
Assistant professor @ZJU_China | PhD @fzj_inm7 | machine learning | computational psychiatry | neuroimage| https://teapaw.org/t.co/MtFduzMclh
Hanzhou, Zhejiang
Joined September 2019
- Tweets34
- Following49
- Followers82
- Likes80
Pinned Tweet
.
Our new paper led by Ji Chen (@INM7_ML_Psy) now out in Biological Psychiatry
We here propose an well-interpretable, dimensional representation of #schizophrenia psychopathology; extensively cross-validated in ~2000 patients across Europe, Asia & the US
biologicalpsychiatryjournal.…
Exciting that interpersonal computational psychiatry offers an explanation for how biased cognitive processes lead to differential negative symptoms, @dr_rick_adams. Thanks @TheLancetPsych and colleagues. Might be interesting alternative to a data-driven view!?! @INM7_ISN @bttyeo
Replying to @Yafeng_Pan
We propose an interpersonal computational framework that (1) leverages the active inference framework to model aberrant social coordination and (2) incorporates dynamical system models to dissect intrapersonal and interpersonal synchronisation to inform a statistical model.
Ji Chen retweeted
Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry - BMC Medicine - BMC Medicine dlvr.it/Src9wy
Ji Chen retweeted
1/9 Paper is out rdcu.be/cNHoL
Here's some takeaways including new tidbits (good & bad!) since the preprint & even after the paper was accepted.
Large sample sizes are helpful for individual-level prediction. We have known that for quite some time, but the recent...
1/5 Our new preprint doi.org/10.1101/2020.08.10.2… uses meta-learning to boost functional connectivity based prediction of *NEW* phenotypes in small samples. We achieve 100%-400% improvements in many scenarios!
@hetong93 @AvramHolmes @anlijuncn @danilobzdok @AvramHolmes @INM7_ISN
Ji Chen retweeted
I'm excited to present the 1st ENIGMA-Sleep project about #insomnia on>1000 dubjects in #WorldSleep2022
Many thanks to Antoine Weihs, Julian Schiel, Habibolah Khazaie, @INM7_ISN @PTenigma @sofievalk @enigmabrains @njahanshad Kai Spiegelhalder @Harvey_Bi2333 Kaustubh Patil, P#106
We are extremely glad to notice that our 1st talk on the # Computational psychiatry (CP) seminar will be given by Dr. @AlPowers7 at 9 am EDT this Wednesday (Aug 11). Thank Dr. @HaiyangGeng for coordinating this event. See zoom info on the poster. Pls RT.
Ji Chen retweeted
Work by @INM7_ISN and others (arxiv.org/abs/1912.06686) backs the second interpretation.
Anyhow, good performance on overly homogeneous samples has little external validity or practical usage.
Ji Chen retweeted
Resting-state functional connectivity of three seeds within the lateral temporal lobe predicts individual formal thought disorder severity: great work by
@jchen_ML_Psy w/ @INM7_ISN #schizophrenia #psychiatry #machinelearning
sciencedirect.com/science/ar…
Ji Chen retweeted
Excellent meta-analysis about the common brain networks underlying human social interactions! @INM7_ISN @eredcay sciencedirect.com/science/ar…
Ji Chen retweeted
Replying to @EliBaughan @BorsboomDenny
There are actually many such studies, e.g.
1.@cedrichxia nature.com/articles/s41467-0…
2.@valeria_kebets doi.org/10.1016/j.biopsych.2…
3.@tangsy93 doi.org/10.1016/j.biopsych.2…
4.@hong_seok_jun doi.org/10.1038/s41467-019-0…
5.doi.org/10.1038/s41380-018-0…
6.@INM7_ISN doi.org/10.1016/j.biopsych.2…
And many more!
Ji Chen retweeted
#Autism is often associated with an excess of synapses:
but how does this trait affect large-scale circuit function?
Here's what we found by modelling autism-related pruning deficits across-species🧠🐭
➡️tinyurl.com/y2yfj74o
By @MarcoPagani1985 @mvlombardo & al.
Thread 1/n
Ji Chen retweeted
Phenomenal work from our lab & collaborators led by @jchen_ML_Psy:
Connectivity patterns of task-defined networks allow individual prediction of dimensional schizophrenia psychopathology & link to molecular architecture
Short thread on the highlights ⤵️
biologicalpsychiatryjournal.…
Ji Chen retweeted
Intrinsic connectivity patterns of task-defined brain networks allow individual prediction of cognitive symptom dimension of schizophrenia and are linked to molecular architecture
biologicalpsychiatryjournal.…
Ji Chen retweeted
QUICK introductions to:
- Thresholding connectomes: Is it necessary?
youtu.be/MZEQR7gKfNE
- Null models in network neuroscience
youtu.be/QuEvtbbymqI
- Comparing connectomes: Inference & prediction
youtu.be/X5O1Eh7UfII
Based on recent OHBM course. 10mins per topic!
Happy to be involved in this nice and exciting work!
Excited to share our new preprint led by @DeboDong:
Cross-validated PLS yielded 4 robust dimensions that link cerebellar connectivity gradients trans-diagnostically to distinct clusters of behavioral scores (clinical, cognitive, personality)
biorxiv.org/content/10.1101/…
3
Ji Chen retweeted
NEW Research—First human trial of #COVID19 vaccine finds it is safe and induces rapid immune response: finding from a dose-escalation, single-centre, open-label, non-randomised, phase 1 trial hubs.ly/H0qMrl-0
Thread (1/3)
Ji Chen retweeted
Thx @INM7_ISN !
An amazing & important tool for #Schizophrenia research.
Wonderful collaboration @MHASC1 @CognitionLille
Read the #OA paper here: sciencedirect.com/science/ar…
PANSS sub scales (positive, negative, general psychopathology) are widely used in basic & clinical research on #Schizophrenia ...
but do not represent natural dimensions !
Replacing them with robust & generalizable factors is now easy with our new tool: webtools.inm7.de/sczDCTS/
Ji Chen retweeted
PANSS sub scales (positive, negative, general psychopathology) are widely used in basic & clinical research on #Schizophrenia ...
but do not represent natural dimensions !
Replacing them with robust & generalizable factors is now easy with our new tool: webtools.inm7.de/sczDCTS/
Ji Chen retweeted
New preprint! 👇
We related connectome architecture to patterns of atrophy in the common epilepsies and identified syndrome-specific disease epicenters 📌
Our @enigmabrains analysis pooled data across 19 international sites and included 1,021 patients and 1,564 controls 🌎🌏🌍
Network-based atrophy modelling in the common epilepsies: a worldwide ENIGMA study biorxiv.org/cgi/content/shor… #biorxiv_neursci
Ji Chen retweeted
We have developed a CBT-based program that anyone can download and use to stay mentally healthy in these difficult times. Please share widely!
jimdo-storage.global.ssl.fas…
@jayvanbavel @zakijam @dremilyanhalt @DebiecJacek @mirandarwolpert @NIMHDirector @matthaig1 @AllenFrancesMD


























