{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:28:53Z","timestamp":1791394133330,"version":"4.3.3"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Ministry of Health (Singapore) Health Innovation","award":["MH 110:12\/12-30"],"award-info":[{"award-number":["MH 110:12\/12-30"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Neonatal jaundice monitoring is resource-intensive. Existing artificial intelligence methods use image or clinical data, but none systematically combine both or compare feature contributions. This study fills that gap by extracting and analyzing multimodal features on a large dataset, identifying an optimal feature set for accurate, accessible jaundice assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>This study collected clinical data and skin images from 3 body regions of 633 neonates, generating 460 features across 4 categories. Four tree-based models were used to predict total serum bilirubin levels and feature importance analysis guided the selection of an optimal feature set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The optimal performance was achieved using the Light Gradient Boosting Machine (LGBM) model with 140 selected features, yielding a root mean square error (RMSE) of 2.0477 mg\/dL and a Pearson correlation of 0.8435. This represents a performance gain of over 10% in RMSE compared to models using only a single data modality. Moreover, selecting the top 30 features based on SHapley Additive exPlanation (SHAP) allows for a substantial reduction in data dimensionality, while maintaining performance within 5% of the optimal model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Color features contributed over 60% of the total importance, with clinical data adding more than 25%, led by hour of life. Light temperature also affected predictions, while texture features had minimal impact. Among body regions, the abdomen provided the most informative signals for jaundice severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed algorithm shows promise for real-world use by enabling timely, automated jaundice assessment for families, while also offering insights for future research and broader medical applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooaf165","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T13:07:45Z","timestamp":1764248865000},"source":"Crossref","is-referenced-by-count":5,"title":["Multimodal feature analysis for automated neonatal jaundice assessment using machine learning"],"prefix":"10.1093","volume":"8","author":[{"given":"Yunfeng","family":"Liang","sequence":"first","affiliation":[{"name":"Data aNalytics & AI, Synapxe Pte Ltd , Singapore 139691,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zou","sequence":"additional","affiliation":[{"name":"Data aNalytics & AI, Synapxe Pte Ltd , Singapore 139691,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Millie Ming Rong","family":"Goh","sequence":"additional","affiliation":[{"name":"Data aNalytics & AI, Synapxe Pte Ltd , Singapore 139691,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alvin Jia Hao","family":"Ngeow","sequence":"additional","affiliation":[{"name":"Department of Neonatal and Developmental Medicine, Singapore General Hospital , Singapore 169854,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngiap Chuan","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Research, SingHealth Polyclinics , Singapore 150167,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy Wee An","family":"Ta","sequence":"additional","affiliation":[{"name":"Data aNalytics & AI, Synapxe Pte Ltd , Singapore 139691,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han Leong","family":"Goh","sequence":"additional","affiliation":[{"name":"Data aNalytics & AI, Synapxe Pte Ltd , Singapore 139691,","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"2025120909582494600_ooaf165-B1","doi-asserted-by":"crossref","first-page":"F317","DOI":"10.1136\/adc.2008.150714","article-title":"Visual assessment of jaundice in term and late preterm infants","volume":"94","author":"Keren","year":"2009","journal-title":"Arch Dis Child Fetal Neonatal Ed"},{"key":"2025120909582494600_ooaf165-B2","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.jpeds.2012.08.022","article-title":"Predischarge screening for severe neonatal hyperbilirubinemia identifies infants who need phototherapy","volume":"162","author":"Bhutani","year":"2013","journal-title":"J Pediatr"},{"key":"2025120909582494600_ooaf165-B3","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1542\/peds.113.4.775","article-title":"Incidence, course, and prediction of hyperbilirubinemia in near-term and term