{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T13:57:23Z","timestamp":1790517443221,"version":"4.1.0"},"reference-count":47,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100003093","name":"Ministry of Higher Education, Malaysia","doi-asserted-by":"publisher","award":["FRGS\/1\/2023\/ICT02\/USM\/02\/5"],"award-info":[{"award-number":["FRGS\/1\/2023\/ICT02\/USM\/02\/5"]}],"id":[{"id":"10.13039\/501100003093","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Technology and Health Care"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Assessment of Systemic Lupus Erythematosus (SLE) activity is complicated by clinical heterogeneity and data scarcity. Additionally, the \u201cblack-box\u201d nature of many machine learning models creates significant barriers to their adoption in reliable clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop an interpretable machine learning framework that transforms high-dimensional clinical data into a transparent scorecard for disease activity assessment, specifically addressing small-sample constraints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In a cohort of 104 female SLE patients, LASSO regression selected 14 robust predictors from 149 variables spanning immunological and hematological domains. Eleven machine learning algorithms were systematically evaluated using stratified five-fold cross-validation. The optimal base model was transformed into a disease activity scorecard using a dynamic binning strategy to capture nonlinear effects.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>While Random Forest achieved the highest test-set AUC (0.883) among standalone algorithms, Logistic Regression was selected for its superior stability (AUC: 0.867) and interpretability. The derived scorecard demonstrated strong discrimination on the hold-out internal test set (AUC: 0.917), with the highest observed AUC among the evaluated models. At an optimized threshold, it achieved balanced sensitivity (0.917) and high specificity (0.840), with key predictors aligning with established pathophysiology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Reliable prediction in data-limited settings can be achieved without sacrificing interpretability. The proposed framework provides an interpretable proof-of-concept decision-support tool for disease activity assessment in data-limited clinical settings. Although the proposed scorecard demonstrated promising performance on internal validation, prospective multi-center and external validation are required before routine clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/09287329261488670","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T02:07:37Z","timestamp":1790129257000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["A small-data machine learning framework with interpretable scorecards for disease activity assessment: A systemic lupus erythematosus case study"],"prefix":"10.1177","author":[{"given":"Kun","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-1691","authenticated-orcid":false,"given":"Nur Hana","family":"Samsudin","sequence":"additional","affiliation":[{"name":"School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Rheumatology and Immunology, Affiliated Hospital of Yangzhou University, Yangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1136\/lupus-2024-001456"},{"key":"e_1_3_3_3_2","first-page":"1934","article-title":"The Systemic Lupus Activity Measure-Revised, the Mexican Systemic Lupus Erythematosus Disease Activity Index (SLEDAI), and a Modified SLEDAI-2K are adequate instruments to measure disease activity in systemic lupus erythematosus","volume":"31","author":"Uribe AG","year":"2004","unstructured":"Uribe AG, Vil\u00e1 LM, McGwin G, et al. The Systemic Lupus Activity Measure-Revised, the Mexican Systemic Lupus Erythematosus Disease Activity Index (SLEDAI), and a Modified SLEDAI-2K are adequate instruments to measure disease activity in systemic lupus erythematosus. J Rheumatol. 2004; 31: 1934\u20131940.","journal-title":"J Rheumatol."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124518"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124074"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1177\/09612033221114805"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00011-023-01793-1"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.860726"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1413569"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2023.103294"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129948"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122178"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124742"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126904"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123987"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11092406"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.40930"},{"key":"e_1_3_3_18_2","first-page":"373","article-title":"The Systemic Lupus International Collaborating Clinics\/American College of Rheumatology (SLICC\/ACR) damage index for systemic lupus erythematosus international comparison","volume":"27","author":"Gladman DD","unstructured":"Gladman DD, Goldsmith CH, Urowitz MB, et al. The Systemic Lupus International Collaborating Clinics\/American College of Rheumatology (SLICC\/ACR) damage index for systemic lupus erythematosus international comparison. J Rheumatol [Internet] 2000 Feb; 27: 373\u2013376, http:\/\/europepmc.org\/abstract\/MED\/10685799.","journal-title":"J Rheumatol [Internet]"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf072"},{"key":"e_1_3_3_20_2","volume-title":"Applied logistic regression","author":"Hosmer DW","year":"1998","unstructured":"Hosmer DW, Lemeshow S. Applied logistic regression. Wiley-Interscience Publication, 1998."