{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:11:10Z","timestamp":1775146270091,"version":"3.50.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"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>Background<\/jats:title><jats:p>The Department of Rehabilitation Medicine is key to improving patients\u2019 quality of life. Driven by chronic diseases and an aging population, there is a need to enhance the efficiency and resource allocation of outpatient facilities. This study aims to analyze the treatment preferences of outpatient rehabilitation patients by using data and a grading tool to establish predictive models. The goal is to improve patient visit efficiency and optimize resource allocation through these predictive models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Data were collected from 38 Chinese institutions, including 4,244 patients visiting outpatient rehabilitation clinics. Data processing was conducted using Python software. The pandas library was used for data cleaning and preprocessing, involving 68 categorical and 12 continuous variables. The steps included handling missing values, data normalization, and encoding conversion. The data were divided into 80% training and 20% test sets using the Scikit-learn library to ensure model independence and prevent overfitting. Performance comparisons among XGBoost, random forest, and logistic regression were conducted using metrics, including accuracy and receiver operating characteristic (ROC) curves. The imbalanced learning library\u2019s SMOTE technique was used to address the sample imbalance during model training. The model was optimized using a confusion matrix and feature importance analysis, and partial dependence plots (PDP) were used to analyze the key influencing factors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>XGBoost achieved the highest overall accuracy of 80.21% with high precision and recall in Category 1. random forest showed a similar overall accuracy. Logistic Regression had a significantly lower accuracy, indicating difficulties with nonlinear data. The key influencing factors identified include distance to medical institutions, arrival time, length of hospital stay, and specific diseases, such as cardiovascular, pulmonary, oncological, and orthopedic conditions. The tiered diagnosis and treatment tool effectively helped doctors assess patients\u2019 conditions and recommend suitable medical institutions based on rehabilitation grading.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study confirmed that ensemble learning methods, particularly XGBoost, outperform single models in classification tasks involving complex datasets. Addressing class imbalance and enhancing feature engineering can further improve model performance. Understanding patient preferences and the factors influencing medical institution selection can guide healthcare policies to optimize resource allocation, improve service quality, and enhance patient satisfaction. Tiered diagnosis and treatment tools play a crucial role in helping doctors evaluate patient conditions and make informed recommendations for appropriate medical care.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1473837","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T14:27:18Z","timestamp":1736951238000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Prediction of outpatient rehabilitation patient preferences and optimization of graded diagnosis and treatment based on XGBoost machine learning algorithm"],"prefix":"10.3389","volume":"7","author":[{"given":"Xuehui","family":"Fan","sequence":"first","affiliation":[]},{"given":"Ruixue","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Kaiwen","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jingpu","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Yulong","family":"Wang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"iii91","DOI":"10.1093\/heapol\/czx118","article-title":"From bouncing back, to nurturing emergence: reframing the concept of resilience in health systems strengthening","volume":"32","author":"Barasa","year":"2017","journal-title":"Health Policy Plan."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1377\/hlthaff.2014.0041","article-title":"Big data in health care: using analytics to identify and manage high-risk and high-cost patients","volume":"33","author":"Bates","year":"2014","journal-title":"Health Aff. (Millwood)"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1016\/j.ajodo.2023.09.011","article-title":"Decision trees and random forests","volume":"164","author":"Becker","year":"2023","journal-title":"Am. J. Orthod. Dentofacial Orthop."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/s12939-024-02158-8","article-title":"Does supplemental private health insurance impact health care utilization and seeking behavior of residents covered by social health insurance? Evidence from China National Health Services Survey","volume":"23","author":"Bie","year":"2024","journal-title":"Int. J. Equity Health"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","article-title":"SMOTE for high-dimensional class-imbalanced data","volume":"14","author":"Blagus","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"eaat9644","DOI":"10.1126\/science.aat9644","article-title":"The promise and peril of universal health care","volume":"361","author":"Bloom","year":"2018","journal-title":"Science"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1111\/jpm.12985","article-title":"The experience of healthcare professionals implementing recovery-oriented practice in mental health inpatient units: a qualitative evidence synthesis","volume":"31","author":"Chatwiriyaphong","year":"2024","journal-title":"J. Psychiatr. Ment. Health Nurs."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e13484","DOI":"10.2196\/13484","article-title":"Use and understanding of anonymization and de-identification in the biomedical literature: scoping review","volume":"21","author":"Chevrier","year":"2019","journal-title":"J. Med. Internet Res."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1276232","DOI":"10.3389\/fonc.2023.1276232","article-title":"Machine learning algorithms to uncover risk factors of breast cancer: insights from a large case-control study","volume":"13","author":"Dianati-Nasab","year":"2023","journal-title":"Front. Oncol."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"S26","DOI":"10.1046\/j.1525-1497.1999.00267.x","article-title":"The doctor-patient relationship: challenges, opportunities, and strategies","author":"Dorr Goold","year":"1999","journal-title":"J. Gen. Intern. Med."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1016\/j.jtcvs.2023.11.040","article-title":"Lung resection after initial nonoperative treatment for non-small cell lung cancer","volume":"168","author":"Dunne","year":"2023","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1257\/jep.7.4.135","article-title":"Supply-side and demand-side cost sharing in health care","volume":"7","author":"Ellis","year":"1993","journal-title":"J. Econ. Perspect."