A multi-task learning formulation for predicting disease progression

By Jiayu Zhou, Lei Yuan, Jun Liu, Jieping Ye. 2011

263 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Physiology, Psychiatry and Mental health, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Jianpeng Xu
2. Pang-Ning Tan
3. Jiayu Zhou
4. Qiang Yang
5. Yu Zhang
6. Kaixiang Lin
7. Lifeng Luo
8. Jieping Ye

In Physiology

1. Jianpeng Xu
2. Pang-Ning Tan
3. Jiayu Zhou
4. Kaixiang Lin
5. Qiang Yang
6. Yu Zhang
7. Lifeng Luo
8. Inci M. Baytas

In Psychiatry and Mental health

1. Qiang Yang
2. Yu Zhang
3. Jianpeng Xu
4. Pang-Ning Tan
5. Jiayu Zhou
6. Kaixiang Lin
7. Lifeng Luo
8. Inci M. Baytas

In Medical & Health AI

1. Qiang Yang
2. Yu Zhang
3. Jianpeng Xu
4. Pang-Ning Tan
5. Jiayu Zhou
6. Kaixiang Lin
7. Lifeng Luo
8. Jing Gao

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “…[106], splice-site prediction [106], protein subcellular location prediction [107], Alzheimer’s disease assessment scale cognitive subscale [108], prediction of cognitive outcomes from neuroimaging measures in Alzheimer’s disease [109], identification of longitudinal phenotypic markers for…”
• A Survey on Multi-Task Learning (2017, methodology): “In [188], a multi-task method based on a temporal group Lasso and the `2,1 norm regularization is proposed for the mini mental state examination and Alzheimers disease assessment scale cognitive subscale.”
• Learning Multi-Level Task Groups in Multi-Task Learning (2015, background): “MTL has gained its popularity among a wide range of applications including image annotation (Fan, Gao, and Luo 2008), speech recognition (Parameswaran and Weinberger 2010), disease progression predication (Zhou et al. 2011) and so on.”
• Action2Activity: Recognizing Complex Activities from Sensor Data (2015, background): “It ensures that all tasks share a common set of features, while each one keeps its own specific features [Zhou et al. , 2011b].”
• Robust multi-task feature learning (2012, background): “Multi-task learning has been applied successfully in a wide range of applications including object recognition [8], speech recognition [28], handwritten digits recognition [30] and disease progression prediction [44].”
• FORMULA: FactORized MUlti-task LeArning for task discovery in personalized medical models (2015, methodology): “Multi-task learning has also been used for feature learning and selection [1] or temporal learning [28, 20] by considering each time point as one task.”
• High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction (2012, methodology): “Therefore, if longitudinal cognitive ou tcomes are available, it would be beneficial to use the complete information for the identification of rel evant imaging markers [9, 10].”
• Efficient multi-task feature learning with calibration (2014, background): “…regularized parameters are set as λ 1 = λ 2 = λ 0 =1 n i , where n i is the number of samples from the i -th task. are 191 normal control (NC), 319 mild cognitive impairment (MCI), and 138 patients with probably Alzheimer’s disease (AD) [please refer to [36, 37] for more details about the data].”
• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks (2015, background): “in many applications, such as disease prediction [44], [45] and financial stock selection [46].”
• Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks (2017, background): “Mining EHR data is a hot research topic in healthcare informatics. tackled tasks include electronic genotyping and phenotyping [5, 16, 19, 32], disease progression [12, 26, 27, 33], adverse drug event detection [21], diagnosis prediction [9–11, 25, 31], and so on.”
• Interactive Multi-task Relationship Learning (2016, methodology): “The experimental setup is same as described in the paper [37].”
• GSpartan: a Geospatio-Temporal Multi-task Learning Framework for Multi-location Prediction (2016, methodology): “The low-rank representation, defined by a set of base models, represents the possible macroscale phenomena that could help explain the temporal variability of the data.”
• Flexible Clustered Multi-Task Learning by Learning Representative Tasks (2016, background): “The new approach allows an arbitrary task to be described by multiple representative tasks, effectively soft-assigning a task to multiple clusters with different weights.”
• Privacy-Preserving Distributed Multi-Task Learning with Asynchronous Updates (2017, background): “Several types of shared representations can be encountered in MTL literature such as shared feature subspace [2, 11], shared feature subset [12, 31, 46, 50], clustering structure [47] and shared parameters in neural networks [8].”
• Multi-Stage Multi-Task Learning with Reduced Rank (2016, background): “Luo 2008), speech recognition (Parameswaran and Weinberger 2010), age estimation (Zhang and Yeung 2010b), disease progression predication (Zhou et al. 2011), and so on.”
• Online Multi-Task Learning Framework for Ensemble Forecasting (2017, methodology): “[8] employed a task relationship to ensure smoothness between time series predictions.”
• Robust Dynamic Trajectory Regression on Road Networks: A Multi-task Learning Framework (2014, methodology): “Other comparable algorithms include DTRTS in [5], TGL in [11], Algorithm 1 Accelerated Proximal Method for RDMTR Input: X(1), .”
• Patient Subtyping via Time-Aware LSTM Networks (2017, methodology): “Œese methods are required to answer di‚erent questions related to disease progression modeling and risk prediction [8, 9, 13, 21, 29, 31].”
• Multitask Diffusion Adaptation Over Networks (2013, background): “Themultitask learning problem is relevant in several machine learning formulations and has found applications in web page categorization [34], web-search ranking [35], and disease progression modeling [36], among other areas.”