Establishment of predictive models for acute complicated appendicitis during pregnancy—A retrospective case–control study

Abstract

Objective To develop a scoring system based on clinical and imaging features to distinguish complicated appendicitis (CA) from uncomplicated appendicitis (UCA) during pregnancy. Method This was a retrospective case–control study. Patients diagnosed with acute appendicitis during pregnancy were included, and they were divided into a CA group and a UCA group based on the intraoperative findings and the biopsy results. Multivariate logistic regression and machine learning were employed to establish a predictive model. Results A total of 342 patients were included in this study. Among them, 141 (41.23%) patients were diagnosed with CA. The predictive model contained six indices, including symptom duration time more than 24 h, fever, heart rate at least 98 beats/minute, monocyte count at least 0.72 × 109/L, lymphocyte count at least 1 × 109/L and direct bilirubin at least 4.75 μmol/L. The total score was 31 points, and a score of more than 15.5 points predicted the development of CA during pregnancy with area under the curve (AUC) of 0.80 (95% confidence interval 0.75–0.84) and specificity of 0.84. A decision flow chart for distinguishing CA from UCA during pregnancy was developed by Decision Tree with an AUC of 0.78. Conclusion The models combining clinical findings and laboratory tests, developed by two methods, can distinguish CA from UCA in pregnancy in a convenient and visualized way. Trial Registration The research has been registered in Chinese Clinical Trial Registry on January 7, 2022 with registration ID ChiCTR2200055339.

Artificial Intelligence and Acute Appendicitis: A Systematic Review of Diagnostic and Prognostic Models

“…The primary factor contributing to a high risk of bias was selection bias [ 30 , 32 , 33 , 36 , 39 , 42 , 44 , 45 ], identified in eight studies. Furthermore, seven studies lacked internal validation and thus were excluded from further quality assessment [ 34 , 35 , 37 , 38 , 40 , 41 , 43 ]. Additionally, six studies had issues related to their analyses [ 29 – 32 , 42 , 44 ].…”

“…Over half of the studies (51%) utilized a singular algorithmic model, while the remainder employed multiple models, varying from two [ 26 , 40 , 43 , 44 ] to six [ 25 ] in number. Comprehensive data on the types of models employed are outlined in Tables 1 and 3 .…”

“…The ANN model and its variants were the most commonly employed, being featured in 13 studies [ 21 , 24 – 27 , 32 – 34 , 37 , 38 , 40 , 42 , 45 ]. LR followed in frequency, appearing in nine studies [ 3 , 24 – 26 , 28 , 30 , 32 , 42 , 43 ]. DT [ 25 , 30 , 35 , 36 , 40 , 41 , 43 ] and SVM [ 23 , 24 , 28 , 30 , 37 , 45 ] were each utilized in seven studies, while RF [ 23 , 24 , 29 , 31 , 45 ] was implemented in six studies.…”

“…LR followed in frequency, appearing in nine studies [ 3 , 24 – 26 , 28 , 30 , 32 , 42 , 43 ]. DT [ 25 , 30 , 35 , 36 , 40 , 41 , 43 ] and SVM [ 23 , 24 , 28 , 30 , 37 , 45 ] were each utilized in seven studies, while RF [ 23 , 24 , 29 , 31 , 45 ] was implemented in six studies.…”

“…The comprehensive performance data for each model can be found in Table 2 . The models’ performance underwent no types of validation in seven studies [ 34 , 35 , 37 , 38 , 40 , 41 , 43 ], underwent solely internal validation in 21 studies [ 3 , 19 – 33 , 39 , 42 , 44 , 45 ], and was subject to both internal and external validation in only one study [ 12 ].…”