newborns","volume":"113","author":"Sarici","year":"2004","journal-title":"Pediatrics"},{"key":"2025120909582494600_ooaf165-B4","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1542\/peds.114.1.297","article-title":"Management of hyperbilirubinemia in the newborn infant 35 or more weeks of gestation","volume":"114","author":"American Academy of Pediatrics Subcommittee on Hyperbilirubinemia","year":"2004","journal-title":"Pediatrics"},{"key":"2025120909582494600_ooaf165-B5","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1515\/cclm-2024-0620","article-title":"Bilirubin measurements in neonates: uniform neonatal treatment can only be achieved by improved standardization","volume":"62","author":"Hulzebos","year":"2024","journal-title":"Clin Chem Lab Med"},{"key":"2025120909582494600_ooaf165-B6","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1001\/archpedi.154.4.391","article-title":"Accuracy of clinical judgment in neonatal jaundice","volume":"154","author":"Moyer","year":"2000","journal-title":"Arch Pediatr Adolesc Med"},{"key":"2025120909582494600_ooaf165-B7","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1038\/s41390-021-01543-1","article-title":"Screening methods for neonatal hyperbilirubinemia: benefits, limitations, requirements, and novel developments","volume":"90","author":"Hulzebos","year":"2021","journal-title":"Pediatr Res"},{"key":"2025120909582494600_ooaf165-B8","doi-asserted-by":"crossref","first-page":"103088","DOI":"10.1016\/j.artmed.2025.103088","article-title":"Artificial intelligence non-invasive methods for neonatal jaundice detection: a review","volume":"162","author":"Oiza Salami","year":"2025","journal-title":"Artif Intell Med"},{"key":"2025120909582494600_ooaf165-B9","first-page":"331","author":"De Greef","year":"2014"},{"key":"2025120909582494600_ooaf165-B10","doi-asserted-by":"crossref","first-page":"e2017-0312","DOI":"10.1542\/peds.2017-0312","article-title":"Use of a smartphone app to assess neonatal jaundice","volume":"140","author":"Taylor","year":"2017","journal-title":"Pediatrics"},{"key":"2025120909582494600_ooaf165-B11","doi-asserted-by":"crossref","first-page":"2532","DOI":"10.1111\/apa.15287","article-title":"Bilirubin estimates from smartphone images of newborn infants\u2019 skin correlated highly to serum bilirubin levels","volume":"109","author":"Aune","year":"2020","journal-title":"Acta Paediatr (Stockh)"},{"key":"2025120909582494600_ooaf165-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-016-0523-4","article-title":"Neonatal jaundice detection system","volume":"40","author":"Ayd\u0131n","year":"2016","journal-title":"J Med Syst"},{"key":"2025120909582494600_ooaf165-B13","doi-asserted-by":"crossref","first-page":"623","DOI":"10.3390\/biomedinformatics4010034","article-title":"Real-time jaundice detection in neonates based on machine learning models","volume":"4","author":"Abdulrazzak","year":"2024","journal-title":"BioMedInformatics"},{"key":"2025120909582494600_ooaf165-B14","doi-asserted-by":"crossref","first-page":"7038","DOI":"10.3390\/s21217038","article-title":"Neonatal jaundice diagnosis using a smartphone camera based on eye, skin, and fused features with transfer learning","volume":"21","author":"Althnian","year":"2021","journal-title":"Sensors"},{"key":"2025120909582494600_ooaf165-B15","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1364\/BOE.10.001250","article-title":"Jaundice eye color index (JECI): quantifying the yellowness of the sclera in jaundiced neonates with digital photography","volume":"10","author":"Leung","year":"2019","journal-title":"Biomed Opt Express"},{"key":"2025120909582494600_ooaf165-B16","doi-asserted-by":"crossref","first-page":"6481","DOI":"10.1038\/s41598-025-89528-6","article-title":"Feasibility study of texture-based machine learning approach for early detection of neonatal jaundice","volume":"15","author":"Phattraprayoon","year":"2025","journal-title":"Sci Rep"},{"key":"2025120909582494600_ooaf165-B17","doi-asserted-by":"crossref","first-page":"159","DOI":"10.11648\/j.ajp.20190503.24","article-title":"A classification model for severity of neonatal jaundice using deep learning","volume":"5","author":"Chidozie Egejuru","year":"2019","journal-title":"AJP"},{"key":"2025120909582494600_ooaf165-B18","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1038\/s41390-019-0384-x","article-title":"Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning","volume":"86","author":"Daunhawer","year":"2019","journal-title":"Pediatr Res"},{"key":"2025120909582494600_ooaf165-B19","doi-asserted-by":"crossref","first-page":"11571","DOI":"10.1038\/s41598-025-96100-9","article-title":"Artificial intelligence-based non-invasive bilirubin prediction for neonatal jaundice using 1d convolutional neural network","volume":"15","author":"Makhloughi","year":"2025","journal-title":"Sci