Knowledge Guided Multi-instance Multi-label Learning via Neural Networks in Medicines Prediction

Junyuan Shang, Shenda Hong, Yuxi Zhou, Meng Wu, Hongyan Li
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:831-846, 2018.

Abstract

Predicting medicines for patients with co-morbidity has long been recognized as a hard task due to complex dependencies between diseases and medicines. Efforts have been made recently to build high-order dependency between diseases and medicines by extracting knowledge from electronic health records (EHR). But current works failed to utilize additional knowledge and ignored the data skewness problem which lead to sub-optimal combination of medicines. In this paper, we formulate the medicines prediction task in multi-instance multi-label learning framework considering the multi-diagnoses as input instances and multi-medicines as output labels. We propose a knowledge-guided multi-instance multi-label networks called \mname where two types of additional knowledge are incorporated into a RNN encoder-decoder model. The utilization of structural knowledge like clinical ontology provides a way to learn better representation called tree embedding by utilizing the ancestors’ information. Contextual knowledge is a global summarization of input instances which is informative for personal prediction. Experiments are conducted on a real world clinical dataset which showed the necessity to combine both contextual and structural knowledge and the \mname performs better than baselines up to 4+% in terms of Jaccard similarity score.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-shang18c, title = {Knowledge Guided Multi-instance Multi-label Learning via Neural Networks in Medicines Prediction}, author = {Shang, Junyuan and Hong, Shenda and Zhou, Yuxi and Wu, Meng and Li, Hongyan}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {831--846}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/shang18c/shang18c.pdf}, url = {https://proceedings.mlr.press/v95/shang18c.html}, abstract = {Predicting medicines for patients with co-morbidity has long been recognized as a hard task due to complex dependencies between diseases and medicines. Efforts have been made recently to build high-order dependency between diseases and medicines by extracting knowledge from electronic health records (EHR). But current works failed to utilize additional knowledge and ignored the data skewness problem which lead to sub-optimal combination of medicines. In this paper, we formulate the medicines prediction task in multi-instance multi-label learning framework considering the multi-diagnoses as input instances and multi-medicines as output labels. We propose a knowledge-guided multi-instance multi-label networks called \mname where two types of additional knowledge are incorporated into a RNN encoder-decoder model. The utilization of structural knowledge like clinical ontology provides a way to learn better representation called tree embedding by utilizing the ancestors’ information. Contextual knowledge is a global summarization of input instances which is informative for personal prediction. Experiments are conducted on a real world clinical dataset which showed the necessity to combine both contextual and structural knowledge and the \mname performs better than baselines up to 4+% in terms of Jaccard similarity score.} }
Endnote
%0 Conference Paper %T Knowledge Guided Multi-instance Multi-label Learning via Neural Networks in Medicines Prediction %A Junyuan Shang %A Shenda Hong %A Yuxi Zhou %A Meng Wu %A Hongyan Li %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-shang18c %I PMLR %P 831--846 %U https://proceedings.mlr.press/v95/shang18c.html %V 95 %X Predicting medicines for patients with co-morbidity has long been recognized as a hard task due to complex dependencies between diseases and medicines. Efforts have been made recently to build high-order dependency between diseases and medicines by extracting knowledge from electronic health records (EHR). But current works failed to utilize additional knowledge and ignored the data skewness problem which lead to sub-optimal combination of medicines. In this paper, we formulate the medicines prediction task in multi-instance multi-label learning framework considering the multi-diagnoses as input instances and multi-medicines as output labels. We propose a knowledge-guided multi-instance multi-label networks called \mname where two types of additional knowledge are incorporated into a RNN encoder-decoder model. The utilization of structural knowledge like clinical ontology provides a way to learn better representation called tree embedding by utilizing the ancestors’ information. Contextual knowledge is a global summarization of input instances which is informative for personal prediction. Experiments are conducted on a real world clinical dataset which showed the necessity to combine both contextual and structural knowledge and the \mname performs better than baselines up to 4+% in terms of Jaccard similarity score.
APA
Shang, J., Hong, S., Zhou, Y., Wu, M. & Li, H.. (2018). Knowledge Guided Multi-instance Multi-label Learning via Neural Networks in Medicines Prediction. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:831-846 Available from https://proceedings.mlr.press/v95/shang18c.html.

Related Material