PRIMARCH-APP AI: Development and Internal Validation of an Explainable Machine Learning Model for Preoperative Prediction of Complicated Acute Appendicitis.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	PRIMARCH-APP AI: Development and Internal Validation of an Explainable Machine Learning Model for Preoperative Prediction of Complicated Acute Appendicitis.
Συγγραφείς:	Molnar DC, Cosma CD, Botoncea M, Tudor A, Butiurcă VO, Molnar C, Andrei BS
Πηγή:	Chirurgia (Bucharest, Romania : 1990) [Chirurgia (Bucur)] 2026 Jul; Vol. 121 (4), pp. 371-382.
Τύπος έκδοσης:	Journal Article; Observational Study; Validation Study
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Editura Celsius Country of Publication: Romania NLM ID: 9213031 Publication Model: Print Cited Medium: Print ISSN: 1221-9118 (Print) Linking ISSN: 12219118 NLM ISO Abbreviation: Chirurgia (Bucur) Subsets: MEDLINE
Imprint Name(s):	Publication: Bucuresti : Editura Celsius Original Publication: Bucuresti : Editura Medicală, 1990-
Ιατρικοί όροι (MeSH):	Appendectomy/methods , Appendicitis/surgery , Appendicitis/diagnosis , Appendicitis/complications , Boosting Machine Learning Algorithms*, Adult ; Female ; Humans ; Male ; Middle Aged ; Acute Disease ; Logistic Models ; Predictive Learning Models ; Predictive Value of Tests ; Preoperative Period ; Prospective Studies ; Random Forest ; Reproducibility of Results ; Risk Assessment ; ROC Curve ; Sensitivity and Specificity
Περίληψη:	Background: Early identification of complicated acute appendicitis may improve preoperative risk stratification and support surgical decision-making. This study aimed to develop and internally validate an explainable machine-learning model for predicting complicated acute appendicitis using routinely available preoperative variables. Methods: In this prospective observational cohort study, 199 adult patients undergoing emergency appendectomy were included. Demographic, clinical, laboratory, scoring, and imaging variables collected before surgery were used to develop logistic regression, random forest, and XGBoost models. Performance was evaluated using five-fold cross-validation and a stratified held-out test set. Model explainability was assessed using SHapley Additive exPlanations (SHAP). Results: Complicated acute appendicitis was identified in 57/199 patients (28.6%). Random forest and XGBoost achieved the highest test ROC-AUC (0.934). Random forest demonstrated the best overall probability performance, with 87.5% accuracy, 72.7% sensitivity, 93.1% specificity, and a Brier score of 0.091. SHAP analysis identified heart rate, Alvarado score, rebound tenderness, symptom duration, and appendiceal diameter among the most influential predictors. Conclusions: PRIMARCH-APP AI demonstrated high discrimination and clinically interpretable prediction of complicated acute appendicitis using routinely available preoperative data. External and prospective multicenter validation is required before clinical implementation. (Celsius.)
Contributed Indexing:	Keywords: SHAP; acuteappendicitis; artificialintelligence; complicatedappendicitis; explainableartificialintelligence; machinelearning; riskprediction
Entry Date(s):	Date Created: 20260907 Date Completed: 20260907 Latest Revision: 20260911
Update Code:	20260912
DOI:	10.21614/chirurgia.3376
PMID:	42703976
Βάση Δεδομένων:	MEDLINE

Περιγραφή
ISSN:	1221-9118
DOI:	10.21614/chirurgia.3376