Abstract

Breast cancer is currently one of the main causes of death and tumoral diseases in women. Even if early diagnosis processes have evolved in the last years thanks to the popularization of mammogram tests, nowadays, it is still a challenge to have available reliable diagnosis systems that are exempt of variability in their interpretation. To this end, in this work, the design and development of an intelligent clinical decision support system to be used in the preventive diagnosis of breast cancer is presented, aiming both to improve the accuracy in the evaluation and to reduce its uncertainty. Through the integration of expert systems (based on Mamdani-type fuzzy-logic inference engines) deployed in cascade, exploratory factorial analysis, data augmentation approaches, and classification algorithms such as k-neighbors and bagged trees, the system is able to learn and to interpret the patient’s medical-healthcare data, generating an alert level associated to the danger she has of suffering from cancer. For the system’s initial performance tests, a software implementation of it has been built that was used in the diagnosis of a series of patients contained into a 130-cases database provided by the School of Medicine and Public Health of the University of Wisconsin-Madison, which has been also used to create the knowledge base. The obtained results, characterized as areas under the ROC curves of 0.95–0.97 and high success rates, highlight the huge diagnosis and preventive potential of the developed system, and they allow forecasting, even when a detailed and contrasted validation is still pending, its relevance and applicability within the clinical field.

Highlights

  • Breast cancer is, after lung cancer, the second main cause of death by tumoral diseases in women as well as one of the more frequently diagnosed malignant cancer types [1,2]

  • Different studies were carried out that assess the efficiency and convenience of performing mammogram-based screenings [3,4,5,6,7,8,9,10], which generally conclude that they are a significant help to reduce the mortality associated to breast cancer, even if they might show a certain trend toward over-diagnosing [10]

  • It is reasonable to state that the efficiency in the interpretation of mammogram images is key in the detection, diagnosis, and potential treatment of breast cancer cases

Read more

Summary

Introduction

After lung cancer, the second main cause of death by tumoral diseases in women as well as one of the more frequently diagnosed malignant cancer types [1,2]. It is relevant to indicate that the diagnosis methods based on medical images, such as mammography, echography, or magnetic resonance, are used as well as a complement in the confirmation diagnosis of breast cancer cases in women showing any characteristic sign or symptom, even if it is necessary to point out that at this moment there are not published studies, indicating that the absence of this implies the absence of breast cancer in the patient [18] Within this healthcare context, which is common in countries having a centralized healthcare system, and in light of all those matters previously commented, in this field, it is key to have tools available that allow providing support to the difficult process of evaluating and diagnosing breast cancer, trying to minimize as much as possible its subjective variability, which is translated into medical terms as false positive and false negative diagnosis cases.

Materials and Methods
Database Usage
Conceptual Design and Description of the System
Implementation of the System
Data Preparation
Determination of Latent Factors
The Machine Learning Algorithm
Data Processing and Interpretation
Generation of Alerts and Decision Making
Interpretation of the Results
Findings
Discussion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call