EUVIMEDEUVIMED entdecken
KommentarOpen Access · CC BY 4.0

Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Reply to Pagnoni et al. Toward Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Comment on “Ledziński et al. Personalized Medicine in Pulmonary Arterial Hypertension: Utilizing Artificial Intelligence for Death Prevention. J. Clin. Med. 2025, 14, 8325”

Łukasz Ledziński iD, Grzegorz Grześk iD, Michał Ziołkowski, Marcin Waligóra iD, Marcin Kurzyna iD, Tatiana Mularek-Kubzdela iD, Anna Smukowska-Gorynia, Ilona Skoczylas, Łukasz Chrzanowski, Piotr Błaszczak iD, Miłosz Jaguszewski, Beata Kuśmierczyk-Droszcz und 17 weitere

Journal of Clinical Medicine · 28.02.2026 · 15 (5) · 1838

DOI: 10.3390/jcm15051838 ↗

Kurz gefasst

Kommentar in der Zeitschrift Journal of Clinical Medicine, online erschienen am 28.02.2026. Verfasst von Łukasz Ledziński und 28 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology and Clinical Pharmacology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Toruń, 85-168 Bydgoszcz, Poland. Die Arbeit nennt 7 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The present Reply addresses the commentary by Pagnoni et al. on our recent study exploring explainable artificial intelligence (AI) for mortality risk prediction in pulmonary arterial hypertension (PAH). We acknowledge the importance of several key issues raised by the authors, including endpoint selection, calibration, decision thresholds, and external validation, all of which are central to translating AI-based prognostic models into clinical practice. Our original endpoint, defined as death by the next follow-up visit, was driven by the structure of nationwide registry data and reflects real-world clinical workflows, although we recognize the advantages of predefined time horizons and time-to-event approaches for future analyses. We discuss the trade-off between sensitivity and precision, emphasizing our deliberate prioritization of minimizing false-negative classifications in high-risk patients, while acknowledging the need for structured clinical pathways to manage false-positive results. We further address calibration and threshold selection, underscoring the necessity of additional clinical studies to support intervention-oriented recommendations. The role of phenotypic determinants and modifiable risk factors in enhancing personalization is highlighted as a key direction for future model development. We reaffirm the value of SHAP-based explainability for improving model transparency, while recognizing the need for continued refinement and clinical validation. Finally, we emphasize the strengths and challenges inherent to registry-based analyses, the importance of external validation, and the need for methodologically sound comparisons with established risk calculators. Overall, this exchange underscores the critical role of interdisciplinary collaboration in advancing clinically actionable and interpretable AI solutions for PAH.

Autor:innen und Institutionen

  • Department of Cardiology and Clinical Pharmacology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Toruń, 85-168 Bydgoszcz, Poland.
  • Department of Cardiac and Vascular Diseases, St. John Paul II Hospital in Krakow, 31-202 Krakow, Poland.
  • Pulmonary Circulation Centre, Department of Cardiac and Vascular Diseases, Faculty of Medicine, Jagiellonian University Medical College, 31-202 Krakow, Poland.
  • Center for Innovative Medical Education, Department of Medical Education, Faculty of Medicine, Jagiellonian University Medical College, 30-688 Krakow, Poland.
  • Department of Pulmonary Circulation, Thromboembolic Diseases and Cardiology, Centre of Postgraduate Medical Education, Fryderyk Chopin Hospital in European Health Centre Otwock, 05-400 Otwock, Poland.
  • Department of Cardiology, Poznan University of Medical Sciences, 61-701 Poznan, Poland.

ORCID-Profile: Łukasz Ledziński, Grzegorz Grześk, Marcin Waligóra, Marcin Kurzyna, Tatiana Mularek-Kubzdela, Piotr Błaszczak, Katarzyna Ptaszyńska, Katarzyna Mizia-Stec, Ewa Lewicka, Michał Tomaszewski, Wojciech Jacheć, Michał Florczyk, Zbigniew Gąsior, Piotr Pruszczyk, Olga Dzikowska-Diduch, Grzegorz Kopeć

Zitieren

APA

Ledziński, Ł., Grześk, G., Ziołkowski, M., Waligóra, M., Kurzyna, M., Mularek-Kubzdela, T., Smukowska-Gorynia, A., Skoczylas, I., Chrzanowski, Ł., Błaszczak, P., Jaguszewski, M., Kuśmierczyk-Droszcz, B., Ptaszyńska, K., Mizia-Stec, K., Malinowska, E., Peregud-Pogorzelska, M., Lewicka, E., Tomaszewski, M., Jacheć, W., …, & Kopeć, G. (2026). Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Reply to Pagnoni et al. Toward Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Comment on “Ledziński et al. Personalized Medicine in Pulmonary Arterial Hypertension: Utilizing Artificial Intelligence for Death Prevention. J. Clin. Med. 2025, 14, 8325”. Journal of Clinical Medicine, 15(5), 1838. https://doi.org/10.3390/jcm15051838

Vancouver

Ledziński Ł, Grześk G, Ziołkowski M, Waligóra M, Kurzyna M, Mularek-Kubzdela T, et al. Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Reply to Pagnoni et al. Toward Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Comment on “Ledziński et al. Personalized Medicine in Pulmonary Arterial Hypertension: Utilizing Artificial Intelligence for Death Prevention. J. Clin. Med. 2025, 14, 8325”. Journal of Clinical Medicine. 2026;15(5):1838. doi:10.3390/jcm15051838

BibTeX
@article{Ledziski2026,
  author = {Ledziński, Łukasz and Grześk, Grzegorz and Ziołkowski, Michał and Waligóra, Marcin and Kurzyna, Marcin and Mularek-Kubzdela, Tatiana and Smukowska-Gorynia, Anna and Skoczylas, Ilona and Chrzanowski, Łukasz and Błaszczak, Piotr and Jaguszewski, Miłosz and Kuśmierczyk-Droszcz, Beata and Ptaszyńska, Katarzyna and Mizia-Stec, Katarzyna and Malinowska, Ewa and Peregud-Pogorzelska, Małgorzata and Lewicka, Ewa and Tomaszewski, Michał and Jacheć, Wojciech and Florczyk, Michał and Mroczek, Ewa and Gąsior, Zbigniew and Pawlak, Agnieszka and Betkier-Lipińska, Katarzyna and Pruszczyk, Piotr and Dzikowska-Diduch, Olga and Widejko, Katarzyna and Winowska-Józwa, Judyta and Kopeć, Grzegorz},
  title = {Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Reply to Pagnoni et al. Toward Clinically Actionable Explainable AI in Pulmonary Arterial Hypertension: Endpoints, Calibration, and External Validation. Comment on “Ledziński et al. Personalized Medicine in Pulmonary Arterial Hypertension: Utilizing Artificial Intelligence for Death Prevention. J. Clin. Med. 2025, 14, 8325”},
  journal = {Journal of Clinical Medicine},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {1838},
  doi = {10.3390/jcm15051838}
}
Kostenlos starten →