Novel solutions for an old disease: Diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks
SurgeryPublished 14 May 2010
Chung-Ho Hsieh, Ruey-Hwa Lu, Nai-Hsin Lee, Wen‐Ta Chiu, Min‐Huei Hsu, Yu‐Chuan Li
Citations170
SJR quartileQ1
SJR score1.09
SNIP1.16
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making.
Abstract
We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making.
Keywords
Decision SciencesMedicine
Machine LearningRandom Forests
126,192 Citations2001Leo Breiman
Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Machine LearningSupport-vector networks
40,463 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Elsevier eBooksData Mining: Practical Machine Learning Tools and Techniques
25,718 Citations2011Ian H. Witten, Eibe Frank
RadiologyThe meaning and use of the area under a receiver operating characteristic (ROC) curve.
21,812 Citations1982J A Hanley, Barbara J. McNeil
A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented and it is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a random chosen non-diseased subject.
A study of cross-validation and bootstrap for accuracy estimation and model selection
10,733 Citations1995Ron Kohavi
The results indicate that for real-word datasets similar to the authors', the best method to use for model selection is ten fold stratified cross validation even if computation power allows using more folds.
Journal of Biomedical InformaticsLogistic regression and artificial neural network classification models: a methodology review
2,180 Citations2002Stephan Dreiseitl, Lucila Ohno‐Machado
This review summarizes the differences and similarities of logistic regression and artificial neural networks from a technical point of view, and compares them with other machine learning algorithms.
Annals of Emergency MedicineA practical score for the early diagnosis of acute appendicitis
1,519 Citations1986Alfredo Alvarado
A practical diagnostic score is devised that may help in interpreting the confusing picture of acute appendicitis.
IEEE Transactions on Knowledge and Data EngineeringBenchmarking attribute selection techniques for discrete class data mining
1,231 Citations2003Mark A. Hall, Geoffrey Holmes
A benchmark comparison of several attribute selection methods for supervised classification by cross-validating the attribute rankings with respect to a classification learner to find the best attributes.
Journal of Clinical EpidemiologyExternal validation is necessary in prediction research:
697 Citations2003Sacha E. Bleeker, Henriëtte A. Moll +5 more
For relatively small data sets, internal validation of prediction models by bootstrap techniques may not be sufficient and indicative for the model's performance in future patients.
BMJComputer-aided Diagnosis of Acute Abdominal Pain
674 Citations1972F T de Dombal, D J Leaper +3 more
It is suggested as a result of these studies that the provision of such a system to aid the clinician is both feasible in a real-time clinical setting, and likely to be of practical value, albeit in a small percentage of cases.
British journal of surgeryMeta-analysis of the clinical and laboratory diagnosis of appendicitis
618 Citations2004Roland E. Andersson
This review analyses the diagnostic value of elements of disease history, clinical findings and laboratory test results in suspected appendicitis.
The LancetIntroduction to neural networks
608 Citations1995Simon S. Cross, Robert F. Harrison +1 more
Archives of SurgeryThe Clinical and Economic Correlates of Misdiagnosed Appendicitis
420 Citations2002David R. Flum, Thomas D. Koepsell
Annals of SurgeryAppendectomy
357 Citations1997Douglas A. Hale, Mark P. Molloy +3 more
Despite a marked decline in associated mortality over the past 50 years, rates of perforation and negative appendectomy remain unchanged because they are influenced strongly by factors untouched by the intervening technologic advances.
Journal of the American College of SurgeonsHow Time Affects the Risk of Rupture in Appendicitis
353 Citations2006Nina A. Bickell, Arthur H. Aufses +2 more
Physicians should be cautious about delaying surgery beyond 36 hours from symptom onset in patients with appendicitis and risk of rupture in ensuing 12-hour periods rises to 5% after 36 hours of untreated symptoms.
American Journal of RoentgenologySonographic detection of the normal and abnormal appendix.
242 Citations1992Michel Rioux
Sonography is useful in detecting acute appendicitis and can clearly show the normal appendix more frequently than previously reported, andRuptured appendix was predicted in all cases.
PubMedDiagnostic scores for acute appendicitis. Abdominal Pain Study Group.
213 Citations1995Christian Ohmann, Qin Yang +1 more
Evaluation of the published data showed that the Alvarado score fulfilled all four criteria and the Lindberg, the Fenyö and the Christian scores fulfilled two criteria each, whereas the evaluation gives more realistic estimates of the routine performance in different clinical environments.
