Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012
Acuity scores, such as APACHE, SAPS, MPM, and SOFA, are widely used to account for population differ ences in studies aiming to compare how medications, care guidelines, surgery, and other interventions impact mortality in Intensive Care Unit (ICU) patients. By contrast, the focus of the PhysioNet/C...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Computing in Cardiology
2015
|
| Online Access: | http://hdl.handle.net/1721.1/93166 https://orcid.org/0000-0002-6318-2978 https://orcid.org/0000-0001-8464-5866 |
| _version_ | 1826189902759329792 |
|---|---|
| author | Silva, Ikaro Moody, George B. Scott, Daniel J. Celi, Leo Anthony G. Mark, Roger Greenwood |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Silva, Ikaro Moody, George B. Scott, Daniel J. Celi, Leo Anthony G. Mark, Roger Greenwood |
| author_sort | Silva, Ikaro |
| collection | MIT |
| description | Acuity scores, such as APACHE, SAPS, MPM, and SOFA, are widely used to account for population differ ences in studies aiming to compare how medications, care guidelines, surgery, and other interventions impact mortality in Intensive Care Unit (ICU) patients. By contrast, the focus of the PhysioNet/CinC Challenge 2012 is to develop methods for patient-specific prediction of in-hospital mortality. The data used for the challenge consisted of 5 general descriptors and 36 time series (measurements of vital signs and laboratory results) from the first 48 hours of the first available ICU stay of 12,000 adult patients from the MIMIC II database. The challenge was organized as two events: event 1 measured performance of a binary classifier, and event 2 measured performance of a risk estimator. The score of event 1 was the lower of sensitivity and positive predictive value. The score for event 2 was a range-normalized Hosmer-Lemeshow statistic. A baseline algorithm (using SAPS-1) obtained event 1 and 2 scores of 0.3125 and 68.58 respectively. Most participants submitted entries that outperformed the baseline algorithm. The top final scores for events 1 and 2 were 0.5353 and 17.88 respectively. |
| first_indexed | 2024-09-23T08:28:42Z |
| format | Article |
| id | mit-1721.1/93166 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:28:42Z |
| publishDate | 2015 |
| publisher | Computing in Cardiology |
| record_format | dspace |
| spelling | mit-1721.1/931662024-03-20T19:32:38Z Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 Silva, Ikaro Moody, George B. Scott, Daniel J. Celi, Leo Anthony G. Mark, Roger Greenwood Massachusetts Institute of Technology. Institute for Medical Engineering & Science Harvard University--MIT Division of Health Sciences and Technology Silva, Ikaro Moody, George B. Scott, Daniel J. Celi, Leo Anthony G. Mark, Roger Greenwood Acuity scores, such as APACHE, SAPS, MPM, and SOFA, are widely used to account for population differ ences in studies aiming to compare how medications, care guidelines, surgery, and other interventions impact mortality in Intensive Care Unit (ICU) patients. By contrast, the focus of the PhysioNet/CinC Challenge 2012 is to develop methods for patient-specific prediction of in-hospital mortality. The data used for the challenge consisted of 5 general descriptors and 36 time series (measurements of vital signs and laboratory results) from the first 48 hours of the first available ICU stay of 12,000 adult patients from the MIMIC II database. The challenge was organized as two events: event 1 measured performance of a binary classifier, and event 2 measured performance of a risk estimator. The score of event 1 was the lower of sensitivity and positive predictive value. The score for event 2 was a range-normalized Hosmer-Lemeshow statistic. A baseline algorithm (using SAPS-1) obtained event 1 and 2 scores of 0.3125 and 68.58 respectively. Most participants submitted entries that outperformed the baseline algorithm. The top final scores for events 1 and 2 were 0.5353 and 17.88 respectively. National Institute for Biomedical Imaging and Bioengineering (U.S.) National Institute of General Medical Sciences (U.S.) (NIH cooperative agreement U01-EB-008577) National Institute of General Medical Sciences (U.S.) (NIH grant R01-EB-001659) 2015-01-23T15:06:37Z 2015-01-23T15:06:37Z 2012-09 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-2076-4 2325-8861 2325-887X 978-1-4673-2074-0 IEEE Catalog Number - CFP12CAR-PRT http://hdl.handle.net/1721.1/93166 Silva, Ikaro, George Moody, Daniel J Scott, Leo A. Celi, and Roger G Mark. "Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012." Computing in Cardiology 2012, Volume 39. p.245-248. https://orcid.org/0000-0002-6318-2978 https://orcid.org/0000-0001-8464-5866 en_US http://www.cinc.org/archives/2012/pdf/0245.pdf Computing in Cardiology Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Computing in Cardiology PMC |
| spellingShingle | Silva, Ikaro Moody, George B. Scott, Daniel J. Celi, Leo Anthony G. Mark, Roger Greenwood Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title | Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title_full | Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title_fullStr | Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title_full_unstemmed | Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title_short | Predicting In-Hospital Mortality of ICU Patients: The PhysioNet/Computing in Cardiology Challenge 2012 |
| title_sort | predicting in hospital mortality of icu patients the physionet computing in cardiology challenge 2012 |
| url | http://hdl.handle.net/1721.1/93166 https://orcid.org/0000-0002-6318-2978 https://orcid.org/0000-0001-8464-5866 |
| work_keys_str_mv | AT silvaikaro predictinginhospitalmortalityoficupatientsthephysionetcomputingincardiologychallenge2012 AT moodygeorgeb predictinginhospitalmortalityoficupatientsthephysionetcomputingincardiologychallenge2012 AT scottdanielj predictinginhospitalmortalityoficupatientsthephysionetcomputingincardiologychallenge2012 AT celileoanthonyg predictinginhospitalmortalityoficupatientsthephysionetcomputingincardiologychallenge2012 AT markrogergreenwood predictinginhospitalmortalityoficupatientsthephysionetcomputingincardiologychallenge2012 |