Accurate privacy-preserving prediction using electronic health record (EHR) data distributed in multiple hospitals is essential to enable stakeholders related to healthcare services to obtain useful information without privacy leakage. In this paper, we propose harmonized embedding-based self-attentive encoder (HarmoSATE), which is a new method for privacy-preserving federated predictive analysis. We extract contextual embeddings of local institutions using Word2Vec, and then harmonize locally-trained embeddings using a neural network-based harmonization technique. The proposed method uses a deep representative encoder based on self-attention to learn complex and dynamic patterns inherent to harmonized embeddings of medical concepts. To evaluate our method, we implemented experiments using sequential medical codes collected from the Medical Information Mart for Intensive Care-III dataset in a distributed setting. It achieved a significant increase in average AUC, ranging from 3% to 8% depending on the experiments compared to baseline models, demonstrating superior prediction accuracy of a patient's diagnosis in the next admission. HarmoSATE can be a useful alternative to obtain accurate and practical results for various predictive tasks that use sensitive and distributed EHR data while preserving patients' privacy.

In classification problems, feature selection is used to identify important input features to reduce the dimensionality of the input space while improving or maintaining classification performance. Traditional feature selection algorithms are designed to handle single-label learning, but classification problems have recently emerged in multi-label domain. In this study, we propose a novel feature selection algorithm for classifying multi-label data. This proposed method is based on dynamic mutual information, which can handle redundancy among features controlling the input space. We compare the proposed method with some existing problem transformation and algorithm adaptation methods applied to real multi-label datasets using the metrics of multi-label accuracy and hamming loss. The results show that the proposed method demonstrates more stable and better performance for nearly all multi-label datasets.

Recommendation systems have required centralized storage of user data, but due to privacy concerns, recent studies adopted federated learning (FL) that discloses intermediate statistics instead of raw data to build privacy-preserving federated recommendation systems. However, they suffer from inefficiencies in privacy-preserving mechanisms and inaccuracies in simple algorithms that ignore sequential information. This study proposes an extension of Word2Vec for a privacy-preserving federated sequential recommendation system (PPFSRS). This method exploits sequential information to generate contextual item representations for accurate recommendations while concealing privacy-sensitive features efficiently. Specifically, we mixed updates from negative samples to inhibit the direct leakage of purchased items from model updates. In addition, our method computes approximate model updates that can occur when sensitive features only belong to negative samples to prevent inference attacks. In experiments, we used benchmark datasets for recommendation and simulated highly distributed data such that each user stores historical data locally. While preserving privacy with reasonable complexity, the proposed method showed little degradation in recommendation performance compared to FL-based Word2Vec without privacy-preserving mechanisms. Utilizing contextual item representations trained by our method from highly distributed data will be a practical starting point for PPFSRS in a cross-device setting.

Classification of microarray data plays a significant role in the diagnosis and prediction of cancer. However, its high-dimensionality (>tens of thousands) compared to the number of observations (

A tree model with low time complexity can support the application of artificial intelligence to industrial systems. Variable selection based tree learning algorithms are more time efficient than existing Classification and Regression Tree (CART) algorithms. To our best knowledge, there is no attempt to deal with categorical input variable in variable selection based multi-output tree learning. Also, in the case of multi-output regression tree, a conventional variable selection based algorithm is not suitable to large datasets. We propose a mutual information-based multi-output tree learning algorithm that consists of variable selection and split optimization. The proposed method discretizes each variable based on k-means into 2–4 clusters and selects the variable for splitting based on the discretized variables using mutual information. This variable selection component has relatively low time complexity and can be applied regardless of output dimension and types. The proposed split optimization component is more efficient than an exhaustive search. The performance of the proposed tree learning algorithm is similar to or better than that of a multi-output version of CART algorithm on a specific dataset. In addition, with a large dataset, the time complexity of the proposed algorithm is significantly reduced compared to a CART algorithm.

Sharing electronic health record data is essential for advanced analysis, but may put sensitive information at risk. Several studies have attempted to address this risk using contextual embedding, but with many hospitals involved, they are often inefficient and inflexible. Thus, we propose a bilingual autoencoder-based model to harmonize local embeddings in different spaces. Cross-hospital reconstruction of embeddings makes encoders map embeddings from hospitals to a shared space and align them spontaneously. We also suggest two-phase training to prevent distortion of embeddings during harmonization with hospitals that have biased information. In experiments, we used medical event sequences from the Medical Information Mart for Intensive Care-III dataset and simulated the situation of multiple hospitals. For evaluation, we measured the alignment of events from different hospitals and the prediction accuracy of a patient’s diagnosis in the next admission in three scenarios in which local embeddings do not work. The proposed method efficiently harmonizes embeddings in different spaces, increases prediction accuracy, and gives flexibility to include new hospitals, so is superior to previous methods in most cases. It will be useful in predictive tasks to utilize distributed data while preserving private information.

Data stream clustering is an unsupervised learning method for sequential data. Data stream clustering has some challenging issues, such as handling limited memory, dealing with evolving clusters, and detecting noise data. We propose a hybrid data stream clustering method that combines model-based c lustering and density-based clustering. The proposed method finds evolving clusters quickly and obtains cluster information easily. We use multiple hypothesis testing to handle noise data by controlling a decision error. In this testing method, we employ the positive false discovery rate as the decision error. We use a density-based algorithm to discover cluster evolution from newly arrived data. Then, we estimate a Gaussian mixture model and update the clustering results by combining past cluster information and the cluster information for newly arrived data. We applied the proposed method to several synthetic and real datasets. The experimental results demonstrate that the proposed method works effectively for a data stream that includes noise data. In addition, the proposed method yields robust results relative to input parameters compared to an existing density-based data stream clustering method.

We consider multi-task learning, which simultaneously learns related prediction tasks, to improve generalization performance. We factorize a coefficient matrix as the product of two matrices based on a low-rank assumption. These matrices have sparsities to simultaneously perform variable selection and learn and overlapping group structure among the tasks. The resulting bi-convex objective function is minimized by alternating optimization, where sub-problems are solved using alternating direction method of multipliers and accelerated proximal gradient descent. Moreover, we provide the performance bound of the proposed method. The effectiveness of the proposed method is validated for both synthetic and real-world datasets.

Sudden death testing can be utilized for deciding upon the lot acceptance of manufactured parts. Variables single, and double sampling plans are proposed for the lot acceptance of parts whose life follows a Weibull distribution with known shape parameter. The proposed plans are different from the existing ones in that the lot acceptance criteria do not depend on the estimated scale parameter. Design parameters of both sampling plans are determined by using the usual two-point approach. The number of groups is determined independently of the group size, and even independently of the shape parameter. Also, the double sampling plan can reduce the average number of groups required. The effects of mis-specification of the shape parameter on the probability of accepting the lots under the single sampling plan are analyzed & discussed.