ABSTRACT
This paper presents a technique for computing patient similarity using time series data effectively combined with static data. Time series data of inpatients, such as heart rate, blood pressure, Oxygen saturation, respiration are measured at regular intervals, especially for inpatients in intensive care unit (ICU). The static data are mainly patient background and demographic data, including age, weight, height and gender. The similarity computation is done in unsupervised way. It is therefore free from data labeling requirement. However, such patient similarity can be very useful in developing various clinical decision support systems including treatment, medication, hospital admission and diagnosis. Our proposed technique works in three main steps. First, patient similarity is computed for each individual time series. Second, patients are grouped by clustering the static data. Finally, similarities from individual time series are combined and effectively blended with the patient group information to create a nearest neighborhood model. This model consists of a collection of the nearest neighbors for a given patient. We encounter several challenges for this task, including dealing with multi-variate time series data, variable sampling quantities and rates, missing values, and combining time-series with static data. We evaluate the proposed technique on a real patient database on two target features, namely, ‘diagnosis’ and ‘admission type’. Notable performance is recorded for both targets, achieving f1-score as high as 0.8. We believe this technique can effectively combine different types of clinical data and develop an efficient unsupervised framework for computing patient similarity to be utilized for clinical decision support systems.
- Donald J. Berndt and James Clifford. 1994. Using Dynamic Time Warping to Find Patterns in Time Series. In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining(AAAIWS’94). AAAI Press, 359–370.Google Scholar
- Andrei Z Broder, Moses Charikar, Alan M Frieze, and Michael Mitzenmacher. 2000. Min-Wise Independent Permutations. J. Comput. System Sci. 60, 3 (2000), 630 – 659. https://doi.org/10.1006/jcss.1999.1690Google ScholarDigital Library
- Xiongcai Cai, Oscar Perez-Concha, Enrico Coiera, Fernando Martin-Sanchez, Richard Day, David Roffe, and Blanca Gallego. 2016. Real-time prediction of mortality, readmission, and length of stay using electronic health record data. Journal of the American Medical Informatics Association 23, 3(2016), 553–561. https://doi.org/10.1093/jamia/ocv110Google ScholarCross Ref
- Matthew Herland, Taghi M. Khoshgoftaar, and Randall Wald. 2013. Survey of Clinical Data Mining Applications on Big Data in Health Informatics. In Proc. ICMLA ’13 - Volume 02. 465–472.Google ScholarDigital Library
- A. K. Jain, M. N. Murty, and P. J. Flynn. 1999. Data Clustering: A Review. ACM Comput. Surv. 31, 3 (1999), 264–323.Google ScholarDigital Library
- Tapas Kanungo, David Mount, Nathan Netanyahu, Christine Piatko, Ruth Silverman, and Angela Wu. 2002. An Efficient K-Means Clustering Algorithm Analysis and Implementation. IEEE TPMAI 24 (07 2002), 881–892.Google Scholar
- Li Li, Wei-Yi Cheng, Benjamin S Glicksberg, Omri Gottesman, Ronald Tamler, Rong Chen, Erwin P Bottinger, and Joel T Dudley. 2015. Identification of type 2 diabetes subgroups through topological analysis of patient similarity. Science translational medicine 7, 311 (2015), 311ra174–311ra174.Google Scholar
- Tianle Ma and Aidong Zhang. 2017. Integrate multi-omic data using affinity network fusion (ANF) for cancer patient clustering. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 7–10.Google ScholarCross Ref
- Yi Mao, Wenlin Chen, Yixin Chen, Chenyang Lu, Marin Kollef, and Thomas Bailey. [n.d.]. An Integrated Data Mining Approach to Real-time Clinical Monitoring and Deterioration Warning. In Proc. SIGKDD ’12. 1140–1148.Google Scholar
- Shraddha Pai and Gary D Bader. 2018. Patient similarity networks for precision medicine. J. of Mol. Biology (2018).Google Scholar
- Shraddha Pai, Shirley Hui, Ruth Isserlin, Muhammad A Shah, Hussam Kaka, and Gary D Bader. 2018. netDx: Interpretable patient classification using integrated patient similarity networks. bioRxiv (2018).Google Scholar
- [12] Physionet-MIMICIII.[n.d.]. https://archive.physionet.org/physiobank/database/mimic3cdb/.Google Scholar
- Sanjay Purushotham, Chuizheng Meng, Zhengping Che, and Yan Liu. 2017. Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets. CoRR abs/1710.08531(2017). arxiv:1710.08531http://arxiv.org/abs/1710.08531Google Scholar
- Anshumali Shrivastava and Ping Li. 2014. In Defense of MinHash Over SimHash. arxiv:stat.CO/1407.4416Google Scholar
- Bo Wang, Aziz M Mezlini, Feyyaz Demir, Marc Fiume, Zhuowen Tu, Michael Brudno, Benjamin Haibe-Kains, and Anna Goldenberg. 2014. Similarity network fusion for aggregating data types on a genomic scale. Nature methods 11, 3 (2014), 333.Google Scholar
- Yu and Shi. 2003. Multiclass spectral clustering. In Proceedings Ninth IEEE International Conference on Computer Vision. 313–319 vol.1. https://doi.org/10.1109/ICCV.2003.1238361Google Scholar
- Effective Patient Similarity Computation for Clinical Decision Support Using Time Series and Static Data
Recommendations
A Novel Temporal Similarity Measure for Patients Based on Irregularly Measured Data in Electronic Health Records
BCB '16: Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health InformaticsPatient similarity measurement is an important tool for cohort identification in in clinical decision support applications. A reliable similarity metric can be used for deriving diagnostic or prognostic information about a target patient using other ...
Similarity Measure of Multivariate Time Series Based on Segmentation
ICMLC '20: Proceedings of the 2020 12th International Conference on Machine Learning and ComputingSimilarity measure of time series is a fundamental problem in data mining tasks. However, most of the similarity methods are mainly for univariate time series, rather than multivariate time series. Among the existing approaches for multivariate time ...
Feature extraction from unequal length heterogeneous EHR time series via dynamic time warping and tensor decomposition
AbstractElectronic Health Records (EHR) data is routinely generated patient data that can provide useful information for analytical tasks such as disease detection and clinical event prediction. However, temporal EHR data such as physiological vital signs ...
Comments