Prognosticating Colorectal Cancer Recurrence using an Interpretable Deep Multi-view Network

Danliang Ho, Iain Bee Huat Tan, Mehul Motani
Proceedings of Machine Learning for Health, PMLR 158:97-109, 2021.

Abstract

Colorectal cancer (CRC) is among the top three most common cancers worldwide, and around 30-50% of patients who have undergone curative-intent surgery will eventually develop recurrence. Early and accurate detection of cancer recurrence is essential to improve the health outcomes of patients. In our study, we propose an explainable multi-view deep neural network capable of extracting and integrating features from heterogeneous healthcare records. Our model takes in inputs from multiple views and comprises: 1) two subnetworks adapted to extract high quality features from time-series and tabular data views, and 2) a network that combines the two outputs and predicts CRC recurrence. Our model achieves an AUROC score of 0.95, and precision, sensitivity and specificity scores of 0.84, 0.82 and 0.96 respectively, outperforming all-known published results based on the commonly-used CEA prognostic marker, as well as that of most commercially available diagnostic assays. We explain our model’s decision by highlighting important features within both data views that contribute to the outcome, using SHAP with a novel workaround that alleviates assumptions on feature independence. Through our work, we hope to contribute to the adoption of AI in healthcare by creating accurate and interpretable models, leading to better post-operative management of CRC patients.

Cite this Paper

BibTeX
@InProceedings{pmlr-v158-ho21a, title = {Prognosticating Colorectal Cancer Recurrence using an Interpretable Deep Multi-view Network}, author = {Ho, Danliang and Tan, Iain Bee Huat and Motani, Mehul}, booktitle = {Proceedings of Machine Learning for Health}, pages = {97--109}, year = {2021}, editor = {Roy, Subhrajit and Pfohl, Stephen and Rocheteau, Emma and Tadesse, Girmaw Abebe and Oala, Luis and Falck, Fabian and Zhou, Yuyin and Shen, Liyue and Zamzmi, Ghada and Mugambi, Purity and Zirikly, Ayah and McDermott, Matthew B. A. and Alsentzer, Emily}, volume = {158}, series = {Proceedings of Machine Learning Research}, month = {04 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v158/ho21a/ho21a.pdf}, url = {https://proceedings.mlr.press/v158/ho21a.html}, abstract = {Colorectal cancer (CRC) is among the top three most common cancers worldwide, and around 30-50% of patients who have undergone curative-intent surgery will eventually develop recurrence. Early and accurate detection of cancer recurrence is essential to improve the health outcomes of patients. In our study, we propose an explainable multi-view deep neural network capable of extracting and integrating features from heterogeneous healthcare records. Our model takes in inputs from multiple views and comprises: 1) two subnetworks adapted to extract high quality features from time-series and tabular data views, and 2) a network that combines the two outputs and predicts CRC recurrence. Our model achieves an AUROC score of 0.95, and precision, sensitivity and specificity scores of 0.84, 0.82 and 0.96 respectively, outperforming all-known published results based on the commonly-used CEA prognostic marker, as well as that of most commercially available diagnostic assays. We explain our model’s decision by highlighting important features within both data views that contribute to the outcome, using SHAP with a novel workaround that alleviates assumptions on feature independence. Through our work, we hope to contribute to the adoption of AI in healthcare by creating accurate and interpretable models, leading to better post-operative management of CRC patients.} }
Endnote
%0 Conference Paper %T Prognosticating Colorectal Cancer Recurrence using an Interpretable Deep Multi-view Network %A Danliang Ho %A Iain Bee Huat Tan %A Mehul Motani %B Proceedings of Machine Learning for Health %C Proceedings of Machine Learning Research %D 2021 %E Subhrajit Roy %E Stephen Pfohl %E Emma Rocheteau %E Girmaw Abebe Tadesse %E Luis Oala %E Fabian Falck %E Yuyin Zhou %E Liyue Shen %E Ghada Zamzmi %E Purity Mugambi %E Ayah Zirikly %E Matthew B. A. McDermott %E Emily Alsentzer %F pmlr-v158-ho21a %I PMLR %P 97--109 %U https://proceedings.mlr.press/v158/ho21a.html %V 158 %X Colorectal cancer (CRC) is among the top three most common cancers worldwide, and around 30-50% of patients who have undergone curative-intent surgery will eventually develop recurrence. Early and accurate detection of cancer recurrence is essential to improve the health outcomes of patients. In our study, we propose an explainable multi-view deep neural network capable of extracting and integrating features from heterogeneous healthcare records. Our model takes in inputs from multiple views and comprises: 1) two subnetworks adapted to extract high quality features from time-series and tabular data views, and 2) a network that combines the two outputs and predicts CRC recurrence. Our model achieves an AUROC score of 0.95, and precision, sensitivity and specificity scores of 0.84, 0.82 and 0.96 respectively, outperforming all-known published results based on the commonly-used CEA prognostic marker, as well as that of most commercially available diagnostic assays. We explain our model’s decision by highlighting important features within both data views that contribute to the outcome, using SHAP with a novel workaround that alleviates assumptions on feature independence. Through our work, we hope to contribute to the adoption of AI in healthcare by creating accurate and interpretable models, leading to better post-operative management of CRC patients.
APA
Ho, D., Tan, I.B.H. & Motani, M.. (2021). Prognosticating Colorectal Cancer Recurrence using an Interpretable Deep Multi-view Network. Proceedings of Machine Learning for Health, in Proceedings of Machine Learning Research 158:97-109 Available from https://proceedings.mlr.press/v158/ho21a.html.

Related Material