Filters








12 Hits in 0.77 sec

Interpretability and Explainability: A Machine Learning Zoo Mini-tour [article]

Ričards Marcinkevičs, Julia E. Vogt
2020 arXiv   pre-print
In this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics, law, and natural sciences. Although interpretability and explainability have escaped a clear universal definition, many techniques motivated by these properties have been developed over the recent 30 years with the focus currently shifting towards deep learning
more » ... ethods. In this review, we emphasise the divide between interpretability and explainability and illustrate these two different research directions with concrete examples of the state-of-the-art. The review is intended for a general machine learning audience with interest in exploring the problems of interpretation and explanation beyond logistic regression or random forest variable importance. This work is not an exhaustive literature survey, but rather a primer focusing selectively on certain lines of research which the authors found interesting or informative.
arXiv:2012.01805v1 fatcat:rges764sdnchtb32fkaa44tsdq

Discovery of Important Subsequences in Electrocardiogram Beats Using the Nearest Neighbour Algorithm [article]

Ricards Marcinkevics, Steven Kelk, Carlo Galuzzi, Berthold Stegemann
2019 arXiv   pre-print
Ričards Marcinkevičs received the BSc degree in data science and knowledge engineering from Maastricht University, in 2017.  ...  Marcinkevičs, S. Kelk and C. Galuzzi are with the Deparment of Data Science and Knowledge and Engineering (DKE), Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands. B.  ... 
arXiv:1901.09187v1 fatcat:c47dmzl4j5ejxjrxeheyn7e4bu

Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis

Ricards Marcinkevics, Patricia Reis Wolfertstetter, Sven Wellmann, Christian Knorr, Julia E. Vogt
2021 Frontiers in Pediatrics  
Given the absence of consolidated and standardized international guidelines for managing pediatric appendicitis and the few strictly data-driven studies in this specific, we investigated the use of machine learning (ML) classifiers for predicting the diagnosis, management and severity of appendicitis in children.Materials and Methods: Predictive models were developed and validated on a dataset acquired from 430 children and adolescents aged 0-18 years, based on a range of information
more » ... g history, clinical examination, laboratory parameters, and abdominal ultrasonography. Logistic regression, random forests, and gradient boosting machines were used for predicting the three target variables.Results: A random forest classifier achieved areas under the precision-recall curve of 0.94, 0.92, and 0.70, respectively, for the diagnosis, management, and severity of appendicitis. We identified smaller subsets of 6, 17, and 18 predictors for each of targets that sufficed to achieve the same performance as the model based on the full set of 38 variables. We used these findings to develop the user-friendly online Appendicitis Prediction Tool for children with suspected appendicitis.Discussion: This pilot study considered the most extensive set of predictor and target variables to date and is the first to simultaneously predict all three targets in children: diagnosis, management, and severity. Moreover, this study presents the first ML model for appendicitis that was deployed as an open access easy-to-use online tool.Conclusion: ML algorithms help to overcome the diagnostic and management challenges posed by appendicitis in children and pave the way toward a more personalized approach to medical decision-making. Further validation studies are needed to develop a finished clinical decision support system.
doi:10.3389/fped.2021.662183 pmid:33996697 pmcid:PMC8116489 fatcat:iuescpk2tvhx5mqziczbhwraue

Multichannel electrocardiogram diagnostics for the diagnosis of arrhythmogenic right ventricular dysplasia

Ricards Marcinkevics, James O'Neill, Hannah Law, Eleftheria Pervolaraki, Andrew Hogarth, Craig Russell, Berthold Stegemann, Arun V Holden, Muzahir H Tayebjee
2017 Europace  
-The identification of arrhythmogenic right ventricular dysplasia (ARVD) from 12 channel standard ECG is challenging. High density ECG data may identify lead locations and criteria with a higher sensitivity. Methods and Results -80 channel ECG recording from patients diagnosed with ARVD and controls were quantified by magnitude and integral measures of QRS and T waves, and by a measure (the average silhouette width) of differences in the shapes of the normalised ECG cycles. The channels with
more » ... best separability between ARVD patients and controls were near the right ventricular wall, at the third intercostal space. These channels showed pronounced differences in P waves compared to controls, as well as the expected differences in QRS and T waves. Conclusions -Multichannel recordings, as in body surface mapping, adds little to the reliability of diagnosing ARVD from ECGs. However, repositioning ECG electrodes to a high anterior position can improve the identification of ECG variations in ARVD. Additionally, increased P wave amplitude appears to be associated with ARVD. Arrhythmogenic right ventricular cardiomyopathy Arrhythmogenic right ventricular dysplasia Multichannel ECG recording P wave amplitude Multichannel ECG diagnostics for the diagnosis of arrhythmogenic right ventricular dysplasia Condensed abstract This study examines the use of 80-lead ECGs in the diagnosis of arrhythmogenic right ventricular dysplasia (ARVD). Findings show that high anterior chest lead positions improve diagnosis of ARVD and interestingly, ARVD patients have increased P-wave amplitude. However, additional channels of 80-lead ECGs add little in the diagnosis of ARVD. Total word count: 3,049 words Journal Subject Terms: Arrhythmia, Electrocardiogram (ECG) 1 What's New?  80 channel ECG recordings from ARVD patient and control groups allow the selection of recording sites that are best for separating the ECG waveforms between the two groups, using methods based on the ECG waveform rather than measures of amplitudes and durations of its components.  These methods show that high anterior chest lead positions provide the most discrimination between ARVD patients and controls and demonstrate well-known differences in T wave polarity and QRS integral.  There is also an association between increased P wave amplitude and the presence of ARVD.  The additional channels of the 80-lead ECGs add little to the discriminability between ARVD patients and controls.
doi:10.1093/europace/eux124 pmid:29016773 fatcat:o67ieddd5ffzrjwj6hfbzdrc7a

