264,148 Hits in 4.2 sec

Learning patient-specific predictive models from clinical data

Shyam Visweswaran, Derek C. Angus, Margaret Hsieh, Lisa Weissfeld, Donald Yealy, Gregory F. Cooper
2010 Journal of Biomedical Informatics  
We introduce an algorithm for learning patient-specific models from clinical data to predict outcomes.  ...  The patient-specific algorithm uses Markov blanket (MB) models, carries out Bayesian model averaging over a set of models to predict the outcome for the patient case at hand, and employs a patient-specific  ...  Acknowledgments This work was supported by grants NLM R01-LM008374 and NIGMS R01-GM061992, and by training grant T15-LM/DE07059 from the National Library of Medicine to the University of Pittsburgh's Biomedical  ... 
doi:10.1016/j.jbi.2010.04.009 pmid:20450985 pmcid:PMC2933959 fatcat:lfnsi4v76rdj7pfwck6qxafsiy

Learning Adaptive Forecasting Models from Irregularly Sampled Multivariate Clinical Data

Zitao Liu, Milos Hauskrecht
The proposed model (1) learns the population trend from a collection of time series for past patients; (2) captures individual-specific short-term multivariate variability; and (3) adapts by automatically  ...  Building accurate predictive models of clinical multivariate time series is crucial for understanding of the patient condition, the dynamics of a disease, and clinical decision making.  ...  Acknowledgments The work presented in this paper was supported by grant R01GM088224 from the NIH.  ... 
pmid:27525189 pmcid:PMC4980099 fatcat:euu3a267wzhzbnr5kf75bijsqq

Learning Tasks for Multitask Learning

Harini Suresh, Jen J. Gong, John V. Guttag
2018 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18  
Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings.  ...  These models are often developed and evaluated on datasets with heterogeneous patient populations.  ...  Learning Predictive Models In the prediction step, in order to go from a patient timeseries to a mortality prediction, we use an LSTM for all of the model configurations.  ... 
doi:10.1145/3219819.3219930 dblp:conf/kdd/SureshGG18 fatcat:r72yv7exj5c65dpsjqon4yshai

Pre-training transformer-based framework on large-scale pediatric claims data for downstream population-specific tasks [article]

Xianlong Zeng, Simon Lin, Chang Liu
2021 arXiv   pre-print
By learning from the large amount of healthcare data, various data-driven models have been built to predict future events for different medical tasks, such as auto diagnosis and heart-attack prediction  ...  Although EHR is abundant, the population that satisfies specific criteria for learning population-specific tasks is scarce, making it challenging to train data-hungry deep learning models.  ...  The dataset was obtained from a density sampled study that contains more than 600,000 enrollees' medical claims.  ... 
arXiv:2106.13095v1 fatcat:bzrnujwcvjhwzd2gh73pbexr7u

Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study

Kristin M. Corey, Sehj Kashyap, Elizabeth Lorenzi, Sandhya A. Lagoo-Deenadayalan, Katherine Heller, Krista Whalen, Suresh Balu, Mitchell T. Heflin, Shelley R. McDonald, Madhav Swaminathan, Mark Sendak, Karim Brohi
2018 PLoS Medicine  
In an effort to better identify high-risk surgical patients from complex data, a machine learning project trained on Pythia was built to predict postoperative complication risk.  ...  Pythia is an automated, clinically curated surgical data pipeline and repository housing all surgical patient electronic health record (EHR) data from a large, quaternary, multisite health institute for  ...  Discussion We demonstrated that machine learning models built from highly curated, clinically meaningful features from local, structured EHR data were able to achieve high sensitivity and specificity for  ... 
doi:10.1371/journal.pmed.1002701 fatcat:jfurdgytfzbn5dm6g3qj5oj6ua

Cardiac Complication Risk Profiling for Cancer Survivors via Multi-View Multi-Task Learning [article]

Thai-Hoang Pham, Changchang Yin, Laxmi Mehta, Xueru Zhang, Ping Zhang
2021 arXiv   pre-print
First, data heterogeneity relates to those methods leveraging clinical data from a single view only while the data can be considered from multiple views (e.g., sequence of clinical visits, set of clinical  ...  Second, generalized prediction relates to most of those methods focusing on single-task learning, whereas each complication onset is predicted independently, leading to suboptimal models.  ...  Patient representation learning. The abundance of realworld data in recent years creates an unprecedented opportunity to apply machine learning and data mining methods for clinical risk predictions.  ... 
arXiv:2109.12276v1 fatcat:2bvamr3suvcgdmti7qaxuakpn4

Applied Machine Learning and Artificial Intelligence in Rheumatology

Maria Hügle, Patrick Omoumi, Jaap van Laar, Joschka Boedecker, Thomas Hügle
2020 Rheumatology Advances in Practice  
Growing datasets provide a sound basis with which to apply machine learning methods that learn from previous experiences.  ...  Machine learning as a field of artificial intelligence is increasingly applied in medicine to assist patients and physicians.  ...  Their best model yielded 85% accuracy and sensitivity/specificity of 44%/74%. A study in the UK used random forests to identify RA patients from the clinical codes in an EMR 31 .  ... 
doi:10.1093/rap/rkaa005 pmid:32296743 pmcid:PMC7151725 fatcat:76uspjabtfamfm42cmlsx4c5g4

