Integration of Physical Examination, Old and New Biomarkers, and Ultrasonography by Using Neural Networks for Pediatric Appendicitis

Current use of artificial intelligence in the diagnosis and management of acute appendicitis

INTRODUCTION

Acute appendicitis is a common and time-sensitive surgical emergency, requiring rapid and accurate diagnosis and management to prevent complications. Artificial intelligence (AI) has emerged as a transformative tool in healthcare, offering significant potential to improve the diagnosis and management of acute appendicitis. This review provides an overview of the evolving role of AI in the diagnosis and management of acute appendicitis, highlighting its benefits, challenges, and future perspectives.

EVIDENCE ACQUISITION

We performed a literature search on articles published from 2018 to September 2023. We included only original articles.

EVIDENCE SYNTHESIS

Overall, 121 studies were examined. We included 32 studies: 23 studies addressed the diagnosis, five the differentiation between complicated and uncomplicated appendicitis, and 4 studies the management of acute appendicitis.

CONCLUSIONS

AI is poised to revolutionize the diagnosis and management of acute appendicitis by improving accuracy, speed and consistency. It could potentially reduce healthcare costs. As AI technologies continue to evolve, further research and collaboration are needed to fully realize their potential in the diagnosis and management of acute appendicitis.

Artificial intelligence in the diagnosis and treatment of acute appendicitis: a narrative review

Artificial intelligence is transforming healthcare. Artificial intelligence can improve patient care by analyzing large amounts of data to help make more informed decisions regarding treatments and enhance medical research through analyzing and interpreting data from clinical trials and research projects to identify subtle but meaningful trends beyond ordinary perception. Artificial intelligence refers to the simulation of human intelligence in computers, where systems of artificial intelligence can perform tasks that require human-like intelligence like speech recognition, visual perception, pattern-recognition, decision-making, and language processing. Artificial intelligence has several subdivisions, including machine learning, natural language processing, computer vision, and robotics. By automating specific routine tasks, artificial intelligence can improve healthcare efficiency. By leveraging machine learning algorithms, the systems of artificial intelligence can offer new opportunities for enhancing both the efficiency and effectiveness of surgical procedures, particularly regarding training of minimally invasive surgery. As artificial intelligence continues to advance, it is likely to play an increasingly significant role in the field of surgical learning. Physicians have assisted to a spreading role of artificial intelligence in the last decade. This involved different medical specialties such as ophthalmology, cardiology, urology, but also abdominal surgery. In addition to improvements in diagnosis, ascertainment of efficacy of treatment and autonomous actions, artificial intelligence has the potential to improve surgeons' ability to better decide if acute surgery is indicated or not. The role of artificial intelligence in the emergency departments has also been investigated. We considered one of the most common condition the emergency surgeons have to face, acute appendicitis, to assess the state of the art of artificial intelligence in this frequent acute disease. The role of artificial intelligence in diagnosis and treatment of acute appendicitis will be discussed in this narrative review.

Artificial Intelligence in the Diagnosis and Management of Appendicitis in Pediatric Departments: A Systematic Review

INTRODUCTION

 Artificial intelligence (AI) is a growing field in medical research that could potentially help in the challenging diagnosis of acute appendicitis (AA) in children. However, usefulness of AI in clinical settings remains unclear. Our aim was to assess the accuracy of AIs in the diagnosis of AA in the pediatric population through a systematic literature review.

METHODS

 PubMed, Embase, and Web of Science were searched using the following keywords: "pediatric," "artificial intelligence," "standard practices," and "appendicitis," up to September 2023. The risk of bias was assessed using PROBAST.

RESULTS

 A total of 302 articles were identified and nine articles were included in the final review. Two studies had prospective validation, seven were retrospective, and no randomized control trials were found. All studies developed their own algorithms and had an accuracy greater than 90% or area under the curve >0.9. All studies were rated as a "high risk" concerning their overall risk of bias.

CONCLUSION

 We analyzed the current status of AI in the diagnosis of appendicitis in children. The application of AI shows promising potential, but the need for more rigor in study design, reporting, and transparency is urgent to facilitate its clinical implementation.

Predictive Factors of Acute Appendicitis in Children With Non-Visualized Appendix on Ultrasound: A Prospective Cohort Study

