Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

An interpretable machine learning tool for rheumatoid arthritis screening: integrating novel cellular morphological parameters with routine blood count indices.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: An interpretable machine learning tool for rheumatoid arthritis screening: integrating novel cellular morphological parameters with routine blood count indices.
Συγγραφείς: You L; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China., Li X; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China., Luo R; Department of Hospital Infection Management, West China Hospital, Sichuan University, Chengdu, China., Peng C; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China., Liu Q; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China., Sun R; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China., Zhang N; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China., Hou J; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China., Yang B; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China. yangbinhx@scu.edu.cn.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China. yangbinhx@scu.edu.cn.
Πηγή: Clinical rheumatology [Clin Rheumatol] 2026 Jun; Vol. 45 (6), pp. 3181-3194. Date of Electronic Publication: 2026 Apr 13.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Springer Country of Publication: Germany NLM ID: 8211469 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1434-9949 (Electronic) Linking ISSN: 07703198 NLM ISO Abbreviation: Clin Rheumatol Subsets: MEDLINE
Imprint Name(s): Publication: <2008->: Heidelberg : Springer
Original Publication: Brussels : Acta Medica Belgica, [1982-
Ιατρικοί όροι (MeSH): Arthritis, Rheumatoid*/diagnosis , Arthritis, Rheumatoid*/blood , Boosting Machine Learning Algorithms*, Biomarkers/blood ; Adult ; Female ; Humans ; Male ; Middle Aged ; Area Under Curve ; Blood Cell Count ; Predictive Learning Models ; Retrospective Studies ; Sensitivity and Specificity
Περίληψη: Background: Rheumatoid arthritis (RA) is a chronic autoimmune disease that can cause significant disability. Early detection is vital for improving outcomes, but current diagnostic methods are costly and lack accessibility for wide-scale screening. While routine blood cell parameters are promising, novel cellular morphological indices (e.g., NE-SFL, LY-Y) remain under-explored for RA screening. This study aimed to develop a machine learning model for RA screening by integrating novel morphological with routine blood parameters.
Methods: This retrospective study analyzed 43 blood cell parameters from 3009 participants. Feature selection used multiple machine learning (ML) algorithms, and eight predictive models were developed. Performance was evaluated on an independent test set via AUC, accuracy, sensitivity, specificity, calibration, and decision curve analysis. Model interpretability was provided by SHapley Additive exPlanations (SHAP).
Results: Seven key predictors were identified. The XGBoost model performed best, achieving an AUC of 0.929, accuracy of 0.890, sensitivity of 0.774, and specificity of 0.915 on the test set. SHAP analysis showed that novel cellular morphological parameters were the primary predictive drivers, exceeding some traditional inflammatory markers.
Conclusion: We developed and validated a high-performance, interpretable ML model using blood parameters to identify individuals at high risk for RA. The results highlight the significant value of novel morphological parameters for RA screening. An accompanying online tool offers a feasible, low-cost solution for non-invasive RA screening in primary care settings. Key Points •Focus on RA screening: The model is designed specifically for screening and risk stratification of RA where timely intervention is most critical. •High performance with routine data: Using only seven readily available blood parameters, our XGBoost model achieved an AUC of 0.929 on an independent test set, demonstrating performance comparable to more complex or costly modalities •Translational readiness: We have operationalized this model into a freely accessible online tool, enabling immediate clinical use. This tool can serve as an efficient "pre-screening filter" in routine health checks, guiding the referral of high-risk individuals for specialist evaluation and confirmatory testing (e.g., anti-CCP, imaging). •Interpretability for clinical trust: We employed SHAP analysis to ensure model transparency, explaining both global feature importance and individual predictions. This interpretability is crucial for fostering clinician adoption and understanding the biological underpinnings of the predictions, such as the prominent role of cellular morphological parameters like LY-Y and NE-SFL.
(© 2026. The Author(s), under exclusive licence to International League of Associations for Rheumatology (ILAR).)
Competing Interests: Declarations. Ethics approval: Ethical approval for this study was granted by the ethics committee of West China Tianfu Hospital, Sichuan University (Approval No: 20250015). Disclosures: None.
