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

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.

Role of immature granulocytes and total bilirubin values in the diagnosis of perforated appendicitis in patients over 65 years

OBJECTIVE

The aim of this study was to investigate the effectiveness of immature granulocyte count, immature granulocyte percentage, and total bilirubin value in predicting complicated and perforated appendicitis in patients aged 65 years and older with a diagnosis of appendicitis.

METHODS

In this study, 84 patients, aged 65 years and older, who had appendectomy demographic information, preoperative white blood cell count, neutrophil/lymphocyte ratio, immature granulocyte count and immature granulocyte percentage, operation findings, and pathology results were collected retrospectively. They were grouped into 4 categories: complicated, non-complicated, perforated, and non-perforated, according to the data and surgical findings.

RESULTS

Total bilirubin and immature granulocyte count were found to be statistically significant in predicting complicated and perforated appendicitis in patients aged 65 years and older with a diagnosis of appendicitis. The total bilirubin was found to have the following values in differentiating complicated appendicitis: area under the curve=0.883, sensitivity=78.3%, and specificity=88.5%. Total bilirubin had the highest discrimination power with area under the curve=0.804 in differentiating perforation.

CONCLUSION

The immature granulocyte percentage and total bilirubin count are the fast, inexpensive, and reliable parameters that can be used to predict complicated and perforated appendicitis in patients aged 65 years and older.

Predicting Characteristics Associated with Breast Cancer Survival Using Multiple Machine Learning Approaches

Breast cancer is one of the most commonly diagnosed female disorders globally. Numerous studies have been conducted to predict survival markers, although the majority of these analyses were conducted using simple statistical techniques. In lieu of that, this research employed machine learning approaches to develop models for identifying and visualizing relevant prognostic indications of breast cancer survival rates. A comprehensive hospital-based breast cancer dataset was collected from the National Cancer Institute's SEER Program's November 2017 update, which offers population-based cancer statistics. The dataset included female patients diagnosed between 2006 and 2010 with infiltrating duct and lobular carcinoma breast cancer (SEER primary cites recode NOS histology codes 8522/3). The dataset included nine predictor factors and one predictor variable that were linked to the patients' survival status (alive or dead). To identify important prognostic markers associated with breast cancer survival rates, prediction models were constructed using K-nearest neighbor (K-NN), decision tree (DT), gradient boosting (GB), random forest (RF), AdaBoost, logistic regression (LR), voting classifier, and support vector machine (SVM). All methods yielded close results in terms of model accuracy and calibration measures, with the lowest achieved from logistic regression (accuracy = 80.57 percent) and the greatest acquired from the random forest (accuracy = 94.64 percent). Notably, the multiple machine learning algorithms utilized in this research achieved high accuracy, suggesting that these approaches might be used as alternative prognostic tools in breast cancer survival studies, especially in the Asian area.

Hyperbilirubinemia as a predictor of severity of acute appendicitis

Objective

This study aimed to investigate the clinical significance of preoperative hyperbilirubinemia in Japanese patients and to assess its clinical potential as a predictor of the severity of acute appendicitis.

Methods

We studied 318 patients with appendicitis who underwent appendectomy between July 2010 and June 2017. We analyzed preoperative data including age, sex, white blood cell count, C-reactive protein (CRP) level, fever, peritoneal irritation signs, and serum total bilirubin level as potential risk factors for complicated (perforated or gangrenous) appendicitis, using multivariate analysis.

Results

Complicated appendicitis was significantly more frequent in patients with hyperbilirubinemia (>1.1 mg/dL), high CRP level (>0.5 mg/dL), positive peritoneal irritation signs, and fever (>37.3°C). Multivariate analysis revealed older age (>64 years), hyperbilirubinemia, high CRP level, and fever (odds ratios 3.36, 1.75, 7.61, and 2.43, respectively) as risk factors for complicated appendicitis. Multivariate analysis also identified hyperbilirubinemia, high CRP level, and fever (odds ratios 1.99, 5.90, and 2.72, respectively) as risk factors for complicated appendicitis among patients aged <65 years.

Conclusions

Hyperbilirubinemia, high CRP level, and fever may be useful predictors of the severity of acute appendicitis, with hyperbilirubinemia being especially useful among patients aged <65 years.

Predicting factors for survival of breast cancer patients using machine learning techniques

BACKGROUND

Breast cancer is one of the most common diseases in women worldwide. Many studies have been conducted to predict the survival indicators, however most of these analyses were predominantly performed using basic statistical methods. As an alternative, this study used machine learning techniques to build models for detecting and visualising significant prognostic indicators of breast cancer survival rate.

METHODS

A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis.

RESULTS

In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis.

CONCLUSION

Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.

Phlegmonous appendicitis in children is characterized by eosinophilia in white blood cell counts

BACKGROUND

Phlegmonous and complicated appendicitis represent independent entities depending on hereditary immunological mechanisms. However, clinically there are no means to distinguish uncomplicated phlegmonous from complicated appendicitis. The ability to distinguish these two forms of appendicitis is relevant as current attempts are to treat both forms of the disease differently. The aim of the present study was to investigate differences in white blood cell counts (WBCs) in these conditions to identify areas of interest for future molecular studies.

