Mathematical-Statistical Concepts for Modelling and Prediction of Longterm Follow-up

Newer statistical methods for modeling and prediction of long-term follow-up in schizophrenia are presented. These include the extended Cox model, the Generalized Estimating Equations (GEE) method and the Artificial Neural Networks (ANN) approach.

References

• 1 Albert P S. Longitudinal data analysis (repeated measures) in clinical trials.  Stat Med. 1999;  18 1707-1732
• 2 Angst J, Gamma A, Sellaro R, Lavori P W, Zhang H. Recurrence of bipolar disorders and major depression - A life-long perspective.  Eur Arch Psychiatry Clin Neurosci. 2003;  253 236-240
• 3 Anderson P K, Gill R D. Cox’s regression model for counting processes: A large sample study.  Ann Stat. 1982;  10 1100-1120
• 4 Anderson P K, Borgan O, Gill R D, Keiding N. Statistical models based on counting processes. Heidelberg-New York; Springer 1992
• 5 Awad A G. Prediction research of neuroleptic treatment outcome in schizophrenia - state of the art: 1978-1993. In: Gaebel W, Awad AW, (editors) Prediction of neuroleptic treatment outcome in schizophrenia. Wien; Springer 1994: pp 1-14
• 6 Breiman L, Friedman J H, Olshen R A, Stone C L. Classification and regression trees (CART). Monterey; Wadsworth 1984
• 7 Burton P, Gurrin L, Sly P. Extending the simple linear regression model to account for correlated responses: An introduction to Generalized Estimating Equations and Multilevel Mixed Modelling.  Stat Med. 1998;  17 1261-1291
• 8 Cox D R. Regression models and life tables.  J Royal Stat Soc. 1972;  34 (Series B) 187 - 220
• 9 Doering S, Müller E, Köpcke W, Gaebel W, Linden M, Müller P, Müller-Spahn F, Tegeler J, Schüssler G. Predicators of relapse and rehospitalization in schizophrenia and schizoaffective disorders.  Schizophr Bull. 1998;  24 187-198
• 10 Everitt B S, Landau S. The use of multivariate statistical methods in psychiatry.  Stat Methods Med Res. 1998;  7 253-277
• 11 Fitzmaurice G M, Laird N M, Zahner G E, Daskalakis C. Bivariate logistic regression analysis of childhood psychopathology ratings using multiple informants.  Am J Epidemiol. 1995;  142 1194-1203
• 12 Fleming T R, Harrington D P. Counting processes and survival analysis. New York; Wiley 1991
• 13 Gaebel W. Prediction research of outcome in neuroleptic treatment - definitions and concepts. In: Gaebel W, Awad AW, (editors) Prediction of neuroleptic treatment outcome in schizophrenia. Wien; Springer 1994: pp 15-26
• 14 Insightful Corporation, S-PLUS® Version 3.3 (1995), 2000 (1999), and 6.1 (2002). 1995-2002
• 15 Kleinbaum D G. Logistic Regression - a self-learning text. New York; Springer 1994
• 16 Köpcke W. Design, methodological and statistical issues in prediction research of neuroleptic response. In: Gaebel W, Awad AW, (editors) Prediction of neuroleptic treatment outcome in schizophrenia. Wien; Springer 1994: pp 155-164
• 17 Liang K Y, Zeger S L. Longitudinal data analysis using generalized linear models.  Biometrika. 1996;  73 13-22
• 18 Mancl L A. GEEPLUS SAS Macro for regression modelling of correlated and longitudinal data. Technical Report 9503. University of Washington, Dental Public Health Sciences 1995
• 19 McCulloch W, Pitts W. A logical calculus of the ideas immanent in nervous activity.  Bull Math Biophys. 1943;  5 115-133
• 20 Papadourakis G, Vourkas M, Micheloyannis S, Jervis B. Use of artificial neural networks for clinical diagnosis.  Math Comput Simul. 1996;  40 623-635
• 21 Pickels A. Psychiatric epidemiology.  Stat Meth Med Res. 1998;  7 235-251
• 22 Pietzcker A, Gaebel W, Köpcke W, Linden M, Müller P, Müller-Spahn F, Tegeler J. Intermittent vs. maintenance neuroleptic long-term treatment in schizophrenia - Two-years results of a German multicenter study.  J Psychiatr Res. 1993;  27 321-339
• 23 Politi E, Balduzzi C, Bussi R, Bellodi L. Artificial neural networks: a study in clinical psychopharmacology.  Psychiatry Res. 1999;  87 203-215
• 24 Ravdin P M, Clark G M. A practical application of neural network analysis for predicting outcome of individual breast cancer patients.  Breast Cancer Res Treat. 1992;  22 285-293
• 25 Reed R D, Marks R J. Neural Smithing - Supervised Learning in Feedforward Artificial Neural Networks. Boston; MIT Press 2002
• 26 Ripley B D. Pattern recognition and neural networks. Cambridge; Cambridge University Press 1996
• 27 Rojas R. Neural Networks - A Systematic Introduction. Berlin, New-York; Springer Verlag 1996
• 28 SA S. Institute Inc., Statistical Analysis System SAS®, release 6.10 (1996), 6.12 (1998), and 8.2 (2002). 1996-2002
• 29 Schwarz G, Vach W, Schuhmacher M. On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology.  Stat Med. 2000;  19 541-561
• 30 Seuchter S A, Eisenacher M, Riesbeck M, Gaebel W, Köpcke W. Methods for predictor analysis of repeated measurements: Appplication to psychiatric data.  Methods Inf Med. 2004;  43 (2) 184-191
• 31 Simonoff E, Pickels A, Meyer J, Silberg J. Epidemiology of child psychopathology in the Virginia Twin study of adolescent behavioural development: influence of age, gender and impairment on rates of disorder.  Arch Gen Psychiatry. 1997;  54 801-808
• 32 Statsoft I nc. Statistica Neural Networks®, release 4.0F. 2000
• 33 Thernau T M. Extending the Cox model. In: Lin DY, Fleming TR, (editors) Proceedings of the first Seattle symposium in biostatistics: Survival analysis. New York; Springer 1997: pp 51-84
• 34 Uitti R J, Ahlskog J E, Maraganore D M, Muenter M D, Atkinson E J, Cha R H, O’Brian P C. (1993). Levodopa therapy and survival in idiopathic Parkinson’s disease: Olmsted County Project.  Neurology. 1993;  43 1918-1926
• 35 Ziegler A, Kastner C, Blettner M. The Generalized Estimating Equations.  An Annotated Bibliography Biometrical Journal. 1998;  40 115-139