An ensemble classifier approach for disease diagnosis using Random Forest

Pachange, Sarika; Joglekar, Bela; Kulkarni, Parag

doi:10.1109/indicon.2015.7443826

Cited by 7 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The result of crisp has also shown that we can diagnose the patient's low or high risk of disease [41]. Recently several neuro-fuzzy techniques have been reported in the literature [7], [9], [10] and [20] for classification of patterns.…”

Section: Currently Used Methods For Pulmonary Tuberculosis Diagnmentioning

confidence: 99%

“…Long -term lung damage is associated with delayed treatment of PTB, often clinically mistaken for nontuberculosis pneumonia due to symptom similarities and presentation of chest X -ray (CXR) [6]. They reported that a delay in treatment of more than twelve weeks would result in a greater extent of patients with serious TB, a higher mortality rate, and a more prominent disappointment in treatment [7] [8]. For some reasons [9] and [10], diagnosis of tuberculosis is difficult.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applications of Soft Computing Techniques for Pulmonary Tuberculosis Diagnosis

2019

IJRTE

View full text Add to dashboard Cite

Recently, several interesting research studies have been reported on soft computing approaches. Soft computing approaches are solving several kinds of problems and provide alternative solutions. Different Soft computing techniques or approaches have been applied in medical care data for effective diagnosis prediction. Those approaches implemented on diseases diagnosing of pulmonary tuberculosis and obtaining better results in comparison to traditional approaches. This approach is an aggregation of methodologies that were combined various model and provide solutions to those problems that are difficult to handle in real-world situations. Researchers keep developing of an accurate and reliable intelligent decision-making method for the construction of pulmonary tuberculosis diagnosis system. The existing diagnostic testing system procedures are not only tedious, they also take a long time to analyze. Therefore, the diagnosis of tuberculosis still requires further improvements to new rapid and accurate diagnostic model and techniques that enable higher sensitivity and specificity to be achieved, thus promoting disease control and Prevention. State of the art makes approaches to soft computing more powerful, more reliable and more efficient. The importance of this review paper is to distinguish the different soft computing approaches used to support pulmonary tuberculosis disease diagnosis, identification, prediction and intelligent classification. In the field, researchers and medical practitioners look forward to using approaches to soft computing. Some of these are an artificial neural network, genetic algorithm, and support vector machine, fuzzy logic etc. latest methods in the diagnostic field uses artificial neural network. Some of the other benefits of Artificial neural network is an easy - to - optimize, resources and adoptable non - linear modeling of expansive data sets and predictive inference accuracy demonstrating that artificial neural network could serve as a valuable decision support tool in various fields, including medicine

show abstract

Section: Currently Used Methods For Pulmonary Tuberculosis Diagnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Applications of Soft Computing Techniques for Pulmonary Tuberculosis Diagnosis

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…The RF (Pachange et al, 2015) is an assembly method, where multiple decision trees are combined to generate predictions. This method is based on building decision trees, where data are divided using the problem variables, applying some criterion that evaluates and maximizes the gain of information.…”

Section: Techniquesmentioning

confidence: 99%

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Fernández-Ruiz,

Núñez-Vidal,

Hidalgo-delaguía

et al. 2024

Front. Comput. Neurosci.

View full text Add to dashboard Cite

This research work introduces a novel, nonintrusive method for the automatic identification of Smith–Magenis syndrome, traditionally studied through genetic markers. The method utilizes cepstral peak prominence and various machine learning techniques, relying on a single metric computed by the research group. The performance of these techniques is evaluated across two case studies, each employing a unique data preprocessing approach. A proprietary data “windowing” technique is also developed to derive a more representative dataset. To address class imbalance in the dataset, the synthetic minority oversampling technique (SMOTE) is applied for data augmentation. The application of these preprocessing techniques has yielded promising results from a limited initial dataset. The study concludes that the k-nearest neighbors and linear discriminant analysis perform best, and that cepstral peak prominence is a promising measure for identifying Smith–Magenis syndrome.

show abstract

“…Currently, data mining and machine learning techniques allow the exploration and analyzation of data patterns through statistical methods and artificial intelligence [ 1 , 2 , 3 ]. Researchers can obtain correlations and patterns from large data sets to create new knowledge with the help of machine learning and artificial intelligence [ 4 , 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Algorithms in the Prediction of Hospitalized Patients with Schizophrenia

Alonso

Marques

Agarwal

et al. 2022

Sensors

View full text Add to dashboard Cite

New computational methods have emerged through science and technology to support the diagnosis of mental health disorders. Predictive models developed from machine learning algorithms can identify disorders such as schizophrenia and support clinical decision making. This research aims to compare the performance of machine learning algorithms: Decision Tree, AdaBoost, Random Forest, Naïve Bayes, Support Vector Machine, and k-Nearest Neighbor in the prediction of hospitalized patients with schizophrenia. The data set used in the study contains a total of 11,884 electronic admission records corresponding to 6933 patients with various mental health disorders; these records belong to the acute units of 11 public hospitals in a region of Spain. Of the total, 5968 records correspond to patients diagnosed with schizophrenia (3002 patients) and 5916 records correspond to patients with other mental health disorders (3931 patients). The results recommend Random Forest with the best accuracy of 72.7%. Furthermore, this algorithm presents 79.6%, 72.8%, 72.7%, and 72.7% for AUC, precision, F1-Score, and recall, respectively. The results obtained suggest that the use of machine learning algorithms can classify hospitalized patients with schizophrenia in this population and help in the hospital management of this type of disorder, to reduce the costs associated with hospitalization.

show abstract

An ensemble classifier approach for disease diagnosis using Random Forest

Cited by 7 publications

References 22 publications

Applications of Soft Computing Techniques for Pulmonary Tuberculosis Diagnosis

Applications of Soft Computing Techniques for Pulmonary Tuberculosis Diagnosis

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Comparison of Machine Learning Algorithms in the Prediction of Hospitalized Patients with Schizophrenia

Contact Info

Product

Resources

About