by machine learning

1. Objectives: The aim was to evaluate the potential for monotonicity constraints to bias machine learning systems to learn rules that were both accurate and meaningful. 2. Methods: Two data sets from problems as diverse as screening for dementia and assessing the risk of mental retardation were collected and a rule learning system with and without monotonicity constraints was run on each. The rules were shown to experts who were asked how willing they would be to use such rules in practice. The accuracy of the rules was also evaluated. 3. Results: Rules learned with monotonicity constraints were at least as accurate as rules learned without such constraints. Experts were on average more willing to use the rules learned with the monotonicity constraints. 4. Conclusions: Analysis of medical databases has the potential of improving patient outcomes and/or lowering the cost of health care delivery. A variety of techniques from statistics, pattern recognition, machine learning, and neural networks have been proposed to “mine” this data by uncovering patterns that may be used to guide decision making. This study suggests that the cognitive factors that make learned models coherent and, therefore, credible to experts. One factor that influences the acceptance of learned models is consistency with existing medical knowledge.