METHODS

White blood cell counts of patients aged between 7 and 14 years who underwent appendectomy from January 2008 to June 2016 were investigated with special reference to particular cellular subpopulations.

RESULTS

A total of 647 children were included in the study. Within distinct inflammatory patterns, significant eosinophilia and basophilia were found in phlegmonous inflammation compared with complicated inflammation (0.11 ± 0.19 × 10⁹/L vs. 0.046 ± 0.104 × 10⁹/L, P < 0.0001, and 0.033 ± 0.031 × 10⁹/L vs. 0.028 ± 0.024 × 10⁹/L, P < 0.001).

CONCLUSIONS

Compared with complicated disease, phlegmonous appendicitis seems to depend primarily on eosinophil inflammation. This observation is stable over time and indicates a direction for investigation of underlying genetic prerequisites.

Evaluation of the diagnostic value of serum level of total bilirubin in patients with suspected acute appendicitis

Introduction

Clinical diagnosis of acute appendicitis still remains a problem. Delays in diagnosis of acute appendicitis may cause perforation and septic peritonitis which result in increasing morbidity and mortality. The aim of this study was to determine the sensitivity, specificity and the diagnostic value of total serum bilirubin levels as a predictor of acute appendicitis.

Methods

In this cross-sectional study, patients who underwent appendectomy with the diagnosis of acute appendicitis from April 2012 to March 2013 at Emam Reza Hospital in Mashhad (Iran) were enrolled. Serum bilirubin-Total and Direct-, were measured. Then based on the final pathologic reports, patients were categorized into five groups of normal appendix, chronic inflammatory changes, acute appendicitis, gangrenous and/or necrotic changes, and perforated appendicitis. Independent sample t-test, ANOVA, and Chi-square test were used for data analysis by SPSS version 16.

Results

There were 174 patients studied, (117 male, 57 female) with a mean age of 27.15±0.7 years. All of the patients had rebound tenderness; 75.3% had nausea, 58.6% had anorexia and 21.3% had fever. The histological reports of all patients showed 76.4% acute appendicitis. Analyzing p-values for SGPT, SGOT, WBC was (p=0.903) and differential count was (p=0.959). The study showed no significant difference between the pathological groups. However, there were no significant differences in serum total bilirubin levels between the pathological groups. Total bilirubin showed sensitivity of 48% and specificity of 61% in the diagnosis of acute appendicitis. Total serum bilirubin more than 0.85 mg/dl was the cut-off value with the best performance for diagnosis of appendicitis.

Conclusion

Bilirubin levels are reliable, sensitive and specific to diagnosis and a prediction of complicated appendicitis.

Able but not willing? Exploring divides in digital versus physical payment use in China

Purpose

– China is the world’s largest user market for digital technologies and experiencing unprecedented rates of rural-urban migration set to create the world’s first “urban billion”. This is an important context for studying nuanced adoption behaviours that define a digital divide. Large-scale studies are required to determine what behaviours exist in such populations, but can offer limited ability to draw inferences about why. The purpose of this paper is to report a large-scale study inside China that probes a nuanced “digital divide” behaviour: consumer demographics indicating ability to pay by electronic means but behaviour suggesting lack of willingness to do so, and extends current demographics to help explain this.

Design/methodology/approach

– The authors report trans-national access to commercial “Big Data” inside China capturing the demographics and consumption of millions of consumers across a wide range of physical and digital market channels. Focusing on one urban location we combine traditional demographics with a new measure that reflecting migration: “Distance from Home”, and use data-mining techniques to develop a model that predicts use behaviour.

Findings

– Use behaviour is predictable. Most use is explained by value of the transaction. “Distance from Home” is more predictive of technology use than traditional demographics.

Research limitations/implications

– Results suggest traditional demographics are insufficient to explain “why” use/non-use occurs and hence an insufficient basis to formulate and target government policy.

Originality/value

– The authors understand this to be the first large-scale trans-national study of use/non-use of digital channels within China, and the first study of the impact of distance on ICT adoption.

Association Rules to Identify Complications of Cerebral Infarction in Patients with Atrial Fibrillation

Objectives

The purpose of this study was to find risk factors that are associated with complications of cerebral infarction in patients with atrial fibrillation (AF) and to discover useful association rules among these factors.

Methods

The risk factors with respect to cerebral infarction were selected using logistic regression analysis with the Wald's forward selection approach. The rules to identify the complications of cerebral infarction were obtained by using the association rule mining (ARM) approach.

Results

We observed that 4 independent factors, namely, age, hypertension, initial electrocardiographic rhythm, and initial echocardiographic left atrial dimension (LAD), were strong predictors of cerebral infarction in patients with AF. After the application of ARM, we obtained 4 useful rules to identify complications of cerebral infarction: age (>63 years) and hypertension (Yes) and initial ECG rhythm (AF) and initial Echo LAD (>4.06 cm); age (>63 years) and hypertension (Yes) and initial Echo LAD (>4.06 cm); hypertension (Yes) and initial ECG rhythm (AF) and initial Echo LAD (>4.06 cm); age (>63 years) and hypertension (Yes) and initial ECG rhythm (AF).

Conclusions

Among the induced rules, 3 factors (the initial ECG rhythm [i.e., AF], initial Echo LAD, and age) were strongly associated with each other.