Comparison of multiple prediction models for ambulation following spinal cord injury

Comparison of multiple prediction models for ambulation following spinal cord injury

Few studies have properly compared predictive performance of different models using the same medical data set. We developed and compared 3 models (logistic regression, neural networks, and rough sets) in the in prediction of ambulation at hospital discharge following spinal cord injury. We used the...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:Proceedings. AMIA Symposium. - 1998. - (1998) vom: 13., Seite 528-32
1. Verfasser: Rowland, T (VerfasserIn)
Weitere Verfasser: Ohno-Machado, L, Ohrn, A
Format: Aufsatz
Sprache:English
Veröffentlicht: 1998
Zugriff auf das übergeordnete Werk:Proceedings. AMIA Symposium
Schlagworte:Comparative Study Journal Article Research Support, U.S. Gov't, Non-P.H.S. Research Support, U.S. Gov't, P.H.S.
LEADER 01000naa a22002652 4500
001 NLM098643932
003 DE-627
005 20231222112457.0
007 tu
008 231222s1998 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0329.xml 
035 |a (DE-627)NLM098643932 
035 |a (NLM)9929275 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Rowland, T  |e verfasserin  |4 aut 
245 1 0 |a Comparison of multiple prediction models for ambulation following spinal cord injury 
264 1 |c 1998 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 16.03.1999 
500 |a Date Revised 10.12.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a Few studies have properly compared predictive performance of different models using the same medical data set. We developed and compared 3 models (logistic regression, neural networks, and rough sets) in the in prediction of ambulation at hospital discharge following spinal cord injury. We used the multi-center Spinal Cord Injury Model System database. All models performed well and had areas under the receiver operating characteristic curve in the 0.88-0.91 range. All models had sensitivity, specificity, and accuracy greater than 80% at ideal thresholds. The performance of neural network and logistic regression methods was not statistically different (p = 0.48). The rough sets classifier performed statistically worse than either the neural network or logistic regression models (p-values 0.002 and 0.015 respectively) 
650 4 |a Comparative Study 
650 4 |a Journal Article 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
650 4 |a Research Support, U.S. Gov't, P.H.S. 
700 1 |a Ohno-Machado, L  |e verfasserin  |4 aut 
700 1 |a Ohrn, A  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t Proceedings. AMIA Symposium  |d 1998  |g (1998) vom: 13., Seite 528-32  |w (DE-627)NLM098642928  |x 1531-605X  |7 nnns 
773 1 8 |g year:1998  |g day:13  |g pages:528-32 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |j 1998  |b 13  |h 528-32