Weiter zum Inhalt Weiter zur Fußzeile

Prediction of metastatic pheochromocytoma and paraganglioma: a machine learning modelling study using data from a cross sectional cohort ...

Forschungsdaten: DatensatzMessreihen

Personen und Einrichtungen

  • Christina Pamporaki - , Medizinische Klinik und Poliklinik 3 (Urheber:in)
  • Annika MA Berends - , University Medical Center Groningen (Urheber:in)
  • Angelos Filippatos - , University of Patras (Urheber:in)
  • Tamara Prodanov - , National Institutes of Health (NIH) (Urheber:in)
  • Leah Meuter - , National Institutes of Health (NIH) (Urheber:in)
  • Aleksander Prejbisz - , Cardinal Stefan Wyszynski Institute of Cardiology (Urheber:in)
  • Felix Beuschlein - , Ludwig-Maximilians-Universität München (LMU) (Urheber:in)
  • Martin Fassnacht - , Julius-Maximilians-Universität Würzburg (Urheber:in)
  • Henri J.L.M. Timmers - , Radboud University Nijmegen (Urheber:in)
  • Svenja Nölting - , Ludwig-Maximilians-Universität München (LMU) (Urheber:in)
  • Kaushik Ganesh Abhyankar - , Institut für Leichtbau und Kunststofftechnik (ILK) (Urheber:in)
  • Andreea Georgiana Constantinescu - , Medizinische Klinik und Poliklinik 3 (Urheber:in)
  • Carola Kunath - , Technische Universität Dresden (Urheber:in)
  • Robbert J. de Haas - , University of Groningen (Urheber:in)
  • Katharina Wang - , Ludwig-Maximilians-Universität München (LMU) (Urheber:in)
  • Hanna Remde - , Julius-Maximilians-Universität Würzburg (Urheber:in)
  • Stefan Bornstein - , Medizinische Klinik und Poliklinik 3 (Urheber:in)
  • Andrzeij Januszewicz - , Cardinal Stefan Wyszynski Institute of Cardiology (Urheber:in)
  • Mercedes Robledo - , Spanish National Cancer Research Center, Madrid (Urheber:in)
  • Jacques W.M. Lenders - , Technische Universität Dresden (Urheber:in)
  • Michiel N Kerstens - , University Medical Center Groningen (Urheber:in)
  • Karel Pacak - , National Institutes of Health (NIH) (Urheber:in)
  • Graeme Eisenhofer - , Medizinische Klinik und Poliklinik 3 (Urheber:in)


Background: Pheochromocytomas and paragangliomas (PPGL) have up to 20% rate of metastatic disease that cannot be reliably predicted. This study prospectively assessed whether the dopamine metabolite, methoxytyramine, might predict metastatic disease, whether predictions might be improved using machine learning models that incorporate other features and how ML-based predictions compare to predictions by specialists in the field. Methods: In this machine learning modelling study we used cross-sectional cohort data from the PMT trial, based in Germany, Poland, and the Netherlands, to prospectively examine the utility of methoxytyramine to predict metastatic disease in 267 patients with pheochromocytomas and paragangliomas and positive biochemical test results at initial screening. Another retrospective dataset from 493 patients with PPGL enrolled under clinical protocols in National Institutes of Health (00-CH-0093) and the Netherlands (PRESCRIPT trial), was used to train and validate machine learning models according to selections of additional features. The best performing machine learning models were then externally validated using data for all patients in PMT. For comparison, 12 specialists provided predictions of metastatic disease using data from the training and external validation datasets. Findings: Prospective predictions indicated that plasma methoxytyramine could identify metastatic disease at respective sensitivities and specificities of 52% and 85%. The best performing ML model was based on an ensemble tree classifier algorithm that utilized nine features: plasma methoxytyramine, metanephrine and normetanephrine, age, sex, previous history of PPGL, location and size of primary tumors, presence of multifocal disease. This model presented with an area under the receiver-operating characteristic curve of 0·942 (CI:0·894-0·969) that was larger (P<0·0001) than that of the best performing specialist before (0·815, CI:0·778-0·853) and after provision of SDHB variant data (0·812, CI:0·781-0·854). Sensitivity for prediction of metastatic disease in the external validation cohort reached 83% at a specificity of 92%. Interpretation: Although methoxytyramine has some utility for prediction of metastatic PPGL, sensitivity is limited. Predictive value is considerably enhanced with ML models that incorporate the above mentioned features. Our final model provides a preoperative approach to predict metastases in patients with PPGL, and thereby guide individualized patient management and follow-up.
Daten zugänglich seit19 März 2023
Zugriffsoptionen Offen

Verknüpfte Inhalte