{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T18:27:53Z","timestamp":1793644073890,"version":"4.5.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Blastocyst transfer has been associated with shorter leukocyte telomere length in ART-conceived children, suggesting that extended embryo culture may accelerate aging in offspring. Selecting Day 3 embryos with high developmental potential for transfer could address this issue. The aim of this study is to investigate whether machine learning combined with Raman spectroscopy of spent Day 3 culture medium can serve as a potential method for predicting extended embryo culture outcomes, thereby enabling embryo selection at the cleavage stage.<\/jats:p>\n                    <jats:sec>\n                      <jats:title>Methods<\/jats:title>\n                      <jats:p>This prospective study analyzed 172 Day 3 culture medium samples with known extended culture outcomes from 78 couples collected between February 2020 and February 2021. Samples were categorized into three groups based on extended culture outcomes: morphologically good blastocysts (group A), morphologically non-good blastocysts (group B), and clinically non-useful embryos (group C). For each sample, 30\u201340 Raman spectra were acquired. Machine learning analyses (both unsupervised and supervised) were performed for data visualization and clustering. Eighty percent of the samples from each group were used as training data, while the remaining 20% served as the test set. Twelve machine learning models, including both deep learning and traditional approaches, were independently trained and evaluated. Accuracy, sensitivity, and specificity were calculated for each model. Finally, the best four top-performing models were further combined using a stacking strategy for final prediction.<\/jats:p>\n                    <\/jats:sec>\n                    <jats:sec>\n                      <jats:title>Results<\/jats:title>\n                      <jats:p>The study included good-prognosis females (average age: 29.55 \u00b1 2.94 years) with an adequate number of Day 3 embryos (median: 9 [7, 11]). Supervised machine learning of labeled Raman spectra revealed distinct clusters for each group. The best-performing models were multilayer perceptron, artificial neural network, gated recurrent unit, and linear discriminant analysis. Using the stacking strategy, two samples were misclassified, and 33 were correctly predicted. Sensitivity for A, B, and C predictions was 0.92, 1.00, and 0.94, respectively. Specificity for A, B, and C predictions was 1.00, 0.93, and 1.00, respectively. The overall accuracy, sensitivity, and specificity were 0.94, 0.93, and 0.97, respectively.<\/jats:p>\n                    <\/jats:sec>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our preliminary study suggests that machine learning combined with Raman spectra of spent Day 3 culture medium represents a promising non-invasive approach for embryo selection at the cleavage stage.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2025.1608318","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T05:29:12Z","timestamp":1757914152000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Embryo selection at the cleavage stage using Raman spectroscopy of day 3 culture medium and machine learning: a preliminary study"],"prefix":"10.3389","volume":"16","author":[{"given":"Fang","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanjun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanbi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuliang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/s0015-0282(01)03235-6","article-title":"Integration of blastocyst transfer for all patients","volume":"77","author":"Wilson","year":"2002","journal-title":"Fertil Steril"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1093\/humrep\/dei217","article-title":"Live Birth Rate Is Significantly Higher after Blastocyst Transfer Than after Cleavage-Stage Embryo Transfer When at Least Four Embryos Are Available on Day 3 of Embryo Culture. A Randomized Prospective Study","volume":"20","author":"Papanikolaou","year":"2005","journal-title":"Hum Reprod"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.fertnstert.2007.05.036","article-title":"Single-blastocyst transfer decreases twin gestation without affecting pregnancy outcome","volume":"89","author":"Styer","year":"2008","journal-title":"Fertil Steril"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1471-0528.2007.01584.x","article-title":"Selective single blastocyst transfer reduces the multiple pregnancy rate and increases pregnancy rates: A pre- and postintervention study","volume":"115","author":"Khalaf","year":"2008","journal-title":"BJOG"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.4103\/jhrs.JHRS_130_16","article-title":"Single blastocyst transfer: the key to reduce multiple pregnancy rates without compromising the live birth rate","volume":"10","author":"Sundhararaj","year":"2017","journal-title":"J Hum Reprod Sci"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rbmo.2015.09.016","article-title":"Should we be promoting embryo transfer at blastocyst stage","volume":"32","author":"Maheshwari","year":"2016","journal-title":"Reprod BioMed Online"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-02108-3","article-title":"Leukocyte