The Modified Heidelberg and the AI Appendicitis Score Are Superior to Current Scores in Predicting Appendicitis in Children: A Two-Center Cohort Study

Stiel, Carolin; Elrod, Julia; Klinke, Michaela; Herrmann, Jochen; Junge, Carl-Martin; Ghadban, Tarik; Reinshagen, Konrad; Boettcher, Michael

doi:10.3389/fped.2020.592892

Cited by 17 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our 10-fold CV results ( Table 3 ) are overall comparable to the performance levels reported by Reismann et al ( 40 ), Akmese et al ( 41 ), Aydin et al ( 42 ), and Stiel et al ( 43 ) whose studies are similar to ours. Compared to the previous work on using ML to predict pediatric appendicitis ( 40 – 43 ), our analysis considers the most extensive set of variables and, to the best of our knowledge, is the first to simultaneously predict diagnosis, management, and severity of appendicitis in pediatric patients. In a retrospective study Cohen et al found that children with a normal WBC count and an appendix non-visualized on US could initially be kept under observation ( 46 ).…”

Section: Discussionsupporting

confidence: 91%

“…Several studies have used ML to support the diagnosis of appendicitis ( 30 , 38 , 39 ). Four recent studies have focused exclusively on the pediatric population ( 40 – 43 ). Reismann et al performed feature selection and trained a logistic regression to diagnose appendicitis and differentiate between uncomplicated and complicated cases of pediatric acute appendicitis ( 40 ).…”

Section: Discussionmentioning

confidence: 99%

“…Their decision tree model achieved AUROCs of 0.94 and 0.79 for predicting appendicitis and uncomplicated appendicitis, respectively. Stiel et al applied different appendicitis scores (AS, PAS, Heidelberg, and Tzanakis Score) to a dataset of pediatric patients presenting with abdominal pain to predict diagnosis and perforated appendicitis ( 43 ). The Heidelberg Score was modified and a data-driven score was developed using decision trees and random forests, achieving AUROCs of, respectively, 0.92 and 0.86 for appendicitis diagnosis, and both 0.71 for perforation.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, we targeted the prediction of all three targets simultaneously: diagnosis, management, and severity. None of the machine learning models mentioned above were deployed as an open access online tool ( 40 – 43 ), whereas our models are available as an easy-to-use APT.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis

Marcinkevičs

Wolfertstetter²,

Wellmann

et al. 2021

Front. Pediatr.

View full text Add to dashboard Cite

Background: Given the absence of consolidated and standardized international guidelines for managing pediatric appendicitis and the few strictly data-driven studies in this specific, we investigated the use of machine learning (ML) classifiers for predicting the diagnosis, management and severity of appendicitis in children.Materials and Methods: Predictive models were developed and validated on a dataset acquired from 430 children and adolescents aged 0-18 years, based on a range of information encompassing history, clinical examination, laboratory parameters, and abdominal ultrasonography. Logistic regression, random forests, and gradient boosting machines were used for predicting the three target variables.Results: A random forest classifier achieved areas under the precision-recall curve of 0.94, 0.92, and 0.70, respectively, for the diagnosis, management, and severity of appendicitis. We identified smaller subsets of 6, 17, and 18 predictors for each of targets that sufficed to achieve the same performance as the model based on the full set of 38 variables. We used these findings to develop the user-friendly online Appendicitis Prediction Tool for children with suspected appendicitis.Discussion: This pilot study considered the most extensive set of predictor and target variables to date and is the first to simultaneously predict all three targets in children: diagnosis, management, and severity. Moreover, this study presents the first ML model for appendicitis that was deployed as an open access easy-to-use online tool.Conclusion: ML algorithms help to overcome the diagnostic and management challenges posed by appendicitis in children and pave the way toward a more personalized approach to medical decision-making. Further validation studies are needed to develop a finished clinical decision support system.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis

Marcinkevičs

Wolfertstetter²,

Wellmann

et al. 2021

Front. Pediatr.

View full text Add to dashboard Cite

show abstract

“…Stiel et al proposed a modified Heidelberg score including ultrasound showing appendicitis, CRP > 20 mg/L, rebound tenderness, leukocytes > 11 × 10 9 /L and right lower abdominal tenderness. Modified Heidelberg appendicitis provides good predictability for both general appendicitis and PA ( Stiel et al, 2020 ). ( Table 2 )…”

Section: Rating Related Indexesmentioning

confidence: 99%

Related Markers for the Precision Diagnosis of Complex Appendicitis in Children

Zhou

Wang

et al. 2022

Front. Pharmacol.

View full text Add to dashboard Cite

Acute appendicitis is the most common surgical emergency in children. Despite the high incidence rate of appendicitis, it is sometimes misdiagnosed or missed. Complex appendicitis (CA) in children is characterized by a critical condition, several complications, and high mortality. Precision distinguishing between simple appendicitis and CA correctly is key to choosing appropriate treatment. A safe, cheap, rapid, extensive and accurate diagnostic marker of appendicitis will be of great significance for emergency general surgeons to treat suspected CA. Many studies have investigated possible diagnostic markers for the diagnosis of CA in children. In this study, studies related to CA in children in recent years are summarized, and the related markers and scoring system for the diagnosis of CA in children are summarized.

show abstract