EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Incremental value of quantitative SPECT/CT integrated parameters in a multimodal machine-learning model for differentiating spinal tuberculosis from pyogenic spondylitis

Jiaxing Wang, Xingyu Duan, Jiong Wang, Mengqi Zhu, Yuxin Gao, Yingqin Jia, Qian Zhao, Ningkui Niu

Frontiers in Cellular and Infection Microbiology · 18.08.2026 · 16

DOI: 10.3389/fcimb.2026.1897479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Cellular and Infection Microbiology, online erschienen am 18.08.2026. Verfasst von Jiaxing Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedics, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China. Hauptthemen laut MEDLINE: Spondylitis, Machine Learning, Tuberculosis, Spinal, Single Photon Emission Computed Tomography Computed Tomography. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop and internally validate a multimodal machine-learning model integrating clinical characteristics, laboratory markers, conventional imaging findings, and quantitative SPECT/CT parameters for differentiating spinal tuberculosis (STB) from pyogenic spondylitis (PS), and to evaluate the incremental diagnostic value of quantitative SPECT/CT parameters.

Methods

This retrospective study included 96 patients with STB and 69 with PS confirmed by microbiological, molecular, or histopathological examinations between September 2024 and May 2026. Demographic characteristics, laboratory markers, conventional imaging findings, and quantitative SPECT/CT parameters were collected. Two prespecified integrated quantitative SPECT/CT parameters, LBI SUVmax and LBI SUVmean , were used to construct a baseline model, a quantitative SPECT/CT-only model, and a fusion model. Elastic Net logistic regression was used for the primary analysis, and radial basis function support vector machine (RBF-SVM) was used for robustness analysis. Internal validation was performed using repeated stratified nested cross-validation. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), Brier score, and calibration measures. Incremental diagnostic value was assessed using 2, 000 patient-level paired bootstrap replicates. Two prespecified sensitivity analyses were also performed.

Results

All seven integrated quantitative SPECT/CT parameters were significantly higher in the PS group than in the STB group (all P < 0.01). In the Elastic Net analysis, the baseline, quantitative SPECT/CT-only, and fusion models achieved AUCs of 0.788, 0.871, and 0.899, respectively. Compared with the baseline model, the fusion model increased the AUC by 0.110 (95% CI, 0.054–0.172) and reduced the Brier score by 0.048 (95% CI, 0.024–0.070). The RBF-SVM fusion model achieved an AUC of 0.957; however, its incremental AUC over the corresponding baseline model was only 0.021 (95% CI, −0.003 to 0.050). Both sensitivity analyses yielded findings consistent in direction with the primary analysis, and inclusion of all seven quantitative parameters did not further improve model performance.

Conclusion

LBI SUVmax and LBI SUVmean improved the discrimination between STB and PS when added to conventional clinical, laboratory, and imaging information and demonstrated consistent incremental value in the Elastic Net primary analysis and prespecified sensitivity analyses. Integrated quantitative SPECT/CT parameters may therefore provide useful complementary diagnostic information; however, their clinical applicability requires confirmation through multicenter external validation and prospective studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SpondylitisMachine LearningTuberculosis, SpinalSingle Photon Emission Computed Tomography Computed TomographyHumansRetrospective StudiesFemaleDiagnosis, DifferentialMaleMiddle AgedROC CurveAdultAged

Stichwörter der Autor:innen

SPECT/CTdifferential diagnosismachine learningpyogenic spondylitisspinal tuberculosis

Autor:innen und Institutionen

  • Department of Orthopedics, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China.
  • Ningxia Medical University, Yinchuan, Ningxia, China.
  • Key Laboratory of Clinical Pathogenic Microorganisms, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China.
  • Department of Nuclear Medicine, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China.
  • Research Center for Prevention and Control of Bone and Joint Tuberculosis, General Hospital of Ningxia Medical University, Yinchuan, Ningxia, China.

Zitieren

APA

Wang, J., Duan, X., Wang, J., Zhu, M., Gao, Y., Jia, Y., Zhao, Q., & Niu, N. (2026). Incremental value of quantitative SPECT/CT integrated parameters in a multimodal machine-learning model for differentiating spinal tuberculosis from pyogenic spondylitis. Frontiers in Cellular and Infection Microbiology, 16. https://doi.org/10.3389/fcimb.2026.1897479

Vancouver

Wang J, Duan X, Wang J, Zhu M, Gao Y, Jia Y, et al. Incremental value of quantitative SPECT/CT integrated parameters in a multimodal machine-learning model for differentiating spinal tuberculosis from pyogenic spondylitis. Frontiers in Cellular and Infection Microbiology. 2026;16. doi:10.3389/fcimb.2026.1897479

BibTeX
@article{Wang2026,
  author = {Wang, Jiaxing and Duan, Xingyu and Wang, Jiong and Zhu, Mengqi and Gao, Yuxin and Jia, Yingqin and Zhao, Qian and Niu, Ningkui},
  title = {Incremental value of quantitative SPECT/CT integrated parameters in a multimodal machine-learning model for differentiating spinal tuberculosis from pyogenic spondylitis},
  journal = {Frontiers in Cellular and Infection Microbiology},
  year = {2026},
  volume = {16},
  doi = {10.3389/fcimb.2026.1897479}
}
Kostenlos starten →