Background: Most studies have demonstrated the high accuracy of ultrasound for the diagnosis of acute appendicitis (AA) in children. However, the lack of visualization of the appendix on ultrasound is usually a challenge. The aim of this study was to identify any factors that might help the physician make the right decision when dealing with a child with suspected appendicitis and an appendix not seen on ultrasound. Patients and Methods: After receiving Institutional Review Board approval, we conducted a prospective study in a pediatric emergency department from January 1, 2022, to December 31, 2022. All children under 14 years of age with suspected AA and an appendix not visualized on ultrasound were included. Results: During the study period, 333 children presented with suspected AA. Of these patients, 106 had an appendix not seen on ultrasound. Our patients' median age was 10 years (interquartile range [IQR], 8-11 years), with 54.7% (n = 58) of children being female. Twenty-five (23.6%) were ultimately diagnosed with AA based on pathologic examination. Multivariable logistic regression analysis revealed that Alvarado score ≥6 and increased peri-appendiceal fat echogenicity were predictive for AA. The combination of these two factors provided a positive predictive value of 100%. A white blood cell (WBC) count ≤10 × 109/L and/or a C-reactive protein (CRP) level ≤6 mg/L makes the diagnosis of appendicitis unlikely. Conclusions: In conclusion, our study demonstrated that an Alvarado score at or above six and increased peri-appendiceal fat echogenicity are independent predictive factors of AA in children with non-visualized appendix on ultrasound. The combination of these two factors would confirm the diagnosis of AA in these patients.

Artificial intelligence for predicting acute appendicitis: a systematic review

BACKGROUND

Paediatric appendicitis may be challenging to diagnose, and outcomes difficult to predict. While diagnostic and prognostic scores exist, artificial intelligence (AI) may be able to assist with these tasks.

METHOD

A systematic review was conducted aiming to evaluate the currently available evidence regarding the use of AI in the diagnosis and prognostication of paediatric appendicitis. In accordance with the PRISMA guidelines, the databases PubMed, EMBASE, and Cochrane Library were searched. This review was prospectively registered on PROSPERO.

RESULTS

Ten studies met inclusion criteria. All studies described the derivation and validation of AI models, and none described evaluation of the implementation of these models. Commonly used input parameters included varying combinations of demographic, clinical, laboratory, and imaging characteristics. While multiple studies used histopathological examination as the ground truth for a diagnosis of appendicitis, less robust techniques, such as the use of ICD10 codes, were also employed. Commonly used algorithms have included random forest models and artificial neural networks. High levels of model performance have been described for diagnosis of appendicitis and, to a lesser extent, subtypes of appendicitis (such as complicated versus uncomplicated appendicitis). Most studies did not provide all measures of model performance required to assess clinical usability.

CONCLUSIONS

The available evidence suggests the creation of prediction models for diagnosis and classification of appendicitis using AI techniques, is being increasingly explored. However, further implementation studies are required to demonstrate benefit in system or patient-centred outcomes with model deployment and to progress these models to the stage of clinical usability.

Application of Artificial Neural Network Models to Differentiate Between Complicated and Uncomplicated Acute Appendicitis

Preoperative prediction of complicated appendicitis is challenging, and many clinical tools are developed to predict complicated appendicitis. This study evaluated whether a supervised learning method can recognize complicated appendicitis in emergency department (ED). Consecutive patients with acute appendicitis presenting to the ED were enrolled and included into training and testing datasets at a ratio of 70:30. The multilayer perceptron artificial neural network (ANN) models were trained to perform binary outcome classification between uncomplicated and complicated acute appendicitis. Measures of sensitivity, specificity, positive and negative likelihood ratio (LR + and LR-), and a c statistic of a receiver of operating characteristic curve were used to evaluate an ANN model. The simplest ANN model by Bröker et al. including the C-reactive protein (CRP) and symptom duration as variables achieved a c statistic value of 0.894. The ANN models developed by Avanesov et al. including symptom duration, appendiceal diameter, periappendiceal fluid, extraluminal air, and abscess as variables attained a high diagnostic performance (a c statistic value of 0.949) and good efficiency (sensitivity of 78.6%, specificity of 94.5%, LR + of 14.29, LR- of 0.23 in the testing dataset); and our own model by H.A. Lin et al. including the CRP level, neutrophil-to-lymphocyte ratio, fat-stranding sign, appendicolith, and ascites exhibited high accuracy (c statistic of 0.950) and outstanding efficiency (sensitivity of 85.7%, specificity of 91.7%, LR + of 10.36, LR- of 0.16 in the testing dataset). The ANN models developed by Avanesov et al. and H.A. Lin et al. developed model exhibited a high diagnostic performance.

The importance of physician speciality on the diagnosis of acute appendicitis and its effect on morbidity in children

AIM

Most acute appendicitis (AA) patients present first to physicians who are not paediatric surgeons. The aim of this study was to investigate whether there is a relationship between the speciality of the first physician and delays in diagnosis and morbidity in AA.

METHODS

The study was planned prospectively. Patients who were operated on between 15 June 2017 and 2018 due to abdominal pain were included. Demographic data of the patients, speciality of the doctors who examined them and postoperative complications were recorded. The patients were divided into three groups: those who were diagnosed at the first examination, those who were diagnosed at the second examination and those who were diagnosed after three or more examinations.

RESULTS

A total of 414 patients were included in the study. There were 255 (61.6%) patients in group 1, 135 (32.6%) patients in group 2 and 24 (5.8%) patients in group 3. The mean age of the patients in group 3 was lower (P < 0.05). Postoperative complications and hospital stay were higher in group 3 (P < 0.05). While 91.8% of the patients in group 1 were examined by a paediatrician, this rate was significantly lower in the other groups (P < 0.05).

CONCLUSIONS

If children presenting with abdominal pain are evaluated primarily by paediatricians, consultation with paediatric surgeons is faster. The awareness of doctors of other specialities should be increased through regular periodic training.

On the Way to Improve Diagnostic Marker Panel for Acute Appendicitis in Adults: the Role of Calprotectin

Calprotectin is a positive acute-phase protein participating in innate immune responses and inflammatory processes. This protein is produced mainly in neutrophils, which infiltrate inflamed tissues and then increase the level of calprotectin in plasma, urine, or body secretions. Its measurement is used in the diagnosis of many inflammatory diseases of the gastrointestinal tract. Here, we reviewed the studies evaluating the utility of calprotectin when the patient is suspected of acute appendicitis, one of the most common causes of abdominal pain. Fecal and serum calprotectin provide clinicians additional information as compared to routinely performed laboratory analyses. Moreover, among all forms of the protein, the fecal calprotectin seems to be a particularly promising biomarker due to its high resistance to degradation in the stool. In the future, innovative methods in the form of neural networks may play a valuable role in developing such panels. These findings are important because current literature showed that sensitive and specific markers of acute appendicitis are still urgently needed.

Diagnostic performance of calprotectin and APPY-1 test in pediatric acute appendicitis: a systematic review and a meta-analysis

BACKGROUND

Pediatric acute appendicitis (AA) is a challenging pathology to diagnose. In the last decades, multiple biomarkers have been evaluated in different human biological samples to improve diagnostic performance. This study aimed to examine the diagnostic performance of serum, fecal and urinary calprotectin as well as the role of the APPY-1 biomarker panel in pediatric acute appendicitis.

METHODS

We conducted a systematic review of the literature that involved an extensive search in the main databases of medical bibliography (Medline, PubMed, Web of Science and SciELO). Two independent reviewers selected the relevant articles based on the previously defined inclusion and exclusion criteria. Methodological quality of the selected article was rated using the QUADAS2 index. Data extraction was performed by two independent reviewers. A synthesis of the results, a standardization of the metrics and two random-effect meta-analyses, one for serum calprotectin and one for APPY-1, were performed.

RESULTS

The research resulted in 173 articles. Thirty-eight duplicates were removed. Among the remaining 135 articles, we excluded 125 following the inclusion and exclusion criteria, resulting in the 10 studies included in this review. This systematic review included data from of 3901 participants (1276 patients with confirmed diagnosis of AA and 2625 controls). The age of the participants ranged from 0 to 21 years. Four of the studies compared serum calprotectin values and reported significant differences between groups, but inconsistent results regarding cutoff points, sensitivity and specificity. Two publications compared urinary values of calprotectin and presented inconsistent results regarding sensitivity and specificity as well. One publication evaluated the diagnostic performance of fecal calprotectin, but it did not provide data on measured values. Four studies evaluated the diagnostic performance of APPY-1 test in pediatric acute appendicitis. The calculated pooled sensitivity and specificity of those studies were 97.37 (95% CI 95.60-98.44) and 36.74 (95% CI 32.28-41.44), respectively, and the calculated pooled NLR, 0.0714 (95% CI 0.041-0.115).

CONCLUSION

Serum calprotectin has limited diagnostic yield in pediatric acute appendicitis. Its performance seems to increase with the hours of clinical evolution and in advanced AA, although the evidence is limited. There is not enough evidence on the usefulness of urinary or fecal calprotectin in the diagnosis of pediatric acute appendicitis. On the other hand, the APPY-1 is a reliable test to exclude the diagnosis of AA in patients at low or moderate risk according to PAS and Alvarado Score.

A Correlation of Blood Panel Results and Histologically Confirmed Appendicitis

Background

Appendicitis is the most common indication for emergency surgery in the world. There is no one laboratory or radiological test that is used to diagnose it. Various routine and novel blood markers have been identified, however none have proved to be conclusive. The aim of this study was to combine routine blood markers to increase the sensitivity and specificity in diagnosing histologically confirmed appendicitis.

Methods

We retrospectively reviewed the theatre logs for the calendar year of 2015 to identify all of the appendectomies which were performed. We reviewed all of the admission bloods for the patients - including their white blood cell (WBC) count, their neutrophil count, and their C-Reactive protein (CRP) value. We also reviewed all of the histology to identify the inflamed appendices, and analysed all of this information together.

Results

The neutrophil count is the most sensitive of the three blood markers with a score of 82%. It has a specificity of 63%. The CRP value is the most specific of the three blood markers with a value of 67% and a sensitivity of 76%. WBC has a sensitivity of 75% and a specificity of 63%. Combining all of the blood values (i.e. elevated white blood cell count or elevated neutrophil count or elevated CRP) demonstrates a sensitivity of 96% and a specificity of 45%.

Conclusion

Combining routine admission blood markers (WBC, neutrophil count, and CRP) can assist in diagnosing appendicitis in unwell patients with abdominal pain.