telomere length in children born following blastocyst-stage embryo transfer","volume":"28","author":"Wang","year":"2022","journal-title":"Nat Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.fertnstert.2012.12.044","article-title":"Epigenetic disturbances in in vitro cultured gametes and embryos: implications for human assisted reproduction","volume":"99","author":"El Hajj","year":"2013","journal-title":"Fertil Steril"},{"key":"B9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.rbmo.2021.09.022","article-title":"Inter-centre reliability in embryo grading across several ivf clinics is limited: implications for embryo selection","volume":"44","author":"Cimadomo","year":"2022","journal-title":"Reprod BioMed Online"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2021.785658","article-title":"Analysis of biochemical and clinical pregnancy loss between frozen-thawed embryo transfer of blastocysts and day 3 cleavage embryos in young women: A comprehensive comparison","volume":"12","author":"Dai","year":"2021","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.fertnstert.2012.12.004","article-title":"Analysis of metabolism to select viable human embryos for transfer","volume":"99","author":"Gardner","year":"2013","journal-title":"Fertil Steril"},{"key":"B12","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1071\/RD15340","article-title":"Measuring embryo metabolism to predict embryo quality","volume":"28","author":"Thompson","year":"2016","journal-title":"Reprod Fertil Dev"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpba.2024.116366","article-title":"Raman spectroscopy: A promising analytical tool used in human reproductive medicine","volume":"249","author":"Zheng","year":"2024","journal-title":"J Pharm BioMed Anal"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.fertnstert.2007.07.1390","article-title":"Noninvasive metabolomic profiling of embryo culture media using raman and near-infrared spectroscopy correlates with reproductive potential of embryos in women undergoing in vitro fertilization","volume":"88","author":"Seli","year":"2007","journal-title":"Fertil Steril"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3390\/ijms14046556","article-title":"Noninvasive metabolomic profiling of human embryo culture media using a simple spectroscopy adjunct to morphology for embryo assessment in in vitro fertilization (Ivf)","volume":"14","author":"Zhao","year":"2013","journal-title":"Int J Mol Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.anireprosci.2018.07.001","article-title":"Non-invasive metabolomic profiling of culture media of icsi- and ivf-derived early developmental cattle embryos via raman spectroscopy","volume":"196","author":"Li","year":"2018","journal-title":"Anim Reprod Sci"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2023.1164757","article-title":"Rapid and non-invasive diagnostic techniques for embryonic developmental potential: A metabolomic analysis based on raman spectroscopy to identify the pregnancy outcomes of ivf-et","volume":"11","author":"Meng","year":"2023","journal-title":"Front Cell Dev Biol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1016\/j.fertnstert.2018.11.036","article-title":"Raman profiling of embryo culture medium to identify aneuploid and euploid embryos","volume":"111","author":"Liang","year":"2019","journal-title":"Fertil Steril"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.777259","article-title":"Non-invasive metabolomic profiling of embryo culture medium using raman spectroscopy with deep learning model predicts the blastocyst development potential of embryos","volume":"12","author":"Zheng","year":"2021","journal-title":"Front Physiol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2286","DOI":"10.1038\/s41598-020-59347-y","article-title":"Sperm enrichment from poor semen samples by double density gradient centrifugation in combination with swim-up for ivf cycles","volume":"10","author":"Dai","year":"2020","journal-title":"Sci Rep"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/s0015-0282(00)00645-2","article-title":"Blastocyst quality affects the success of blastocyst-stage embryo transfer","volume":"74","author":"Balaban","year":"2000","journal-title":"Fertil Steril"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2021.120300","article-title":"Raman spectroscopy and machine learning for the classification of breast cancers","volume":"264","author":"Zhang","year":"2022","journal-title":"Spectrochim Acta A Mol Biomol Spectrosc"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980942","article-title":"Analysis of dimensionality reduction techniques on big data","volume":"8","author":"Reddy","year":"2020","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1021\/acs.iecr.9b00975","article-title":"A deep learning approach for process data visualization using T-distributed stochastic neighbor embedding","volume":"58","author":"Zhu","year":"2019","journal-title":"Ind Eng Chem Res"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.69","article-title":"Latent dirichlet allocation models for image classification","volume":"35","author":"Rasiwasia","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1002\/cem.1006","article-title":"Opls discriminant analysis: combining the strengths of pls-da and simca classification","volume":"20","author":"Bylesj\u00f6","year":"2006","journal-title":"J