References: Finckh A, Gilbert B, Hodkinson B et al (2022) Global epidemiology of rheumatoid arthritis. Nat Rev Rheumatol 18(10):591–602. (PMID: 36068354)
van Mulligen E, Rutten-van Molken M, van der Helm-van Mil A (2024) Early identification of rheumatoid arthritis: does it induce treatment-related cost savings? Ann Rheum Dis 83(12):1647–1656. (PMID: 10.1136/ard-2024-22574639019569)
Aletaha D, Neogi T, Silman AJ et al (2010) 2010 rheumatoid arthritis classification criteria: an American College of Rheumatology/European League Against Rheumatism collaborative initiative. Ann Rheum Dis 69(9):1580–1588. (PMID: 10.1136/ard.2010.13846120699241)
Bugatti S, De Stefano L, Gandolfo S, Ciccia F, Montecucco C (2023) Autoantibody-negative rheumatoid arthritis: still a challenge for the rheumatologist. Lancet Rheumatol 5(12):e743–e755. (PMID: 10.1016/S2665-9913(23)00242-438251565)
Ke J, Qiu F, Fan W, Wei S (2023) Associations of complete blood cell count-derived inflammatory biomarkers with asthma and mortality in adults: a population-based study. Front Immunol 14:1205687. (PMID: 10.3389/fimmu.2023.12056873757525110416440)
Briciu V, Leucuta DC, Muntean M et al (2025) Differences in the inflammatory response and outcome among hospitalized patients during different waves of the COVID-19 pandemic. Front Immunol 16:1545181. (PMID: 10.3389/fimmu.2025.15451814021356011983512)
Lv J, Li J, Ren X, Huang Q, Deng S (2025) Machine learning for discriminating microcytic hypochromic anemia based on erythrocyte parameters. Int J Lab Hematol. https://doi.org/10.1111/ijlh.14524. (PMID: 10.1111/ijlh.1452440590058)
Jin L, Li L, Lu Y, Cai G, Lin L, Lin J (2025) Development and validation of a user-friendly predictive model using demographic and complete blood count data to facilitate early diagnosis on suspicion of myeloproliferative neoplasms. Int J Lab Hematol. https://doi.org/10.1111/ijlh.14452. (PMID: 10.1111/ijlh.1445240931321)
Shimoni Z, Froom P, Benbassat J (2022) Parameters of the complete blood count predict in hospital mortality. Int J Lab Hematol 44(1):88–95. (PMID: 10.1111/ijlh.1368434464032)
Mercan R, Bitik B, Tufan A et al (2016) The association between neutrophil/lymphocyte ratio and disease activity in rheumatoid arthritis and ankylosing spondylitis. J Clin Lab Anal 30(5):597–601. (PMID: 10.1002/jcla.2190826666737)
Lappe JM, Horne BD, Shah SH et al (2011) Red cell distribution width, C-reactive protein, the complete blood count, and mortality in patients with coronary disease and a normal comparison population. Clin Chim Acta 412(23–24):2094–2099. (PMID: 10.1016/j.cca.2011.07.01821821014)
Ozturk ZA, Unal A, Yigiter R et al (2013) Is increased red cell distribution width (RDW) indicating the inflammation in Alzheimer’s disease (AD)? Arch Gerontol Geriatr 56(1):50–54. (PMID: 10.1016/j.archger.2012.10.00223103090)
Agnello L, Giglio RV, Bivona G et al (2021) The value of a complete blood count (CBC) for sepsis diagnosis and prognosis. Diagnostics. https://doi.org/10.3390/diagnostics11101881. (PMID: 10.3390/diagnostics11101881349435768700711)
Urrechaga E (2020) Reviewing the value of leukocytes cell population data (CPD) in the management of sepsis. Ann Transl Med 8(15):953. (PMID: 10.21037/atm-19-3173329537537475430)
Shi Y, Zhou M, Chang C et al (2024) Advancing precision rheumatology: applications of machine learning for rheumatoid arthritis management. Front Immunol 15:1409555. (PMID: 10.3389/fimmu.2024.14095553891540811194317)
Kedra J, Davergne T, Braithwaite B, Servy H, Gossec L (2021) Machine learning approaches to improve disease management of patients with rheumatoid arthritis: review and future directions. Expert Rev Clin Immunol 17(12):1311–1321. (PMID: 10.1080/1744666X.2022.201777334890271)
Wang J, Tian Y, Zhou T, Tong D, Ma J, Li J (2023) A survey of artificial intelligence in rheumatoid arthritis. Rheumatol Immunol Res 4(2):69–77. (PMID: 10.2478/rir-2023-00113748547610362600)
