Decision model for acute appendicitis treatment with decision tree technology--a modification of the Alvarado scoring system

Study of pediatric appendicitis scores and management strategies: A prospective observational feasibility study

OBJECTIVE

The objective was to investigate the feasibility of prospectively validating multiple clinical prediction scores (CPSs) for pediatric appendicitis in an Australian pediatric emergency department (ED).

METHODS

A literature search was conducted to identify potential CPSs and a single-center prospective observational feasibility study was performed between November 2022 and May 2023 to evaluate the performance of identified CPSs. Children 5-15 years presenting with acute right-sided or generalized abdominal pain and clinician suspicion of appendicitis were included. CPSs were calculated by the study team from prospectively clinician-collected data and/or review of medical records. Accuracy of CPSs were assessed by area under the receiver operating characteristic curve (AUC) and proportions correctly identifiable as either low-risk or high-risk with the best performing CPS compared to clinician gestalt. Final diagnosis of appendicitis was confirmed on histopathology or by telephone/email follow-up for those discharged directly from ED.

RESULTS

Thirty CPSs were identified in the literature search and 481 patients were enrolled in the study. A total of 150 (31.2%) patients underwent appendectomy with three (2.0%) having a normal appendix on histopathology. All identified CPSs were calculable for at least 50% of the patient cohort. The pediatric Appendicitis Risk Calculator for pediatric EDs (pARC-ED; n = 317) was the best performing CPS with AUC 0.90 (95% confidence interval [CI] 0.86-0.94) and specificity 99.0% (95% CI 96.4%-99.7%) in diagnosing high-risk cases and a misclassification rate of 4.5% for low-risk cases.

CONCLUSIONS

The study identified 30 CPSs that could be validated in a majority of patients to compare their ability to assess risk of pediatric appendicitis. The pARC-ED had the highest predictive accuracy and can potentially assist in risk stratification of children with suspected appendicitis in pediatric EDs. A multicenter study is now under way to evaluate the potential of these CPSs in a broader range of EDs to aid clinical decision making in more varied settings.

Entropy removal of medical diagnostics

Shannon entropy is a core concept in machine learning and information theory, particularly in decision tree modeling. To date, no studies have extensively and quantitatively applied Shannon entropy in a systematic way to quantify the entropy of clinical situations using diagnostic variables (true and false positives and negatives, respectively). Decision tree representations of medical decision-making tools can be generated using diagnostic variables found in literature and entropy removal can be calculated for these tools. This concept of clinical entropy removal has significant potential for further use to bring forth healthcare innovation, such as quantifying the impact of clinical guidelines and value of care and applications to Emergency Medicine scenarios where diagnostic accuracy in a limited time window is paramount. This analysis was done for 623 diagnostic tools and provided unique insights into their utility. For studies that provided detailed data on medical decision-making algorithms, bootstrapped datasets were generated from source data to perform comprehensive machine learning analysis on these algorithms and their constituent steps, which revealed a novel and thorough evaluation of medical diagnostic algorithms.

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

BACKGROUND

To assess the efficacy of artificial intelligence (AI) models in diagnosing and prognosticating acute appendicitis (AA) in adult patients compared to traditional methods. AA is a common cause of emergency department visits and abdominal surgeries. It is typically diagnosed through clinical assessments, laboratory tests, and imaging studies. However, traditional diagnostic methods can be time-consuming and inaccurate. Machine learning models have shown promise in improving diagnostic accuracy and predicting outcomes.

MAIN BODY

A systematic review following the PRISMA guidelines was conducted, searching PubMed, Embase, Scopus, and Web of Science databases. Studies were evaluated for risk of bias using the Prediction Model Risk of Bias Assessment Tool. Data points extracted included model type, input features, validation strategies, and key performance metrics.

RESULTS

In total, 29 studies were analyzed, out of which 21 focused on diagnosis, seven on prognosis, and one on both. Artificial neural networks (ANNs) were the most commonly employed algorithm for diagnosis. Both ANN and logistic regression were also widely used for categorizing types of AA. ANNs showed high performance in most cases, with accuracy rates often exceeding 80% and AUC values peaking at 0.985. The models also demonstrated promising results in predicting postoperative outcomes such as sepsis risk and ICU admission. Risk of bias was identified in a majority of studies, with selection bias and lack of internal validation being the most common issues.

CONCLUSION

AI algorithms demonstrate significant promise in diagnosing and prognosticating AA, often surpassing traditional methods and clinical scores such as the Alvarado scoring system in terms of speed and accuracy.

Development and Validation of a Differential Diagnosis Model for Acute Appendicitis and Henoch-Schonlein Purpura in Children

Objective: To study and develop a predictive model for the differential diagnosis of acute appendicitis (AA) and Henoch-Schonlein purpura (HSP) in children and to validate the model internally and externally. Methods: The complete data of AA and HSP cases were retrospectively analyzed and divided into internal and external verification groups. SPSS software was used for single-factor analysis and screening of independent variables, and R software was used for the development and verification of the diagnostic model. Lasso regression analysis was used to screen predictors and Lasso-logistic regression model was constructed, and K-fold cross-validation was used for the internal verification. In addition, nonfever patients were selected for model development and validation in the same way. Receiver operating characteristic (ROC) curves and calibration curves were drawn, respectively, to evaluate the 2 models. Results: Internal development and validation of the model showed that fever, neutrophil ratio (NEUT%), albumin (ALB), direct bilirubin (DBIL), C-reactive protein (CRP), and K were predictive factors for the diagnosis of HSP. The model was presented in the form of a nomogram, and the area under ROC curve of the development group and verification group was 0.9462 (95% confidence interval [CI] = 0.9402-0.9522) and 0.8931 (95% CI = 0.8724-0.9139), respectively. In the model of patients without fever, NEUT%, platelets (PLT), ALB, DBIL, alkaline phosphatase (ALP), CRP, and K were predictive factors for the diagnosis of HSP, and the area under ROC curve of the development group and verification group was 0.9186 (95% CI = 0.908-0.9293) and 0.8591 (95% CI = 0.8284-0.8897), respectively. Conclusion: In this study, 2 diagnostic models were constructed for fever or not, both of which had good discrimination and calibration, and were helpful to distinguish AA and HSP in children.

Performance optimization of support vector machine with oppositional grasshopper optimization for acute appendicitis diagnosis

Preoperative differentiation of complicated and uncomplicated appendicitis is challenging. The research goal was to construct a new intelligent diagnostic rule that is accurate, fast, noninvasive, and cost-effective, distinguishing between complicated and uncomplicated appendicitis. Overall, 298 patients with acute appendicitis from the Wenzhou Central Hospital were recruited, and information on their demographic characteristics, clinical findings, and laboratory data was retrospectively reviewed and applied in this study. First, the most significant variables, including C-reactive protein (CRP), heart rate, body temperature, and neutrophils discriminating complicated from uncomplicated appendicitis, were identified using random forest analysis. Second, an improved grasshopper optimization algorithm-based support vector machine was used to construct the diagnostic model to discriminate complicated appendicitis (CAP) from uncomplicated appendicitis (UAP). The resultant optimal model can produce an average of 83.56% accuracy, 81.71% sensitivity, 85.33% specificity, and 0.6732 Matthews correlation coefficients. Based on existing routinely available markers, the proposed intelligent diagnosis model is highly reliable. Thus, the model can potentially be used to assist doctors in making correct clinical decisions.

Appendicitis risk prediction models in children presenting with right iliac fossa pain (RIFT study): a prospective, multicentre validation study

BACKGROUND

Acute appendicitis is the most common surgical emergency in children. Differentiation of acute appendicitis from conditions that do not require operative management can be challenging in children. This study aimed to identify the optimum risk prediction model to stratify acute appendicitis risk in children.

METHODS

We did a rapid review to identify acute appendicitis risk prediction models. A prospective, multicentre cohort study was then done to evaluate performance of these models. Children (aged 5-15 years) presenting with acute right iliac fossa pain in the UK and Ireland were included. For each model, score cutoff thresholds were systematically varied to identify the best achievable specificity while maintaining a failure rate (ie, proportion of patients identified as low risk who had acute appendicitis) less than 5%. The normal appendicectomy rate was the proportion of resected appendixes found to be normal on histopathological examination.

FINDINGS

15 risk prediction models were identified that could be assessed. The cohort study enrolled 1827 children from 139 centres, of whom 630 (34·5%) underwent appendicectomy. The normal appendicectomy rate was 15·9% (100 of 630 patients). The Shera score was the best performing model, with an area under the curve of 0·84 (95% CI 0·82-0·86). Applying score cutoffs of 3 points or lower for children aged 5-10 years and girls aged 11-15 years, and 2 points or lower for boys aged 11-15 years, the failure rate was 3·3% (95% CI 2·0-5·2; 18 of 539 patients), specificity was 44·3% (95% CI 41·4-47·2; 521 of 1176), and positive predictive value was 41·4% (38·5-44·4; 463 of 1118). Positive predictive value for the Shera score with a cutoff of 6 points or lower (72·6%, 67·4-77·4) was similar to that of ultrasound scan (75·0%, 65·3-83·1).

