Comparison of the levels of accuracy of an artificial neural network model and a logistic regression model for the diagnosis of acute appendicitis. J Med Syst. 2007;31:357-364. [PMID: 17918689 DOI: 10.1007/s10916-007-9077-9]

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 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.

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.

Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice

Machine learning encompasses statistical approaches such as logistic regression (LR) through to more computationally complex models such as neural networks (NN). The aim of this study is to review current published evidence for performance from studies directly comparing logistic regression, and neural network classification approaches in medicine.

A literature review was carried out to identify primary research studies which provided information regarding comparative area under the curve (AUC) values for the overall performance of both LR and NN for a defined clinical healthcare-related problem. Following an initial search, articles were reviewed to remove those that did not meet the criteria and performance metrics were extracted from the included articles. Teh initial search revealed 114 articles; 21 studies were included in the study. In 13/21 (62%) of cases, NN had a greater AUC compared to LR, but in most the difference was small and unlikely to be of clinical significance; (unweighted mean difference in AUC 0.03 (95% CI 0-0.06) in favour of NN versus LR.

In the majority of cases examined across a range of clinical settings, LR models provide reasonable performance that is only marginally improved using more complex methods such as NN. In many circumstances, the use of a relatively simple LR model is likely to be adequate for real-world needs but in specific circumstances in which large amounts of data are available, and where even small increases in performance would provide significant management value, the application of advanced analytic tools such as NNs may be indicated.

Machine learning to guide clinical decision-making in abdominal surgery-a systematic literature review

PURPOSE

An indication for surgical therapy includes balancing benefits against risk, which remains a key task in all surgical disciplines. Decisions are oftentimes based on clinical experience while guidelines lack evidence-based background. Various medical fields capitalized the application of machine learning (ML), and preliminary research suggests promising implications in surgeons' workflow. Hence, we evaluated ML's contemporary and possible future role in clinical decision-making (CDM) focusing on abdominal surgery.

METHODS

Using the PICO framework, relevant keywords and research questions were identified. Following the PRISMA guidelines, a systemic search strategy in the PubMed database was conducted. Results were filtered by distinct criteria and selected articles were manually full text reviewed.

RESULTS

Literature review revealed 4,396 articles, of which 47 matched the search criteria. The mean number of patients included was 55,843. A total of eight distinct ML techniques were evaluated whereas AUROC was applied by most authors for comparing ML predictions vs. conventional CDM routines. Most authors (N = 30/47, 63.8%) stated ML's superiority in the prediction of benefits and risks of surgery. The identification of highly relevant parameters to be integrated into algorithms allowing a more precise prognosis was emphasized as the main advantage of ML in CDM.

CONCLUSIONS

A potential value of ML for surgical decision-making was demonstrated in several scientific articles. However, the low number of publications with only few collaborative studies between surgeons and computer scientists underpins the early phase of this highly promising field. Interdisciplinary research initiatives combining existing clinical datasets and emerging techniques of data processing may likely improve CDM in abdominal surgery in the future.

To Scan or Not to Scan: Development of a Clinical Decision Support Tool to Determine if Imaging Would Aid in the Diagnosis of Appendicitis

BACKGROUND

Appendicitis is one of the most common surgically treated diseases in the world. CT scans are often over-utilized and ordered before a surgeon has evaluated the patient. Our aim was to develop a tool using machine learning (ML) algorithms that would help determine if there would be benefit in obtaining a CT scan prior to surgeon consultation.

METHODS

Retrospective chart review of 100 randomly selected cases who underwent appendectomy and 100 randomly selected controls was completed. Variables included components of the patient's history, laboratory values, CT readings, and pathology. Pathology was used as the gold standard for appendicitis diagnosis. All variables were then used to build the ML algorithms. Random Forest (RF), Support Vector Machine (SVM), and Bayesian Network Classifiers (BNC) models with and without CT scan results were trained and compared to CT scan results alone and the Alvarado score using area under the Receiver Operator Curve (ROC), sensitivity, and specificity measures as well as calibration indices from 500 bootstrapped samples.

RESULTS

Among the cases that underwent appendectomy, 88% had pathology-confirmed appendicitis. All the ML algorithms had better sensitivity, specificity, and ROC than the Alvarado score. SVM with and without CT had the best indices and could predict if imaging would aid in appendicitis diagnosis.

CONCLUSION

This study demonstrated that SVM with and without CT results can be used for selective imaging in the diagnosis of appendicitis. This study serves as the initial step and proof-of-concept to externally validate these results with larger and more diverse patient population.

