A Database-driven decision support system: customized mortality prediction
We hypothesize that local customized modeling will provide more accurate mortality prediction than the current standard approach using existing scoring systems. Mortality prediction models were developed for two subsets of patients in Multi-parameter Intelligent Monitoring for Intensive Care (MIMIC)...
| Auteurs principaux: | , , , , , |
|---|---|
| Autres auteurs: | |
| Format: | Article |
| Langue: | en_US |
| Publié: |
MDPI AG
2013
|
| Accès en ligne: | http://hdl.handle.net/1721.1/77628 https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 |
| _version_ | 1826211588384751616 |
|---|---|
| author | Celi, Leo Anthony G. Galvin, Sean Davidzon, Guido Lee, Joon Scott, Daniel Mark, Roger Greenwood |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Celi, Leo Anthony G. Galvin, Sean Davidzon, Guido Lee, Joon Scott, Daniel Mark, Roger Greenwood |
| author_sort | Celi, Leo Anthony G. |
| collection | MIT |
| description | We hypothesize that local customized modeling will provide more accurate mortality prediction than the current standard approach using existing scoring systems. Mortality prediction models were developed for two subsets of patients in Multi-parameter Intelligent Monitoring for Intensive Care (MIMIC), a public de-identified ICU database, and for the subset of patients >80 years old in a cardiac surgical patient registry. Logistic regression (LR), Bayesian network (BN) and artificial neural network (ANN) were employed. The best-fitted models were tested on the remaining unseen data and compared to either the Simplified Acute Physiology Score (SAPS) for the ICU patients, or the EuroSCORE for the cardiac surgery patients. Local customized mortality prediction models performed better as compared to the corresponding current standard severity scoring system for all three subsets of patients: patients with acute kidney injury (AUC = 0.875 for ANN, vs. SAPS, AUC = 0.642), patients with subarachnoid hemorrhage (AUC = 0.958 for BN, vs. SAPS, AUC = 0.84), and elderly patients undergoing open heart surgery (AUC = 0.94 for ANN, vs. EuroSCORE, AUC = 0.648). Rather than developing models with good external validity by including a heterogeneous patient population, an alternative approach would be to build models for specific patient subsets using one’s local database. |
| first_indexed | 2024-09-23T15:08:22Z |
| format | Article |
| id | mit-1721.1/77628 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:08:22Z |
| publishDate | 2013 |
| publisher | MDPI AG |
| record_format | dspace |
| spelling | mit-1721.1/776282022-09-29T12:56:30Z A Database-driven decision support system: customized mortality prediction Celi, Leo Anthony G. Galvin, Sean Davidzon, Guido Lee, Joon Scott, Daniel Mark, Roger Greenwood Massachusetts Institute of Technology. Institute for Medical Engineering & Science Harvard University--MIT Division of Health Sciences and Technology Celi, Leo Anthony G. Lee, Joon Scott, Daniel Mark, Roger Greenwood We hypothesize that local customized modeling will provide more accurate mortality prediction than the current standard approach using existing scoring systems. Mortality prediction models were developed for two subsets of patients in Multi-parameter Intelligent Monitoring for Intensive Care (MIMIC), a public de-identified ICU database, and for the subset of patients >80 years old in a cardiac surgical patient registry. Logistic regression (LR), Bayesian network (BN) and artificial neural network (ANN) were employed. The best-fitted models were tested on the remaining unseen data and compared to either the Simplified Acute Physiology Score (SAPS) for the ICU patients, or the EuroSCORE for the cardiac surgery patients. Local customized mortality prediction models performed better as compared to the corresponding current standard severity scoring system for all three subsets of patients: patients with acute kidney injury (AUC = 0.875 for ANN, vs. SAPS, AUC = 0.642), patients with subarachnoid hemorrhage (AUC = 0.958 for BN, vs. SAPS, AUC = 0.84), and elderly patients undergoing open heart surgery (AUC = 0.94 for ANN, vs. EuroSCORE, AUC = 0.648). Rather than developing models with good external validity by including a heterogeneous patient population, an alternative approach would be to build models for specific patient subsets using one’s local database. National Institutes of Health (U.S.) (National Institute of Biomedical Imaging and Bioengineering (U.S.)) (Grant R01 EB001659) 2013-03-12T18:03:24Z 2013-03-12T18:03:24Z 2012-09 2012-09 Article http://purl.org/eprint/type/JournalArticle 2075-4426 http://hdl.handle.net/1721.1/77628 Celi, Leo Anthony et al. “A Database-driven Decision Support System: Customized Mortality Prediction.” Journal of Personalized Medicine 2.4 (2012): 138–148. © 2012 MDPI AG https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 en_US http://dx.doi.org/10.3390/jpm2040138 Journal of Personalized Medicine Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf MDPI AG MDPI |
| spellingShingle | Celi, Leo Anthony G. Galvin, Sean Davidzon, Guido Lee, Joon Scott, Daniel Mark, Roger Greenwood A Database-driven decision support system: customized mortality prediction |
| title | A Database-driven decision support system: customized mortality prediction |
| title_full | A Database-driven decision support system: customized mortality prediction |
| title_fullStr | A Database-driven decision support system: customized mortality prediction |
| title_full_unstemmed | A Database-driven decision support system: customized mortality prediction |
| title_short | A Database-driven decision support system: customized mortality prediction |
| title_sort | database driven decision support system customized mortality prediction |
| url | http://hdl.handle.net/1721.1/77628 https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 |
| work_keys_str_mv | AT celileoanthonyg adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT galvinsean adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT davidzonguido adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT leejoon adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT scottdaniel adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT markrogergreenwood adatabasedrivendecisionsupportsystemcustomizedmortalityprediction AT celileoanthonyg databasedrivendecisionsupportsystemcustomizedmortalityprediction AT galvinsean databasedrivendecisionsupportsystemcustomizedmortalityprediction AT davidzonguido databasedrivendecisionsupportsystemcustomizedmortalityprediction AT leejoon databasedrivendecisionsupportsystemcustomizedmortalityprediction AT scottdaniel databasedrivendecisionsupportsystemcustomizedmortalityprediction AT markrogergreenwood databasedrivendecisionsupportsystemcustomizedmortalityprediction |