INTERPRETATION

The Shera score has the potential to identify a large group of children at low risk of acute appendicitis who could be considered for early discharge. Risk scoring does not identify children who should proceed directly to surgery. Medium-risk and high-risk children should undergo routine preoperative ultrasound imaging by operators trained to assess for acute appendicitis, and MRI or low-dose CT if uncertainty remains.

FUNDING

None.

Evaluation of appendicitis risk prediction models in adults with suspected appendicitis

BACKGROUND

Appendicitis is the most common general surgical emergency worldwide, but its diagnosis remains challenging. The aim of this study was to determine whether existing risk prediction models can reliably identify patients presenting to hospital in the UK with acute right iliac fossa (RIF) pain who are at low risk of appendicitis.

METHODS

A systematic search was completed to identify all existing appendicitis risk prediction models. Models were validated using UK data from an international prospective cohort study that captured consecutive patients aged 16-45 years presenting to hospital with acute RIF in March to June 2017. The main outcome was best achievable model specificity (proportion of patients who did not have appendicitis correctly classified as low risk) whilst maintaining a failure rate below 5 per cent (proportion of patients identified as low risk who actually had appendicitis).

RESULTS

Some 5345 patients across 154 UK hospitals were identified, of which two-thirds (3613 of 5345, 67·6 per cent) were women. Women were more than twice as likely to undergo surgery with removal of a histologically normal appendix (272 of 964, 28·2 per cent) than men (120 of 993, 12·1 per cent) (relative risk 2·33, 95 per cent c.i. 1·92 to 2·84; P < 0·001). Of 15 validated risk prediction models, the Adult Appendicitis Score performed best (cut-off score 8 or less, specificity 63·1 per cent, failure rate 3·7 per cent). The Appendicitis Inflammatory Response Score performed best for men (cut-off score 2 or less, specificity 24·7 per cent, failure rate 2·4 per cent).

CONCLUSION

Women in the UK had a disproportionate risk of admission without surgical intervention and had high rates of normal appendicectomy. Risk prediction models to support shared decision-making by identifying adults in the UK at low risk of appendicitis were identified.

Diagnosis of pain in the right iliac fossa. A new diagnostic score based on Decision-Tree and Artificial Neural Network Methods

INTRODUCTION

Pain in the right iliac fossa (RIF) continues to pose diagnostic challenges. The objective of this study is the development of a RIF pain diagnosis model based on classification trees of type CHAID (Chi-Square Automatic Interaction Detection) and on an artificial neural network (ANN).

METHODS

Prospective study of 252 patients who visited the hospital due to RIF pain. Demographic, clinical, physical examination and analytical data were registered. Patients were classified into 4 groups: NsP (nonspecific RIFP group), AA (acute appendicitis), NIRIF (RIF pain with no inflammation) and IRIF (RIF pain with inflammation). A CHAID-type classification tree model and an ANN were constructed. The classic models (Alvarado [ALS], Appendicitis Inflammatory Response [AIR] and Fenyö-Linberg [FLS]) were also evaluated. Discrimination was assessed using ROC curves (AUC [95% CI]) and the correct classification rate (CCR).

RESULTS

53% were men. Mean age 33.3±16 years. The largest group was the NsP (45%), AA (37%), NRIF (12%) and IRIF (6%). The analytical model results were: ALS (0.82 [0.76-0.87]), AIR (0.83 [0.77-0.88]) and FLS (0.88 [0.84-0.92]). CHAID determined 10 decision groups: 3 with high probability for NsP, 3 high for AA and 4 special groups with no predominant diagnosis. CCR of ANN and CHAID were 75% and 74.2%, respectively.

CONCLUSIONS

The methodology based on CHAID-type classification trees establishes a diagnostic model based on four pain groups in RIF and generates decision rules that can help us in the diagnosis of processes with RIF pain.

Low mitochondrial DNA copy number of resected cecum appendix correlates with high severity of acute appendicitis

BACKGROUND/PURPOSE

The roles of mitochondrial DNA alterations in acute appendicitis (AA) remain unclear. We evaluated the alterations of mtDNA copy number and mtDNA integrity [proportion of mtDNA templates without 8-hydroxyl-2'-deoxyguanosine (8-OHdG)] of the resected cecum appendixes in clinically suspected acute appendicitis (CSAA).

METHODS

A total of 228 CSAA patients, including 50 harbored negative AA (NAA), 155 true AA (TAA) without rupture and 23 TAA with rupture, who underwent appendectomies were enrolled. Tissues of resected cecum appendixes from the paraffin-embedded pathological blocks were subjected to DNA extraction, and their mtDNA copy number and mtDNA integrity were determined by quantitative real-time polymerase chain reaction (Q-PCR).

