Incentivising High Quality Crowdsourcing Clinical Data for Disease Prediction

Predictive modeling is fundamental in transforming large clinical data sets into actionable knowledge which can guide clinical decision making and personalized medicine. Although several studies have merged data mining techniques with statistical analysis to extract hidden patterns from large database, these proposed mechanisms are excessively complex for practical use. Therefore, it is essential that a better tool is developed for disease progression and survival rate predictions. In this paper, we first present how carefully chosen clinical features with our proper data cleaning method improves the accuracy of the the Amyotrophic Lateral Sclerosis (ALS) disease progression and survival rate predictions. In addition, we present an incentive model which provides individual rationality and platform profitability features to encourage hospitals to share high quality data for such predictions. Our evaluation results show promising outcomes for our proposed approaches.