Rep"},{"key":"2025120909582494600_ooaf165-B20","doi-asserted-by":"crossref","first-page":"10","DOI":"10.53894\/ijirss.v5i1.334","article-title":"A mobile computer-aided diagnosis of neonatal hyperbilirubinemia using digital image processing and machine learning techniques","volume":"5","author":"Dissaneevate","year":"2022","journal-title":"Int J Innov Res Scientif Stud"},{"key":"2025120909582494600_ooaf165-B21","first-page":"454","article-title":"Advancement of dermal icterus in the jaundiced newborn","volume":"118","author":"Kramer","year":"1969","journal-title":"Am J Dis Child"},{"key":"2025120909582494600_ooaf165-B22","doi-asserted-by":"crossref","first-page":"e2450260","DOI":"10.1001\/jamanetworkopen.2024.50260","article-title":"Development and validation of a smartphone application for neonatal jaundice screening","volume":"7","author":"Ngeow","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2025120909582494600_ooaf165-B23","doi-asserted-by":"crossref","first-page":"2116","DOI":"10.3906\/elk-2008-76","article-title":"Classification of neonatal jaundice in mobile application with noninvasive imageprocessing methods","volume":"29","author":"Hardalac","year":"2021","journal-title":"Turk J Electr Eng Comput Sci"},{"key":"2025120909582494600_ooaf165-B24","first-page":"1","volume-title":"2016 International Conference on ICT in Business Industry & Government (ICTBIG)","author":"Kolkur","year":"2016"},{"key":"2025120909582494600_ooaf165-B25","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1002\/ima.22490","article-title":"Automatic skin cancer detection in dermoscopy images by combining convolutional neural networks and texture features","volume":"31","author":"Alizadeh","year":"2021","journal-title":"Int J Imaging Syst Technol"},{"key":"2025120909582494600_ooaf165-B26","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1542\/peds.103.1.6","article-title":"Predictive ability of a predischarge hour-specific serum bilirubin for subsequent significant hyperbilirubinemia in healthy term and near-term newborns","volume":"103","author":"Bhutani","year":"1999","journal-title":"Pediatrics"},{"key":"2025120909582494600_ooaf165-B27","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.imavis.2018.05.004","article-title":"Speeded up detection of squared fiducial markers","volume":"76","author":"Romero-Ramirez","year":"2018","journal-title":"Image Vis Comput"},{"key":"2025120909582494600_ooaf165-B28","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.patcog.2015.09.023","article-title":"Generation of fiducial marker dictionaries using mixed integer linear programming","volume":"51","author":"Garrido-Jurado","year":"2016","journal-title":"Pattern Recognit"},{"key":"2025120909582494600_ooaf165-B29","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1016\/j.procs.2023.01.111","article-title":"Non-invasive early diagnosis of jaundice with computer vision","volume":"218","author":"Sreedha","year":"2023","journal-title":"Proc Comput Sci"},{"key":"2025120909582494600_ooaf165-B30","first-page":"012022","volume-title":"IOP Conference Series: Materials Science and Engineering","author":"Putri Rahayu","year":"2021"},{"key":"2025120909582494600_ooaf165-B31","first-page":"1","article-title":"Biliscreen: smartphone-based scleral jaundice monitoring for liver and pancreatic disorders","volume":"1","author":"Mariakakis","year":"2017","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"},{"key":"2025120909582494600_ooaf165-B32","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1013200319198","article-title":"Statistical color models with application to skin detection","volume":"46","author":"Jones","year":"2002","journal-title":"Int J Comput Vis"},{"key":"2025120909582494600_ooaf165-B33","first-page":"1","article-title":"Utilization of Individual Typology Angle (Ita) and Hue Angle in the Measurement of Skin Color on Images","volume":"28","author":"Wu","year":"2020","journal-title":"bioimages"},{"key":"2025120909582494600_ooaf165-B34","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2025120909582494600_ooaf165-B35","first-page":"785","author":"Chen","year":"2016"},{"key":"2025120909582494600_ooaf165-B36","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025120909582494600_ooaf165-B37","first-page":"2623","author":"Akiba","year":"2019"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/6\/ooaf165\/65818524\/ooaf165.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/6\/ooaf165\/65818524\/ooaf165.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T14:58:38Z","timestamp":1765292318000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooaf165\/8374784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf165","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,12]]},"published":{"date-parts":[[2025,11,3]]},"article-number":"ooaf165"}}