Explainable AI in Healthcare and Medicine

Building a Culture of Transparency and Accountability
Herausgegeben:Shaban-Nejad, Arash; Michalowski, Martin; Buckeridge, David L.

• Gebundenes Buch

Produktbeschreibung

This book highlights the latest advances in the application of artificial intelligence and data science in health care and medicine. Featuring selected papers from the 2020 Health Intelligence Workshop, held as part of the Association for the Advancement of Artificial Intelligence (AAAI) Annual Conference, it offers an overview of the issues, challenges, and opportunities in the field, along with the latest research findings. Discussing a wide range of practical applications, it makes the emerging topics of digital health and explainable AI in health care and medicine accessible to a broad readership. The availability of explainable and interpretable models is a first step toward building a culture of transparency and accountability in health care. As such, this book provides information for scientists, researchers, students, industry professionals, public health agencies, and NGOs interested in the theory and practice of computational models of public and personalized health intelligence.

Produktdetails

• Studies in Computational Intelligence 914
• Verlag: Springer / Springer International Publishing / Springer, Berlin
• Artikelnr. des Verlages: 978-3-030-53351-9
• 1st ed. 2021
• Seitenzahl: 368
• Erscheinungstermin: 3. November 2020
• Englisch
• Abmessung: 241mm x 160mm x 26mm
• Gewicht: 688g
• ISBN-13: 9783030533519
• ISBN-10: 3030533514
• Artikelnr.: 59588026

Inhaltsangabe

Explainability and Interpretability: Keys to Deep Medicine.- Fast Similar Patient Retrieval from Large Scale Healthcare Data: A Deep Learning-based Binary Hashing Approach.- A Kernel to Exploit Informative Missingness in Multivariate Time Series from EHRs.- Machine learning discrimination of Parkinson's Disease stages from walk-er-mounted sensors data.- Personalized Dual-Hormone Control for Type 1 Diabetes Using Deep Rein-forcement Learning.- A Generalizable Method for Automated Quality Control of Functional Neuroimaging Datasets.- Uncertainty Characterization for Predictive Analytics with Clinical Time Series Data.- A Dynamic Deep Neural Network for Multimodal Clinical Data Analysis.- DeStress: Deep Learning for Unsupervised Identification of Mental Stress in Firefighters from Heart-rate Variability (HRV) Data.- A Deep Learning Approach for Classifying Nonalcoholic Steatohepatitis Pa-tients from Nonalcoholic Fatty Liver Disease Patients using Electronic Medical Records.