Bertke S, Hein M, Schubauer-Berigan M, Deddens J (2013) A simulation study of relative efficiency and bias in the nested case-control study design. Epidemiol Methods 2(1):85–93. (PMID: 10.1515/em-2013-0007263455804558410)
Bai L, Zhang Y, Wang P, Zhu X, Xiong JW, Cui L (2022) Improved diagnosis of rheumatoid arthritis using an artificial neural network. Sci Rep 12(1):9810. (PMID: 10.1038/s41598-022-13750-9356977549192742)
Bishop EL, Gudgeon N, Fulton-Ward T, et al (2024) TNF-alpha signals through ITK-Akt-mTOR to drive CD4(+) T cell metabolic reprogramming, which is dysregulated in rheumatoid arthritis. Sci Signal 17(833):eadg5678.
Jing W, Liu C, Su C et al (2023) Role of reactive oxygen species and mitochondrial damage in rheumatoid arthritis and targeted drugs. Front Immunol 14:1107670. (PMID: 10.3389/fimmu.2023.1107670368451279948260)
Fresneda Alarcon M, Abdullah GA, Beggs JA et al (2025) Complexity of the neutrophil transcriptome in early and severe rheumatoid arthritis: a role for microRNAs? J Leukoc Biol. https://doi.org/10.1093/jleuko/qiaf090. (PMID: 10.1093/jleuko/qiaf0904059036312210129)
Zhang L, Yuan Y, Xu Q, Jiang Z, Chu CQ (2019) Contribution of neutrophils in the pathogenesis of rheumatoid arthritis. J Biomed Res 34(2):86–93. (PMID: 10.7555/JBR.33.20190075323059627183296)
Kaundal U, Khullar A, Leishangthem B et al (2021) The effect of methotrexate on neutrophil reactive oxygen species and CD177 expression in rheumatoid arthritis. Clin Exp Rheumatol 39(3):479–486. (PMID: 10.55563/clinexprheumatol/4h5onh32573414)
Song CS, Park DI, Yoon MY et al (2012) Association between red cell distribution width and disease activity in patients with inflammatory bowel disease. Dig Dis Sci 57(4):1033–1038. (PMID: 10.1007/s10620-011-1978-222147246)
Ku NS, Kim HW, Oh HJ et al (2012) Red blood cell distribution width is an independent predictor of mortality in patients with gram-negative bacteremia. Shock 38(2):123–127. (PMID: 10.1097/SHK.0b013e31825e2a8522683729)
Jin Z, Cai G, Zhang P et al (2021) The value of the neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio as complementary diagnostic tools in the diagnosis of rheumatoid arthritis: a multicenter retrospective study. J Clin Lab Anal 35(1):e23569. (PMID: 10.1002/jcla.2356932951253)
Mc Ardle A, Kwasnik A, Szentpetery A et al (2022) Identification and evaluation of serum protein biomarkers that differentiate psoriatic arthritis from rheumatoid arthritis. Arthritis Rheumatol 74(1):81–91. (PMID: 10.1002/art.4189934114357)
Grant Information: 82372322 National Natural Science Foundation of China; 82572640 National Natural Science Foundation of China
Contributed Indexing: Keywords: Blood cell population parameters; Machine learning; Rheumatoid arthritis; SHAP; Screening; XGBoost
Substance Nomenclature: 0 (Biomarkers)
Entry Date(s): Date Created: 20260413 Date Completed: 20260612 Latest Revision: 20260618
Update Code: 20260618
DOI: 10.1007/s10067-026-08115-w
PMID: 41973142
Βάση Δεδομένων: MEDLINE
FullText Links:
  – Type: other
    Url: https://resolver.ebsco.com:443/public/rma-ftfapi/ejs/direct?AccessToken=4CFB8BCDBFFAB8286524&Show=Object
Text:
  Availability: 0
CustomLinks:
  – Url: https://dx.doi.org/doi:10.1007/s10067-026-08115-w
    Name: EDS - Springer Nature Journals (s7799221)
    Category: fullText
    Text: View record at Springer
Header DbId: cmedm
DbLabel: MEDLINE
An: 41973142
