{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:30:27Z","timestamp":1787027427104,"version":"build-2736575974"},"reference-count":39,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007217","name":"Kaohsiung Municipal Kai-Syuan Psychiatric Hospital","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007217","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/00en92979","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Motor abnormalities are frequently observed in schizophrenia, but accessible methods for objective gait quantification remain limited. This exploratory controlled-setting study examined whether markerless smartphone-based video analysis combined with interpretable machine learning could quantify gait-related motor phenotypes in individuals with schizophrenia. Methods: Gait videos were collected from 100 individuals with schizophrenia and 35 healthy controls using a single-site, single-device, standardized recording setup. MediaPipe Pose was used to extract skeletal landmarks and derive 12 image-plane spatiotemporal and estimated two-dimensional knee-kinematic gait features. After temporal segmentation and quality control, 404 usable gait segments derived from 135 participants were analyzed as repeated segment-level observations. Decision Tree and Support Vector Machine models were applied for exploratory segment-level group-separation analysis using segment-wise 15-fold cross-validation after the full post-quality-control dataset had been balanced before fold allocation. Results: Several extracted gait features differed between groups, particularly image-plane ankle displacement, mean step displacement, displacement velocity, step characteristics, and knee-joint motion. In the Decision Tree model, image-plane ankle displacement served as the primary root node, indicating its central role in internal segment-level group separation. However, the healthy control group was substantially younger and not age-matched. In addition, the segment-level statistical comparisons did not account for within-participant clustering. Accordingly, the reported p values and confidence intervals may overstate statistical precision. Separately, segment-wise cross-validation allowed segments from the same participant to occur across folds and resampling was performed before fold partitioning. Because oversampling was performed with replacement, duplicated segment instances could also occur across training and validation folds. Consequently, the statistical findings should be interpreted as exploratory segment-level patterns rather than participant-level inference, and the machine-learning performance estimates should be regarded only as potentially optimistic apparent internal segment-level results and should not be regarded as evidence of participant-level generalization, diagnostic validity, screening accuracy, or clinical applicability. Conclusions: Markerless video-based gait analysis with interpretable machine learning may provide a feasible research-support approach for quantifying gait-related motor phenotypes in individuals with schizophrenia. These findings should not be interpreted as evidence for participant-level clinical classification, diagnostic or screening validity, clinical utility, or readiness for deployment, or as proof of cross-device or cross-environment reproducibility. Future studies require matched controls, psychiatric comparison groups, subject-wise validation, external datasets, calibrated gait measures, systematic cross-configuration reproducibility testing, and privacy-preserving data governance.<\/jats:p>","DOI":"10.3390\/diagnostics16162585","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T10:04:36Z","timestamp":1786961076000},"page":"2585","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Markerless Video-Based Gait Analysis for Motor Phenotyping in Individuals with Schizophrenia Using Interpretable Machine Learning"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3914-1049","authenticated-orcid":false,"given":"Posen","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Occupational Therapy, I-Shou University, Kaohsiung 84001, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Shan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Chi Mei Medical Center, Tainan 71004, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1175-0531","authenticated-orcid":false,"given":"Shih-Yen","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, I-Shou University, Kaohsiung 84001, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6285-1802","authenticated-orcid":false,"given":"Chin-Hsuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Occupational Therapy, I-Shou University, Kaohsiung 84001, Taiwan"},{"name":"School of Occupational Therapy, College of Medicine, National Taiwan University, Taipei 100225, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.neubiorev.2018.01.011","article-title":"Motor dysfunction as research domain in the period preceding manifest schizophrenia: A systematic review","volume":"87","author":"Hirjak","year":"2018","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1007\/s00406-022-01402-y","article-title":"Movement markers of schizophrenia: A detailed analysis of patients\u2019 gait patterns","volume":"272","author":"Martin","year":"2022","journal-title":"Eur. Arch. Psychiatry Clin. Neurosci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1002\/mds.23050","article-title":"Motor behavior abnormalities in drug-na\u00efve patients with schizophrenia spectrum disorders","volume":"25","author":"Peralta","year":"2010","journal-title":"Mov. Disord."