{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T19:37:48Z","timestamp":1772048268362,"version":"3.50.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T00:00:00Z","timestamp":1756857600000},"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. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Patients missing their appointments (no-shows) are a persistent issue that results in idle resources while delaying critical patient prognosis. Likewise, long waiting times increase frustration for patients, leaving a negative impression on the appointment. In this paper, we explore 3 modalities of diagnostic and interventional radiology appointments for pediatric patients at the Hospital for Sick Children (SickKids), Toronto, ON, Canada. Our goal was to survey machine learning methods that best predict the risk of patient no-shows and long wait-times exceeding 1\u202fhour for scheduling teams to propose targeted downstream accommodations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We experimented with 6 predictive model types separately trained on both tasks which included extreme gradient boosting (XGBoost), Random Forest (RF), Support Vector Machine, Logistic Regression, Artificial Neural Network, and a pre-trained large language model (LLM). Utilizing 20 features containing a mixture of patient demographics and appointment related data, we experimented with different data balancing methods including instance hardness threshold (IHT) and class weighting to reduce bias in prediction. We then conducted a comparative study of the improvements made by utilizing continuous contextual data in our LLM which boasted a 51% improvement in F1 score for the wait-time model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our XGBoost model had the best combination of AUC and F1 scores (0.96 and 0.62, respectively) for predicting no-show while RF had the best AUC and F1 scores (0.83 and 0.61, respectively) for wait-time prediction. The LLMs also performed well for 90% probability thresholds (high risk patients) while being robustly calibrated on unseen test data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Our results surveyed multiple algorithms and data balancing methods to propose the greatest performing models on our tasks, implemented a unique methodology to use LLMs on heterogeneous data within this domain, and demonstrated the greater importance of contextual appointment data over patient demographic features for a more equitable prediction algorithm. Going forward, the predictive output (calibrated probabilities of events) can be used as stochastic input for risk-based optimized scheduling to provide accommodation for patients less likely to receive quality access to healthcare.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1652397","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T05:38:39Z","timestamp":1756877919000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting pediatric diagnostic imaging patient no-show and extended wait-times using LLMs, regression, and tree based models"],"prefix":"10.3389","volume":"8","author":[{"given":"Daniel","family":"Rafique","sequence":"first","affiliation":[]},{"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Laura","family":"Belsito","sequence":"additional","affiliation":[]},{"given":"Melissa D.","family":"McCradden","sequence":"additional","affiliation":[]},{"given":"Mjaye L.","family":"Mazwi","sequence":"additional","affiliation":[]},{"given":"Wayne","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Graham","family":"Ohanlon","sequence":"additional","affiliation":[]},{"given":"Kyle","family":"Tsang","sequence":"additional","affiliation":[]},{"given":"Manohar","family":"Shroff","sequence":"additional","affiliation":[]},{"given":"Birgit","family":"Ertl-Wagner","sequence":"additional","affiliation":[]},{"given":"Farzad","family":"Khalvati","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,9,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.healthpol.2005.01.001","article-title":"The economics of non-attendance and the expected effect of charging a fine on non-attendees","volume":"74","author":"Bech","year":"2005","journal-title":"Health Policy"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"104","DOI":"10.4236\/jilsa.2015.74010","article-title":"A KNN Undersampling approach for data balancing","volume":"7","author":"Beckmann","year":"2015","journal-title":"J. Intell. Learn. Syst. Appl."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"321","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":"ref4","doi-asserted-by":"publisher","first-page":"1288329","DOI":"10.3389\/frhs.2023.1288329","article-title":"Socioeconomic and demographic factors predictive of missed appointments in outpatient radiation oncology: an evaluation of access","volume":"3","author":"Chen","year":"2023","journal-title":"Front. Health Serv."},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"ref6","author":"Chen","year":"2004"},{"key":"ref7","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1001\/jamadermatol.2013.5771","article-title":"A multivariate analysis of dermatology missed appointment predictors","volume":"149","author":"Cronin","year":"2013","journal-title":"JAMA Dermatol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1177\/1460458210380521","article-title":"Using no-show modeling to improve clinic performance","volume":"16","author":"Daggy","year":"2010","journal-title":"Health Informatics J."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.healthpol.2018.02.002","article-title":"No-shows in appointment scheduling \u2013 a systematic literature review","volume":"122","author":"Dantas","year":"2018","journal-title":"Health Policy"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.24251\/HICSS.2019.451","article-title":"Deep learning for predicting non-attendance in hospital outpatient appointments","author":"Dashtban","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1080\/20476965.2021.1924085","article-title":"Predicting non-attendance in hospital outpatient appointments using deep learning approach","volume":"11","author":"Dashtban","year":"2021","journal-title":"Health Syst."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1186\/s12913-023-10418-6","article-title":"Decision analysis framework for predicting no-shows to appointments using machine learning algorithms","volume":"24","author":"Deina","year":"2024","journal-title":"BMC Health Serv. Res."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s10729-022-09626-z","article-title":"Predicting no-show appointments in a pediatric hospital in Chile using machine learning","volume":"26","author":"Dunstan","year":"2023","journal-title":"Health Care Manag. Sci."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1300\/j026v15n04_02","article-title":"Tackling no-show behavior","volume":"15","author":"Garuda","year":"1998","journal-title":"Health Mark. Q."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e1708","DOI":"10.7205\/milmed-d-16-00345","article-title":"Modeling patient no-show history and predicting future outpatient appointment behavior in the veterans health administration","volume":"182","author":"Goffman","year":"2017","journal-title":"Mil. