Low-Rank Sparse Feature Selection for Patient Similarity Learning

Zhan, Mengting; Cao, Shilei; Qian, Buyue; Chang, Shiyu; Wei, Jishang

doi:10.1109/icdm.2016.0182

Cited by 19 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Efficiency We also evaluate the efficiency of the proposed interpretation methods. In this experiment, we adopt a widely used metric learning model, i.e., LowRank (Zhan et al 2016), which aims to learn a metric that can measure the similarity degree between a pair of instances. In this experiment, we generate several synthetic datasets by varying the value of D from 2 to 9.…”

Section: Methodsmentioning

confidence: 99%

Towards Interpretation of Pairwise Learning

Huai

Wang

Miao

et al. 2020

AAAI

View full text Add to dashboard Cite

Recently, there are increasingly more attentions paid to an important family of learning problems called pairwise learning, in which the associated loss functions depend on pairs of instances. Despite the tremendous success of pairwise learning in many real-world applications, the lack of transparency behind the learned pairwise models makes it difficult for users to understand how particular decisions are made by these models, which further impedes users from trusting the predicted results. To tackle this problem, in this paper, we study feature importance scoring as a specific approach to the problem of interpreting the predictions of black-box pairwise models. Specifically, we first propose a novel adaptive Shapley-value-based interpretation method, based on which a vector of importance scores associated with the underlying features of a testing instance pair can be adaptively calculated with the consideration of feature correlations, and these scores can be used to indicate which features make key contributions to the final prediction. Considering that Shapley-value-based methods are usually computationally challenging, we further propose a novel robust approximation interpretation method for pairwise models. This method is not only much more efficient but also robust to data noise. To the best of our knowledge, we are the first to investigate how to enable interpretation in pairwise learning. Theoretical analysis and extensive experiments demonstrate the effectiveness of the proposed methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Towards Interpretation of Pairwise Learning

Huai

Wang

Miao

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…Some researchers have looked into measuring patient similarity based on the concept of sparsity. For example, the methods in [20][21][22] imposed the sparse regularization on dimension reduction projection to reduce irrelevant and redundant information, but they did not consider the robustness to noise corruption. Also, most of the methods mentioned above are not competent in handling incomplete input matrices [23].…”

Section: Related Workmentioning

confidence: 99%

SparGE: Sparse Coding-based Patient Similarity Learning via Low-rank Constraints and Graph Embedding

Wang¹,

Ng²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Patient similarity assessment (PSA) is pivotal to evidence-based and personalized medicine, enabled by analyzing the increasingly available electronic health records (EHRs). However, machine learning approaches for PSA has to deal with inherent data deficiencies of EHRs, namely missing values, noise, and small sample sizes. In this work, an end-to-end discriminative learning framework, called SparGE, is proposed to address these data challenges of EHR for PSA. SparGE measures similarity by jointly sparse coding and graph embedding. First, we use low-rank constrained sparse coding to identify and calculate weight for similar patients, while denoising against missing values. Then, graph embedding on sparse representations is adopted to measure the similarity between patient pairs via preserving local relationships defined by distances. Finally, a global cost function is constructed to optimize related parameters. Experimental results on two private and public real-world healthcare datasets, namely SingHEART and MIMIC-III, show that the proposed SparGE significantly outperforms other machine learning patient similarity methods.

show abstract

“…The wide availability of Electronic Health Records (EHRs) makes it possible to quickly and accurately calculate the similarity between patients. Many similarity learning methods have been proposed (Tsevas and Iakovidis, 2011 ; Wang et al, 2012b ; Barkhordari and Niamanesh, 2015 ; Wang and Sun, 2015 ; Sha et al, 2016 ; Zhan et al, 2016 ; Sharafoddini et al, 2017 ; Huai et al, 2018 ; Suo et al, 2018 ) on healthcare datasets. Existing methods have successfully derived the similarity measure from EHRs data through mapping the medical events into vector spaces.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous Information Network-Based Patient Similarity Search

Huang

Lü

Guo

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Patient similarity search is a fundamental and important task in artificial intelligence-assisted medicine service, which is beneficial to medical diagnosis, such as making accurate predictions for similar diseases and recommending personalized treatment plans. Existing patient similarity search methods retrieve medical events associated with patients from Electronic Health Record (EHR) data and map them to vectors. The similarity between patients is expressed by calculating the similarity or dissimilarity between the corresponding vectors of medical events, thereby completing the patient similarity measurement. However, the obtained vectors tend to be high dimensional and sparse, which makes it hard to calculate patient similarity accurately. In addition, most of existing methods cannot capture the time information in the EHR, which is not conducive to analyzing the influence of time factors on patient similarity search. To solve these problems, we propose a patient similarity search method based on a heterogeneous information network. On the one hand, the proposed method uses a heterogeneous information network to connect patients, diseases, and drugs, which solves the problem of vector representation of mixed information related to patients, diseases, and drugs. Meanwhile, our method measures the similarity between patients by calculating the similarity between nodes in the heterogeneous information network. In this way, the challenges caused by high-dimensional and sparse vectors can be addressed. On the other hand, the proposed method solves the problem of inaccurate patient similarity search caused by the lack of use of time information in the patient similarity measurement process by encoding time information into an annotated heterogeneous information network. Experiments show that our method is better than the compared baseline methods.

show abstract

Low-Rank Sparse Feature Selection for Patient Similarity Learning

Cited by 19 publications

References 16 publications

Towards Interpretation of Pairwise Learning

Towards Interpretation of Pairwise Learning

SparGE: Sparse Coding-based Patient Similarity Learning via Low-rank Constraints and Graph Embedding

Heterogeneous Information Network-Based Patient Similarity Search

Contact Info

Product

Resources

About