Detection of risk factors of PCOS patients with Local Interpretable Model-agnostic Explanations (LIME) Method that an explainable artificial intelligence model

Authors : İpek BALIKÇI ÇİÇEK, Zeynep KÜÇÜKAKÇALI, Fatma Hilal YAĞIN

Pages : 59-63

Doi:10.52876/jcs.1004847

View : 16 | Download : 19

Publication Date : 2021-12-30

Article Type : Research Paper

Abstract :Aim: In this study, it is aimed to extract patient-based explanations of the contribution of important features in the decision-making process insert ignore into journalissuearticles values(estimation); of the Random forest insert ignore into journalissuearticles values(RF); model, which is difficult to interpret for PCOS disease risk, with Local Interpretable Model-Agnostic Explanations insert ignore into journalissuearticles values(LIME);. Materials and Methods: In this study, the Local Interpretable Model-Agnostic Annotations insert ignore into journalissuearticles values(LIME); method was applied to the “Polycystic ovary syndrome” dataset to explain the Random Forest insert ignore into journalissuearticles values(RF); model, which is difficult to interpret for PCOS risk factors estimation. This dataset is available at https://www.kaggle.com/prasoonkottarathil/polycystic-ovary-syndrome-pcos. Results: Accuracy, sensitivity, specificity, positive predictive value, negative predictive value and balanced accuracy obtained from the Random Forest method were 86.03%, 86.32%, 85.37%, 93.18%, 72.92% and 85.84% respectively. According to the obtained results, the observations whose results were obtained, the values of Follicle insert ignore into journalissuearticles values(No); L. and Follicle insert ignore into journalissuearticles values(No); R. in different value ranges were positively correlated with the absence of PCOS. For the observations whose absence of PCOS results were obtained, the variables RBSinsert ignore into journalissuearticles values(mg/dl);, bmi_y, fsh_lh, TSH insert ignore into journalissuearticles values(mIU/L);, Endometrium insert ignore into journalissuearticles values(mm); also played a role in obtaining the results. In addition, for the observations whose results were obtained, the values of Follicle No L and Follicle No R in different value ranges were also found to be positively correlated with PCOS. In addition, beta-HCGinsert ignore into journalissuearticles values(mIU/mL);, PRGinsert ignore into journalissuearticles values(ng/mL);, RBSinsert ignore into journalissuearticles values(mg/dl);, bmi_y, Endometrium insert ignore into journalissuearticles values(mm);, fsh_lh variables also played a role in obtaining the results for PCOS. Conclusion: When the observations obtained from the results are examined, it can be said that the Follicle insert ignore into journalissuearticles values(No); L. and Follicle insert ignore into journalissuearticles values(No); R. variables are the most effective variables on the presence or absence of PCOS. For different value ranges of these two variables, the result of PCOS or not varies. Based on this, it can be said that different values of Follicle insert ignore into journalissuearticles values(No); L. and Follicle insert ignore into journalissuearticles values(No); R. variables for PCOS status may be effective in determining the disease.
Keywords : PCOS, random forest, Explainable Artificial Intelligence, Local Interpretable Model agnostic Explanations LIME,