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1038\/s41582-020-0403-x","article-title":"Neurological soft signs predict outcomes in schizophrenia","volume":"16","author":"Toro","year":"2020","journal-title":"Nat. Rev. Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.schres.2017.10.007","article-title":"Motor dysfunction as an intermediate phenotype across schizophrenia and other psychotic disorders: Progress and perspectives","volume":"200","author":"Hirjak","year":"2018","journal-title":"Schizophr. Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Presta, V., Paraboschi, F., Marsella, F., Lucarini, V., Galli, D., Mirandola, P., Banchini, A., Marchesi, C., Galuppo, L., and Vitale, M. (2021). Posture and gait in the early course of schizophrenia. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0245661"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s41537-022-00324-x","article-title":"Psychomotor slowing alters gait velocity, cadence, and stride length and indicates negative symptom severity in psychosis","volume":"8","author":"Nuoffer","year":"2022","journal-title":"Schizophrenia"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1111\/eip.13340","article-title":"Posture, gait and self-disorders: An empirical study in individuals with schizophrenia","volume":"17","author":"Tonna","year":"2023","journal-title":"Early Interv. Psychiatry"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Martin, L.A., Melchert, D., Knack, M., and Fuchs, T. (2023). Relating movement markers of schizophrenia to self-experience\u2014A mixed-methods study. Front. Psychiatry, 14.","DOI":"10.3389\/fpsyt.2023.1212508"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lee, P., Chen, T.-B., Lin, H.-Y., Yeh, L.-R., Liu, C.-H., and Chen, Y.-L. (2024). Integrating openpose and SVM for quantitative postural analysis in young adults: A temporal-spatial approach. Bioengineering, 11.","DOI":"10.3390\/bioengineering11060548"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sabashi, K., Ishida, T., Matsumoto, H., Mikami, K., Chiba, T., Yamanaka, M., Aoki, Y., and Tohyama, H. (2021). Dynamic postural control correlates with activities of daily living and quality of life in patients with knee osteoarthritis. BMC Musculoskelet. Disord., 22.","DOI":"10.1186\/s12891-021-04164-1"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hadamus, A., B\u0142a\u017ckiewicz, M., Kowalska, A.J., Wydra, K.T., Grabowicz, M., \u0141ukowicz, M., Bia\u0142oszewski, D., and Marczy\u0144ski, W. (2022). Nonlinear and linear measures in the differentiation of postural control in patients after total hip or knee replacement and healthy controls. Diagnostics, 12.","DOI":"10.3390\/diagnostics12071595"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lee, P., Chen, T.-B., Wang, C.-Y., Hsu, S.-Y., and Liu, C.-H. (2021). Detection of postural control in young and elderly adults using deep and machine learning methods with Joint\u2013Node plots. Sensors, 21.","DOI":"10.3390\/s21093212"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"14065","DOI":"10.1038\/s41598-021-93530-z","article-title":"Algorithm based on one monocular video delivers highly valid and reliable gait parameters","volume":"11","author":"Azhand","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"9575","DOI":"10.1109\/JSEN.2019.2928777","article-title":"Deep learning for monitoring of human gait: A review","volume":"19","author":"Alharthi","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4054","DOI":"10.1038\/s41467-020-17807-z","article-title":"Deep neural networks enable quantitative movement analysis using single-camera videos","volume":"11","author":"Yang","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","unstructured":"Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., and Grundmann, M. (2020). BlazePose: On-device real-time body pose tracking. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022, January 19\u201320). YOLO-Pose: Enhancing YOLO for multi-person pose estimation using object keypoint similarity loss. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"ref_20","unstructured":"Hii, C.S.T., Gan, K.B., Zainal, N., Ibrahim, N.M., Rani, S.A.M., and Abd Shattar, N. (2022). Marker-free gait analysis using pose estimation model. Proceedings of the 2022 IEEE 20th Student Conference on Research and Development (SCOReD), IEEE."