Neural networks in medical journals: current trends and implications for BioPattern

Artificial neural networks have featured in a wide range of medical journals, often with promising results. This paper reviews the clinical fields where neural network methods figure most prominently, the main algorithms featured, methodologies for model selection and the need for rigorous evaluation of results. Common methodological shortcomings shared with other publications in medical statistical are identified, yielding a checklist for study design in BioPattern. Links are also made with staged methodologies for the development of medical decision support systems as a means of clearly specifying the purpose of individual studies so as to ensure maximum impact on follow-up studies leading to clinical trials.