The problem : 

Nowadays, an increasing number of machine learning methods are being used to develop medical applications. Many implementations use state-of-art methods, such as deep learning for tasks of classification, clustering and regression. But also new concerns arise: privacy preserving, model interpretability and fairness can be as important as accuracy metrics when evaluating a model. To have a set of tools and services available to developers may enable them to develop new trustworthiness-aware applications more easily.

Who benefit: 
Software Development Professionals
Startups, SMEs and IT vendors
ICT Policy Makers
Health Data Services
The benefits: 
  • Organizations can reuse assets, generated reports, practices and recommendations in order to provide trustworthiness-aware applications.
  • ICT Policy Makers can use generated reports in order to take decisions considering, for instance, privacy and fairness (e.g. protection for minority groups, discrimination, racism) aspects.
  • IT Vendors and data curators can offer services that allows processing sensitive data without problems related to data leakage.
  • Data scientists and more and more specifically, physicians, can use generated reports in order to understand the decisions taken by the algorithms and evaluate their results make sense (results are not black boxes).
  • Software developers can use Lemonade, a web based workflow tool which integrates all project features in a easy to use tool, allowing users to develop solutions without needing software programming.
The Innovation/Technical Implementation: 

This integrates different third-party libraries, platforms, practices and tools in a solution toolset able to process large volumes of data, to provide reports about the results of algorithms regarding trustworthiness and to provide higher level of software abstractions (workflows in Lemonade). The toolset includes tools to big data processing (Apache Spark framework), data anonymization (privacy preserving in ARX library), fairness (Aequitas framework)  and interpretability (LIME and SHAP libraries) reports and deep learning processing (Keras and Tensorflow libraries in GPGPUs). The toolset is available in a higher level abstraction as Lemonade workflows or directly as development libraries.

Future developments: 

Lemonade Framework was developed in the context of EUBra-BIGSEA project. Now, we are integrating features related to trustworthiness and deep learning in the framework. We have plans to allow developers to define neural networks directly in Lemonade, using Keras as abstraction. Also, different views of fairness (e.g. if a machine learning algorithm is “racist”) and interpretability (e.g. display which parts of images are relevant for an algorithm in order to a physician evaluate  a diagnosis) are going to be implemented as reports in the interface.