Clinical Scores and Machine Learning at Matched Variable Domains in Acute Appendicitis: Performance of Recommended Rule-Out Thresholds in a CT-Verified Cohort
- 1Department of General Surgery, School of Medicine, Koç University, Istanbul 34450, Türkiye
- 2Department of Industrial Engineering, Faculty of Engineering, Koç University, Istanbul 34450, Türkiye
- 3School of Medicine, Koç University, Istanbul 34450, Türkiye
Abstract
Background/Objectives: Clinical scores are recommended for excluding acute appendicitis without imaging, but their rule-out thresholds were derived in patients selected on suspicion of appendicitis. This study tested whether these thresholds retain their reported sensitivity in patients selected by CT performance, estimated the incremental diagnostic value of successive layers of clinical information, and, as an exploratory aim, compared machine learning models with the scores. Methods: This single centre retrospective cohort comprised 761 emergency department patients undergoing abdominal CT for acute abdominal pain. The Alvarado score, the Appendicitis Inflammatory Response (AIR) score and the Adult Appendicitis Score (AAS) were reconstructed from data documented before CT. The reference standard was histopathology in operated patients and the index CT report with the clinical course otherwise. Models were fitted to five cumulative information layers by cross-validation, with nested algorithm selection and a temporal split. Results: Appendicitis was confirmed in 178 patients (23.4%). Sensitivity at the recommended thresholds was 0.680 (95% CI 0.609 to 0.751), 0.848 (0.791 to 0.899) and 0.697 (0.628 to 0.764), against published values of 0.99, 0.95 and 0.959, leaving 57, 27 and 54 confirmed cases in the low probability strata, and the shortfall was present in both temporal periods. Discrimination was preserved, with areas under the curve of 0.848, 0.868 and 0.881. Model discrimination rose from 0.874 with symptoms to 0.918 with laboratory values, with each increment conditional on the preceding layers and the pattern similar with a single algorithm held fixed. With nested selection, the model was not distinguishable from the AAS, and in the later temporal period its deferral threshold attained a sensitivity of 0.925. Conclusions: In a population defined by imaging rather than by clinical suspicion, the recommended rule-out thresholds did not translate. Thresholds should be re-derived and verified in the population in which imaging is to be deferred. The model analysis was exploratory and was not externally validated.
Related
- Clinical Prediction Model Performance Metrics Cluster at Arbitrary Thresholds and are Incorrectly Reported in High-Ranking Journals: An Observational Meta-Research Study
- Clinical performance and decision thresholds of an automated plasma p-tau217 assay for amyloid pathology in a Taiwanese memory clinic.
- Effectiveness of Discrete Strategies and Implementation Bundles for Improving Clinician Prescription of Clinical Practice Guideline–Recommended Medications for Atherosclerotic Occlusive Disease: A Systematic Review and Meta‐Analysis
- Clinical and Laboratory Prediction of Histopathologically Complicated Acute Appendicitis and Associated Surgical Outcomes: A Retrospective Cohort Study
- Clinical, laboratory, operative, and appendiceal morphometric correlates of histopathological appendicitis severity: A retrospective cohort study from Palestine
BibTeX
@article{celik2026clinical,
title = {{Clinical Scores and Machine Learning at Matched Variable Domains in Acute Appendicitis: Performance of Recommended Rule-Out Thresholds in a CT-Verified Cohort}},
author = {Burak Celik and Ipek Pehlivan and Alper Hatipoglu and Zeynep Ece Dimitoka and Safa Toprak and Ibrahim Halil Ozata and Emre Balik and Metin Turkay},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15208141},
url = {https://www.mdpi.com/2077-0383/15/20/8141},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Clinical Scores and Machine Learning at Matched Variable Domains in Acute Appendicitis: Performance of Recommended Rule-Out Thresholds in a CT-Verified Cohort
AU - Burak Celik
AU - Ipek Pehlivan
AU - Alper Hatipoglu
AU - Zeynep Ece Dimitoka
AU - Safa Toprak
AU - Ibrahim Halil Ozata
AU - Emre Balik
AU - Metin Turkay
PY - 2026
DA - 2026/10/01
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15208141
UR - https://www.mdpi.com/2077-0383/15/20/8141
AB - Background/Objectives: Clinical scores are recommended for excluding acute appendicitis without imaging, but their rule-out thresholds were derived in patients selected on suspicion of appendicitis. This study tested whether these thresholds retain their reported sensitivity in patients selected by CT performance, estimated the incremental diagnostic value of successive layers of clinical information, and, as an exploratory aim, compared machine learning models with the scores. Methods: This single centre retrospective cohort comprised 761 emergency department patients undergoing abdominal CT for acute abdominal pain. The Alvarado score, the Appendicitis Inflammatory Response (AIR) score and the Adult Appendicitis Score (AAS) were reconstructed from data documented before CT. The reference standard was histopathology in operated patients and the index CT report with the clinical course otherwise. Models were fitted to five cumulative information layers by cross-validation, with nested algorithm selection and a temporal split. Results: Appendicitis was confirmed in 178 patients (23.4%). Sensitivity at the recommended thresholds was 0.680 (95% CI 0.609 to 0.751), 0.848 (0.791 to 0.899) and 0.697 (0.628 to 0.764), against published values of 0.99, 0.95 and 0.959, leaving 57, 27 and 54 confirmed cases in the low probability strata, and the shortfall was present in both temporal periods. Discrimination was preserved, with areas under the curve of 0.848, 0.868 and 0.881. Model discrimination rose from 0.874 with symptoms to 0.918 with laboratory values, with each increment conditional on the preceding layers and the pattern similar with a single algorithm held fixed. With nested selection, the model was not distinguishable from the AAS, and in the later temporal period its deferral threshold attained a sensitivity of 0.925. Conclusions: In a population defined by imaging rather than by clinical suspicion, the recommended rule-out thresholds did not translate. Thresholds should be re-derived and verified in the population in which imaging is to be deferred. The model analysis was exploratory and was not externally validated.
SN - 2077-0383
ER -