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1001\/archinte.1982.00340160143026","article-title":"A multivariate approach to the prediction of no-show behavior in a primary care center","volume":"142","author":"Goldman","year":"1982","journal-title":"Arch. Intern. Med."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1186\/s40537-019-0274-4","article-title":"Severely imbalanced big data challenges: investigating data sampling approaches","volume":"6","author":"Hasanin","year":"2019","journal-title":"J. Big Data"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1258\/jtt.2011.110707","article-title":"Use of telephone and SMS reminders to improve attendance at hospital appointments: a systematic review","volume":"17","author":"Hasvold","year":"2011","journal-title":"J. Telemed. Telecare"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1108\/ijhcqa-06-2015-0077","article-title":"Time dependent patient no-show predictive modelling development","volume":"29","author":"Huang","year":"2016","journal-title":"Int. J. Health Care Qual. Assur."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"127343","DOI":"10.1109\/access.2020.3008150","article-title":"An experimental investigation of calibration techniques for imbalanced data","volume":"8","author":"Huang","year":"2020","journal-title":"IEEE Access"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.cali.2017.01.004","article-title":"An\u00e1lisis del coste econ\u00f3mico del absentismo de pacientes en consultas externas","volume":"32","author":"Jabalera Mesa","year":"2017","journal-title":"Rev. Calidad Asistencial"},{"key":"ref23","article-title":"Smooth isotonic regression: a new method to calibrate predictive models","author":"Jiang","year":"2011"},{"key":"ref24","author":"Joseph","year":"2019"},{"key":"ref25","author":"Joseph","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.procs.2022.12.026","article-title":"Machine learning for prediction of wait times in outpatient clinic","volume":"215","author":"Joseph","year":"2022","journal-title":"Proc. Comput. Sci."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e0288540","DOI":"10.1371\/journal.pone.0288540","article-title":"Optimal selection of resampling methods for imbalanced data with high complexity","volume":"18","author":"Kim","year":"2023","journal-title":"PLoS One"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1177\/1932296815614866","article-title":"Machine-learning-based prediction of a missed scheduled clinical appointment by patients with diabetes","volume":"10","author":"Kurasawa","year":"2015","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1111\/j.1540-5915.2007.00158.x","article-title":"Clinic overbooking to improve patient access and increase provider productivity","volume":"38","author":"LaGanga","year":"2007","journal-title":"Decis. Sci."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/1472-6963-5-51","article-title":"Predictors of failed attendances in a multi-specialty outpatient Centre using electronic databases","volume":"5","author":"Lee","year":"2005","journal-title":"BMC Health Serv. Res."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.puhe.2007.01.007","article-title":"Missed appointments at a Swiss university outpatient clinic","volume":"121","author":"Lehmann","year":"2007","journal-title":"Public Health"},{"key":"ref32","author":"Lin","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1038\/s41746-022-00594-w","article-title":"Machine learning approaches to predicting no-shows in pediatric medical appointment","volume":"5","author":"Liu","year":"2022","journal-title":"NPJ Digit. Med."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"215013271881169","DOI":"10.1177\/2150132718811692","article-title":"Data analytics and modeling for appointment no-show in community health centers","volume":"9","author":"Mohammadi","year":"2018","journal-title":"J. Prim. Care Community Health"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3109\/17538157.2014.965303","article-title":"Large-scale assessment of missed opportunity risks in a complex hospital setting","volume":"41","author":"Peng","year":"2014","journal-title":"Inform. Health Soc. Care"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"507","DOI":"10.3390\/info13110507","article-title":"No-show in medical appointments with machine learning techniques: a systematic literature review","volume":"13","author":"Salazar","year":"2022","journal-title":"Information"},{"key":"ref37","author":"Samorani","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.invent.2018.06.002","article-title":"Using text message reminders in health care services: a narrative literature review","volume":"13","author":"Schwebel","year":"2018","journal-title":"Internet Interv."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TSMCA.2009.2029559","article-title":"RUSBoost: a hybrid approach to alleviating class imbalance","volume":"40","author":"Seiffert","year":"2010","journal-title":"IEEE Trans. Syst. Man Cybern. Syst. Hum."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: deep learning is not all you need","volume":"81","author":"Shwartz-Ziv","year":"2022","journal-title":"Inform. Fusion"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10994-013-5422-z","article-title":"An instance level analysis of data complexity","volume":"95","author":"Smith","year":"2013","journal-title":"Springer Mach. Learn."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"968319","DOI":"10.3389\/fpubh.2023.968319","article-title":"Exploring potential barriers in equitable access to pediatric diagnostic imaging using machine learning","volume":"11","author":"Taheri-Shirazi","year":"2023","journal-title":"Front. Public Health"},{"key":"ref43","first-page":"263","article-title":"New-patient no-shows in an urban family practice center: analysis and intervention","volume":"22","author":"Vikander","year":"1986","journal-title":"J Fam Pract."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1080\/07370016.2018.1555315","article-title":"Evaluating patient navigation to improve first appointment no-show rates in uninsured patients with diabetes","volume":"36","author":"Weaver","year":"2019","journal-title":"J. Community Health Nurs."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"2252","DOI":"10.1002\/cncr.32043","article-title":"Effectiveness of a short message service intervention to motivate people with positive results in preliminary colorectal cancer screening to undergo colonoscopy: a randomized controlled trial","volume":"125","author":"Wu","year":"2019","journal-title":"Cancer"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1652397\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T05:38:40Z","timestamp":1756877920000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1652397\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,3]]},"references-count":45,"alternative-id":["10.3389\/frai.2025.1652397"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1652397","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,3]]},"article-number":"1652397"}}