},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"e_1_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C. XGBoost: A scalable tree boosting system. In: ACM SIGKDD International conference on knowledge discovery and data mining. 2016 pp. 785\u201394. doi:10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_24_2","first-page":"3147","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"2017","author":"Ke G","year":"2017","unstructured":"Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 2017; 2017: 3147\u20133155.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-88615-2_4"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022643204877"},{"key":"e_1_3_3_28_2","first-page":"1","article-title":"Linear discriminant analysis","volume":"392","author":"Fisher EM.","year":"1936","unstructured":"Fisher EM. Linear discriminant analysis. Stat Discrete Methods Data Sci 1936; 392: 1\u20135.","journal-title":"Stat Discrete Methods Data Sci"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-443-36304-7.00018-9"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2024.101419"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3422319"},{"key":"e_1_3_3_33_2","first-page":"1","article-title":"Innovation and challenges of artificial intelligence technology in personalized healthcare","volume":"14","author":"Li YH","year":"2024","unstructured":"Li YH, Li YL, Wei MY, et al. Innovation and challenges of artificial intelligence technology in personalized healthcare. Sci Rep 2024; 14: 1\u20139.","journal-title":"Sci Rep"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102412"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02647-4"},{"key":"e_1_3_3_36_2","first-page":"6","article-title":"All models are wrong and yours are useless: making clinical prediction models impactful for patients","volume":"8","author":"Markowetz F.","year":"2024","unstructured":"Markowetz F. All models are wrong and yours are useless: making clinical prediction models impactful for patients. NPJ Precis Oncol 2024; 8: 6\u20138.","journal-title":"NPJ Precis Oncol"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11926-025-01193-w"},{"key":"e_1_3_3_38_2","first-page":"1","article-title":"Hyponatremia in patients with systemic lupus erythematosus","volume":"6","author":"Shin JI","year":"2016","unstructured":"Shin JI, Park SJ, Suh CH, et al. Hyponatremia in patients with systemic lupus erythematosus. Sci Rep 2016; 6: 1\u20137.","journal-title":"Sci Rep"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-025-03536-5"},{"key":"e_1_3_3_40_2","first-page":"113","article-title":"Study of serum complement 3 split product iC3b\/C3 ratio in a cohort of systemic lupus erythematosus patients","volume":"117","author":"Hosny SM","year":"2024","unstructured":"Hosny SM, Mohamed ES, Sayed Abd El Fattah MS. Study of serum complement 3 split product iC3b\/C3 ratio in a cohort of systemic lupus erythematosus patients. Int J Med (Dubai) 2024; 117: 113\u2013114.","journal-title":"Int J Med (Dubai)"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2024-eular.592"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ard.2025.07.028"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1080\/03009742.2024.2321700"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-024-03275-z"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2024.103721"},{"key":"e_1_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Leo G Edouard O Gael V. Why do tree-based models still outperform deep learning on typical tabular data?. In: NeurIPS Advances in Neural Information Processing Systems 2022 pp.507\u2013520. Neural Information Processing Systems.","DOI":"10.52202\/068431-0037"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1136\/lupus-2025-001696"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1686057"}],"container-title":["Technology and Health Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09287329261488670","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/09287329261488670","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09287329261488670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T13:18:10Z","timestamp":1790515090000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/09287329261488670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":47,"alternative-id":["10.1177\/09287329261488670"],"URL":"https:\/\/doi.org\/10.1177\/09287329261488670","relation":{},"ISSN":["0928-7329","1878-7401"],"issn-type":[{"value":"0928-7329","type":"print"},{"value":"1878-7401","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"article-number":"09287329261488670"}}