Chemom"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.5555\/1639537.1639542","article-title":"Multilayer perceptron and neural networks","volume":"8","author":"Popescu","year":"2009","journal-title":"WToC Syst"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-67340-0","article-title":"Artificial neural network","author":"Zhang","year":"2018","journal-title":"tsaic Res e"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1109\/MWSCAS.2017.8053243","article-title":"Gate-variants of gated recurrent unit (Gru) neural networks","author":"Dey","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"Bent\u00e9jac","year":"2021","journal-title":"Artif Intell Rev"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/ICCS45141.2019.9065747","article-title":"A brief review of nearest neighbor algorithm for learning and classification","volume-title":"2019 international conference on intelligent computing and control systems (ICCS)","author":"Taunk","year":"2019"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J Insur Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.5555\/3104482.3104606","article-title":"Locally linear support vector machines","author":"Ladick\u00fd","year":"2011"},{"key":"B35","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-1-4419-9878-1","article-title":"Linear discriminant analysis","author":"Xanthopoulos","year":"2013"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-15-S16-S11","article-title":"Genetic algorithm with logistic regression for prediction of progression to alzheimer\u2019s disease","volume":"15","author":"Johnson","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e1434","DOI":"10.1002\/wics.1434","article-title":"A review of quadratic discriminant analysis for high-dimensional data","volume":"10","author":"Qin","year":"2018","journal-title":"Wiley Interdiscip Rev Comput Stat"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611972719.13","article-title":"Rsvm: reduced support vector machines","author":"Lee","year":"2001"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.5555\/1621804.1621819","article-title":"Automatic arabic document categorization based on the na\u00efve bayes algorithm","author":"El Kourdi","year":"2004","journal-title":"Proc Workshop Comput Approaches to Arabic Script-based Languages"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3207287","article-title":"A survey of ensemble learning: concepts, algorithms, applications, and prospects","volume":"10","author":"Mienye","year":"2022","journal-title":"IEEE Access"},{"key":"B41","doi-asserted-by":"publisher","first-page":"105151","DOI":"10.1016\/j.engappai.2022.105151","article-title":"Ensemble deep learning: A review","volume":"115","author":"Ganaie","year":"2022","journal-title":"Eng Appl Artif Intell"},{"key":"B42","doi-asserted-by":"publisher","first-page":"26","DOI":"10.3390\/computers12020026","article-title":"Automatic evaluation of neural network training results","volume":"12","author":"Barinov","year":"2023","journal-title":"Computers (Basel)"},{"key":"B43","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.fertnstert.2007.11.058","article-title":"Noninvasive metabolomic profiling of human embryo culture media using raman spectroscopy predicts embryonic reproductive potential: A prospective blinded pilot study","volume":"90","author":"Scott","year":"2008","journal-title":"Fertil Steril"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.23736\/S2724-606X.20.04765-6","article-title":"Endometriosis-associated infertility: surgery or ivf","volume":"73","author":"Muzii","year":"2021","journal-title":"Minerva Obstet Gynecol"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.fertnstert.2024.02.049","article-title":"Uterine fibroid-related infertility: mechanisms and management","volume":"122","author":"Donnez","year":"2024","journal-title":"Fertil Steril"},{"key":"B46","doi-asserted-by":"publisher","first-page":"e13935","DOI":"10.7717\/peerj.13935","article-title":"Morphology of inner cell mass: A better predictive biomarker of blastocyst viability","volume":"10","author":"Sivanantham","year":"2022","journal-title":"PeerJ"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1055\/s-0033-1363556","article-title":"Metabolomic assessment of embryo viability","volume":"32","author":"Uyar","year":"2014","journal-title":"Semin Reprod Med"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10466-8","article-title":"Deep learning modelling techniques: current progress, applications, advantages, and challenges","volume":"56","author":"Ahmed","year":"2023","journal-title":"Artif Intell Rev"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1093\/humrep\/dez163","article-title":"Day 5 versus day 6 blastocyst transfers: A systematic review and meta-analysis of clinical outcomes","volume":"34","author":"Bourdon","year":"2019","journal-title":"Hum Reprod"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1608318\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T05:29:13Z","timestamp":1757914153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1608318\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":49,"alternative-id":["10.3389\/fendo.2025.1608318"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1608318","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]},"article-number":"1608318"}}