Comparing Interpretable AI Approaches for the Clinical Environment: an Application to COVID-19

Onari, Mohsen Abbaspour; Nobile, Marco S.; Grau, Isel; Fuchs, Caro; Zhang, Yingqian; Boer, Arjen‐Kars; Scharnhorst, Volkher

doi:10.1109/cibcb55180.2022.9863020

Cited by 4 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Description of Method J48 [111] Machine learning decision tree classification algorithm based on Iterative Dichotomies. RIPPER [112,113] Rule-based ML algorithm, in which rules are learned from the data directly. pyFUME [112] Can create rules based on fuzzy logic.…”

Section: Methods [Source]mentioning

confidence: 99%

See 1 more Smart Citation

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

Khalili,

Wimmer

2024

Life

View full text Add to dashboard Cite

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic.

show abstract

Section: Methods [Source]mentioning

confidence: 99%

“…RIPPER [112,113] Rule-based ML algorithm, in which rules are learned from the data directly. pyFUME [112] Can create rules based on fuzzy logic.…”

Section: Methods [Source]mentioning

confidence: 99%

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

Khalili,

Wimmer

2024

Life

View full text Add to dashboard Cite

show abstract

“…The fuzzy rules, the linguistic values, the fuzzy sets and the shape of the membership functions are usually defined by the modeller, according to the available knowledge about the system to be described, unless a data-driven approach is exploited [ 39 ]. Fuzzy set theory and fuzzy logic found applications across several scientific and engineering disciplines, and FIS allowed fuzzy logic to be effectively adopted in several contexts, both in knowledge-based or data-driven applications, to support decision-making [ 40 , 41 ], meta-heuristics [ 42 ], modelling and control [ 43 , 44 ], clustering [ 45 ], classification tasks [ 46 ] and regression problems [ 47 ].…”

Section: Methodsmentioning

confidence: 99%

Characterization of bird formations using fuzzy modelling

Perinot

Fritz

Fusani

et al. 2023

J. R. Soc. Interface.

Self Cite

View full text Add to dashboard Cite

The investigation of the emergent collective behaviour in flying birds is a challenging task, yet it has always fascinated scientists from different disciplines. In the attempt of studying and modelling line formation, we collected high-precision position data of 29 free-flying northern bald ibises ( Geronticus eremita ) using Global Navigation Satellite System loggers, to investigate whether the spatial relationships within a flock can be explained by birds maintaining energetically advantageous positions. Specifically, we exploited domain knowledge and available literature information to model by means of fuzzy logic where the air vortices lie behind a flying bird. This allowed us to determine when a leading bird provides the upwash to a following bird, reducing its overall effort. Our results show that the fuzzy model allows to easily distinguish which bird is flying in the wake of another individual, provides a clear indication about flying flock dynamics and also gives a hint about birds' social relationships.

show abstract