stefania de vito

Can scientists learn from performers to better engage an audience? go.nature.com/4rJVypn

🔍 Explore the ECTRIMS Spotlight Series. Curated by our scientific content writer @stefania_devito, it explores the most important topics in MS research and care. Explore the full Spotlight Series now 👉 bit.ly/3LDjHOZ #SpotlightSeries #MSResearch #Neurology

📣 ✨Excited bout our latest work in @Patterns_CP @CellPressNews: GREEN a light-weight #NeuralNetwork with Riemannian Geometry + learnable wavelets for #EEG #biomarkers: doi.org/10.1016/j.patt… Joint work with @JP4illard & @hippneuro ! Thread 🧵👇🏻👇🏾👇

To preprocess or not to preprocess your #EEG 🔮when using #ML? 💫An enhanced version of our latest work at @Roche is now published in @eBioMedicine thelancet.com/journals/ebiom… #DeepDive #Thread 🧵in next post 👉👉🏾👉🏻

By setting priorities in #womenshealth topics, Ruth Ann Marrie, Past Chair of the International Advisory Committee on Clinical Trials in #MS, hopes it "will encourage researchers to investigate these questions in a timely fashion." Read about it here ➡️ bit.ly/48Z9NNg

To preprocess or not to preprocess your #EEG (when building #ML models) 🔮? 💫We are thrilled to share our latest #preprint, studying the challenge of learning brain-specific biomarkers from EEG 🧠📶 using #ML ⚙️🖥️: biorxiv.org/content/10.110… We compile arguments and evidence from benchmarking age- & sex-prediction on > 2600 EEGs from two large public datasets. We found that basic artifact rejection consistently led to better model performance, whereas removal of ocular and muscle artifacts hampered performance. As it turns out that those peripheral signals are predictive themselves! Our results therefore argue in favor of the need to diligently process EEG data, if the goal is to have brain-specific biomarkers (and if prediction is not the only objective). Our efforts to build more interpretable #ML models for EEG led us to extending the established Morlet wavelet methodology for spectral analysis of EEG to accommodate state-of-the-art ML models based on covariance matrices. This allowed us to perform head-to-head comparisons between classical EEG features and frequency-specific model predictions for, both, brain and artifact signals. Compared to classical band-pass filtering, wavelets even led to improvements in prediction performance. Joint work with Philipp Bomatter, @JP4illard, Pilar Garces & Jörg F Hipp.

📢🥁💫 Check out our last paper on #interpretability #XAI for heterogeneous datasets has been accepted for #NeurIPS2023 arxiv.org/abs/2309.07593. #PyTorch #Python #rstats #scikit_learn, #DeepLearning & classical #MachineLearning. Thread 🧵👇🏿👇👇🏽

@JFBonnefon Happy anniversary!!

Nobody's is sure how to dress up to the ERC interviews twitter.com/TCabarti/statu…

Italian study shows ventilation can cut school COVID cases by 82% reuters.com/world/europe/i…

scientificamerican.com/article/to-kee… Keep Students in STEM fields, Let's Weed Out the Weed-Out Math Classes via @sciam

Comment lutter contre le #coronavirus ... Vidéo du gouvernement allemand sur le #COVID19 (sous-titré en anglais). Et c'est top 👍

I am very excited to share our latest work published in @eLife! We combined #MEG, #fMRI and #MRI for #BrainAge prediction & #biomarker development. Each modality added unique information & enhanced brain-behavior mapping! elifesciences.org/articles/54055 Thread👇

Excited to share our paper @NeuroImage_EiC by @DavSabbagh with @PierreAblin @GaelVaroquaux @agramfort doi.org/10.1016/j.neur… Nonlinear subject-level regression on M/EEG using linear models without source localization: theory + empirical benchmarks Thread👇

Fifty years ago, Apollo astronauts first landed on the Moon. What better way to celebrate than constructing tiny versions of some of the mission's iconic vehicles and scientists? Sign up for Nature Briefing for a chance to win (current readers can enter and win too) 🚀

New scientific commentary by @RodikaSokoliuk x @damiancruse on our new paper in @Brain1878 twitter.com/dngman/status/… #EEG #consciousness #diagnosis #python @RaimondoFede @jdsitt @StanDehaene @jrking0 @mne_news @scikit_learn

Engemann et al. show that machine learning on EEG signals allows robust classification of state-of-consciousness in data from brain-injured patients in multiple hospitals. bit.ly/2DXiXkh

1/ New paper out! @Brain1878 bit.ly/2Pet8Cg Robust #MachineLearning of diagnosis from #EEG in disorders of #consciousness powered by @CEAParisSaclay @cdf1530 @Coma_Science @dc_uba @ERC_Research @Inria_Saclay @Inserm @mne_news @NeuroSpin_91 @icm_institute @scikit_learn

Harder faster... AutoReject-er 🎶🚀🛸! We proudly present our first official pip release: mail.nmr.mgh.harvard.edu/pipermail//mne… It's never been easier: from autoreject import AutoReject; epochs_clean = AutoReject(n_jobs=8).fit_transform(epochs) #EEG #MEG #Python #MachineLearning #neuroscience

Always wondered how hypothesis tests and out-of-sample predictions come together (or don't)? Our new preprint biorxiv.org/content/early/… looks at this issue in more than 100k simulations and empirical analysis of several medical datasets. #MachineLearning #statistics #Python #rstats