Filters








10,771 Hits in 7.6 sec

Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning [article]

Jeong Min Lee, Milos Hauskrecht
2021 arXiv   pre-print
To address the problem, we develop a new adaptive event sequence prediction framework that learns to adjust its prediction for individual patients through an online model update.  ...  Developing accurate prediction models for such sequences is of a great importance for defining representations of a patient state and for improving patient care.  ...  For example, for continuous-valued clinical time-series prediction, Liu and Hauskrecht [16] have a pool of population and patient-specific time-series models and at any point of time the switching method  ... 
arXiv:2104.01787v2 fatcat:vc4e23qlnradtlsikdh4eev2ie

Analysis of Linear and Nonlinear Central-Cardiorespiratory Coupling Pathways in Healthy Subjects

Steffen Schulz, Aniol Serra Juhé, Beatriz Giraldo, Jens Haueisen, Karl-Juergen Baer, Andreas Voss
2018 2018 Computing in Cardiology Conference (CinC)  
In this study, we investigated the centralcardiorespiratory network (CCRN) applying linear and nonlinear causal coupling approaches (normalized short time partial directed coherence, multivariate transfer  ...  64-channel EEG were recorded for 15 minutes under resting conditions.  ...  Acknowledgements This work was partly supported by grants from the Federal Ministry for Economic Affairs and Energy (BMWI) KF2447309KJ4 and ZF4485201  ... 
doi:10.22489/cinc.2018.061 dblp:conf/cinc/0002JGHBV18 fatcat:x5u373wom5ampovuyhdzrxwiv4

Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping [article]

Michael Moor and Max Horn and Bastian Rieck and Damian Roqueiro and Karsten Borgwardt
2020 arXiv   pre-print
Our deep learning model employs a temporal convolutional network that is embedded in a Multi-task Gaussian Process Adapter framework, making it directly applicable to irregularly-spaced time series data  ...  This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner based on time series distances.  ...  Moreover, we develop MGP-TCN, which is the first model that can leverage temporal convolutions on irregularly-sampled multivariate time series. • We provide the first fully-accessible framework for the  ... 
arXiv:1902.01659v4 fatcat:24b4iwpih5d5rijci4chl5ybie

Data Mining and Electronic Health Records: Selecting Optimal Clinical Treatments in Practice [article]

Casey Bennett, Thomas Doub
2011 arXiv   pre-print
Models produced via data mining and predictive analysis profile inherited risks and environmental/behavioral factors associated with patient disorders, which can be utilized to generate predictions about  ...  Here, we evaluate the predictive capacity of a clinical EHR of a large mental healthcare provider (~75,000 distinct clients a year) to provide decision support information in a real-world clinical setting  ...  Davis Foundation for their support in these efforts. The authors would also like to recognize April Bragg, PhD, for her assistance in manuscript preparation.  ... 
arXiv:1112.1668v1 fatcat:a4xuchldvrhw5ejwoqdv4uy56m

Longitudinal healthcare analytics for disease management: Empirical demonstration for low back pain

Michael Mueller-Peltzer, Stefan Feuerriegel, Anne Molgaard Nielsen, Alice Kongsted, Werner Vach, Dirk Neumann
2020 Decision Support Systems  
Acknowledgments We thank Tim Howells for his professional language editing services.  ...  Formally, the parameters in our works should be estimated via Research framework for evaluating our cross-sectional time series model, so that we estimate parameters to multiple time series within a cohort  ...  Research framework for evaluating our cross-sectional time series model, so that we estimate parameters to multiple time series within a cohort (as opposed to only a single time series as in traditional  ... 
doi:10.1016/j.dss.2020.113271 fatcat:lfpybn3xlbcwlljexm6jjqhr7u

Brain responses to biological motion predict treatment outcome in young children with autism

D Yang, K A Pelphrey, D G Sukhodolsky, M J Crowley, E Dayan, N C Dvornek, A Venkataraman, J Duncan, L Staib, P Ventola
2016 Translational Psychiatry  
The predictive value of our findings for individual children with ASD was supported by a multivariate pattern analysis with cross validation.  ...  Predicting who will respond to a particular treatment for ASD, we believe the current findings mark the very first evidence of prediction/stratification biomarkers in young children with ASD.  ...  We also thank Jessica Schrouff, Carlton Chu and John Ashburner for their help with multivariate pattern analyses.  ... 
doi:10.1038/tp.2016.213 pmid:27845779 pmcid:PMC5314125 fatcat:fimwyp5oivfn3m52r7gfsotkje

Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare [article]

Ingyo Chung, Saehoon Kim, Juho Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang
2019 arXiv   pre-print
Our proposed framework targets at making personalized and reliable predictions from time-series data, such as Electronic Health Records (EHR), by modeling two complementary components: i) a shared component  ...  We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention.  ...  the showcase of our framework for EHR analysis that uses RNN for capturing complex global trend in time-series and GP for personalized and reliable prediction with uncertainty estimate. • We show practical  ... 
arXiv:1806.01551v3 fatcat:ggydqdhq25dvzcewkz7mb4efwe

Dynamic Prediction for Multiple Repeated Measures and Event Time Data: An Application to Parkinson's Disease [article]

