27 papers · ranked by Valyu relevance
Pantelis Linardatos, Vasilis Papastefanopoulos, Sotiris Kotsiantis
Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into…
Gabriel Terejanu, Jawad Chowdhury, Rezaur Rashid, Asif Chowdhury
The vast majority of research on explainability focuses on post-explainability rather than explainable modeling. Namely, an explanation model is derived to explain a complex black box model built with the sole purpose of achieving the highest performance possible. In part, this trend might be driven by the…
Vaishak Belle, Ioannis Papantonis
Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However…
Ted L. Chang, Hongjing Xia, Sonya Mahajan, Rohit Mahajan + 5 more
We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients that mimics the piecewise linearity of ReLU-activated deep neural networks. We used the framework to formulate a survival model for using medical claims to predict hospital readmission and death…
Esra Zihni, Vince Istvan Madai, Michelle Livne, Ivana Galinovic + 4 more
'Ahmed A. Khalil' 'Jochen B. Fiebach' 'Dietmar Frey' 'Ruxandra Stoean'] State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks…
Frantishek Akulich, Hadis Anahideh, Manaf Sheyyab, Dhananjay Ambre
Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction between matter and electromagnetic radiation, particularly holds a lot of…
D. Petkovic, A. Alavi, D. Cai, J. Yang + 1 more
Machine Learning (ML) is becoming an increasingly critical technology in many areas. However, its complexity and its frequent non-transparency create significant challenges, especially in the biomedical and health areas. One of the critical components in addressing the above challenges is the explainability or…
Authors not listed
Traditional and non-classical machine learning models for solid-state structure prediction have predominantly relied on compositional features (derived from properties of constituent elements) to predict the existence of structure and its properties. However, the lack of structural information can be a source of…
Schwartz, Sagi, Qinling Wang, Fang Fang
Predicting default is essential for banks to ensure profitability and financial stability. While modern machine learning methods often outperform traditional regression techniques, their lack of transparency limits their use in regulated environments. Explainable artificial intelligence (XAI) has emerged as a solution…
Zohreh Shams, Botty Dimanov, Sumaiyah Kola, Nikola Simidjievski + 6 more
Deep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining…
Rikab Gambhir, Luisa Lucie-Smith, Jesse Thaler
We review the concepts of interpretability and explainability as they apply to machine learning in physics. We define interpretability as concerning the structural transparency of a model (the ability to understand or approximate its inner workings) and explainability as concerning the scientific content of a model…
Naveed Akhtar
Deep visual models have widespread applications in high-stake domains. Hence, their black-box nature is currently attracting a large interest of the research community. We present the first survey in Explainable AI that focuses on the methods and metrics for interpreting deep visual models. Covering the landmark…
David Martínez-Enguita, Thomas Hillerton, Julia Åkesson, Maria Lerm + 1 more
Genome-scale DNA methylation (DNAm) profiles capture organismal physiology, but most predictive models lack transparency and multi-level applicability. Here we develop an explainable framework that quantifies respiratory, cardiovascular, and metabolic status as bounded health scores (0–1) derived from sex-specific…
Bryant Han, Qingling Duan, Ting Hu
Machine learning models in biomedicine have become increasingly complex, often functioning as black boxes. However, understanding contributors to disease and making actionable health interventions requires interpretable models. Common explainable AI methods like SHAP focus on feature importance but fall short in…
Marco Bertolini, Linlin Zhao, Djork-Arné Clevert, Floriane Montanari
The field of explainable AI applied to molecular property prediction models has often been reduced to deriving atomic contributions. This has impaired the interpretability of such models, as chemists rather think in terms of larger, chemically meaningful structures, which often do not simply reduce to the sum of their…
Authors not listed
