Statistical Analysis of Complex Systems in Biomedicine

The future explanatory power in biomedicine will be at the molecular-genetic level of analysis (rather than the epidemiologic-demographic or anatomic-cellular levels). This is the level of complex systems. Complex systems are characterized by nonlinearity and complex interactions. It is difficult for traditional statistical methods to capture complex systems because traditional methods attempt to find the model that best fits the statistician’s understanding of the phenomenon; complex systems are difficult to understand and therefore difficult to fit with a simple model. Artificial neural networks are nonparametric regression models. They can capture any phenomena, to any degree of accuracy (depending on the adequacy of the data and the power of the predictors), without prior knowledge of the phenomena. Further, artificial neural networks can be represented, not only as formulae, but also as graphical models. Graphical models can increase analytic power and flexibility. Artificial neural networks are a powerful method for capturing complex phenomena, but their use requires a paradigm shift, from exploratory analysis of the data to exploratory analysis of the model.

[1]  A J Gabor,et al.  Automated interictal EEG spike detection using artificial neural networks. , 1992, Electroencephalography and clinical neurophysiology.

[2]  Robin J. Leach,et al.  Mutations of a mutS homolog in hereditary nonpolyposis colorectal cancer , 1993, Cell.

[3]  A Manduca,et al.  Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence. , 1992, Medical physics.

[4]  C. Floyd,et al.  Acute pulmonary embolism: artificial neural network approach for diagnosis. , 1993, Radiology.

[5]  A. Knudson.  Hereditary cancer, oncogenes, and antioncogenes. , 1985, Cancer research.

[6]  P. Wilding,et al.  Application of neural networks to the interpretation of laboratory data in cancer diagnosis. , 1992, Clinical chemistry.

[7]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[8]  T J O'Leary,et al.  Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis. , 1992, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[9]  Wray L. Buntine.  Operations for Learning with Graphical Models , 1994, J. Artif. Intell. Res..

[10]  M. Steel.  Cancer genes: complexes and complexities , 1993, The Lancet.

[11]  B. Vogelstein,et al.  A genetic model for colorectal tumorigenesis , 1990, Cell.

[12]  Philip H. W. Leong,et al.  MATIC—An Intracardiac Tachycardia Classification System , 1992, Pacing and clinical electrophysiology : PACE.

[13]  J N Weinstein,et al.  Neural computing in cancer drug development: predicting mechanism of action. , 1992, Science.

[14]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[15]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[16]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.

[17]  S. Palombo,et al.  Connectivity and Condensation in Dreaming , 1992, Journal of the American Psychoanalytic Association.

[18]  R. Fleischmann,et al.  Mutation of a mutL homolog in hereditary colon cancer. , 1994, Science.

[19]  J A Orr,et al.  Intelligent alarms reduce anesthesiologist's response time to critical faults. , 1992, Anesthesiology.

[20]  N. Copeland,et al.  The human mutator gene homolog MSH2 and its association with hereditary nonpolyposis colon cancer , 1993, Cell.

[21]  Max H. Myers,et al.  Manual for Staging of Cancer , 1992 .