Jue Wang, Sheng Luo, Liang Li
2017 arXiv   pre-print
We develop a Bayesian approach for parameter estimation and a dynamic prediction framework for predicting target patients' future outcome trajectories and risk of a survival event, based on their multivariate  ...  In this article, we first propose a joint model that consists of a semiparametric multilevel latent trait model (MLLTM) for the multiple longitudinal outcomes, and a survival model for event time.  ...  Quantifying and comparing dynamic predictive accuracy of joint  ... 
arXiv:1603.06476v2 fatcat:cwineh75pves3g3mz74ie5oxny

EHRs connect research and practice: Where predictive modeling, artificial intelligence, and clinical decision support intersect

Casey C. Bennett, Thomas W. Doub, Rebecca Selove
2012 Health Policy and Technology  
populations, and serving as a component of embedded clinical artificial intelligences that "learn" over time.  ...  Based on modeling of various clinical indicators at baseline, the highest accuracy in predicting individual patient response ranged from 70-72% within the models tested.  ...  In terms of actual application, modeling can be used to support clinical decisions provided a flexible, adaptable IT framework can consolidate data from different sources.  ... 
doi:10.1016/j.hlpt.2012.03.001 fatcat:n5py7cjywzfdvalzfhsr2lhgam

Data warehousing methods and processing infrastructure for brain recovery research

T Gee, S Kenny, C J Price, M L Seghier, S L Small, A P Leff, A Pacurar, S C Strother
2010 Archives Italiennes de Biologie  
We present a brief overview of three (potentially converging) approaches to neuroimaging data warehousing and processing that aim to support these diverse methods for facilitating prediction of cognitive  ...  Such data-driven approaches are likely to have an early impact on clinically relevant brain recovery while we simultaneously pursue the much more challenging model-based approaches that depend on a deep  ...  Acknowledgements This work was partly supported by a James S.  ... 
pmid:21175009 fatcat:foqhy4w3lvfhlah675y4el4zzi

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

Lucy M. Bull, Mark Lunt, Glen P. Martin, Kimme Hyrich, Jamie C. Sergeant
2020 Diagnostic and Prognostic Research  
MEDLINE, Embase and Web of Science were searched for articles reporting the development of a multivariable CPM for individual-level prediction of future binary or time-to-event outcomes and modelling repeated  ...  Clinical prediction models (CPMs) predict the risk of health outcomes for individual patients. The majority of existing CPMs only harness cross-sectional patient information.  ...  Development of a multivariable CPM, which predicts a binary or time-to- event outcome. 2 Modelling techniques for longitudinal and survival/ binary data.  ... 
doi:10.1186/s41512-020-00078-z pmid:32671229 pmcid:PMC7346415 fatcat:a2ebh47refddrm37whyjbrnwde

Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics [article]

Iñigo Urteaga, Tristan Bertin, Theresa M. Hardy, David J. Albers, Noémie Elhadad
2019 arXiv   pre-print
We present an end-to-end statistical framework for personalized, accurate, and minimally invasive modeling of female reproductive hormonal patterns.  ...  Our results show the validity of our proposed hormonal dynamic modeling framework, as it provides accurate predictive performance across different realistic sampling budgets and outperforms baselines methods  ...  Acknowledgments We thank the anonymous reviewers for their feedback and comments, as well as Clue (2019) by BioWink GmbH for the information on cycle length and ovulation day.  ... 
arXiv:1908.10226v1 fatcat:s7dbqlcmrvcyzmqlaieibttxqa

Time series analysis as input for clinical predictive modeling: Modeling cardiac arrest in a pediatric ICU

Curtis E Kennedy, James P Turley
2011 Theoretical Biology and Medical Modelling  
The purpose of this study is to propose a method that will allow for time series data to be used in clinical prediction models.  ...  Methods: We reviewed prediction models from nonclinical domains that employ time series data, and identified the steps that are necessary for building predictive models using time series clinical data.  ...  Conclusions: We have proposed a ten step process that results in data sets that contain time series features and are suitable for predictive modeling by a number of methods.  ... 
doi:10.1186/1742-4682-8-40 pmid:22023778 pmcid:PMC3213024 fatcat:7xoia6uccnh4fcmwchcjws7eku

AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

Liantao Ma, Junyi Gao, Yasha Wang, Chaohe Zhang, Jiangtao Wang, Wenjie Ruan, Wen Tang, Xin Gao, Xinyu Ma
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
It is still challenging to adaptively make use of the features for patients in diverse conditions. Third, using prediction models as the black box will limit the reliability in clinical practice.  ...  It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy  ...  As depicted by Figure 1 , EMR can be seen as a type of multivariate time series data and provide essential healthcare information for the data-driven healthcare prediction.  ... 
doi:10.1609/aaai.v34i01.5427 fatcat:6frbuzgbvjfudewcddahlinmvq

AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration [article]

Liantao Ma, Junyi Gao, Yasha Wang, Chaohe Zhang, Jiangtao Wang, Wenjie Ruan, Wen Tang, Xin Gao, Xinyu Ma
2019 arXiv   pre-print
It is still challenging to adaptively make use of the features for patients in diverse conditions. Third, using prediction models as the black box will limit the reliability in clinical practice.  ...  It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy  ...  As depicted by Figure 1 , EMR can be seen as a type of multivariate time series data and provide essential healthcare information for the data-driven healthcare prediction.  ... 
arXiv:1911.12205v1 fatcat:k5xjqmx5bveczdmlbdwzlkjkai
« Previous Showing results 1 — 15 out of 10,771 results