Interpretable machine learning model to predict survival days of malignant brain tumor patients
An artificial intelligence (AI) model’s performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best featu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/acd5a9 |
| _version_ | 1797816949406695424 |
|---|---|
| author | Snehal Rajput Rupal A Kapdi Mehul S Raval Mohendra Roy |
| author_facet | Snehal Rajput Rupal A Kapdi Mehul S Raval Mohendra Roy |
| author_sort | Snehal Rajput |
| collection | DOAJ |
| description | An artificial intelligence (AI) model’s performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best feature set for predicting the survival days (SD) of GBM patients that outrank the current state-of-the-art methodologies. The proposed approach is an end-to-end AI model. This model first segments tumors from healthy brain parts in patients’ MRI images, extracts features from the segmented results, performs feature selection, and makes predictions about patients’ survival days (SD) based on selected features. The extracted features are primarily shape-based, location-based, and radiomics-based features. Additionally, patient metadata is also included as a feature. The selection methods include recursive feature elimination, permutation importance (PI), and finding the correlation between the features. Finally, we examined features’ behavior at local (single sample) and global (all the samples) levels. In this study, we find that out of 1265 extracted features, only 29 dominant features play a crucial role in predicting patients’ SD. Among these 29 features, one is metadata (age of patient), three are location-based, and the rest are radiomics features. Furthermore, we find explanations of these features using post-hoc interpretability methods to validate the model’s robust prediction and understand its decision. Finally, we analyzed the behavioral impact of the top six features on survival prediction, and the findings drawn from the explanations were coherent with the medical domain. We find that after the age of 50 years, the likelihood of survival of a patient deteriorates, and survival after 80 years is scarce. Again, for location-based features, the SD is less if the tumor location is in the central or back part of the brain. All these trends derived from the developed AI model are in sync with medically proven facts. The results show an overall 33% improvement in the accuracy of SD prediction compared to the top-performing methods of the BraTS-2020 challenge. |
| first_indexed | 2024-03-13T08:45:14Z |
| format | Article |
| id | doaj.art-893861ea05d845dab4c8183066b1751a |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-13T08:45:14Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-893861ea05d845dab4c8183066b1751a2023-05-30T05:59:35ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014202502510.1088/2632-2153/acd5a9Interpretable machine learning model to predict survival days of malignant brain tumor patientsSnehal Rajput0https://orcid.org/0000-0001-8240-3740Rupal A Kapdi1https://orcid.org/0000-0003-1995-4149Mehul S Raval2https://orcid.org/0000-0002-3895-1448Mohendra Roy3https://orcid.org/0000-0001-5815-3294SOT, Pandit Deendayal Energy University , PDEU Road, Gandhinagar 382007, Gujarat, IndiaInstitute of Technology, Nirma University , SG Highway, Ahmedabad 382481, Gujarat, IndiaSchool of Engineering and Applied Science, Ahmedabad University , Commerce Six Roads, Ahmedabad 380009, Gujarat, IndiaSOT, Pandit Deendayal Energy University , PDEU Road, Gandhinagar 382007, Gujarat, IndiaAn artificial intelligence (AI) model’s performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best feature set for predicting the survival days (SD) of GBM patients that outrank the current state-of-the-art methodologies. The proposed approach is an end-to-end AI model. This model first segments tumors from healthy brain parts in patients’ MRI images, extracts features from the segmented results, performs feature selection, and makes predictions about patients’ survival days (SD) based on selected features. The extracted features are primarily shape-based, location-based, and radiomics-based features. Additionally, patient metadata is also included as a feature. The selection methods include recursive feature elimination, permutation importance (PI), and finding the correlation between the features. Finally, we examined features’ behavior at local (single sample) and global (all the samples) levels. In this study, we find that out of 1265 extracted features, only 29 dominant features play a crucial role in predicting patients’ SD. Among these 29 features, one is metadata (age of patient), three are location-based, and the rest are radiomics features. Furthermore, we find explanations of these features using post-hoc interpretability methods to validate the model’s robust prediction and understand its decision. Finally, we analyzed the behavioral impact of the top six features on survival prediction, and the findings drawn from the explanations were coherent with the medical domain. We find that after the age of 50 years, the likelihood of survival of a patient deteriorates, and survival after 80 years is scarce. Again, for location-based features, the SD is less if the tumor location is in the central or back part of the brain. All these trends derived from the developed AI model are in sync with medically proven facts. The results show an overall 33% improvement in the accuracy of SD prediction compared to the top-performing methods of the BraTS-2020 challenge.https://doi.org/10.1088/2632-2153/acd5a9explainable AImachine learningfeatures importancebrain tumor segmentationsurvival predictioninterpretability |
| spellingShingle | Snehal Rajput Rupal A Kapdi Mehul S Raval Mohendra Roy Interpretable machine learning model to predict survival days of malignant brain tumor patients Machine Learning: Science and Technology explainable AI machine learning features importance brain tumor segmentation survival prediction interpretability |
| title | Interpretable machine learning model to predict survival days of malignant brain tumor patients |
| title_full | Interpretable machine learning model to predict survival days of malignant brain tumor patients |
| title_fullStr | Interpretable machine learning model to predict survival days of malignant brain tumor patients |
| title_full_unstemmed | Interpretable machine learning model to predict survival days of malignant brain tumor patients |
| title_short | Interpretable machine learning model to predict survival days of malignant brain tumor patients |
| title_sort | interpretable machine learning model to predict survival days of malignant brain tumor patients |
| topic | explainable AI machine learning features importance brain tumor segmentation survival prediction interpretability |
| url | https://doi.org/10.1088/2632-2153/acd5a9 |
| work_keys_str_mv | AT snehalrajput interpretablemachinelearningmodeltopredictsurvivaldaysofmalignantbraintumorpatients AT rupalakapdi interpretablemachinelearningmodeltopredictsurvivaldaysofmalignantbraintumorpatients AT mehulsraval interpretablemachinelearningmodeltopredictsurvivaldaysofmalignantbraintumorpatients AT mohendraroy interpretablemachinelearningmodeltopredictsurvivaldaysofmalignantbraintumorpatients |