Artificial intelligence in pharmacovigilance: Do we need explainability?
Sign Up to like & getrecommendations! Published in 2022 at "Pharmacoepidemiology and Drug Safety"
DOI: 10.1002/pds.5501
Abstract: With increasing deployment of complex and opaque machine learning algorithms (black boxes) to make decisions in areas that profoundly affect individuals such as underwriting, judicial sentencing, and robotic driving, are increasing calls for explanations of… read more here.
Keywords: explainability; black boxes; intelligence pharmacovigilance; artificial intelligence ... See more keywords
Rethinking explainability: toward a postphenomenology of black-box artificial intelligence in medicine
Sign Up to like & getrecommendations! Published in 2022 at "Ethics and Information Technology"
DOI: 10.1007/s10676-022-09631-4
Abstract: In recent years, increasingly advanced artificial intelligence (AI), and in particular machine learning, has shown great promise as a tool in various healthcare contexts. Yet as machine learning in medicine has become more useful and… read more here.
Keywords: explainability; black box; medicine; artificial intelligence ... See more keywords
Clinical Explainability Failure (CEF) & Explainability Failure Ratio (EFR) – Changing the Way We Validate Classification Algorithms
Sign Up to like & getrecommendations! Published in 2022 at "Journal of Medical Systems"
DOI: 10.1007/s10916-022-01806-2
Abstract: Adoption of Artificial Intelligence (AI) algorithms into the clinical realm will depend on their inherent trustworthiness, which is built not only by robust validation studies but is also deeply linked to the explainability and interpretability… read more here.
Keywords: explainability; failure ratio; ratio efr; explainability failure ... See more keywords
Artificial Intelligence, Responsibility Attribution, and a Relational Justification of Explainability
Sign Up to like & getrecommendations! Published in 2020 at "Science and Engineering Ethics"
DOI: 10.1007/s11948-019-00146-8
Abstract: This paper discusses the problem of responsibility attribution raised by the use of artificial intelligence (AI) technologies. It is assumed that only humans can be responsible agents; yet this alone already raises many issues, which… read more here.
Keywords: justification explainability; responsibility attribution; artificial intelligence; responsibility ... See more keywords
Physician understanding, explainability, and trust in a hypothetical machine learning risk calculator
Sign Up to like & getrecommendations! Published in 2020 at "Journal of the American Medical Informatics Association : JAMIA"
DOI: 10.1093/jamia/ocz229
Abstract: OBJECTIVE Implementation of machine learning (ML) may be limited by patients' right to "meaningful information about the logic involved" when ML influences healthcare decisions. Given the complexity of healthcare decisions, it is likely that ML… read more here.
Keywords: understanding explainability; risk; trust; explainability trust ... See more keywords
Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.2984412
Abstract: Peer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of… read more here.
Keywords: explainability; granting scoring; machine; peer peer ... See more keywords
Bridging the Gap Between AI and Explainability in the GDPR: Towards Trustworthiness-by-Design in Automated Decision-Making
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Computational Intelligence Magazine"
DOI: 10.1109/mci.2021.3129960
Abstract: Can satisfactory explanations for complex machine learning models be achieved in high-risk automated decision-making? How can such explanations be integrated into a data protection framework safeguarding a right to explanation? This article explores from an… read more here.
Keywords: explainability; decision making; decision; machine learning ... See more keywords
Towards Explainability in Machine Learning: The Formal Methods Way
Sign Up to like & getrecommendations! Published in 2020 at "IT Professional"
DOI: 10.1109/mitp.2020.3005640
Abstract: & CLASSIFICATION IS A central discipline of machine learning (ML) and classifiers have become increasingly popular to support or replace human decisions. We encounter them as email spam detectors, as decision support systems, for example… read more here.
Keywords: methods way; explainability; formal methods; machine learning ... See more keywords
Explainability for artificial intelligence in healthcare: a multidisciplinary perspective
Sign Up to like & getrecommendations! Published in 2020 at "BMC Medical Informatics and Decision Making"
DOI: 10.1186/s12911-020-01332-6
Abstract: Background Explainability is one of the most heavily debated topics when it comes to the application of artificial intelligence (AI) in healthcare. Even though AI-driven systems have been shown to outperform humans in certain analytical… read more here.
Keywords: intelligence healthcare; artificial intelligence; perspective; explainability medical ... See more keywords
Explainability of radiomics through formal methods
Sign Up to like & getrecommendations! Published in 2022 at "Computer methods and programs in biomedicine"
DOI: 10.2139/ssrn.3978710
Abstract: BACKGROUND AND OBJECTIVE Artificial Intelligence has proven to be effective in radiomics. The main problem in using Artificial Intelligence is that researchers and practitioners are not able to know how the predictions are generated. This… read more here.
Keywords: explainability; formal methods; explainability radiomics; radiomics formal ... See more keywords
Population Preferences for Performance and Explainability of Artificial Intelligence in Health Care: Choice-Based Conjoint Survey
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Medical Internet Research"
DOI: 10.2196/26611
Abstract: Background Certain types of artificial intelligence (AI), that is, deep learning models, can outperform health care professionals in particular domains. Such models hold considerable promise for improved diagnostics, treatment, and prevention, as well as more… read more here.
Keywords: health care; health; performance; decision ... See more keywords