{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T17:46:25Z","timestamp":1791740785836,"version":"4.3.4"},"reference-count":35,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Surg Innov"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Objective surgical skill evaluation remains challenging in robotic-assisted surgery. Existing artificial intelligence frameworks often depend on robotic telemetry or \u201cblack-box\u201d deep learning models that reduce interpretability and translational accessibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The present study developed an interpretable computer vision framework for quantitative analysis of robotic surgical motion using dense optical flow\u2013derived biomarkers extracted directly from surgical video recordings. Robotic suturing videos from the publicly available JIGSAWS dataset were analyzed using a Python\/OpenCV-based pipeline. Quantitative motion biomarkers, including motion magnitude, temporal variability, jerk-related parameters, and smoothness indices, were extracted and evaluated across expert, intermediate, and novice surgical groups. The paired left and right stereo views were averaged to produce one feature vector for each independent trial. Statistical comparisons were performed using the Kruskal\u2013Wallis test. Skill classification was evaluated using a class-weighted Random Forest classifier with Leave-One-User-Out cross-validation. Model predictions were interpreted using SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Optical flow analysis successfully extracted reproducible motion biomarkers associated with surgical expertise. Significant differences were observed in mean motion magnitude (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .0035), mean absolute jerk (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .00074), and the unnormalized smoothness index (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .00074). Motion variability did not differ significantly among the groups after trial-level aggregation (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .0769). SPARC showed the expected ordering of normalized smoothness, with the highest values among experts, but the group difference was not statistically significant (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .0647). Principal component analysis demonstrated partial clustering of surgical expertise groups based on extracted motion dynamics. Under Leave-One-User-Out cross-validation, the Random Forest classifier achieved an overall accuracy of 38.5%, a balanced accuracy of 29.5%, a macro-average AUC of 0.401, and a weighted-average AUC of 0.430. Genuine out-of-fold SHAP analysis identified the smoothness index, mean absolute jerk, and mean absolute acceleration as the largest contributors to the model outputs.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Optical flow\u2013derived motion biomarkers provide an interpretable characterization of robotic surgical movement directly from video recordings without requiring robotic telemetry. However, the modest performance under user-independent validation indicates that these biomarkers should not yet be used as a standalone measure of surgical expertise. The proposed framework provides a transparent basis for developing and externally validating video-based surgical skill assessment methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/15533506261495652","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:50:23Z","timestamp":1791478223000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optical Flow\u2013Derived Motion Biomarkers and Explainable Artificial Intelligence for Quantitative Assessment of Robotic Surgical Expertise"],"prefix":"10.1177","author":[{"given":"Sergey A.","family":"Shvetsov","sequence":"first","affiliation":[{"name":"Yerevan State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3531-650X","authenticated-orcid":false,"given":"Mahsa","family":"Kamali","sequence":"additional","affiliation":[{"name":"Yerevan State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1097\/00129689-200202000-00002"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3180350"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.1800840237"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.juro.2018.06.078"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-017-0132-7"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Nagy D\u00c1 Rudas IJ Haidegger T eds. Surgical data science an emerging field of medicine. In 2017 IEEE 30th Neumann Colloquium (NC). IEEE; 2017:59\u201364.","DOI":"10.1109\/NC.2017.8263251"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01995-1"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-018-1735-5"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3054828"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23094496"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","unstructured":"Hutchinson K Chen K Alemzadeh H. Towards interpretable motion-level skill assessment in robotic surgery. arXiv. 2023; arXiv:2311.05838. doi:10.48550\/arXiv.2311.05838","DOI":"10.48550\/arXiv.2311.05838"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Lajk\u00f3 G Elek RN Haidegger T eds. Surgical skill assessment automation based on sparse optical flow data. 2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES). IEEE; 2021:201\u2013208.","DOI":"10.1109\/INES52918.2021.9512917"},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Reiley CE Hager GD eds. Task versus subtask surgical skill evaluation of robotic minimally invasive surgery. In International Conference on Medical Image Computing and computer-assisted Intervention. Springer; 2009:435\u2013442.","DOI":"10.1007\/978-3-642-04268-3_54"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsurg.2019.06.011"},{"key":"e_1_3_3_18_2","first-page":"M2cai","volume-title":"Jhu-Isi Gesture and Skill Assessment Working Set (Jigsaws): A Surgical Activity Dataset for Human Motion Modeling","author":"Gao Y","year":"2014","unstructured":"Gao Y, Vedula SS, Reiley CE, Ahmidi N, Varadarajan B, Lin HC, et al., eds. Jhu-Isi Gesture and Skill Assessment Working Set (Jigsaws): A Surgical Activity Dataset for Human Motion Modeling. MICCAI Workshop; 2014. p. M2cai."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02259-z"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02339-8"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Deo AS Pasupulety U Matsumoto N Moran J Yang C Kim J et al. eds. Automated suturing skill assessment in robot-assisted surgery from endoscopic videos using clinically-guided evaluation criteria. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 2026:7218\u20137228.","DOI":"10.1109\/WACV61042.2026.00697"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2011.2179545"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.3200\/35-09-004-RC"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0202"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_3_26_2","first-page":"07874","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg SM","year":"2017","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:07874.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_27_2","volume-title":"String Motif-based Description of Tool Motion for Detecting Skill and Gestures in Robotic Surgery. International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Ahmidi N","year":"2013","unstructured":"Ahmidi N, Gao Y, B\u00e9jar B, Vedula SS, Khudanpur S, Vidal R, et al., eds. String Motif-based Description of Tool Motion for Detecting Skill and Gestures in Robotic Surgery. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2013."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-010-1190-z"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.08.002"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Zia A Sharma Y Bettadapura V Sarin EL Clements MA Essa I eds. Automated assessment of surgical skills using frequency analysis. In International Conference on Medical Image Computing and computer-assisted Intervention. Springer; 2015:430\u2013438.","DOI":"10.1007\/978-3-319-24553-9_53"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02039-4"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2024.111884"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2019.4917"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9610(02)00891-7"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Holzinger A Biemann C Pattichis CS Kell DB. What do we need to build explainable AI systems for the medical domain? arXiv. 2017; arXiv:1712.09923. doi:10.48550\/arXiv.1712.09923","DOI":"10.48550\/arXiv.1712.09923"}],"container-title":["Surgical Innovation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15533506261495652","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/15533506261495652","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15533506261495652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T17:06:20Z","timestamp":1791738380000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/15533506261495652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":35,"alternative-id":["10.1177\/15533506261495652"],"URL":"https:\/\/doi.org\/10.1177\/15533506261495652","relation":{},"ISSN":["1553-3506","1553-3514"],"issn-type":[{"value":"1553-3506","type":"print"},{"value":"1553-3514","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"article-number":"15533506261495652"}}