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An interpretable machine learning tool for rheumatoid arthritis screening: integrating novel cellular morphological parameters with routine blood count indices.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22You+L%22&quot;&gt;You L&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Li+X%22&quot;&gt;Li X&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Luo+R%22&quot;&gt;Luo R&lt;/searchLink&gt;; Department of Hospital Infection Management, West China Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Peng+C%22&quot;&gt;Peng C&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Liu+Q%22&quot;&gt;Liu Q&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Sun+R%22&quot;&gt;Sun R&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Zhang+N%22&quot;&gt;Zhang N&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Hou+J%22&quot;&gt;Hou J&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China.&lt;br /&gt;&lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Yang+B%22&quot;&gt;Yang B&lt;/searchLink&gt;; Department of Laboratory Medicine, West China Tianfu Hospital, Sichuan University, Chengdu, China. yangbinhx@scu.edu.cn.; Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, China. yangbinhx@scu.edu.cn.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%228211469%22&quot;&gt;Clinical rheumatology&lt;/searchLink&gt; [Clin Rheumatol] 2026 Jun; Vol. 45 (6), pp. 3181-3194. &lt;i&gt;Date of Electronic Publication: &lt;/i&gt;2026 Apr 13.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: &lt;i&gt;Publisher: &lt;/i&gt;&lt;searchLink fieldCode=&quot;PB&quot; term=&quot;%22Springer%22&quot;&gt;Springer &lt;/searchLink&gt;&lt;i&gt;Country of Publication: &lt;/i&gt;Germany &lt;i&gt;NLM ID: &lt;/i&gt;8211469 &lt;i&gt;Publication Model: &lt;/i&gt;Print-Electronic &lt;i&gt;Cited Medium: &lt;/i&gt;Internet &lt;i&gt;ISSN: &lt;/i&gt;1434-9949 (Electronic) &lt;i&gt;Linking ISSN: &lt;/i&gt;&lt;searchLink fieldCode=&quot;IS&quot; term=&quot;%2207703198%22&quot;&gt;07703198 &lt;/searchLink&gt;&lt;i&gt;NLM ISO Abbreviation: &lt;/i&gt;Clin Rheumatol &lt;i&gt;Subsets: &lt;/i&gt;MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: &lt;i&gt;Publication&lt;/i&gt;: &lt;2008-&gt;: Heidelberg : Springer&lt;br /&gt;&lt;i&gt;Original Publication&lt;/i&gt;: Brussels : Acta Medica Belgica, [1982-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Arthritis%2C+Rheumatoid%22&quot;&gt;Arthritis, Rheumatoid*&lt;/searchLink&gt;/&lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Arthritis%2C+Rheumatoid+diagnosis%22&quot;&gt;diagnosis&lt;/searchLink&gt; &lt;br /&gt;&lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Arthritis%2C+Rheumatoid%22&quot;&gt;Arthritis, Rheumatoid*&lt;/searchLink&gt;/&lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Arthritis%2C+Rheumatoid+blood%22&quot;&gt;blood&lt;/searchLink&gt; &lt;br /&gt;&lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Boosting+Machine+Learning+Algorithms%22&quot;&gt;Boosting Machine Learning Algorithms*&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Biomarkers%22&quot;&gt;Biomarkers&lt;/searchLink&gt;/&lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Biomarkers+blood%22&quot;&gt;blood&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Adult%22&quot;&gt;Adult&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Female%22&quot;&gt;Female&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Humans%22&quot;&gt;Humans&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Male%22&quot;&gt;Male&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Middle+Aged%22&quot;&gt;Middle Aged&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Area+Under+Curve%22&quot;&gt;Area Under Curve&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Blood+Cell+Count%22&quot;&gt;Blood Cell Count&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Predictive+Learning+Models%22&quot;&gt;Predictive Learning Models&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Retrospective+Studies%22&quot;&gt;Retrospective Studies&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Sensitivity+and+Specificity%22&quot;&gt;Sensitivity and Specificity&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Rheumatoid arthritis (RA) is a chronic autoimmune disease that can cause significant disability. Early detection is vital for improving outcomes, but current diagnostic methods are costly and lack accessibility for wide-scale screening. While routine blood cell parameters are promising, novel cellular morphological indices (e.g., NE-SFL, LY-Y) remain under-explored for RA screening. This study aimed to develop a machine learning model for RA screening by integrating novel morphological with routine blood parameters.