A Deep Variational Approach to Clustering Survival Data [article]

Laura Manduchi, Ričards Marcinkevičs, Michela C. Massi, Thomas Weikert, Alexander Sauter, Verena Gotta, Timothy Müller, Flavio Vasella, Marian C. Neidert, Marc Pfister, Bram Stieltjes, Julia E. Vogt
2022 arXiv   pre-print
Ričards Marcinkevičs is supported by the SNSF grant #320038189096. Laura Manduchi is supported by the PHRT SHFN grant #1-000018-057: SWISSHEART.  ... 
arXiv:2106.05763v3 fatcat:xihbv3kojje27f63sv7uwwin5q

Rapid and reversible control of human metabolism by individual sleep states

Nora Nowak, Thomas Gaisl, Djordje Miladinovic, Ricards Marcinkevics, Martin Osswald, Stefan Bauer, Joachim Buhmann, Renato Zenobi, Pablo Sinues, Steven A Brown, Malcolm Kohler
2021
Sleep is crucial to restore body functions and metabolism across nearly all tissues and cells, and sleep restriction is linked to various metabolic dysfunctions in humans. Using exhaled breath analysis by secondary electrospray ionization high-resolution mass spectrometry, we measured the human exhaled metabolome at 10-s resolution across a night of sleep in combination with conventional polysomnography. Our subsequent analysis of almost 2,000 metabolite features demonstrates rapid, reversible
more » ... ontrol of major metabolic pathways by the individual vigilance states. Within this framework, whereas a switch to wake reduces fatty acid oxidation, a switch to slow-wave sleep increases it, and the transition to rapid eye movement sleep results in elevation of tricarboxylic acid (TCA) cycle intermediates. Thus, in addition to daily regulation of metabolism, there exists a surprising and complex underlying orchestration across sleep and wake. Both likely play an important role in optimizing metabolic circuits for human performance ll
doi:10.5167/uzh-208485 fatcat:bjudoflyivhtpfgdijol7dt5pq

Concept Bottleneck Model with Additional Unsupervised Concepts [article]

Yoshihide Sawada, Keigo Nakamura
2022 arXiv   pre-print
Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions. arXiv preprint arXiv:1710.04806, 2017. [20] Ricards Marcinkevics and Julia E. Vogt.  ...  Alvarez and Jakkola [4] proposed a SENN to generalize the interpretable linear model and combines the encoder-decoder architectures as in [19], and Marcinkevics and Vogt [20] extended SENN for sequential  ... 
arXiv:2202.01459v1 fatcat:lrx7ps3nhrhxljypvzz3fkliuq

Deep Conditional Gaussian Mixture Model for Constrained Clustering [article]

Laura Manduchi, Kieran Chin-Cheong, Holger Michel, Sven Wellmann, Julia E. Vogt
2022 arXiv   pre-print
Sutter (ETH Zurich), Imant Daunhawer (ETH Zurich), and Ričards Marcinkevičs (ETH Zurich) for their helpful comments and suggestions.  ... 
arXiv:2106.06385v3 fatcat:pho4neagszau5aqi6tbotlzwkq

Generalized Multimodal ELBO [article]

Thomas M. Sutter and Imant Daunhawer, Julia E. Vogt
2021 arXiv   pre-print
ACKNOWLEDGMENTS We would like to thank Ričards Marcinkevičs for helpful discussions and proposing the name "PolyMNIST". ID is supported by the SNSF grant #200021 188466.  ... 
arXiv:2105.02470v2 fatcat:nu6i5suokfgx3fi4357l6udqqi

Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence [article]

Thomas M. Sutter, Imant Daunhawer, Julia E. Vogt
2020 arXiv   pre-print
Acknowledgments and Disclosure of Funding Thanks to Diane Bouchacourt for providing code and Ričards Marcinkevičs for helpful discussions. ID is supported by the SNSF grant #200021_188466.  ... 
arXiv:2006.08242v3 fatcat:g3pcr2xl4rdj3i7prfjitpk6cu

Provable concept learning for interpretable predictions using variational inference [article]

Armeen Taeb, Nicolo Ruggeri, Carina Schnuck, Fanny Yang
2022 arXiv   pre-print
Acknowledgements We thank Christina Heinze-Deml, Laura Manduchi and Ricards Marcinkevics for the useful discussions and feedback on our work.  ... 
arXiv:2204.00492v1 fatcat:hp6mffs3tzem7hr2puk2jsrnly

Learning explanations that are hard to vary [article]

Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi Gresele, Bernhard Schölkopf
2020 arXiv   pre-print
ACKNOWLEDGMENTS We wish to thank Sebastian Gomez, Luca Biggio, Julius von Kügelgen, Paolo Penna, Ioannis Anagno, Ricards Marcinkevics, Sidak Pal Singh, Damien Teney for feedback on the manuscript, and  ... 
arXiv:2009.00329v3 fatcat:hexhmtq57zbmfnjjcqtxzt6evu