Development and Validation of Machine Learning Models Incorporating TGFBIp Expression for Prognosis Prediction in Epithelial Ovarian Cancer
Entwicklung und Validierung von Machine-Learning-Modellen mit TGFBIp-Expression zur Prognosevorhersage beim epithelialen Ovarialkarzinom
Cancer Reports · 2026-11 · 9 (11)
DOI: 10.1002/cnr2.70745 ↗Auf einen Blick
Bei 155 Patient:innen mit epithelialem Ovarialkarzinom verbesserten Machine-Learning-Modelle mit TGFBIp-Expression die Vorhersage von Vitalstatus und Rezidiv. Der größte Zusatznutzen zeigte sich für die Vitalstatus-Prognose.
Fragestellung
Verbessert die TGFBIp-Expression in einem Machine-Learning-Framework die Prognose von Vitalstatus und Rezidiv bei Patient:innen mit epithelialem Ovarialkarzinom?
Methode
Analyse von 155 EOC-Patient:innen aus einem Tissue-Microarray; 12 Machine-Learning-Algorithmen wurden mit vier Merkmalsstrategien verglichen; TGFBIp wurde schrittweise zum klinisch-pathologischen Basismodell hinzugefügt.
Ergebnisse
SVM mit Strategie 4 für Vitalstatus: Test-AUC 0,951 (95 %-KI 0,870–0,998), Accuracy 0,872, Sensitivität 0,920, Spezifität 0,818, NPV 0,900. RF mit Strategie 4 für Rezidiv: Test-AUC 0,936 (95 %-KI 0,816–1,000), Sensitivität 0,974, NPV 0,800. ΔAUC +0,038 (95 %-KI +0,002 bis +0,092) für Vitalstatus.
Schlussfolgerung der Autor:innen
Es wurde ein Machine-Learning-Framework mit kompartmentspezifischer TGFBIp-Expression für die EOC-Prognose etabliert. TGFBIp in Tumorzellen lieferte zusätzliche prognostische Information über konventionelle klinisch-pathologische Parameter hinaus.
Kernaussagen
- TGFBIp verbesserte die Vorhersage des Vitalstatus
- SVM und RF zeigten hohe Test-AUCs
- Tumor-TGFBIp war prognostisch zusätzlich relevant
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Validierungsstudie in der Zeitschrift Cancer Reports, online erschienen am 10.11.2026. Verfasst von Yi Guo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China. Hauptthemen laut MEDLINE: Ovarian Neoplasms, Carcinoma, Ovarian Epithelial, Transforming Growth Factor beta, Biomarkers, Tumor. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Key Research and Development Program of Xuzhou Science and Technology Bureau.
Abstract (Originalsprache)
Background
Epithelial ovarian cancer (EOC) exhibits substantial heterogeneity in clinical outcomes, highlighting the need for diverse prognostic tools. Transforming growth factor‐β‐induced protein (TGFBIp) has been implicated in ovarian cancer progression, but its incremental prognostic value within machine learning frameworks remains unexplored.
Aims
To develop and validate machine learning models incorporating TGFBIp expression to predict vital status and recurrence in EOC patients. Methods and Results We analyzed 155 EOC patients from a tissue microarray. TGFBIp expression in tumor cells and stroma was assessed by immunohistochemistry. Twelve machine learning algorithms were benchmarked across four feature inclusion strategies, with TGFBIp expression sequentially added to a baseline clinicopathological model. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) with bootstrap 95% confidence intervals, the area under the precision‐recall curve, calibration intercept and slope, Brier score, and decision curve analysis (DCA). The incremental value of TGFBIp was formally tested by paired bootstrap comparison of test‐set AUCs. SHAP analysis was performed for model interpretation. The support vector machine (SVM) with Strategy 4 (incorporating both tumor and stromal TGFBIp) was selected for vital status prediction, achieving a test‐set AUC of 0.951 (95% CI 0.870–0.998), accuracy of 0.872, sensitivity of 0.920, specificity of 0.818, and negative predictive value (NPV) of 0.900. The random forest (RF) with Strategy 4 was selected for recurrence prediction, achieving a test‐set AUC of 0.936 (95% CI 0.816–1.000), sensitivity of 0.974, and NPV of 0.800. Adding TGFBIp features significantly improved vital status prediction (ΔAUC +0.038, 95% CI +0.002 to +0.092 for Strategy 4 vs. baseline). Calibration was acceptable for the vital status model (test‐set calibration intercept −0.24, slope 1.25, Brier score 0.071). SHAP analysis identified maximum tumor diameter, grade, stage, and TGFBIp expression as leading predictors; tumoral TGFBIp contributed to both outcomes, whereas stromal TGFBIp contributed mainly to vital status prediction. DCA suggested potential clinical utility across a broad range of threshold probabilities.
Conclusion
We established a machine learning framework incorporating compartment‐specific TGFBIp expression for EOC prognosis. TGFBIp in tumor cells provided incremental prognostic information beyond conventional clinicopathological parameters.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Laboratory Medicine, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
- Department of Laboratory Medicine, The General Hospital of Xuzhou Mining Group, Xuzhou, Jiangsu, China.
- The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou Medical University, Xuzhou, Jiangsu, China.
- Department of Oncological Radiotherapy, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
- Department of Oncological Radiotherapy, The General Hospital of Xuzhou Mining Group, Xuzhou, Jiangsu, China.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Key Research and Development Program of Xuzhou Science and Technology Bureau
Zitieren
APA
Guo, Y., Li, Z., Song, W., & Zhang, L. (2026). Development and Validation of Machine Learning Models Incorporating TGFBIp Expression for Prognosis Prediction in Epithelial Ovarian Cancer. Cancer Reports, 9(11). https://doi.org/10.1002/cnr2.70745
Vancouver
Guo Y, Li Z, Song W, Zhang L. Development and Validation of Machine Learning Models Incorporating TGFBIp Expression for Prognosis Prediction in Epithelial Ovarian Cancer. Cancer Reports. 2026;9(11). doi:10.1002/cnr2.70745
BibTeX
@article{Guo2026,
author = {Guo, Yi and Li, Zhen and Song, Wenwei and Zhang, Lansheng},
title = {Development and Validation of Machine Learning Models Incorporating TGFBIp Expression for Prognosis Prediction in Epithelial Ovarian Cancer},
journal = {Cancer Reports},
year = {2026},
volume = {9},
number = {11},
doi = {10.1002/cnr2.70745}
}
EUVIMED