&lt;br /&gt;Methods: This retrospective study analyzed 43 blood cell parameters from 3009 participants. Feature selection used multiple machine learning (ML) algorithms, and eight predictive models were developed. Performance was evaluated on an independent test set via AUC, accuracy, sensitivity, specificity, calibration, and decision curve analysis. Model interpretability was provided by SHapley Additive exPlanations (SHAP).&lt;br /&gt;Results: Seven key predictors were identified. The XGBoost model performed best, achieving an AUC of 0.929, accuracy of 0.890, sensitivity of 0.774, and specificity of 0.915 on the test set. SHAP analysis showed that novel cellular morphological parameters were the primary predictive drivers, exceeding some traditional inflammatory markers.&lt;br /&gt;Conclusion: We developed and validated a high-performance, interpretable ML model using blood parameters to identify individuals at high risk for RA. The results highlight the significant value of novel morphological parameters for RA screening. An accompanying online tool offers a feasible, low-cost solution for non-invasive RA screening in primary care settings. Key Points •Focus on RA screening: The model is designed specifically for screening and risk stratification of RA where timely intervention is most critical. •High performance with routine data: Using only seven readily available blood parameters, our XGBoost model achieved an AUC of 0.929 on an independent test set, demonstrating performance comparable to more complex or costly modalities •Translational readiness: We have operationalized this model into a freely accessible online tool, enabling immediate clinical use. This tool can serve as an efficient &quot;pre-screening filter&quot; in routine health checks, guiding the referral of high-risk individuals for specialist evaluation and confirmatory testing (e.g., anti-CCP, imaging). •Interpretability for clinical trust: We employed SHAP analysis to ensure model transparency, explaining both global feature importance and individual predictions. This interpretability is crucial for fostering clinician adoption and understanding the biological underpinnings of the predictions, such as the prominent role of cellular morphological parameters like LY-Y and NE-SFL.&lt;br /&gt; (&#169; 2026. The Author(s), under exclusive licence to International League of Associations for Rheumatology (ILAR).)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Declarations. Ethics approval: Ethical approval for this study was granted by the ethics committee of West China Tianfu Hospital, Sichuan University (Approval No: 20250015). Disclosures: None.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Finckh A, Gilbert B, Hodkinson B et al (2022) Global epidemiology of rheumatoid arthritis. Nat Rev Rheumatol 18(10):591–602. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2236068354%22&quot;&gt;36068354)&lt;/searchLink&gt;&lt;br /&gt;van Mulligen E, Rutten-van Molken M, van der Helm-van Mil A (2024) Early identification of rheumatoid arthritis: does it induce treatment-related cost savings? Ann Rheum Dis 83(12):1647–1656. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1136%2Fard-2024-22574639019569%22&quot;&gt;10.1136/ard-2024-22574639019569)&lt;/searchLink&gt;&lt;br /&gt;Aletaha D, Neogi T, Silman AJ et al (2010) 2010 rheumatoid arthritis classification criteria: an American College of Rheumatology/European League Against Rheumatism collaborative initiative. Ann Rheum Dis 69(9):1580–1588. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1136%2Fard%2E2010%2E13846120699241%22&quot;&gt;10.1136/ard.2010.13846120699241)&lt;/searchLink&gt;&lt;br /&gt;Bugatti S, De Stefano L, Gandolfo S, Ciccia F, Montecucco C (2023) Autoantibody-negative rheumatoid arthritis: still a challenge for the rheumatologist. Lancet Rheumatol 5(12):e743–e755. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1016%2FS2665-9913%2823%2900242-438251565%22&quot;&gt;10.1016/S2665-9913(23)00242-438251565)&lt;/searchLink&gt;&lt;br /&gt;Ke J, Qiu F, Fan W, Wei S (2023) Associations of complete blood cell count-derived inflammatory biomarkers with asthma and mortality in adults: a population-based study. Front Immunol 14:1205687. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E3389%2Ffimmu%2E2023%2E12056873757525110416440%22&quot;&gt;10.3389/fimmu.2023.12056873757525110416440)&lt;/searchLink&gt;&lt;br /&gt;Briciu V, Leucuta DC, Muntean M et al (2025) Differences in the inflammatory response and outcome among hospitalized patients during different waves of the COVID-19 pandemic. Front Immunol 16:1545181. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E3389%2Ffimmu%2E2025%2E15451814021356011983512%22&quot;&gt;10.3389/fimmu.2025.15451814021356011983512)&lt;/searchLink&gt;&lt;br /&gt;Lv J, Li J, Ren X, Huang Q, Deng S (2025) Machine learning for discriminating microcytic hypochromic anemia based on erythrocyte parameters. Int J Lab Hematol. https://doi.org/10.1111/ijlh.14524. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1111%2Fijlh%2E1452440590058%22&quot;&gt;10.1111/ijlh.1452440590058)&lt;/searchLink&gt;&lt;br /&gt;Jin L, Li L, Lu Y, Cai G, Lin L, Lin J (2025) Development and validation of a user-friendly predictive model using demographic and complete blood count data to facilitate early diagnosis on suspicion of myeloproliferative neoplasms. Int J Lab Hematol. https://doi.org/10.1111/ijlh.14452. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1111%2Fijlh%2E1445240931321%22&quot;&gt;10.1111/ijlh.1445240931321)&lt;/searchLink&gt;&lt;br /&gt;Shimoni Z, Froom P, Benbassat J (2022) Parameters of the complete blood count predict in hospital mortality. Int J Lab Hematol 44(1):88–95. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1111%2Fijlh%2E1368434464032%22&quot;&gt;10.1111/ijlh.1368434464032)&lt;/searchLink&gt;&lt;br /&gt;Mercan R, Bitik B, Tufan A et al (2016) The association between neutrophil/lymphocyte ratio and disease activity in rheumatoid arthritis and ankylosing spondylitis. J Clin Lab Anal 30(5):597–601. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1002%2Fjcla%2E2190826666737%22&quot;&gt;10.1002/jcla.2190826666737)&lt;/searchLink&gt;&lt;br /&gt;Lappe JM, Horne BD, Shah SH et al (2011) Red cell distribution width, C-reactive protein, the complete blood count, and mortality in patients with coronary disease and a normal comparison population. Clin Chim Acta 412(23–24):2094–2099. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1016%2Fj%2Ecca%2E2011%2E07%2E01821821014%22&quot;&gt;10.1016/j.cca.2011.07.01821821014)&lt;/searchLink&gt;&lt;br /&gt;Ozturk ZA, Unal A, Yigiter R et al (2013) Is increased red cell distribution width (RDW) indicating the inflammation in Alzheimer’s disease (AD)? Arch Gerontol Geriatr 56(1):50–54. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1016%2Fj%2Earchger%2E2012%2E10%2E00223103090%22&quot;&gt;10.1016/j.archger.2012.10.00223103090)&lt;/searchLink&gt;&lt;br /&gt;Agnello L, Giglio RV, Bivona G et al (2021) The value of a complete blood count (CBC) for sepsis diagnosis and prognosis. Diagnostics. https://doi.org/10.3390/diagnostics11101881. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E3390%2Fdiagnostics11101881349435768700711%22&quot;&gt;10.3390/diagnostics11101881349435768700711)&lt;/searchLink&gt;&lt;br /&gt;Urrechaga E (2020) Reviewing the value of leukocytes cell population data (CPD) in the management of sepsis. Ann Transl Med 8(15):953. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E21037%2Fatm-19-3173329537537475430%22&quot;&gt;10.21037/atm-19-3173329537537475430)&lt;/searchLink&gt;&lt;br /&gt;Shi Y, Zhou M, Chang C et al (2024) Advancing precision rheumatology: applications of machine learning for rheumatoid arthritis management. Front Immunol 15:1409555. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E3389%2Ffimmu%2E2024%2E14095553891540811194317%22&quot;&gt;10.3389/fimmu.2024.14095553891540811194317)&lt;/searchLink&gt;&lt;br /&gt;Kedra J, Davergne T, Braithwaite B, Servy H, Gossec L (2021) Machine learning approaches to improve disease management of patients with rheumatoid arthritis: review and future directions. Expert Rev Clin Immunol 17(12):1311–1321. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1080%2F1744666X%2E2022%2E201777334890271%22&quot;&gt;10.1080/1744666X.2022.201777334890271)&lt;/searchLink&gt;&lt;br /&gt;Wang J, Tian Y, Zhou T, Tong D, Ma J, Li J (2023) A survey of artificial intelligence in rheumatoid arthritis. Rheumatol Immunol Res 4(2):69–77. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E2478%2Frir-2023-00113748547610362600%22&quot;&gt;10.2478/rir-2023-00113748547610362600)&lt;/searchLink&gt;&lt;br /&gt;Bertke S, Hein M, Schubauer-Berigan M, Deddens J (2013) A simulation study of relative efficiency and bias in the nested case-control study design. Epidemiol Methods 2(1):85–93. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1515%2Fem-2013-0007263455804558410%22&quot;&gt;10.1515/em-2013-0007263455804558410)&lt;/searchLink&gt;&lt;br /&gt;Bai L, Zhang Y, Wang P, Zhu X, Xiong JW, Cui L (2022) Improved diagnosis of rheumatoid arthritis using an artificial neural network. Sci Rep 12(1):9810. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1038%2Fs41598-022-13750-9356977549192742%22&quot;&gt;10.1038/s41598-022-13750-9356977549192742)&lt;/searchLink&gt;&lt;br /&gt;Bishop EL, Gudgeon N, Fulton-Ward T, et al (2024) TNF-alpha signals through ITK-Akt-mTOR to drive CD4(+) T cell metabolic reprogramming, which is dysregulated in rheumatoid arthritis. Sci Signal 17(833):eadg5678.&lt;br /&gt;Jing W, Liu C, Su C et al (2023) Role of reactive oxygen species and mitochondrial damage in rheumatoid arthritis and targeted drugs. Front Immunol 14:1107670. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E3389%2Ffimmu%2E2023%2E1107670368451279948260%22&quot;&gt;10.3389/fimmu.2023.1107670368451279948260)&lt;/searchLink&gt;&lt;br /&gt;Fresneda Alarcon M, Abdullah GA, Beggs JA et al (2025) Complexity of the neutrophil transcriptome in early and severe rheumatoid arthritis: a role for microRNAs? J Leukoc Biol. https://doi.org/10.1093/jleuko/qiaf090. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1093%2Fjleuko%2Fqiaf0904059036312210129%22&quot;&gt;10.1093/jleuko/qiaf0904059036312210129)&lt;/searchLink&gt;&lt;br /&gt;Zhang L, Yuan Y, Xu Q, Jiang Z, Chu CQ (2019) Contribution of neutrophils in the pathogenesis of rheumatoid arthritis. J Biomed Res 34(2):86–93. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E7555%2FJBR%2E33%2E20190075323059627183296%22&quot;&gt;10.7555/JBR.33.20190075323059627183296)&lt;/searchLink&gt;&lt;br /&gt;Kaundal U, Khullar A, Leishangthem B et al (2021) The effect of methotrexate on neutrophil reactive oxygen species and CD177 expression in rheumatoid arthritis. Clin Exp Rheumatol 39(3):479–486. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E55563%2Fclinexprheumatol%2F4h5onh32573414%22&quot;&gt;10.55563/clinexprheumatol/4h5onh32573414)&lt;/searchLink&gt;&lt;br /&gt;Song CS, Park DI, Yoon MY et al (2012) Association between red cell distribution width and disease activity in patients with inflammatory bowel disease. Dig Dis Sci 57(4):1033–1038. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1007%2Fs10620-011-1978-222147246%22&quot;&gt;10.1007/s10620-011-1978-222147246)&lt;/searchLink&gt;&lt;br /&gt;Ku NS, Kim HW, Oh HJ et al (2012) Red blood cell distribution width is an independent predictor of mortality in patients with gram-negative bacteremia. Shock 38(2):123–127. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1097%2FSHK%2E0b013e31825e2a8522683729%22&quot;&gt;10.1097/SHK.0b013e31825e2a8522683729)&lt;/searchLink&gt;&lt;br /&gt;Jin Z, Cai G, Zhang P et al (2021) The value of the neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio as complementary diagnostic tools in the diagnosis of rheumatoid arthritis: a multicenter retrospective study. J Clin Lab Anal 35(1):e23569. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1002%2Fjcla%2E2356932951253%22&quot;&gt;10.1002/jcla.2356932951253)&lt;/searchLink&gt;&lt;br /&gt;Mc Ardle A, Kwasnik A, Szentpetery A et al (2022) Identification and evaluation of serum protein biomarkers that differentiate psoriatic arthritis from rheumatoid arthritis. Arthritis Rheumatol 74(1):81–91. (PMID: &lt;searchLink fieldCode=&quot;PM&quot; term=&quot;%2210%2E1002%2Fart%2E4189934114357%22&quot;&gt;10.1002/art.4189934114357)&lt;/searchLink&gt;
– Name: GrantInfo
  Label: Grant Information
  Group: Grant
  Data: 82372322 National Natural Science Foundation of China; 82572640 National Natural Science Foundation of China
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: &lt;i&gt;Keywords: &lt;/i&gt;Blood cell population parameters; Machine learning; Rheumatoid arthritis; SHAP; Screening; XGBoost
– Name: NumberCAS
  Label: Substance Nomenclature
  Group: ID
  Data: 0 (Biomarkers)
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: &lt;i&gt;Date Created: &lt;/i&gt;20260413 &lt;i&gt;Date Completed: &lt;/i&gt;20260612 &lt;i&gt;Latest Revision: &lt;/i&gt;20260618
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260618
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1007/s10067-026-08115-w
– Name: AN
  Label: PMID
  Group: ID
  Data: 41973142
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=41973142
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10067-026-08115-w
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 3181
    Subjects:
      – SubjectFull: Biomarkers blood
        Type: general
      – SubjectFull: Adult
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: Middle Aged
        Type: general
      – SubjectFull: Area Under Curve
        Type: general
      – SubjectFull: Blood Cell Count
        Type: general
      – SubjectFull: Predictive Learning Models
        Type: general
      – SubjectFull: Retrospective Studies
        Type: general
      – SubjectFull: Sensitivity and Specificity
        Type: general
      – SubjectFull: Arthritis, Rheumatoid diagnosis
        Type: general
      – SubjectFull: Arthritis, Rheumatoid blood
        Type: general
      – SubjectFull: Boosting Machine Learning Algorithms
        Type: general
    Titles:
      – TitleFull: An interpretable machine learning tool for rheumatoid arthritis screening: integrating novel cellular morphological parameters with routine blood count indices.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: You L
      – PersonEntity:
          Name:
            NameFull: Li X
      – PersonEntity:
          Name:
            NameFull: Luo R
      – PersonEntity:
          Name:
            NameFull: Peng C
      – PersonEntity:
          Name:
            NameFull: Liu Q
      – PersonEntity:
          Name:
            NameFull: Sun R
      – PersonEntity:
          Name:
            NameFull: Zhang N
      – PersonEntity:
          Name:
            NameFull: Hou J
      – PersonEntity:
          Name:
            NameFull: Yang B
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: 2026 Jun
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1434-9949
          Numbering:
            – Type: volume
              Value: 45
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Clinical rheumatology
              Type: main
ResultId 1