Sarah Itani

A multi-level classification framework for multi-site medical data

A classification approach to face the heterogeneity of multisite medical databases.A promising learning scheme to develop consistent aid in diagnosis models.A case study on Attention Deficit Hyperactivity Disorder. Recently, the culture of sharing medical data has emerged impressively, reducing significantly the barrier to the development of medical research accordingly. As open-access large datasets result from this significant initiative, data mining techniques can be considered for the development of interpretable expert systems to help in diagnosis. However, the collaborative effort of information gathering yields heterogeneous databases because of technical and geographical factors. Indeed, on the one hand, the harmonization of protocols for data collection is still missing. On the other hand, cultural and social factors impact locally both the epidemiology and etiology of a given disease. Ignoring these factors could weaken the credibility of studies based on multi-site data. Thereby, our work tackles the development of computer-aided diagnosis systems relying on heterogeneous data. For such a purpose, we propose a multi-level approach (inspired by multi-level statistical modeling) based on decision trees (in the sense of machine learning). This framework is applied on the public ADHD-200 collection for the study of Attention Deficit Hyperactivity Disorder (ADHD).

Specifics of medical data mining for diagnosis aid: A survey

Abstract Data mining continues to play an important role in medicine; specifically, for the development of diagnosis aid models used in expert and intelligent systems. Although we can find abundant research on this topic, clinicians remain reluctant to use decision support tools. Social pressure explains partly this lukewarm position, but concerns about reliability and credibility are also put forward. To address this reticence, we emphasize the importance of the collaboration between both data miners and clinicians. This survey lays the foundation for such an interaction, by focusing on the specifics of diagnosis aid, and the related data modeling goals. On this regard, we propose an overview on the requirements expected by the clinicians, who are both the experts and the final users. Indeed, we believe that the interaction with clinicians should take place from the very first steps of the process and throughout the development of the predictive models, thus not only at the final validation stage. Actually, against a current research approach quite blindly driven by data, we advocate the need for a new expert-aware approach. This survey paper provides guidelines to contribute to the design of daily helpful diagnosis aid systems.