A novel and simple machine learning algorithm for preoperative diagnosis of acute appendicitis in children

Aydın, Emrah; Türkmen, İnan Utku; Namli, Gözde; Öztürk, Çiğdem; Esen, Ayse Banu; Eray, Y Nur; Eroğlu, Egemen; Akova, Fatih

doi:10.1007/s00383-020-04655-7

Cited by 30 publications

(33 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

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.…”

Section: Discussionsupporting

confidence: 91%

See 1 more Smart Citation

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%

“…In their analysis, gradient boosting attained the highest accuracy (95%). Similar to Akmese et al ( 41 ) Aydin et al detected pediatric appendicitis based on demographic and pre-operative laboratory data ( 42 ). In addition, they differentiated between complicated and uncomplicated appendicitis.…”

Section: Discussionmentioning

confidence: 79%

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

“…Aydın et al [ 33 ] used blood tests decision trees for acute appendicitis diagnosis. We compared imaging techniques for diagnosis.…”

Section: Discussionmentioning

confidence: 99%

Applicability of American College of Radiology Appropriateness Criteria Decision-Making Model for Acute Appendicitis Diagnosis in Children

Tunçyürek

Kadam²,

Uzun

et al. 2022

Diagnostics

View full text Add to dashboard Cite

Acute appendicitis is one of the most common causes of abdominal pain in the emergency department and the most common surgical emergency reason for children younger than 15 years of age, which could be enormously dangerous when ruptured. The choice of radiological approach is very important for the diagnosis. In this way, unnecessary surgery is avoided. The aim of this study was to examine the validity of the American College of Radiology appropriateness criteria for radiological imaging in diagnosing acute appendicitis with multivariate decision criteria. In our study, pediatric patients who presented to the emergency department with abdominal pain were grouped according to the Appendicitis Inflammatory Response (AIR) score and the choice of radiological examinations was evaluated with fuzzy-based Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) and with the fuzzy-based Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) model for the validation of the results. As a result of this study, non-contrast computed tomography (CT) was recommended as the first choice for patients with low AIR score (where Φnet=0.0733) and with high AIR scores (where Φnet=0.0702) while ultrasound (US) examination was ranked third in patients with high scores. While computed tomography is at the forefront with many criteria used in the study, it is still a remarkable practice that US examination is in the first place in daily routine. Even though there are studies showing the strengths of these tools, this study is unique in that it provides analytical ranking results for this complex decision-making issue and shows the strengths and weaknesses of each alternative for different scenarios, even considering vague information for the acute appendicitis diagnosis in children for different scenarios.

show abstract

“…Considering the overall drop AcA incidence from 38.93% to 20.06% during 2014 to 2020, and in particular from 37.54% to 20.06% between 2017 and 2020 during the implementation period of AA diagnostic and treatment algorithm, we would like to be cautious optimistic that the algorithm had a role in this positive improvement. mese et al, 2020;Aydin et al, 2020;Marcinkevics et al, 2021). Further studies are necessary to create a feasible tool for surgeons in clinic.…”

Section: Discussionmentioning

confidence: 99%

“…Use of ma-chine-learning techniques in medicine has already begun (Deo, 2015). Results of several pilot projects of using machine learning (ML) in predicting severity of appendicitis have already published and showed their feasibility (Akmese et al, 2020;Aydin et al, 2020;Marcinkevics et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Surgical and non-surgical treatment of paediatric appendicitis: can algorithms help us to predict perforation?

Eņģelis

Kakar

Zviedre

et al. 2022

Proceedings of the Latvian Academy of Sciences. Section B. Natural, Exact, and Applied Sciences.

View full text Add to dashboard Cite

The recent interest in and evidence of non-surgical treatment with antibiotic therapy has led to the recurring issue of differentiating acute no-complicated appendicitis (AnA) and acute complicated appendicitis (AcA) when these are presented in an emergency department. To create the initial version of an acute appendicitis (AA) diagnostic and treatment algorithm, we analysed treatment results of 178 children with AnA and AcA treated at the Children’s Clinical University Hospital in Rīga, in the period between 2010 and 2013. Evaluation of the clinical symptoms, laboratory and radiological findings was included in development of the algorithm. The algorithm was created in 2016 and accepted by the hospital administration. We present the algorithm’s updated version of 2020. The introduction of diagnostic scores and algorithms has standardised and improved the diagnosis of paediatric AA. New diagnostic tests with higher sensitivity and specificity may improve the accuracy of diagnostic algorithms. Measuring multiple effective biomarkers simultaneously may improve the accuracy of diagnostic algorithms and predict the severity of paediatric AA. Machine learning algorithms may be able to process a much larger amount of data and provide a faster conclusion, helping the surgeon make the right decision in diagnosing appendicitis in children and prevent unnecessary surgery.

show abstract

A novel and simple machine learning algorithm for preoperative diagnosis of acute appendicitis in children

Cited by 30 publications

References 28 publications

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

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

Applicability of American College of Radiology Appropriateness Criteria Decision-Making Model for Acute Appendicitis Diagnosis in Children

Surgical and non-surgical treatment of paediatric appendicitis: can algorithms help us to predict perforation?

Contact Info

Product

Resources

About