EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Association and Discrimination of Urinary System Stone Disease Using Anthropometric Indices, Lifestyle Behaviors, and Artificial Intelligence: A Multicenter Case–Control Study

Assoziation und Diskrimination von Harnsteinerkrankung mithilfe anthropometrischer Indizes, Lebensstilverhalten und künstlicher Intelligenz: multizentrische Fall-Kontroll-Studie

Mehmet Erhan Aydın, Coşkun Kaya, Aykut Aykaç, Kadir Yildirim iD, Mucahit Karaduman iD, Fatih Bicaklioglu iD, Yiğit Kudret Akyol iD, Bayram Kolcu, Mehmet Ezer iD, Ferhat Yakup Suceken iD, Hikmet Yasar iD, Muhammed Yildirim iD und 1 weitere

Diagnostics · 28.10.2026 · 16 (21) · 3557

DOI: 10.3390/diagnostics16213557 ↗

Auf einen Blick

In 1.195 Personen war BMI nicht mit Harnsteinerkrankung assoziiert. Zentale Adipositas-Indizes und ein KI-Modell zeigten bessere Trennung zwischen Fällen und Kontrollen.

Fragestellung

Wie gut sind BMI, fünf neuere anthropometrische Indizes und ein hybrides KI-Modell zur Assoziation mit und Diskrimination von Harnsteinerkrankung geeignet?

Methode

Multizentrische Fall-Kontroll-Studie mit 1.195 Teilnehmenden aus 6 Zentren in der Türkei; Vergleich von BMI mit ABSI, BRI, WtHR, ConI und WHR sowie hybrides Autoencoder-KI-Modell.

Ergebnisse

BMI: kein Gruppenunterschied (p = 0,919), AUC 0,498. ABSI, BRI, WtHR, ConI und WHR waren höher in der Stein-Gruppe, mit positiven Quartil-Trends (alle p-trend ≤ 0,001) und AUC 0,547–0,564. XGBoost: 77 % Genauigkeit.

Einschränkungen

Externe Validierung fehlt; Ergebnisse beruhen auf einem einzelnen Testsplit.

Schlussfolgerung der Autor:innen

Die Autor:innen folgern, dass neuere Indizes für zentrale Adipositas unabhängig mit Harnsteinerkrankung assoziiert sind und ein multivariables KI-Modell 77 % Genauigkeit erreichte; für ein klinisches Screening unterstützen die Daten dies nicht.

Kernaussagen

  • BMI zeigte keine Diskriminationskraft (AUC 0,498).
  • ABSI, BRI, WtHR, ConI und WHR waren mit Stein-krankheit assoziiert.
  • Das beste KI-Modell (XGBoost) erreichte 77 % Genauigkeit.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 28.10.2026. Verfasst von Mehmet Erhan Aydın und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Eskişehir City Health Application and Research Center, University of Health Sciences, 26080 Eskişehir, Turkey. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Urinary system stone disease is common and highly recurrent, and body mass index (BMI) poorly reflects the central adiposity linked to stone risk. We compared BMI with five next-generation anthropometric indices (A Body Shape Index [ABSI], Body Roundness Index [BRI], Waist-to-Height Ratio [WtHR], Conicity Index [ConI], Waist-to-Hip Ratio [WHR]) for their association with stone disease, and developed a hybrid autoencoder-based artificial intelligence model integrating anthropometric, clinical, and lifestyle data.

Methods

This multicenter case–control study included 1195 participants (562 stone cases, 633 controls) from six centers in Turkey. Thirty-one variables were grouped into three subgroups (basic measurements, derived indices, clinical/lifestyle data), each processed by a separate autoencoder; combined features were classified with XGBoost, Cubic SVM, Fine KNN, and logistic regression. Each index’s independent association was assessed by quartile-based logistic regression, and discriminative power by ROC/AUC.

Results

BMI showed no between-group difference (p = 0.919) or discriminative power (AUC = 0.498). ABSI, BRI, WtHR, ConI, and WHR were all significantly higher in the stone group, showed positive trends across quartiles after full adjustment (all p-trend ≤ 0.001), and outperformed BMI (AUC 0.547–0.564); associations were strongest for ConI (aOR = 2.62) and ABSI (aOR = 2.57). The hybrid AI model performed best with XGBoost (77% accuracy), followed by Fine KNN (71%), logistic regression (69%), and Cubic SVM (68%).

Conclusions

Unlike BMI, next-generation indices reflecting central adiposity are independently and consistently associated with stone disease, and a multivariable AI model combining anthropometric, clinical, and lifestyle data reached 77% accuracy in separating stone patients from controls on a single test split. These findings are a hypothesis-generating risk-stratification signal that requires external validation, and they do not support clinical screening.

Schlagwörter

Stichwörter der Autor:innen

anthropometrybody mass indexlifestylemachine learningurolithiasis

Autor:innen und Institutionen

  • Department of Urology, Eskişehir City Health Application and Research Center, University of Health Sciences, 26080 Eskişehir, Turkey.
  • Department of Urology, Elazığ Fethi Sekin City Hospital, University of Health Sciences, 23280 Elazığ, Turkey.
  • Department of Software Engineering, Malatya Turgut Özal University, 44100 Malatya, Turkey.
  • Department of Urology, Kartal Dr. Lütfi Kırdar City Hospital, 34865 Istanbul, Turkey.
  • Department of Urology, Kafkas University Medical School, 36040 Kars, Turkey.
  • Department of Urology, Memorial Göztepe Hospital, 34634 Istanbul, Turkey.

ORCID-Profile: Kadir Yildirim, Mucahit Karaduman, Fatih Bicaklioglu, Yiğit Kudret Akyol, Mehmet Ezer, Ferhat Yakup Suceken, Hikmet Yasar, Muhammed Yildirim, Kemal Sarica

Zitieren

APA

Aydın, M. E., Kaya, C., Aykaç, A., Yildirim, K., Karaduman, M., Bicaklioglu, F., Akyol, Y. K., Kolcu, B., Ezer, M., Suceken, F. Y., Yasar, H., Yildirim, M., & Sarica, K. (2026). Association and Discrimination of Urinary System Stone Disease Using Anthropometric Indices, Lifestyle Behaviors, and Artificial Intelligence: A Multicenter Case–Control Study. Diagnostics, 16(21), 3557. https://doi.org/10.3390/diagnostics16213557

Vancouver

Aydın ME, Kaya C, Aykaç A, Yildirim K, Karaduman M, Bicaklioglu F, et al. Association and Discrimination of Urinary System Stone Disease Using Anthropometric Indices, Lifestyle Behaviors, and Artificial Intelligence: A Multicenter Case–Control Study. Diagnostics. 2026;16(21):3557. doi:10.3390/diagnostics16213557

BibTeX
@article{Aydn2026,
  author = {Aydın, Mehmet Erhan and Kaya, Coşkun and Aykaç, Aykut and Yildirim, Kadir and Karaduman, Mucahit and Bicaklioglu, Fatih and Akyol, Yiğit Kudret and Kolcu, Bayram and Ezer, Mehmet and Suceken, Ferhat Yakup and Yasar, Hikmet and Yildirim, Muhammed and Sarica, Kemal},
  title = {Association and Discrimination of Urinary System Stone Disease Using Anthropometric Indices, Lifestyle Behaviors, and Artificial Intelligence: A Multicenter Case–Control Study},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {3557},
  doi = {10.3390/diagnostics16213557}
}
Kostenlos starten →