2202-8-83","article-title":"Effects of affective picture viewing on postural control","volume":"8","author":"Stins","year":"2007","journal-title":"BMC Neurosci"},{"key":"B37","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B38","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1186\/s12888-016-0875-9","article-title":"The German version of the perceived stress scale \u2013 psychometric characteristics in a representative German community sample","volume":"16","author":"Klein","year":"2016","journal-title":"BMC Psychiatry"},{"key":"B39","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1037\/0033-295X.99.3.550","article-title":"Are there basic emotions?","volume":"99","author":"Ekman","year":"1992","journal-title":"Psychol Rev"},{"key":"B40","article-title":"Facial action coding system","author":"Ekman","year":"1978"},{"key":"B41","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","article-title":"DISFA: a spontaneous facial action intensity database","volume":"4","author":"Mavadati","year":"2013","journal-title":"IEEE Trans Affect Comput"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s12652-011-0084-9","article-title":"Repeatability of facial electromyography (EMG) activity over corrugator supercilii and zygomaticus major on differentiating various emotions","volume":"3","author":"Tan","year":"2012","journal-title":"J Ambient Intell Human Comput"},{"key":"B43","first-page":"609","article-title":"Emotion and adaptation","volume-title":"Handbook of Personality: Theory and Research","author":"Smith","year":"1990"},{"key":"B44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-54017-2","volume-title":"Training Emotionaler Kompetenzen","author":"Berking","year":"2015"},{"key":"B45","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10919-008-0048-8","article-title":"Infant smiling dynamics and perceived positive emotion","volume":"32","author":"Messinger","year":"2008","journal-title":"J Nonverbal Behav"},{"key":"B46","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.psyneuen.2014.07.004","article-title":"Anger responses to psychosocial stress predict heart rate and cortisol stress responses in men but not women","volume":"49","author":"Lupis","year":"2014","journal-title":"Psychoneuroendocrinology"},{"key":"B47","doi-asserted-by":"publisher","first-page":"100166","DOI":"10.1016\/j.ynstr.2019.100166","article-title":"In the face of stress: interpreting individual differences in stress-induced facial expressions","volume":"10","author":"Mayo","year":"2019","journal-title":"Neurobiol Stress"},{"key":"B48","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1111\/j.1469-8986.1986.tb00676.x","article-title":"Guidelines for human electromyographic research","volume":"23","author":"Fridlund","year":"1986","journal-title":"Psychophysiology"},{"key":"B49","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1037\/a0030737","article-title":"Gender differences in emotion expression in children: a meta-analytic review","volume":"139","author":"Chaplin","year":"2013","journal-title":"Psychol Bull"},{"key":"B50","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/1528-3542.4.4.378","article-title":"Facial appearance, gender, and emotion expression","volume":"4","author":"Hess","year":"2004","journal-title":"Emotion"},{"key":"B51","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1037\/0021-9010.89.4.715","article-title":"Gender differences: emotional expression and feelings of personal inauthenticity","volume":"89","author":"Simpson","year":"2004","journal-title":"J Appl Psychol"},{"key":"B52","doi-asserted-by":"publisher","first-page":"e0158666","DOI":"10.1371\/journal.pone.0158666","article-title":"Gender differences in emotional response: inconsistency between experience and expressivity","volume":"11","author":"Deng","year":"2016","journal-title":"PLoS One"},{"key":"B53","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.adiac.2014.09.005","article-title":"An assessment of the psychometric properties of the perceived stress scale-10 (PSS10) with a U.S. public accounting sample","volume":"30","author":"Smith","year":"2014","journal-title":"Adv Account"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1027\/1015-5759\/a000699","article-title":"Single item measures in psychological science","volume":"38","author":"Allen","year":"2022","journal-title":"Eur J Psychol Assess"},{"key":"B55","doi-asserted-by":"publisher","first-page":"e0223905","DOI":"10.1371\/journal.pone.0223905","article-title":"Assessing the convergent validity between the automated emotion recognition software Noldus FaceReader 7 and facial action coding system scoring","volume":"14","author":"Skiendziel","year":"2019","journal-title":"PLoS One"},{"key":"B56","doi-asserted-by":"publisher","first-page":"11551","DOI":"10.1038\/s41598-018-29984-5","article-title":"Radar-based heart sound detection","volume":"8","author":"Will","year":"2018","journal-title":"Sci Rep"},{"key":"B57","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/978-3-319-51394-2_21","article-title":"From markers to interventions: the case of just-in-time stress intervention","volume-title":"Mobile Health","author":"Sarker","year":"2017"},{"key":"B58","doi-asserted-by":"crossref","DOI":"10.4108\/icst.bodynets.2014.258237","article-title":"A stress-free life: just-in-time interventions for stress via real-time forecasting and intervention adaptation","author":"Jaimes","year":"2014"},{"key":"B59","first-page":"1","article-title":"Is providing mobile interventions \u201cjust-in-time\u201d helpful? An experimental proof of concept study of just-in-time intervention for stress management","author":"Smyth","year":"2016"},{"key":"B60","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1017\/CBO9780511628191","article-title":"Gender differences in nonverbal communication of emotion","volume-title":"Gender and Emotion: Social Psychological Perspectives","author":"Fischer","year":"2000"},{"key":"B61","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/10615800701740457","article-title":"The case for positive emotions in the stress process","volume":"21","author":"Folkman","year":"2008","journal-title":"Anxiety Stress Coping"},{"key":"B62","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1177\/0956797612445312","article-title":"Grin and bear it: the influence of manipulated facial expression on the stress response","volume":"23","author":"Kraft","year":"2012","journal-title":"Psychol Sci"},{"key":"B63","first-page":"150","article-title":"Optimizing well-being: unveiling eustress and distress through machine learning","author":"Singh","year":"2024"},{"key":"B64","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1080\/15265161.2021.2013977","article-title":"A research ethics framework for the clinical translation of healthcare machine learning","volume":"22","author":"McCradden","year":"2022","journal-title":"Am J Bioeth"},{"key":"B65","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1080\/15265161.2020.1820111","article-title":"Accountability in the machine learning pipeline: the critical role of research ethics oversight open peer commentaries","volume":"20","author":"McCradden","year":"2020","journal-title":"Am J Bioethics"},{"key":"B66","first-page":"429","article-title":"Bias in machine learning software: why? How? What to do?","author":"Chakraborty","year":"2021"},{"key":"B67","doi-asserted-by":"crossref","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning.","author":"Mehrabi","year":"2022"},{"key":"B68","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1578917\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:42:32Z","timestamp":1745991752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1578917\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":68,"alternative-id":["10.3389\/fdgth.2025.1578917"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1578917","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,30]]},"article-number":"1578917"}}