Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors
By F E Harrell, Kerry L Lee, D. B. Mark. 2005
9,356 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Epidemiology, Health Information Management
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Karel G. M. Moons
- Douglas G. Altman
- Tengyu Ma
- Percy Liang
- Ananya Kumar
- Patrick Royston
- Michael I. Jordan
- Philip Dawid
In Epidemiology
- Karel G. M. Moons
- Douglas G. Altman
- Gary S. Collins
- A. Jiménez‐Valverde
- Patrick Royston
- Y. Vergouwe
- Ewout W. Steyerberg
- R. Riley
In Health Information Management
- Ewout W. Steyerberg
- Karel G. M. Moons
- Douglas G. Altman
- Philip Dawid
- A. Jiménez‐Valverde
- L. Chambless
- Raimundo Real
- Jorge M. Lobo
Citations in the corpus
- Verified Uncertainty Calibration (2019, background): “Calibration, including the squared calibration error, has been studied in many fields besides machine learning including meteorology [2, 3, 4, 5, 6], fairness [29, 30], healthcare [1, 31, 32, 33], reinforcement learning [34], natural language processing [7, 8], speech recognition [35], econometrics ”
- Preoperative prediction of severe postoperative pain (2003, methodology): “In contrast to etiological research, it is common in prediction research to use a more liberal p-value than 0.05, e.g. 0.15 or even 0.20 or 0.25, for keeping variables in the model (Chatfield, 1995; Harrell et al., 1996).”
- Evaluating Random Forests for Survival Analysis using Prediction Error Curves (2012, background): “Most popular are the Brier and logarithmic scoring rules (Gneiting and Raftery 2007) and rank statistics like the concordance index which equals the area under the ROC curve (AUC) for binary responses (Harrell Jr., Lee, and Mark 1996).”
- Ecology of butterflies in Europe (2009, background): “This is equivalent to having no more than m/10 predictors with m being the number of observation in the least represented category (Harrell et al., 1996). Reineking & Schröder (2006) show a strong effect of variable selection for low EPV producing larger optimism in case of small EPV due to overfitt”
- Revised international prognostic scoring system for myelodysplastic syndromes. (2012, neutral): “Very low 1313 350 (27) 46 (13) 304 (87) Low 2646 1053 (40) 174 (17) 861 (83) Intermediate 1433 782 (55) 205 (26) 568 (74) High 898 633 (71) 207 (33) 421 (67) Very high 722 619 (86) 193 (31) 422 (69) Total 7012 3437 (49) 825 (24) 2576 (76) IPSS-R IN MDS 2461 BLOOD, 20 SEPTEMBER 2012 VOLUME 120, NUMBE”