},{"key":"ref_21","unstructured":"Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M.G., and Lee, J. (2019). MediaPipe: A framework for building perception pipelines. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hii, C.S.T., Gan, K.B., Zainal, N., Mohamed Ibrahim, N., Azmin, S., Mat Desa, S.H., van de Warrenburg, B., and You, H.W. (2023). Automated gait analysis based on a marker-free pose estimation model. Sensors, 23.","DOI":"10.3390\/s23146489"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1016\/j.apmr.2011.10.022","article-title":"Comparison of pelvic complex kinematics during treadmill and overground walking","volume":"93","author":"Chockalingam","year":"2012","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.clinbiomech.2008.10.005","article-title":"Effect of trunk inclination on lower limb joint and lumbar moments in able men during the stance phase of gait","volume":"24","author":"Leteneur","year":"2009","journal-title":"Clin. Biomech."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1016\/S0268-0033(98)00012-6","article-title":"A kinematic comparison of overground and treadmill walking","volume":"13","author":"Alton","year":"1998","journal-title":"Clin. Biomech."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1177\/107110070602701010","article-title":"Foot and ankle kinematics and ground reaction forces during ambulation","volume":"27","author":"Kitaoka","year":"2006","journal-title":"Foot Ankle Int."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1682\/JRRD.2003.10.0150","article-title":"The effect of walking speed on center of mass displacement","volume":"41","author":"Orendurff","year":"2004","journal-title":"J. Rehabil. Res. Dev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.gaitpost.2012.05.030","article-title":"Gait speed and gender effects on center of pressure progression during normal walking","volume":"37","author":"Chiu","year":"2013","journal-title":"Gait Posture"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.gaitpost.2009.09.013","article-title":"The change of gait parameters during walking at different percentage of preferred walking speed for healthy adults aged 20\u201360 years","volume":"31","author":"Chung","year":"2010","journal-title":"Gait Posture"},{"key":"ref_30","unstructured":"Platt, J.C. (1998). Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines, Microsoft Research. Technical Report MSR-TR-98-14."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1093\/gerona\/glp033","article-title":"Quantitative gait markers and incident fall risk in older adults","volume":"64","author":"Verghese","year":"2009","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.gaitpost.2011.03.024","article-title":"Normative spatiotemporal gait parameters in older adults","volume":"34","author":"Hollman","year":"2011","journal-title":"Gait Posture"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107161","DOI":"10.1016\/j.cmpb.2022.107161","article-title":"Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011\u20132022)","volume":"226","author":"Loh","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Pratap, S., Narayan, J., Hatta, Y., Ito, K., and Hazarika, S.M. (2024). Glove-Net: Enhancing Grasp Classification with Multisensory Data and Deep Learning Approach. Sensors, 24.","DOI":"10.3390\/s24134378"},{"key":"ref_35","unstructured":"World Health Organization (2021). Ethics and Governance of Artificial Intelligence for Health: WHO Guidance, World Health Organization."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Varma, S., and Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinform., 7.","DOI":"10.1186\/1471-2105-7-91"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e49023","DOI":"10.2196\/49023","article-title":"Practical considerations and applied examples of cross-validation for model development and evaluation in health care: Tutorial","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR AI"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Vabalas, A., Gowen, E., Poliakoff, E., and Casson, A.J. (2019). Machine learning algorithm validation with a limited sample size. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0224365"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e220232","DOI":"10.1148\/ryai.220232","article-title":"A guide to cross-validation for artificial intelligence in medical imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol. Artif. Intell."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2585\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:15:15Z","timestamp":1787026515000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,15]]},"references-count":39,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162585"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162585","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,15]]}}}