Multilevel models (MLMs) are increasingly deployed in industry across different functions. Applications usually result in binary classification within groups or hierarchies based on a set of input features. For transparent and ethical applications of such models, sound audit frameworks need to be developed. In this paper, an audit framework for technical assessment of regression MLMs is proposed. The focus is on three aspects: model, discrimination, and transparency & explainability. These aspects are subsequently divided into sub-aspects. Contributors, such as inter MLM-group fairness, feature contribution order, and aggregated feature contribution, are identified for each of these sub-aspects. To measure the performance of the contributors, the framework proposes a shortlist of KPIs, among others, intergroup individual fairness (DiffInd_MLM) across MLM-groups, probability unexplained (PUX) and percentage of incorrect feature signs (POIFS). A traffic light risk assessment method is furthermore coupled to these KPIs. For assessing transparency & explainability, different explainability methods (SHAP and LIME) are used, which are compared with a model intrinsic method using quantitative methods and machine learning modelling.Using an open-source dataset, a model is trained and tested and the KPIs are computed. It is demonstrated that popular explainability methods, such as SHAP and LIME, underperform in accuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution on the outcome). For other contributors, such as group fairness and their associated KPIs, similar analysis and calculations have been performed with the aim of adding profundity to the proposed audit framework. The framework is expected to assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit providers, users, and assessment bodies, as defined in the European Commission’s proposed Regulation on Artificial Intelligence, when deploying AI-systems such as MLMs, to be future-proof and aligned with the regulation.
DOCUMENT
The healthcare sector has been confronted with rapidly rising healthcare costs and a shortage of medical staff. At the same time, the field of Artificial Intelligence (AI) has emerged as a promising area of research, offering potential benefits for healthcare. Despite the potential of AI to support healthcare, its widespread implementation, especially in healthcare, remains limited. One possible factor contributing to that is the lack of trust in AI algorithms among healthcare professionals. Previous studies have indicated that explainability plays a crucial role in establishing trust in AI systems. This study aims to explore trust in AI and its connection to explainability in a medical setting. A rapid review was conducted to provide an overview of the existing knowledge and research on trust and explainability. Building upon these insights, a dashboard interface was developed to present the output of an AI-based decision-support tool along with explanatory information, with the aim of enhancing explainability of the AI for healthcare professionals. To investigate the impact of the dashboard and its explanations on healthcare professionals, an exploratory case study was conducted. The study encompassed an assessment of participants’ trust in the AI system, their perception of its explainability, as well as their evaluations of perceived ease of use and perceived usefulness. The initial findings from the case study indicate a positive correlation between perceived explainability and trust in the AI system. Our preliminary findings suggest that enhancing the explainability of AI systems could increase trust among healthcare professionals. This may contribute to an increased acceptance and adoption of AI in healthcare. However, a more elaborate experiment with the dashboard is essential.
LINK
Multilevel models using logistic regression (MLogRM) and random forest models (RFM) are increasingly deployed in industry for the purpose of binary classification. The European Commission’s proposed Artificial Intelligence Act (AIA) necessitates, under certain conditions, that application of such models is fair, transparent, and ethical, which consequently implies technical assessment of these models. This paper proposes and demonstrates an audit framework for technical assessment of RFMs and MLogRMs by focussing on model-, discrimination-, and transparency & explainability-related aspects. To measure these aspects 20 KPIs are proposed, which are paired to a traffic light risk assessment method. An open-source dataset is used to train a RFM and a MLogRM model and these KPIs are computed and compared with the traffic lights. The performance of popular explainability methods such as kernel- and tree-SHAP are assessed. The framework is expected to assist regulatory bodies in performing conformity assessments of binary classifiers and also benefits providers and users deploying such AI-systems to comply with the AIA.
DOCUMENT
Bedrijven, waaronder telecomproviders, vertrouwen steeds meer op complexe AI-systemen. Het gebrek aan interpreteerbaarheid dat zulke systemen vaak introduceren zorgt voor veel uitdagingen om het onderliggende besluitvormingsproces te begrijpen. Vertrouwen in AI-systemen is belangrijk omdat het bijdraagt aan acceptatie en adoptie onder gebruikers. Het vakgebied Explainable AI (XAI) speelt hierbij een cruciale rol door transparantie en uitleg aan gebruikers te bieden voor de beslissingen en werking van zulke systemen.Doel Bij AI-systemen zijn gewoonlijk verschillende stakeholders betrokken, die elk een unieke rol hebben met betrekking tot deze systemen. Als gevolg hiervan varieert de behoefte voor uitleg afhankelijk van wie het systeem gebruikt. Het primaire doel van dit onderzoek is het genereren en evalueren van op stakeholder toegesneden uitleg voor use cases in de telecomindustrie. Door best practices te identificeren, nieuwe explainability tools te ontwikkelen en deze toe te passen in verschillende use cases, is het doel om waardevolle inzichten op te doen. Resultaten Resultaten omvatten het identificeren van de huidige best practices voor het genereren van betekenisvolle uitleg en het ontwikkelen van op maat gemaakte uitleg voor belanghebbenden voor telecom use-cases. Looptijd 01 september 2023 - 30 augustus 2027 Aanpak Het onderzoek begint met een literatuurstudie, gevolgd door de identificatie van mogelijke use-cases en het in kaart brengen van de behoeften van stakeholders. Vervolgens zullen prototypes worden ontwikkeld en hun vermogen om betekenisvolle uitleg te geven, zal worden geëvalueerd.
Bedrijven, waaronder telecomproviders, vertrouwen steeds meer op complexe AI-systemen. Het gebrek aan interpreteerbaarheid dat zulke systemen vaak introduceren zorgt voor veel uitdagingen om het onderliggende besluitvormingsproces te begrijpen. Vertrouwen in AI-systemen is belangrijk omdat het bijdraagt aan acceptatie en adoptie onder gebruikers. Het vakgebied Explainable AI (XAI) speelt hierbij een cruciale rol door transparantie en uitleg aan gebruikers te bieden voor de beslissingen en werking van zulke systemen.
