EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond Binary Cutoffs: An Explainable Machine Learning Framework for Individualized Diagnostic Reasoning in Suspected Urolithiasis

Kyungman Cha iD, Sang Hoon Oh iD, Jaekwang Shin, Jee Yong Lim iD

Diagnostics · 27.04.2026 · 16 (9) · 1313

DOI: 10.3390/diagnostics16091313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 27.04.2026. Verfasst von Kyungman Cha und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Suwon St. Vincent Hospital, The Catholic University of Korea, Suwon 16247, Republic of Korea. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Catholic University of Korea Seoul St. Mary's Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Emergency department evaluation of suspected urolithiasis increasingly relies on non-contrast CT, yet not all patients require imaging. Existing clinical prediction rules help stratify stone probability, but by converting continuous measurements into fixed binary indicators, they offer little insight into why a particular patient is at risk or how much uncertainty remains after each testing stage—questions that bear directly on individualized diagnostic decisions.

Methods

We retrospectively analyzed 1000 ED patients with suspected urolithiasis who underwent non-contrast CT (stone prevalence 85.0%). A gradient boosting classifier was trained on 17 continuous clinical and laboratory features and compared against binary-thresholded counterparts and an established scoring system; the 17-feature model achieved AUC 0.771 (95% CI 0.726–0.813) versus 0.723 (95% CI 0.675–0.771) for the reference score on this cohort (DeLong p = 0.001). Individual predictions were explained using an interventional Shapley value approach, and a Shannon entropy-based framework was applied to quantify the marginal diagnostic contribution of each sequential testing stage.

Results

Held-out permutation importance identified red blood cell count on microscopy, age, pain duration, and prior stone history as the most influential predictors. Several features showed non-linear contributions that diverged from conventional binary thresholds: creatinine effect crossed zero near 0.90 mg/dL and pain duration peaked between 2 and 5 h. C-reactive protein, absent from existing scoring systems, emerged as a meaningful negative predictor. Sequential entropy analysis showed that dipstick urinalysis provided the largest marginal information gain among non-history stages (6.1% of prior entropy), while physical examination contributed 2.3%. A prevalence sensitivity analysis projected that the framework’s threshold behavior would differ substantially in lower-prevalence populations, underscoring that the cohort-specific cut-points are not portable decision rules. We therefore position the framework as a reasoning aid that complements clinical judgment and imaging, not as a stand-alone triage tool.

Conclusions

Explainable machine learning can address questions that aggregate discrimination metrics cannot: which features drive risk for a given patient, how those effects behave across the continuous measurement range, and how much diagnostic uncertainty each testing stage resolves. The Shapley-based explanations and entropy framework developed here offer a structured approach to individualized diagnostic reasoning in the ED evaluation of suspected urolithiasis, functioning as an interpretive adjunct to, rather than a replacement for, existing clinical tools and CT imaging.

Schlagwörter

Stichwörter der Autor:innen

SHAPShannon entropyclinical prediction rulediagnostic uncertaintyexplainable artificial intelligencegradient boostingurolithiasis

Autor:innen und Institutionen

  • Department of Emergency Medicine, Suwon St. Vincent Hospital, The Catholic University of Korea, Suwon 16247, Republic of Korea.
  • Department of Emergency Medicine, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul 06591, Republic of Korea.
  • Department of Sports and Technology, Seokyeong University, Seoul 02713, Republic of Korea.
  • International Healthcare Center, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul 06591, Republic of Korea.

ORCID-Profile: Kyungman Cha, Sang Hoon Oh, Jee Yong Lim

Förderung

  • The Catholic University of Korea Seoul St. Mary's Hospital

Zitieren

APA

Cha, K., Oh, S. H., Shin, J., & Lim, J. Y. (2026). Beyond Binary Cutoffs: An Explainable Machine Learning Framework for Individualized Diagnostic Reasoning in Suspected Urolithiasis. Diagnostics, 16(9), 1313. https://doi.org/10.3390/diagnostics16091313

Vancouver

Cha K, Oh SH, Shin J, Lim JY. Beyond Binary Cutoffs: An Explainable Machine Learning Framework for Individualized Diagnostic Reasoning in Suspected Urolithiasis. Diagnostics. 2026;16(9):1313. doi:10.3390/diagnostics16091313

BibTeX
@article{Cha2026,
  author = {Cha, Kyungman and Oh, Sang Hoon and Shin, Jaekwang and Lim, Jee Yong},
  title = {Beyond Binary Cutoffs: An Explainable Machine Learning Framework for Individualized Diagnostic Reasoning in Suspected Urolithiasis},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {1313},
  doi = {10.3390/diagnostics16091313}
}
Kostenlos starten →