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

Jeong Min Lee, Milos Hauskrecht
2021 arXiv   pre-print
However, population-based models learned from such sequences may not accurately predict patient-specific dynamics of event sequences.  ...  One important challenge of learning a good predictive model of clinical sequences is patient-specific variability.  ...  One important challenge of learning good predictive models for clinical sequences is patient-specific variability.  ... 
arXiv:2104.01787v2 fatcat:vc4e23qlnradtlsikdh4eev2ie

Integrating Co-clustering and Interpretable Machine Learning for the Prediction of Intravenous Immunoglobulin Resistance in Kawasaki Disease

Haolin Wang, Zhilin Huang, Danfeng Zhang, Johan Arief, Tiewei Lyu, Jie Tian
2020 IEEE Access  
data imputation and (b) patient subgroup-specific predictive models considering the availability of data.  ...  To enable clinically applicable prediction of intravenous immunoglobulin resistance addressing the incompleteness of clinical data and the lack of interpretability of machine learning models, a multistage  ...  Two predictive models can be trained for patient subgroups considering the availability of clinical data.  ... 
doi:10.1109/access.2020.2996302 fatcat:bsxu7rncmjaxzlrccvsysfhvxy

A comparison of machine learning models versus clinical evaluation for mortality prediction in patients with sepsis

William P. T. M. van Doorn, Patricia M. Stassen, Hella F. Borggreve, Maaike J. Schalkwijk, Judith Stoffers, Otto Bekers, Steven J. R. Meex, Ivan Olier
2021 PLoS ONE  
Machine learning models trained with laboratory or a combination of laboratory + clinical data achieved an area-under-the ROC curve of 0.82 (95% CI: 0.80–0.84) and 0.84 (95% CI: 0.81–0.87) for predicting  ...  Conclusion Machine learning models outperformed internal medicine physicians and clinical risk scores in predicting 31-day mortality.  ...  The aim of this study was to develop machine learning-based prediction models for allcause mortality at 31 days based on available laboratory and clinical data from patients presenting to the ED with sepsis  ... 
doi:10.1371/journal.pone.0245157 pmid:33465096 fatcat:5ziasvrd5nezfp3jwton5zgmqa

Artificial Intelligence and the Future of Spine Surgery

Rushikesh S. Joshi, Darryl Lau, Christopher P. Ames
2019 Neurospine  
Machine learning removes the requirements of hard-coding rules for a program, instead allowing the algorithm to extract patterns within the data to make specific predictions or determinations.  ...  At the crux of this, is our ability to leverage powerful tools to learn from, and act on the massive availability of digital data.  ...  Because machine learning algorithms are iteratively trained on previously acquired data and then applied prospectively to new data, patient-specific determinations can be made in areas like outcomes research  ... 
doi:10.14245/ns.1938410.205 pmid:31905450 pmcid:PMC6944989 fatcat:acau6shyhvh6bazh5wxlgcgd4a

From hype to reality: data science enabling personalized medicine

Holger Fröhlich, Rudi Balling, Niko Beerenwinkel, Oliver Kohlbacher, Santosh Kumar, Thomas Lengauer, Marloes H. Maathuis, Yves Moreau, Susan A. Murphy, Teresa M. Przytycka, Michael Rebhan, Hannes Röst (+8 others)
2018 BMC Medicine  
The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective  ...  Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media).  ...  Longitudinal real-world data pose specific challenges for training and validation of predictive models.  ... 
doi:10.1186/s12916-018-1122-7 pmid:30145981 pmcid:PMC6109989 fatcat:wfdozg4funaz5d4nn34bn5i4r4

Personalized Pancreatic Tumor Growth Prediction via Group Learning [article]

Ling Zhang, Le Lu, Ronald M. Summers, Electron Kebebew, Jianhua Yao
2017 arXiv   pre-print
from multimodal imaging data.  ...  Our predictive model is pretrained on a group data set and personalized on the target patient data to estimate the future spatio-temporal progression of the patient's tumor.  ...  /time3) from group data (patient 1 -patient n) and the pair of time1/time2 from personalized data (the target patient, denoted as patient n + 1).  ... 
arXiv:1706.00493v1 fatcat:d2wrb5cgzjea5cqhi75rvuhbju

Weakly supervised temporal model for prediction of breast cancer distant recurrence

Josh Sanyal, Amara Tariq, Allison W. Kurian, Daniel Rubin, Imon Banerjee
2021 Scientific Reports  
The model was trained jointly on manually curated data from 670 patients and NLP-curated data of 8062 patients.  ...  It was validated on manually annotated data from 224 patients with recurrence and achieved 0.94 AUROC.  ...  Acknowledgements This project was supported by a Grant from GE BlueSky (DR, IB).  ... 
doi:10.1038/s41598-021-89033-6 pmid:33947927 fatcat:a5hrjdsbknfudlqq6d3avl74wm

Systematic Methods on Machine Learning Techniques for Clinical Predictive Modelling

Hence the present research focuses on review and analyses the various model, algorithm and machine learning technique for clinical predictive modelling to obtain high performance results from numerous  ...  medical data which relates to the patients of multiple diseases.  ...  node metastasis) and this suggested model trained with 782 patients data from NCDB.Based on tumour DOI, the machine learning approaches are consistently outperformed for respective predictive models.Furthermore  ... 
doi:10.35940/ijitee.e2138.039520 fatcat:3f6v3kehbfc4pme4h5ic6mc5my
« Previous Showing results 1 — 15 out of 264,148 results