British journal of surgerySuspected acute appendicitis: trends in management over 30 years
179 Citations2001P F Jones
Ultrasonography, laparoscopy and computed tomography have also been used to clarify the diagnosis in patients with signs suspicious of acute appendicitis, and this has now been studied over 30 years.
American Journal of RoentgenologyCT and sonographic evaluation of acute right lower quadrant abdominal pain.
168 Citations1998Bernard A. Birnbaum, R. Brooke Jeffrey
The increased availability and use of CT and sonography have dramatically changed the clinical examination and treatment of patients who present with acute abdominal pain and these noninvasive imaging techniques have effectively replaced exploratory laparotomy as the primary means of examining patients.
The American Journal of SurgeryHigh negative appendectomy rates are no longer acceptable
143 Citations1997Michelle Colson, Kristin A. Skinner +1 more
A negative appendectomy rate lower than that in other reported series, while maintaining an acceptable perforation rate is achieved, in the majority of patients, perforated appendicitis is a result of late presentation.
Diseases of the Colon & RectumInfluence of Delays on Perforation Risk in Adults with Acute Appendicitis
108 Citations2008David Kearney, Ronan A. Cahill +3 more
In-hospital delay was not an independent predictor of perforation in adults with acute appendicitis although delays may contribute if patients are left to wait unduly, and tachycardia at presentation may be a quantifiable feature of those more likely to have perforations and who should be given higher surgical priority.
World Journal of SurgeryArtificial Neural Networks: Useful Aid in Diagnosing Acute Appendicitis
72 Citations2007S. G. Prabhudesai, S. Gould +4 more
ANNs can be an effective tool for accurately diagnosing appendicitis and may reduce unnecessary appendectomies.
International Journal of Medical InformaticsNeural network modeling for surgical decisions on traumatic brain injury patients
69 Citations2000Yu‐Chuan Li, Li Liu +2 more
The feasibility of applying neural networks as the mechanism for TBI decision support systems based on clinical databases is demonstrated and the results suggest that neural networks may be a better solution for complex, non-linear medical decision support system than conventional statistical techniques such as logistic regression.
Computer Methods and Programs in BiomedicinePredicting hypotensive episodes during spinal anesthesia with the application of artificial neural networks
57 Citations2008Chao‐Shun Lin, Jainn-Shiun Chiu +4 more
The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for hypotension during spinal anesthesia, in allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of anesthesia.
Computer Methods and Programs in BiomedicineArtificial neural network prediction of clozapine response with combined pharmacogenetic and clinical data
52 Citations2008Chao-Cheng Lin, Daqing Wang +7 more
To train and validate artificial neural networks (ANN), using clinical and pharmacogenetic data, to predict clozapine response in schizophrenic patients, the optimal ANN architecture was found to be a standard feed-forward, fully-connected, back-propagation multilayer perceptron.
Journal of Medical SystemsComparison of the Levels of Accuracy of an Artificial Neural Network Model and a Logistic Regression Model for the Diagnosis of Acute Appendicitis
46 Citations2007Shinya Sakai, Kuriko Kobayashi +4 more
The artificial neural network models provided more accurate results than did the logistic regression models for both indices, especially when categorical variables or normalized variables were used.
Surgical EndoscopyLaparoscopy may be lowering the threshold to operate on patients with suspected appendicitis
32 Citations2002James M. McGreevy, Samuel R.G. Finlayson +4 more
At a tertiary care medical center, the availability of the laparoscopic approach to appendectomy may have lowered the threshold to operate on patients with possible appendicitis, as reflected in higher negative exploration rates and lower rates of perforated appendectomy.
Neural network paradigm comparisons for appendicitis diagnoses
29 Citations2002R.C. Eberhart, Roy W. Dobbins +1 more
The results of comparisons among diagnoses of appendicitis versus nonspecific abdominal pain using three neural-network paradigms are reported and a structure for network input data files that could contribute to a process of standardization is proposed.
Baillière s Clinical GastroenterologyThe acute abdomen: the role of computer-assisted diagnosis
16 Citations1991A A Gunn
The results show that an improvement in diagnostic accuracy and a reduction in admissions and unnecessary laparotomies continues over 15 years, and it is concluded that documentation is essential.