Explainability methods in machine learning-driven research are increasingly being used, but it remains challenging to assess their reliability without deeply investigating the specific problem at hand. In this work, we present a Python-based Workflow for Interpretability Scoring using matched molecular Pairs (WISP).…
Laura Lema-Perez, Rafael Muñoz-Tamayo, Jose Garcia-Tirado, Hernan Alvarez
Empirical and phenomenological based models are used to represent biological and physiological processes. Phenomenological models are derived from the knowledge of the mechanisms that underlie the behaviour of the system under study, while empirical models are derived from analysis of data to quantify relationships…
Shuchun Sun, Pei Xu, Nathan Buchweitz, Cherice N. Hill + 9 more
'Farhad Ahmadi' 'Marshall B. Wilson' 'Angela Mei' 'Xin She' 'Benedikt Sagl' 'Elizabeth H. Slate' 'Janice S. Lee' 'Yongren Wu' 'Hai Yao'] Clarifying multifactorial musculoskeletal disorder etiologies supports risk analysis, development of targeted prevention, and treatment modalities. Deep learning enables comprehensive…
Seungheun Baek, Soyon Park, Yan Ting Chok, Mogan Gim + 1 more
GRN-Aligned Parameter Optimization Authors: ['Seungheun Baek' 'Soyon Park' 'Yan Ting Chok' 'Mogan Gim' 'Jaewoo Kang'] Motivation: Predicting cellular responses to genetic perturbations is essential for understanding biological systems and developing targeted therapeutic strategies. While variational autoencoders (VAEs)…
Mariіa Fedorova, Timothee Mickus, Niko Partanen, Janine Siewert + 2 more
Modeling Authors: ['Mariіa Fedorova' 'Timothee Mickus' 'Niko Partanen' 'Janine Siewert' 'Elena Spaziani' 'Andrey Kutuzov'] | Mariia Fedorova♠ | Timothee Mickus♡ | Niko Partanen♡ | | --- | --- | --- | | Janine Siewert♡ | Elena Spaziani♣ | Andrey Kutuzov♠ | | ♠University of Oslo | ♡University of Helsinki | ♣Sapienza…
Peter B. R. Hartog, Fabian Krüger, Samuel Genheden, Igor V. Tetko
Stakeholders of machine learning models desire explainable artificial intelligence (XAI) to produce human-understandable and consistent interpretations. In computational toxicity, augmentation of text-based molecular representations has been used successfully for transfer learning on downstream tasks. Augmentations of…
Maria H. Rasmussen, Diana S. Christensen, Jan H. Jensen
While there is a great deal of interest in methods aimed at explaining machine learning predictions of chemical properties, it is difficult to quantitatively benchmark such methods, especially for regression tasks. We show that the Crippen logP model (J. Chem. Inf. Comput. Sci. 1999, 39, 868) provides an excellent…
Joshua P. Jahner, C. Alex Buerkle, Dustin G. Gannon, Eliza M. Grames + 11 more
The proliferation of biological data with large numbers of samples and many dimensions is kindling hope that life scientists will be able to fit statistical and machine learning models that are highly predictive and interpretable. However, large biological data sets are commonly burdened with an inherent trade-off…
Authors not listed
Predicting drug-induced toxicity remains a central challenge in computational toxicology, particularly for organ-specific adverse effects that arise from diverse structural, biochemical, and mechanistic origins. Existing deep learning models excel at pattern recognition but often lack mechanistic interpretability…
Fuzhan Rahmanian, Robert M. Lee, Dominik Linzner, Kathrin Michel + 4 more
Predicting and monitoring battery life early and across chemistries is a significant challenge due to the plethora of degradation paths, form factors, and electrochemical testing protocols. Existing models typically translate poorly across different electrode, electrolyte, and additive materials, mostly require a fixed…
Authors not listed
Accurate prediction of melting points for pure molecules remains a significant challenge in predictive chemistry, with implications across various scientific fields, including materials science, drug discovery, and separations chemistry. Traditional methods, such as group contribution (GC) techniques, have shown…
Anna A. Ivanova, Martin Schrimpf, Stefano Anzellotti, Noga Zaslavsky + 2 more
Advances in cognitive neuroscience are often accompanied by an increased complexity in the methods we use to uncover new aspects of brain function. Recently, many studies have started to use large feature sets to predict and interpret brain activity patterns. Of crucial importance in this paradigm is the mapping model…