scholarly journals Joint Learning of Phenotypes and Diagnosis-Medication Correspondence via Hidden Interaction Tensor Factorization

2018 ◽  
Author(s):  
Kejing Yin ◽  
William K. Cheung ◽  
Yang Liu ◽  
Benjamin C. M. Fung ◽  
Jonathan Poon
Keyword(s):  
Critical Care ◽  
Performance Evaluation ◽  
Maximum Likelihood ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Mortality Prediction ◽  
Tensor Factorization ◽  
Joint Learning ◽  
Interaction Tensor ◽  
Mimic Iii

Non-negative tensor factorization has been shown effective for discovering phenotypes from the EHR data with minimal human supervision. In most cases, an interaction tensor of the elements in the EHR (e.g., diagnoses and medications) has to be first established before the factorization can be applied. Such correspondence information however is often missing. While different heuristics can be used to estimate the missing correspondence, any errors introduced will in turn cause inaccuracy for the subsequent phenotype discovery task. This is especially true for patients with multiple diseases diagnosed (e.g., under critical care). To alleviate this limitation, we propose the hidden interaction tensor factorization (HITF) where the diagnosis-medication correspondence and the underlying phenotypes are inferred simultaneously. We formulate it under a Poisson non-negative tensor factorization framework and learn the HITF model via maximum likelihood estimation. For performance evaluation, we applied HITF to the MIMIC III dataset. Our empirical results show that both the phenotypes and the correspondence inferred are clinically meaningful. In addition, the inferred HITF model outperforms a number of state-of-the-art methods for mortality prediction.

scholarly journals Learning Phenotypes and Dynamic Patient Representations via RNN Regularized Collective Non-Negative Tensor Factorization

2019 ◽  
Vol 33 ◽  
pp. 1246-1253 ◽  
Author(s):  
Kejing Yin ◽  
Dong Qian ◽  
William K. Cheung ◽  
Benjamin C. M. Fung ◽  
Jonathan Poon
Keyword(s):  
Temporal Dynamics ◽  
Mortality Prediction ◽  
Temporal Data ◽  
Tensor Factorization ◽  
Observation Window ◽  
Health Records ◽  
Disease States ◽  
Clinical Events ◽  
Proposed Model ◽  
Mimic Iii

Non-negative Tensor Factorization (NTF) has been shown effective to discover clinically relevant and interpretable phenotypes from Electronic Health Records (EHR). Existing NTF based computational phenotyping models aggregate data over the observation window, resulting in the learned phenotypes being mixtures of disease states appearing at different times. We argue that by separating the clinical events happening at different times in the input tensor, the temporal dynamics and the disease progression within the observation window could be modeled and the learned phenotypes will correspond to more specific disease states. Yet how to construct the tensor for data samples with different temporal lengths and properly capture the temporal relationship specific to each individual data sample remains an open challenge. In this paper, we propose a novel Collective Non-negative Tensor Factorization (CNTF) model where each patient is represented by a temporal tensor, and all of the temporal tensors are factorized collectively with the phenotype definitions being shared across all patients. The proposed CNTF model is also flexible to incorporate non-temporal data modality and RNN-based temporal regularization. We validate the proposed model using MIMIC-III dataset, and the empirical results show that the learned phenotypes are clinically interpretable. Moreover, the proposed CNTF model outperforms the state-of-the-art computational phenotyping models for the mortality prediction task.

scholarly journals Generative Visual Dialogue System via Weighted Likelihood Estimation

2019 ◽  
Author(s):  
Heming Zhang ◽  
Shalini Ghosh ◽  
Larry Heck ◽  
Stephen Walsh ◽  
Junting Zhang ◽  
...  
Keyword(s):  
Maximum Likelihood ◽  
State Of The Art ◽  
Estimation Method ◽  
Likelihood Estimation ◽  
Relevant Information ◽  
Weighted Likelihood ◽  
Dialogue System ◽  
Training Scheme ◽  
Weighted Likelihood Estimation ◽  
Modal Reasoning

The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow. Traditional Maximum Likelihood Estimation-based methods only learn from positive responses but ignore the negative responses, and consequently tend to yield safe or generic responses. To address this issue, we propose a novel training scheme in conjunction with weighted likelihood estimation method. Furthermore, an adaptive multi-modal reasoning module is designed, to accommodate various dialogue scenarios automatically and select relevant information accordingly. The experimental results on the VisDial benchmark demonstrate the superiority of our proposed algorithm over other state-of-the-art approaches, with an improvement of 5.81% on recall@10.

IMAGE RESTORATION AND DETAIL PRESERVATION BY BAYESIAN ESTIMATION

2007 ◽  
Vol 07 (03) ◽  
pp. 497-514 ◽  
Author(s):  
HUIYU ZHOU ◽  
TANGWEI LIU ◽  
FAQUAN LIN ◽  
YUSHENG PANG ◽  
JI WU
Keyword(s):  
Wavelet Transform ◽  
Maximum Likelihood ◽  
Noise Suppression ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Discrete Wavelet ◽  
Test Image ◽  
Statistical Representation ◽  
Current State ◽  
Variation Technique

In this paper, we present a novel noise suppression and detail preservation algorithm. The test image is firstly pre-processed through a multiresolution analysis employing the discrete wavelet transform. Then, we apply a fast and robust total variation technique, incorporating a statistical representation in the style of maximum likelihood estimation. Finally, we compare this proposed approach to current state-of-the-art denoising methods using synthetic and real images. The results demonstrate encouraging performance of our algorithm.

scholarly journals Learning to Disambiguate Syntactic Relations

2003 ◽  
Vol 17 (5) ◽  
Author(s):  
Gerold Schneider
Keyword(s):  
Machine Learning ◽  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Natural Language ◽  
Statistical Learning ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Learning Approaches ◽  
Learning Models ◽  
Syntactic Relations

Natural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models based on Maximum-Likelihood Estimation (MLE) can support a highly developed linguistic grammar in the disambiguation process.