RESULTS

During the progression of disease severity from NAA to TAA without rupture and further TAA with rupture, increases of white blood cell (WBC) counts (p = 0.001), positive bacterial culture rates in turbid ascites (p = 0.016) and area (p < 0.001)/or volume (p < 0.001) indices of resected cecum appendixes were noted among CSAA patients. On the contrary, decrease of mtDNA copy number (p = 0.003) was observed during disease progression of CSAA patients, especially in female patients (p = 0.007). Furthermore, lower mtDNA copy numbers were correlated with higher WBC counts (p = 0.001) and larger area (p = 0.003) or volume (p < 0.001) indices of the resected cecum appendixes. However, such an alteration was not observed in mtDNA integrity of resected cecum appendixes.

CONCLUSION

We conclude that a low mtDNA copy number of the resected cecum appendix may reflect high severity of acute appendicitis.

Aid decision algorithms to estimate the risk in congenital heart surgery

BACKGROUND AND OBJECTIVE

In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death.

METHODS

We have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity.

RESULTS

Accuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio.

CONCLUSIONS

According to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery.

The definition of a prolonged intensive care unit stay for spontaneous intracerebral hemorrhage patients: an application with national health insurance research database

Introduction. Length of stay (LOS) in the intensive care unit (ICU) of spontaneous intracerebral hemorrhage (sICH) patients is one of the most important issues. The disease severity, psychosocial factors, and institutional factors will influence the length of ICU stay. This study is used in the Taiwan National Health Insurance Research Database (NHIRD) to define the threshold of a prolonged ICU stay in sICH patients. Methods. This research collected the demographic data of sICH patients in the NHIRD from 2005 to 2009. The threshold of prolonged ICU stay was calculated using change point analysis. Results. There were 1599 sICH patients included. A prolonged ICU stay was defined as being equal to or longer than 10 days. There were 436 prolonged ICU stay cases and 1163 nonprolonged cases. Conclusion. This study showed that the threshold of a prolonged ICU stay is a good indicator of hospital utilization in ICH patients. Different hospitals have their own different care strategies that can be identified with a prolonged ICU stay. This indicator can be improved using quality control methods such as complications prevention and efficiency of ICU bed management. Patients' stay in ICUs and in hospitals will be shorter if integrated care systems are established.

A hybrid decision support model to discover informative knowledge in diagnosing acute appendicitis

Background

The aim of this study is to develop a simple and reliable hybrid decision support model by combining statistical analysis and decision tree algorithms to ensure high accuracy of early diagnosis in patients with suspected acute appendicitis and to identify useful decision rules.

Methods

We enrolled 326 patients who attended an emergency medical center complaining mainly of acute abdominal pain. Statistical analysis approaches were used as a feature selection process in the design of decision support models, including the Chi-square test, Fisher's exact test, the Mann-Whitney U-test (p < 0.01), and Wald forward logistic regression (entry and removal criteria of 0.01 and 0.05, or 0.05 and 0.10, respectively). The final decision support models were constructed using the C5.0 decision tree algorithm of Clementine 12.0 after pre-processing.

Results

Of 55 variables, two subsets were found to be indispensable for early diagnostic knowledge discovery in acute appendicitis. The two subsets were as follows: (1) lymphocytes, urine glucose, total bilirubin, total amylase, chloride, red blood cell, neutrophils, eosinophils, white blood cell, complaints, basophils, glucose, monocytes, activated partial thromboplastin time, urine ketone, and direct bilirubin in the univariate analysis-based model; and (2) neutrophils, complaints, total bilirubin, urine glucose, and lipase in the multivariate analysis-based model. The experimental results showed that the model with univariate analysis (80.2%, 82.4%, 78.3%, 76.8%, 83.5%, and 80.3%) outperformed models using multivariate analysis (71.6%, 69.3%, 73.7%, 69.7%, 73.3%, and 71.5% with entry and removal criteria of 0.01 and 0.05; 73.5%, 66.0%, 80.0%, 74.3%, 72.9%, and 73.0% with entry and removal criteria of 0.05 and 0.10) in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under ROC curve, during a 10-fold cross validation. A statistically significant difference was detected in the pairwise comparison of ROC curves (p < 0.01, 95% CI, 3.13-14.5; p < 0.05, 95% CI, 1.54-13.1). The larger induced decision model was more effective for identifying acute appendicitis in patients with acute abdominal pain, whereas the smaller induced decision tree was less accurate with the test data.

Conclusions

The decision model developed in this study can be applied as an aid in the initial decision making of clinicians to increase vigilance in cases of suspected acute appendicitis.