Management of abdominal emergencies in adults using telemedicine and artificial intelligence

The terms "telemedicine" and "artificial intelligence" (AI) are used today throughout all fields of medicine, with varying degrees of relevance. If telemedicine corresponds to practices currently being developed to supply a high quality response to medical provider shortages in the general provision of healthcare and to specific regional challenges. Through the possibilities of "scalability" and the "augmented physician" that it has helped to create, AI may also constitute a revolution in our practices. In the management of surgical emergencies, abdominal pain is one of the most frequent complaints of patients who present for emergency consultation, and up to 20% of patients prove to have an organic lesion that will require surgical management. In view of the very large number of patients concerned, the variety of clinical presentations, the potential seriousness of the etiological pathology that sometimes involves a life-threatening prognosis, healthcare workers responsible for these patients have logically been led to regularly rely on imaging examinations, which remain the critical key to subsequent management. Therefore, it is not surprising that articles have been published in recent years concerning the potential contributions of telemedicine (and teleradiology) to the diagnostic management of these patients, and also concerning the contribution of AI (albeit still in its infancy) to aid in diagnosis and treatment, including surgery. This review article presents the existing data and proposes a collaborative vision of an optimized patient pathway, giving medical meaning to the use of these tools.

Prediction of excess weight loss after laparoscopic Roux-en-Y gastric bypass: data from an artificial neural network

INTRODUCTION

Laparoscopic Roux-en-Y gastric bypass (LRYGB) has become the gold standard for surgical weight loss. The success of LRYGB may be measured by excess body mass index loss (%EBMIL) over 25 kg/m(2), which is partially determined by multiple patient factors. In this study, artificial neural network (ANN) modeling was used to derive a reasonable estimate of expected postoperative weight loss using only known preoperative patient variables. Additionally, ANN modeling allowed for the discriminant prediction of achievement of benchmark 50% EBMIL at 1 year postoperatively.

METHODS

Six hundred and forty-seven LRYGB included patients were retrospectively reviewed for preoperative factors independently associated with EBMIL at 180 and 365 days postoperatively (EBMIL180 and EBMIL365, respectively). Previously validated factors were selectively analyzed, including age; race; gender; preoperative BMI (BMI0); hemoglobin; and diagnoses of hypertension (HTN), diabetes mellitus (DM), and depression or anxiety disorder. Variables significant upon multivariate analysis (P < .05) were modeled by "traditional" multiple linear regression and an ANN, to predict %EBMIL180 and %EBMIL365.

RESULTS

The mean EBMIL180 and EBMIL365 were 56.4 ± 16.5 % and 73.5 ± 21.5%, corresponding to total body weight losses of 25.7 ± 5.9% and 33.6 ± 8.0%, respectively. Upon multivariate analysis, independent factors associated with EBMIL180 included black race (B = -6.3%, P < .001), BMI0 (B = -1.1%/unit BMI, P < .001), and DM (B = -3.2%, P < .004). For EBMIL365, independently associated factors were female gender (B = 6.4%, P < .001), black race (B = -6.7%, P < .001), BMI0 (B = -1.2%/unit BMI, P < .001), HTN (B = -3.7%, P = .03), and DM (B = -6.0%, P < .001). Pearson r(2) values for the multiple linear regression and ANN models were 0.38 (EBMIL180) and 0.35 (EBMIL365), and 0.42 (EBMIL180) and 0.38 (EBMIL365), respectively. ANN prediction of benchmark 50% EBMIL at 365 days generated an area under the curve of 0.78 ± 0.03 in the training set (n = 518) and 0.83 ± 0.04 (n = 129) in the validation set.

CONCLUSIONS

Available at https://redcap.vanderbilt.edu/surveys/?s=3HCR43AKXR, this or other ANN models may be used to provide an optimized estimate of postoperative EBMIL following LRYGB.

Hip fracture risk assessment: artificial neural network outperforms conditional logistic regression in an age- and sex-matched case control study

BACKGROUND

Osteoporotic hip fractures with a significant morbidity and excess mortality among the elderly have imposed huge health and economic burdens on societies worldwide. In this age- and sex-matched case control study, we examined the risk factors of hip fractures and assessed the fracture risk by conditional logistic regression (CLR) and ensemble artificial neural network (ANN). The performances of these two classifiers were compared.

METHODS

The study population consisted of 217 pairs (149 women and 68 men) of fractures and controls with an age older than 60 years. All the participants were interviewed with the same standardized questionnaire including questions on 66 risk factors in 12 categories. Univariate CLR analysis was initially conducted to examine the unadjusted odds ratio of all potential risk factors. The significant risk factors were then tested by multivariate analyses. For fracture risk assessment, the participants were randomly divided into modeling and testing datasets for 10-fold cross validation analyses. The predicting models built by CLR and ANN in modeling datasets were applied to testing datasets for generalization study. The performances, including discrimination and calibration, were compared with non-parametric Wilcoxon tests.

RESULTS

In univariate CLR analyses, 16 variables achieved significant level, and six of them remained significant in multivariate analyses, including low T score, low BMI, low MMSE score, milk intake, walking difficulty, and significant fall at home. For discrimination, ANN outperformed CLR in both 16- and 6-variable analyses in modeling and testing datasets (p?<?0.005). For calibration, ANN outperformed CLR only in 16-variable analyses in modeling and testing datasets (p?=?0.013 and 0.047, respectively).

CONCLUSIONS

The risk factors of hip fracture are more personal than environmental. With adequate model construction, ANN may outperform CLR in both discrimination and calibration. ANN seems to have not been developed to its full potential and efforts should be made to improve its performance.

Mortality predicted accuracy for hepatocellular carcinoma patients with hepatic resection using artificial neural network

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation.

An approach to model Right Iliac Fossa pain using pain-only-parameters for screening acute appendicitis

Acute appendicitis (AA) is one of the commonest of multiple possible pathologies at the backdrop of Right Iliac Fossa (RIF) pain. RIF is the most common acute surgical condition of the abdomen. Even though AA is a recognized disease entity since decades, its diagnosis still lacks clinical confidence and mandates laboratory tests. Given the issue, this paper proposes a mathematical model using Pain-Only-Parameters (POP) obtained from available literature to screen AA. Weights have been assigned for each POP to create a training data matrix (N = 51) and used to calculate the cumulative effect or weighted sum, which is termed as the Pain Confidence Score (PCS). Based on PCS, a group of real-world patients (N = 40; AA and NA = 20 each) are classified as cases of AA or non-appendicitis (NA) with satisfactory results (sensitivity 85%, specificity 75%, precision 77%, and accuracy 80%). Most rural health centers (RHC) in developing nations lack specialist services and related infrastructure. Hence, such a tool could be useful in RHC to assist general physicians in screening AA and their timely referral to higher centers.

Methodological Triangulation Using Neural Networks for Business Research

Artificial neural network (ANN) modeling methods are becoming more widely used as both a research and application paradigm across a much wider variety of business, medical, engineering, and social science disciplines. The combination or triangulation of ANN methods with more traditional methods can facilitate the development of high-quality research models and also improve output performance for real world applications. Prior methodological triangulation that utilizes ANNs is reviewed and a new triangulation of ANNs with structural equation modeling and cluster analysis for predicting an individual's computer self-efficacy (CSE) is shown to empirically analyze the effect of methodological triangulation, at least for this specific information systems research case. A new construct, engagement, is identified as a necessary component of CSE models and the subsequent triangulated ANN models are able to achieve an 84% CSE group prediction accuracy.

Modeling the Ecological Footprint of Nations via Evolutionary Computation and Machine Learning Models

The per capita Ecological Footprint (EF) is one of the most-widely recognized measures of environmental sustainability. It seeks to quantify the Earth’s biological capacity required to support human activity. This study uses gene expression programming and Self-organizing Maps (SOM) to predict, classify and cluster the EF of 140 nations. A Bayesian approach was used to formally test the research hypotheses. By formulating the linear regression in a probabilistic framework, a Bayesian linear regression model is derived, and a specific simulation method, i.e., Markov Chain Monte Carlo (MCMC), is utilized to estimate the model parameters. Bayesian MCMC methods allow a richer and more complete representation of complex EF data. It also provides a computationally attractive and straightforward method to develop a full and complete description of the inherent uncertainty in parameters, quantiles and performance metrics.

The transcriptomic responses of the eastern oyster, Crassostrea virginica, to environmental conditions

Understanding the mechanisms by which organisms adapt to environmental conditions is a fundamental question for ecology and evolution. In this study, we evaluate changes in gene expression of a marine mollusc, the eastern oyster Crassostrea virginica, associated with the physico-chemical conditions and the levels of metals and other contaminants in their environment. The results indicate that transcript signatures can effectively disentangle the complex interactive gene expression responses to the environment and are also capable of disentangling the complex dynamic effects of environmental factors on gene expression. In this context, the mapping of environment to gene and gene to environment is reciprocal and mutually reinforcing. In general, the response of transcripts to the environment is driven by major factors known to affect oyster physiology such as temperature, pH, salinity, and dissolved oxygen, with pollutant levels playing a relatively small role, at least within the range of concentrations found in the studied oyster habitats. Further, the two environmental factors that dominate these effects (temperature and pH) interact in a dynamic and nonlinear fashion to impact gene expression. Transcriptomic data obtained in our study provide insights into the mechanisms of physiological responses to temperature and pH in oysters that are consistent with the known effects of these factors on physiological functions of ectotherms and indicate important linkages between transcriptomics and physiological outcomes. Should these linkages hold in further studies and in other organisms, they may provide a novel integrated approach for assessing the impacts of climate change, ocean acidification and anthropogenic contaminants on aquatic organisms via relatively inexpensive microarray platforms.

Prediction of clinical conditions after coronary bypass surgery using dynamic data analysis

This work studies the impact of using dynamic information as features in a machine learning algorithm for the prediction task of classifying critically ill patients in two classes according to the time they need to reach a stable state after coronary bypass surgery: less or more than 9 h. On the basis of five physiological variables (heart rate, systolic arterial blood pressure, systolic pulmonary pressure, blood temperature and oxygen saturation), different dynamic features were extracted, namely the means and standard deviations at different moments in time, coefficients of multivariate autoregressive models and cepstral coefficients. These sets of features served subsequently as inputs for a Gaussian process and the prediction results were compared with the case where only admission data was used for the classification. The dynamic features, especially the cepstral coefficients (aROC: 0.749, Brier score: 0.206), resulted in higher performances when compared to static admission data (aROC: 0.547, Brier score: 0.247). The differences in performance are shown to be significant. In all cases, the Gaussian process classifier outperformed to logistic regression.

Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks

BACKGROUND

Diagnosing acute appendicitis clinically is still difficult. We developed random forests, support vector machines, and artificial neural network models to diagnose acute appendicitis.

METHODS

Between January 2006 and December 2008, patients who had a consultation session with surgeons for suspected acute appendicitis were enrolled. Seventy-five percent of the data set was used to construct models including random forest, support vector machines, artificial neural networks, and logistic regression. Twenty-five percent of the data set was withheld to evaluate model performance. The area under the receiver operating characteristic curve (AUC) was used to evaluate performance, which was compared with that of the Alvarado score.

RESULTS

Data from a total of 180 patients were collected, 135 used for training and 45 for testing. The mean age of patients was 39.4 years (range, 16-85). Final diagnosis revealed 115 patients with and 65 without appendicitis. The AUC of random forest, support vector machines, artificial neural networks, logistic regression, and Alvarado was 0.98, 0.96, 0.91, 0.87, and 0.77, respectively. The sensitivity, specificity, positive, and negative predictive values of random forest were 94%, 100%, 100%, and 87%, respectively. Random forest performed better than artificial neural networks, logistic regression, and Alvarado.

CONCLUSION

We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making.

Ultrasonic diagnosis of acute appendicitis with atypical clinical manifestations

AIM: To explore the value of high and low frequency ultrasound in the diagnosis of acute appendicitis with atypical clinical manifestations.

METHODS: A total of 65 acute appendicitis patients with atypical clinical symptoms and signs but confirmed by surgery and pathology were examined and diagnosed by high frequency (7.0-10.0 MHz) associated with low frequency (3.5-4.0 MHz) ultrasound. Their ultrasonic images of acute appendicitis were reviewed retrospectively.

RESULTS: Fifty-four (83.08%) patients were diagnosed by ultrasound. The rates of diagnosis by high frequency and low frequency ultrasound were significantly different (83.08% vs 61.53%, χ² = 4.32, P < 0.05). Some indirect evidences were achieved by ultrasonography: appendiceal fecalith was observed in 33 (61.11%) patients, local adynamic ileus in 25 (46.29%) patients, periappendicular fluid in 21 (38.88%) patients and complex mass in 14 (25.92%) patients. Mesenteric lymphadenectasis was found in 10 (18.52%) patients.

CONCLUSION: In most cases, the correct diagnosis of acute appendicitis with atypical clinical manifestations can be made by high frequency associated with low frequency ultrasound.