A Cautionary Note on Incremental Fit Indices Reported by LISREL

Methodology ◽  
2005 ◽  
Vol 1 (2) ◽  
pp. 81-85 ◽  
Author(s):  
Stefan C. Schmukle ◽  
Jochen Hardt
Keyword(s):  
Factor Analysis ◽  
Maximum Likelihood ◽  
Structural Equation ◽  
Structural Equation Models ◽  
Null Model ◽  
Likelihood Estimation ◽  
Parameter Estimates ◽  
Fit Indices ◽  
Cautionary Note ◽  
Confirmatory Factor

Abstract. Incremental fit indices (IFIs) are regularly used when assessing the fit of structural equation models. IFIs are based on the comparison of the fit of a target model with that of a null model. For maximum-likelihood estimation, IFIs are usually computed by using the χ2 statistics of the maximum-likelihood fitting function (ML-χ2). However, LISREL recently changed the computation of IFIs. Since version 8.52, IFIs reported by LISREL are based on the χ2 statistics of the reweighted least squares fitting function (RLS-χ2). Although both functions lead to the same maximum-likelihood parameter estimates, the two χ2 statistics reach different values. Because these differences are especially large for null models, IFIs are affected in particular. Consequently, RLS-χ2 based IFIs in combination with conventional cut-off values explored for ML-χ2 based IFIs may lead to a wrong acceptance of models. We demonstrate this point by a confirmatory factor analysis in a sample of 2449 subjects.

Estimating the Cost of Car Warranty in Indonesia using the Gertsbakh-Kordonsky Method

2020 ◽  
Vol 2 (1) ◽  
pp. 33-40
Author(s):  
Anggis Sagitarisman ◽  
Aceng Komarudin Mutaqin
Keyword(s):  
Maximum Likelihood ◽  
Likelihood Estimation ◽  
Type A ◽  
Claim Data ◽  
Likelihood Method ◽  
Selling Price ◽  
One Dimensional ◽  
Warranty Period ◽  
Kolmogorov Smirnov ◽  
Warranty Costs

AbstractCar manufacturers in Indonesia need to determine reasonable warranty costs that do not burden companies or consumers. Several statistical approaches have been developed to analyze warranty costs. One of them is the Gertsbakh-Kordonsky method which reduces the two-dimensional warranty problem to one dimensional. In this research, we apply the Gertsbakh-Kordonsky method to estimate the warranty cost for car type A in XYZ company. The one-dimensional data will be tested using the Kolmogorov-Smirnov to determine its distribution and the parameter of distribution will be estimated using the maximum likelihood method. There are three approaches to estimate the parameter of the distribution. The difference between these three approaches is in the calculation of mileage for units that do not claim within the warranty period. In the application, we use claim data for the car type A. The data exploration indicates the failure of car type A is mostly due to the age of the vehicle. The Kolmogorov-Smirnov shows that the most appropriate distribution for the claim data is the three-parameter Weibull. Meanwhile, the estimated using the Gertsbakh-Kordonsky method shows that the warranty costs for car type A are around 3.54% from the selling price of this car unit without warranty i.e. around Rp. 4,248,000 per unit.Keywords: warranty costs; the Gertsbakh-Kordonsky method; maximum likelihood estimation; Kolmogorov-Smirnov test.                                   AbstrakPerusahaan produsen mobil di Indonesia perlu menentukan biaya garansi yang bersifat wajar tidak memberatkan perusahaan maupun konsumen. Beberapa pendekatan statistik telah dikembangkan untuk menganalisis biaya garansi. Salah satunya adalah metode Gertsbakh-Kordonsky yang mereduksi masalah garansi dua dimensi menjadi satu dimensi. Pada penelitian ini, metode Gertsbakh-Kordonsky akan digunakan untuk mengestimasi biaya garansi untuk mobil tipe A pada perusahaan XYZ. Data satu dimensi hasil reduksi diuji kecocokan distribusinya menggunakan uji kecocokan Kolmogorov-Smirnov dan taksiran parameter distribusinya menggunakan metode penaksir kemungkinan maksimum. Ada tiga pendekatan yang digunakan untuk menaksir parameter distribusi. Perbedaan dari ketiga pendekatan tersebut terletak pada perhitungan jarak tempuh untuk unit yang tidak melakukan klaim dalam periode garansi. Sebagai bahan aplikasi, kami menggunakan data klaim unit mobil tipe A. Hasil eksplorasi data menunjukkan bahwa kegagalan mobil tipe A lebih banyak disebabkan karena faktor usia kendaraan. Hasil uji kecocokan distribusi untuk data hasil reduksi menunjukkan bahwa distribusi yang cocok adalah distribusi Weibull 3-parameter. Sementara itu, hasil perhitungan taksiran biaya garansi menunjukan bahwa taksiran biaya garansi untuk unit mobil tipe A sekitar 3,54% dari harga jual unit mobil tipe A tanpa garansi, atau sekitar Rp. 4.248.000,- per unit.Kata Kunci: biaya garansi; metode Gertsbakh-Kordonsky; penaksiran kemungkinan maksimum; uji Kolmogorov-Smirnov.

Sign in / Sign up

Export Citation Format

Share Document