|
Abstract:
|
Artificial Intelligence (AI), is a technology that uses algorithm and software to combine large amount of data to learn automatically from patterns or features in the data and interpret underlined complex phenomena. Artificial intelligence can use different techniques, including models based on statistical analysis of data, expert systems that primarily rely on if-then statements, and machine learning. Machine learning (ML) algorithms build a mathematical model based on sample data, known as “training data”, in order to make predictions or decisions without being explicitly programmed to do so. AI has seen multiple applications in imaging diagnostic devices and in other diagnostic tests. And there will be more in the foreseeable future. However, the performance of the diagnostic device with AI is only going to be as good as it has been trained on. Thus, it is important to establish the performance on a separate dataset independent of the training data et, from actual intended use population to assess the performance. This presentation will focus on examples with various applications of AI in diagnostic devices and the challenges related to study design and clinical validation.
|
