Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Marcinkevics R

PROVIDER: S-EPMC8116489 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceDelayed diagnosis of appendicitis is associated with worse outcomes than timely diagnosis, but clinical features associated with diagnostic delay are uncertain, and the extent to which delays are preventable is unclear.ObjectiveTo determine clinical features associated with delayed diagnosis of pediatric appendicitis, assess the frequency of preventable delay, and compare delay outcomes.Design, setting, and participantsThis case-control study included 748 children treated at 5 pediatric emergency departments in the US between January 1, 2010, and December 31, 2019. Participants were younger than 21 years and had a diagnosis of appendicitis.ExposuresIndividual features of appendicitis and pretest likelihood of appendicitis were measured by the Pediatric Appendicitis Risk Calculator (pARC).Main outcomes and measuresCase patients had a delayed diagnosis of appendicitis, defined as 2 emergency department visits leading to diagnosis and a case review showing the patient likely had appendicitis at the first visit. Control patients had a single emergency department visit yielding a diagnosis. Clinical features and pARC scores were compared by case-control status. Preventability of delay was assessed as unlikely, possible, or likely. The proportion of children with indicated imaging based on an evidence-based cost-effectiveness threshold was determined. Outcomes of delayed diagnosis were compared by case-control status, including hospital length of stay, perforation, and multiple surgical procedures.ResultsA total of 748 children (mean [SD] age, 10.2 [4.3] years; 392 boys [52.4%]; 427 White children [57.1%]) were included in the study; 471 (63.0%) had a delayed diagnosis of appendicitis, and 277 (37.0%) had no delay in diagnosis. Children with a delayed diagnosis were less likely to have pain with walking (adjusted odds ratio [aOR], 0.16; 95% CI, 0.10-0.25), maximal pain in the right lower quadrant (aOR, 0.12; 95% CI, 0.07-0.19), and abdominal guarding (aOR, 0.33; 95% CI, 0.21-0.51), and were more likely to have a complex chronic condition (aOR, 2.34; 95% CI, 1.05-5.23). The pretest likelihood of appendicitis was 39% to 52% lower in children with a delayed vs timely diagnosis. Among children with a delayed diagnosis, 109 cases (23.1%) were likely to be preventable, and 247 (52.4%) were possibly preventable. Indicated imaging was performed in 104 (22.0%) to 289 (61.3%) children with delayed diagnosis, depending on the imputation method for missing data on white blood cell count. Patients with delayed diagnosis had longer hospital length of stay (mean difference between the groups, 2.8 days; 95% CI, 2.3-3.4 days) and higher perforation rates (OR, 7.8; 95% CI, 5.5-11.3) and were more likely to undergo 2 or more surgical procedures (OR, 8.0; 95% CI, 2.0-70.4).Conclusions and relevanceIn this case-control study, delayed appendicitis was associated with initially milder symptoms but worse outcomes. These findings suggest that a majority of delayed diagnoses were at least possibly preventable and that many of these patients did not undergo indicated imaging, suggesting an opportunity to prevent delayed diagnosis of appendicitis in some children.

Project description:Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users-pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups-for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets