Cervical cancer risk prediction with robust ensemble and explainable black boxes method

Abstract

Clinical decision support systems (CDSS) that make use of algorithms based on intelligent systems, such as machine learning or deep learning, they suffer from the fact that often the methods used are hard to interpret and difficult to understand on how some decisions are made; the opacity of some methods, sometimes voluntary due to problems such as data privacy or the techniques used to protect intellectual property, makes these systems very complicated. Besides this series of problems, the results obtained also suffer from the poor possibility of being interpreted; in the clinical context therefore it is required that the methods used are as accurate as possible, transparent techniques and explainable results. In this work the problem of the development of cervical cancer is treated, a disease that mainly affects the female population. In order to introduce advanced machine learning techniques in a clinical decision support system that can be transparent and explainable, a robust, accurate ensemble method is presented, in terms of error and sensitivity linked to the classification of possible development of the aforementioned pathology and advanced techniques are also presented of explainability and interpretability (Explanaible Machine Learning) applied to the context of CDSS such as Lime and Shapley. The results obtained, as well as being interesting, are understandable and can be implemented in the treatment of this type of problem.

A Fast Accurate Deep Learning Framework for Prediction of All Cancer Types

“…To verify their dependability and efficacy, the frameworks were tested on six standard data sets, including breast, lung, prostate, colon, ovarian and cervical cancer. These data sets are freely available and continue to be utilized in the majority of contemporary investigations [20][21][22][23][24][25][26][27].  FS is a method for quickly picking the best features for NN training, possibly enhancing cancer prognostic prediction while also lowering the bulk of the input data to LSTM.…”

“…of hidden layers and no. of neurons/layer) have been published [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]. Accordingly, this thought has been succeeded in the application of deep learning biomedical techniques, especially in case of large datasets which includes two important cases, initial and severe states of the diseases, that happens in all diseases.…”

“…6): it is presented by the UCI ML Repository [47] gathered from specialist's questionnaire in Jakarta. It has 72 records each with 19 features [24].…”

“…Additionally, some deduced advanced metrics such recall, accuracy and precision (shown in Eqs. [18][19][20][21][22][23][24] are used to help more accurately assessment the proposed framework. True Positive (TP): is the number of correct positive predictions.…”

A Clinical Decision Support System for Assessing the Risk of Cervical Cancer: Development and Evaluation Study

“…Although some similar systems have been previously developed for cervical cancer risk assessment, the number and types of input and output variables and the types of rules and algorithms used are different. According to the literature, machine learning algorithms to predict cervical cancer [ 17 ], artificial neural networks (ANNs) to combine the cytology and biomarker results [ 18 ], and ANNs to classify the normal and abnormal cells in the cervix region of the uterus [ 19 ] have been applied in previous studies. However, in these studies, the cytology results were the main input variables.…”