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1061507","DOI":"10.3389\/fendo.2022.1061507","article-title":"Implementation of five machine learning methods to predict the 52-week blood glucose level in patients with type 2 diabetes","volume":"13","author":"Fu","year":"2022","journal-title":"Front. Endocrinol. (Lausanne)"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1326272","DOI":"10.3389\/fpubh.2024.1326272","article-title":"Factors associated with patients' healthcare-seeking behavior and related clinical outcomes under China's hierarchical healthcare delivery system","volume":"12","author":"Guo","year":"2024","journal-title":"Front. Public Health"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","article-title":"Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost","volume":"18","author":"Hou","year":"2020","journal-title":"J. Transl. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial intelligence in healthcare: past, present and future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc. Neurol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.sapharm.2023.02.005","article-title":"Evaluation of the association between health insurance status and healthcare utilization and expenditures among adult cancer survivors in the United States","volume":"19","author":"Kamat","year":"2023","journal-title":"Res. Social Adm. Pharm."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e013059","DOI":"10.1136\/bmjopen-2016-013059","article-title":"Are differences in travel time or distance to healthcare for adults in global north countries associated with an impact on health outcomes? A systematic review","volume":"6","author":"Kelly","year":"2016","journal-title":"BMJ Open"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1370\/afm.68","article-title":"Referral of patients to specialists: factors affecting choice of specialist by primary care physicians","volume":"2","author":"Kinchen","year":"2004","journal-title":"Ann. Fam. Med."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1016\/S0140-6736(18)31668-4","article-title":"Mortality due to low-quality health systems in the universal health coverage era: a systematic analysis of amenable deaths in 137 countries","volume":"392","author":"Kruk","year":"2018","journal-title":"Lancet"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e016242","DOI":"10.1136\/bmjopen-2017-016242","article-title":"Telehealth and patient satisfaction: a systematic review and narrative analysis","volume":"7","author":"Kruse","year":"2017","journal-title":"BMJ Open"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"602","DOI":"10.2471\/BLT.12.113985","article-title":"Health financing for universal coverage and health system performance: concepts and implications for policy","volume":"91","author":"Kutzin","year":"2013","journal-title":"Bull. World Health Organ."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"335","DOI":"10.3390\/healthcare10020335","article-title":"The service capability of primary health institutions under the hierarchical medical system","volume":"10","author":"Liu","year":"2022","journal-title":"Healthcare (Basel)"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/s13054-024-04860-z","article-title":"Use of artificial intelligence in critical care: opportunities and obstacles","volume":"28","author":"Pinsky","year":"2024","journal-title":"Crit. Care"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.1056\/NEJMp1011024","article-title":"What is value in health care?","volume":"363","author":"Porter","year":"2010","journal-title":"N. Engl. J. Med."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1186\/s12875-019-1060-2","article-title":"To what degree do patients actively choose their healthcare provider at the point of referral by their GP? A video observation study","volume":"20","author":"Potappel","year":"2019","journal-title":"BMC Fam. Pract."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1186\/s12913-021-06140-w","article-title":"The effectiveness of different patient referral systems to shorten waiting times for elective surgeries: systematic review","volume":"21","author":"Rathnayake","year":"2021","journal-title":"BMC Health Serv. Res."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1005168","DOI":"10.3389\/fresc.2022.1005168","article-title":"Machine learning predicts improvement of functional outcomes in traumatic brain injury patients after inpatient rehabilitation","volume":"3","author":"Say","year":"2022","journal-title":"Front. Rehabil. Sci."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1213\/ANE.0000000000005247","article-title":"Logistic regression in medical research","volume":"132","author":"Schober","year":"2021","journal-title":"Anesth. Analg."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.eswa.2019.05.028","article-title":"A comparison of random forest variable selection methods for classification prediction modeling","volume":"134","author":"Speiser","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/S1474-4422(19)30415-6","article-title":"Advances and challenges in stroke rehabilitation","volume":"19","author":"Stinear","year":"2020","journal-title":"Lancet Neurol."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1016\/j.spinee.2021.02.024","article-title":"Decision curve analysis to evaluate the clinical benefit of prediction models","volume":"21","author":"Vickers","year":"2021","journal-title":"Spine J."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1186\/1472-6963-12-272","article-title":"Determinants of patient choice of healthcare providers: a scoping review","volume":"12","author":"Victoor","year":"2012","journal-title":"BMC Health Serv. Res."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1177\/0269215519846543","article-title":"User testing of the psychometric properties of pictorial-based disability assessment Longshi scale by healthcare professionals and non-professionals: a Chinese study in Shenzhen","volume":"33","author":"Wang","year":"2019","journal-title":"Clin. Rehabil."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.healthplace.2004.02.003","article-title":"Assessing spatial and nonspatial factors for healthcare access: towards an integrated approach to defining health professional shortage areas","volume":"11","author":"Wang","year":"2005","journal-title":"Health Place"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.socscimed.2018.05.023","article-title":"Spatial accessibility of primary health care in China: a case study in Sichuan Province","volume":"209","author":"Wang","year":"2018","journal-title":"Soc. Sci. Med."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"2696","DOI":"10.1021\/acs.jcim.2c00485","article-title":"Delta machine learning to improve scoring-ranking-screening performances of protein-ligand scoring functions","volume":"62","author":"Yang","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1378\/chest.07-2134","article-title":"Mortality rates for patients with acute lung injury\/ARDS have decreased over time","volume":"133","author":"Zambon","year":"2008","journal-title":"Chest"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"e0144809","DOI":"10.1371\/journal.pone.0144809","article-title":"Study on equity and efficiency of health resources and services based on key indicators in China","volume":"10","author":"Zhang","year":"2015","journal-title":"PLoS One"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1473837\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T14:27:23Z","timestamp":1736951243000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1473837\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":42,"alternative-id":["10.3389\/frai.2024.1473837"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1473837","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"article-number":"1473837"}}