Predicting Complications in Critical Care Using Heterogeneous Clinical Data
Patients in hospitals, particularly in critical care, are susceptible to many complications affecting morbidity and mortality. Digitized clinical data in electronic medical records can be effectively used to develop machine learning models to identify patients at risk of complications early and prov...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2016-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/7593335/ |
| _version_ | 1818876753023598592 |
|---|---|
| author | Vijay Huddar Bapu Koundinya Desiraju Vaibhav Rajan Sakyajit Bhattacharya Shourya Roy Chandan K. Reddy |
| author_facet | Vijay Huddar Bapu Koundinya Desiraju Vaibhav Rajan Sakyajit Bhattacharya Shourya Roy Chandan K. Reddy |
| author_sort | Vijay Huddar |
| collection | DOAJ |
| description | Patients in hospitals, particularly in critical care, are susceptible to many complications affecting morbidity and mortality. Digitized clinical data in electronic medical records can be effectively used to develop machine learning models to identify patients at risk of complications early and provide prioritized care to prevent complications. However, clinical data from heterogeneous sources within hospitals pose significant modeling challenges. In particular, unstructured clinical notes are a valuable source of information containing regular assessments of the patient's condition but contain inconsistent abbreviations and lack the structure of formal documents. Our contributions in this paper are twofold. First, we present a new preprocessing technique for extracting features from informal clinical notes that can be used in a classification model to identify patients at risk of developing complications. Second, we explore the use of collective matrix factorization, a multi-view learning technique, to model heterogeneous clinical data-text-based features in combination with other measurements, such as clinical investigations, comorbidites, and demographic data. We present a detailed case study on postoperative respiratory failure using more than 700 patient records from the MIMIC II database. Our experiments demonstrate the efficacy of our preprocessing technique in extracting discriminatory features from clinical notes as well as the benefits of multi-view learning to combine clinical measurements with text data for predicting complications. |
| first_indexed | 2024-12-19T13:47:24Z |
| format | Article |
| id | doaj.art-5f5507d9bdb540898e18a182b62c55fc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:47:24Z |
| publishDate | 2016-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5f5507d9bdb540898e18a182b62c55fc2022-12-21T20:18:49ZengIEEEIEEE Access2169-35362016-01-0147988800110.1109/ACCESS.2016.26187757593335Predicting Complications in Critical Care Using Heterogeneous Clinical DataVijay Huddar0Bapu Koundinya Desiraju1Vaibhav Rajan2https://orcid.org/0000-0002-6748-6864Sakyajit Bhattacharya3Shourya Roy4Chandan K. Reddy5Xerox Research Centre India, Bangalore, IndiaInstitute of Genomics and Integrative Biology, New Delhi, IndiaXerox Research Centre India, Bangalore, IndiaXerox Research Centre India, Bangalore, IndiaXerox Research Centre India, Bangalore, IndiaDepartment of Computer Science, Virginia Tech, Arlington, VA, USAPatients in hospitals, particularly in critical care, are susceptible to many complications affecting morbidity and mortality. Digitized clinical data in electronic medical records can be effectively used to develop machine learning models to identify patients at risk of complications early and provide prioritized care to prevent complications. However, clinical data from heterogeneous sources within hospitals pose significant modeling challenges. In particular, unstructured clinical notes are a valuable source of information containing regular assessments of the patient's condition but contain inconsistent abbreviations and lack the structure of formal documents. Our contributions in this paper are twofold. First, we present a new preprocessing technique for extracting features from informal clinical notes that can be used in a classification model to identify patients at risk of developing complications. Second, we explore the use of collective matrix factorization, a multi-view learning technique, to model heterogeneous clinical data-text-based features in combination with other measurements, such as clinical investigations, comorbidites, and demographic data. We present a detailed case study on postoperative respiratory failure using more than 700 patient records from the MIMIC II database. Our experiments demonstrate the efficacy of our preprocessing technique in extracting discriminatory features from clinical notes as well as the benefits of multi-view learning to combine clinical measurements with text data for predicting complications.https://ieeexplore.ieee.org/document/7593335/Clinical notestopic modelsheterogeneous datamulti–view learningcollective matrix factorizationpostoperative respiratory failure |
| spellingShingle | Vijay Huddar Bapu Koundinya Desiraju Vaibhav Rajan Sakyajit Bhattacharya Shourya Roy Chandan K. Reddy Predicting Complications in Critical Care Using Heterogeneous Clinical Data IEEE Access Clinical notes topic models heterogeneous data multi–view learning collective matrix factorization postoperative respiratory failure |
| title | Predicting Complications in Critical Care Using Heterogeneous Clinical Data |
| title_full | Predicting Complications in Critical Care Using Heterogeneous Clinical Data |
| title_fullStr | Predicting Complications in Critical Care Using Heterogeneous Clinical Data |
| title_full_unstemmed | Predicting Complications in Critical Care Using Heterogeneous Clinical Data |
| title_short | Predicting Complications in Critical Care Using Heterogeneous Clinical Data |
| title_sort | predicting complications in critical care using heterogeneous clinical data |
| topic | Clinical notes topic models heterogeneous data multi–view learning collective matrix factorization postoperative respiratory failure |
| url | https://ieeexplore.ieee.org/document/7593335/ |
| work_keys_str_mv | AT vijayhuddar predictingcomplicationsincriticalcareusingheterogeneousclinicaldata AT bapukoundinyadesiraju predictingcomplicationsincriticalcareusingheterogeneousclinicaldata AT vaibhavrajan predictingcomplicationsincriticalcareusingheterogeneousclinicaldata AT sakyajitbhattacharya predictingcomplicationsincriticalcareusingheterogeneousclinicaldata AT shouryaroy predictingcomplicationsincriticalcareusingheterogeneousclinicaldata AT chandankreddy predictingcomplicationsincriticalcareusingheterogeneousclinicaldata |