Project

Case based reasoning (CBR) for medical applications

Goal: CBR in the health science are oriented to the case representation where is necessary synthesizing adequate features for CBR, reducing the number of features in highly dimensional data and one important focus will be how case based reasoning can associate probabilities and statistics with its results and taking into account the concurrence of several ailments.

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
11
Reads
0 new
155

Project log

Diego Peluffo
added a research item
Abstract: This paper compares the main combinations of classifiers (Sequential, Parallel and Stacking) over two remarkable medical data collections: Cleveland and Dermatology. The principal rationale underlying the use of multiple classifiers is that together the methods may be powered rather than their individual behavior. Such a premise is validated through the identification of the best the combination reaching the lowest error rate within a case-based reasoning system (CBR). The different combinations are essentially formed by five different classifiers greatly different regarding their nature and inception: SVM (Support Vector Machines), Parzen, Random Forest, K-NN (k-nearest neighbors) and Naive Bayes. From experimental results, it can be inferred that the combination of techniques is greatly useful. Also, in this work, some key aspects and hints are discussed about the relationship between the nature of the input data and the classification (either individual or mixture of classifiers) stage building within a CBR framework.
Xiomara Blanco
added a research item
Case-Based Reasoning Systems (CBR) are in constant evolution, as a result, this article proposes improving the retrieve and adaption stages through a different approach. A series of experiments were made, divided in three sections: a proper pre-processing technique, a cascade classification, and a probability estimation procedure. Every stage offers an improvement, a better data representation, a more efficient classification, and a more precise probability estimation provided by a Support Vector Machine (SVM) estimator regarding more common approaches. Concluding, more complex techniques for classification and probability estimation are possible, improving CBR systems performance due to lower classification error in general cases.
Xiomara Blanco
added a research item
CBR ha demostrado ser apropiado para trabajar con datos de dominios poco estructurados o situaciones donde es difícil la adquisición de conocimiento, como es el caso del diagnóstico médico, donde es posible identificar enfermedades como: cáncer, predicción de epilepsia y diagnóstico de apendicitis. Algunas de las tendencias que se pueden desarrollar para CBR en la ciencia de la salud están orientadas a reducir el número de características en datos de gran dimensión. Una contribución importante puede ser la estimación de probabilidades de pertenencia a cada clase para los nuevos casos. Con el fin de representar adecuadamente la base de datos y evitar los inconvenientes causados por la alta dimensión, ruido y redundancia de los mimos, en este trabajo, se utiliza varios algoritmos en la etapa de pre-procesamiento para realizar una selección de variables y reducción de dimensiones. Además, se realiza una comparación del rendimiento de algunos clasificadores multi-clase representativos para identificar el más eficaz e incluirlo en un esquema CBR. En particular, se emplean cuatro técnicas de clasificación y dos técnicas de reducción para hacer un estudio comparativo de clasificadores multi-clase sobre CBR
Mabel Ortega
added 2 research items
We propose the use of variable selection and dimension reduction techniques in a preprocessing stage for CBR tasks, finally, we make a comparative study of multi-class classifiers to assess processed data performance.
Razonamiento basado en casos aplicado al diagnóstico médico utilizando clasificadores multi-clase: Un estudio preliminar (Case based reasoning applied to medical diagnosis using multi-class classifier: A preliminary study) Abstract: Case-based reasoning (CBR) is a process used for computer processing that tries to mimic the behavior of a human expert in making decisions regarding a subject and learn from the experience of past cases. CBR has demonstrated to be appropriate for working with unstructured domains data or difficult knowledge acquisition situations, such as medical diagnosis, where it is possible to identify diseases such as: cancer diagnosis, epilepsy prediction and appendicitis diagnosis. Some of the trends that may be developed for CBR in the health science are oriented to reduce the number of features in highly dimensional data. An important contribution may be the estimation of probabilities of belonging to each class for new cases. In this paper, in order to adequately represent the database and to avoid the inconveniences caused by the high dimensionality, noise and redundancy, a number of algorithms are used in the preprocessing stage for performing both variable selection and dimension reduction procedures. Also, a comparison of the performance of some representative multi-class classifiers is carried out to identify the most effective one to include within a CBR scheme. Particularly, four classification techniques and two reduction techniques are employed to make a comparative study of multi-class classifiers on CBR. Resumen: CBR ha demostrado ser apropiado para trabajar con datos de dominios poco estructurados o situaciones donde es difícil la adquisición de conocimiento, como es el caso del diagnóstico médico, donde es posible identificar enfermedades como: cáncer, predicción de epilepsia y diagnóstico de apendicitis. Algunas de las tendencias que se pueden desarrollar para CBR en la ciencia de la salud están orientadas a reducir el número de características en datos de gran dimensión. Una contribución importante puede ser la estimación de probabilidades de pertenencia a cada clase para los nuevos casos. Con el fin de representar adecuadamente la base de datos y evitar los inconvenientes causados por la alta dimensión, ruido y redundancia de los mimos, en este trabajo, se utiliza varios algoritmos en la etapa de pre-procesamiento para realizar una selección de variables y reducción de dimensiones. Además, se realiza una comparación del rendimiento de algunos clasificadores multi-clase representativos para identificar el más eficaz e incluirlo en un esquema CBR. En particular, se emplean cuatro técnicas de clasificación y dos técnicas de reducción para hacer un estudio comparativo de clasificadores multi-clase sobre CBR. Palabras clave: Razonamiento basado en casos; alta dimensión; selección de variables.
Xiomara Blanco
added 2 research items
Case-based reasoning (CBR) is a problem solving approach that uses past experience to tackle current problems. CBR has demonstrated to be appropriate for working with unstructured domains data or difficult knowledge acquisition situations, as it is the case of the diagnosis of many diseases. Some of the trends and opportunities that may be developed for CBR in the health science are oriented to reduce the number of features in highly dimensional data, as well as another important focus on how CBR can associate probabilities and statistics with its results by taking into account the concurrence of several ailments. In this paper, in order to adequately represent the database and to avoid the inconveniences caused by the high dimensionality, a number of algorithms are used in the preprocessing stage for performing both variable selection and dimension reduction procedures. Subsequently, we make a comparative study of multi-class classifiers. Particularly, four classification techniques and two reduction techniques are employed to make a comparative study of multi-class classifiers on CBR.
The Case-Based Reasoning (CBR) is an appropriate methodology to apply in diagnosis and treatment. Research in CBR is growing and there are shortcomings, especially in the adaptation mechanism. In this paper, besides presenting a methodological review of the technology applied to the diagnostics and health sector published in recent years, a new proposal is presented to improve the adaptation stage. This proposal is focused on preparing the data to create association rules that help to reduce the number of cases and facilitate learning adaptation rules.
Xiomara Blanco
added a project goal
CBR in the health science are oriented to the case representation where is necessary synthesizing adequate features for CBR, reducing the number of features in highly dimensional data and one important focus will be how case based reasoning can associate probabilities and statistics with its results and taking into account the concurrence of several ailments.