| Title: | Comprehensible predictive modeling using regularized logistic regression and comorbidity based features |
|---|
| Authors: | ID Štiglic, Gregor (Author)
ID Povalej Bržan, Petra (Author)
ID Fijačko, Nino (Author)
ID Wang, Fei (Author)
ID Kalousis, Alexandros (Author)
ID Delibašić, Boris (Author)
ID Obradović, Zoran (Author) |
|---|
| Files: |  PLOS_ONE_2015_Stiglic_et_al._Comprehensible_Predictive_Modeling_Using_Regularized_Logistic_Regression_and_Comorbidity_Based_Features.PDF (1,13 MB)
MD5: 15E50895E2B1843B80D606A3B252707B
 http://dx.plos.org/10.1371/journal.pone.0144439
|
|---|
| Language: | English |
|---|
| Work type: | Scientific work |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FZV - Faculty of Health Sciences
|
|---|
| Abstract: | Different studies have demonstrated the importance of comorbidities to better understand the origin and evolution of medical complications. This study focuses on improvement of the predictive model interpretability based on simple logical features representing comorbidities. We use group lasso based feature interaction discovery followed by a post-processing step, where simple logic terms are added. In the final step, we reduce the feature set by applying lasso logistic regression to obtain a compact set of non-zero coefficients that represent a more comprehensible predictive model. The effectiveness of the proposed approach was demonstrated on a pediatric hospital discharge dataset that was used to build a readmission risk estimation model. The evaluation of the proposed method demonstrates a reduction of the initial set of features in a regression model by 72%, with a slight improvement in the Area Under the ROC Curve metric from 0.763 (95% CI: 0.755%0.771) to 0.769 (95% CI: 0.761%0.777). Additionally, our results show improvement in comprehensibility of the final predictive model using simple comorbidity based terms for logistic regression. |
|---|
| Keywords: | predictive models, logistic regression, readmission classification, comorbidities |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Year of publishing: | 2015 |
|---|
| Number of pages: | str. 1-6 |
|---|
| Numbering: | Letn. 10, št. 12 |
|---|
| PID: | 20.500.12556/DKUM-59294  |
|---|
| ISSN: | 1932-6203 |
|---|
| UDC: | 004.6:61 |
|---|
| ISSN on article: | 1932-6203 |
|---|
| COBISS.SI-ID: | 2183076 |
|---|
| DOI: | 10.1371/journal.pone.0144439 |
|---|
| NUK URN: | URN:SI:UM:DK:PX1JLWNK |
|---|
| Publication date in DKUM: | 19.06.2017 |
|---|
| Views: | 2045 |
|---|
| Downloads: | 448 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
