OSCR

Risk classification of internet gaming disorder based on neurobiological subtyping from impulsivity-linked resting-state functional connectivity: a longitudinal design study.

Code ↔ Paper

1 match between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 1 match
  1. [1] § Methods › Deep clustering framework ↔ idec_model.py, lines 212 to 331 · score 0.53 · reconstruction loss, optimization, pretraining, IDEC, model, AE · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 389 lines · 12 KB · no license · 1 match

  2. from __future__ import print_function, division
  3. import argparse
  4. import numpy as np
  5. from sklearn.cluster import KMeans
  6. from sklearn.metrics.cluster import normalized_mutual_info_score as nmi_score
  7. from sklearn.metrics import adjusted_rand_score as ari_score
  8. import torch
  9. import torch.nn as nn
  10. import torch.nn.functional as F
  11. from torch.nn.parameter import Parameter
  12. from torch.optim import Adam
  13. from torch.utils.data import DataLoader
  14. from torch.nn import Linear
  16. from utils import impulfc_Dataset, cluster_acc
  17. import matplotlib.pyplot as plt
  19. dsm5 = 'path_behavior_DSM'
  20. sub_dsm5 = np.loadtxt(dsm5, delimiter=",")
  21. sub_dsm5 = sub_dsm5.astype(int)
  22. sub_dsm5 = np.where(sub_dsm5 >= 5)
  24. def SSE_distance(hidden, center_cluster):
  26. hidden = hidden.unsqueeze(1)
  28. pdist = nn.PairwiseDistance(p=2)
  29. dis_hidden = []
  31. for batch in range(len(hidden)):
  32. dis_tmp = pdist(hidden[batch], center_cluster)
  34. dis_hidden.append(dis_tmp.cpu().detach().numpy())
  35. dis_cluster = np.apply_along_axis(np.min, axis=1, arr=dis_hidden)
  36. sse = np.sum(dis_cluster)
  37. label_current = np.argmin(dis_hidden, axis=1)
  38. return sse, label_current
  40. class AE(nn.Module):
  42. def __init__(self, n_enc_1, n_enc_2, n_enc_3, n_enc_4, n_enc_5, n_enc_6,
  43. n_dec_1, n_dec_2, n_dec_3, n_dec_4, n_dec_5, n_dec_6,
  44. n_input, n_z):
  45. super(AE, self).__init__()
  47. # encoder
  48. self.enc_1 = Linear(n_input, n_enc_1)
  49. self.bn1 = nn.BatchNorm1d(n_enc_1)
  51. self.enc_2 = Linear(n_enc_1, n_enc_2)
  52. self.bn2 = nn.BatchNorm1d(n_enc_2)
  54. self.enc_3 = Linear(n_enc_2, n_enc_3)
  55. self.bn3 = nn.BatchNorm1d(n_enc_3)
  57. self.enc_4 = Linear(n_enc_3, n_enc_4)
  58. self.bn4 = nn.BatchNorm1d(n_enc_4)
  60. self.enc_5 = Linear(n_enc_4, n_enc_5)
  61. self.bn5 = nn.BatchNorm1d(n_enc_5)
  63. self.enc_6 = Linear(n_enc_5, n_enc_6)
  64. self.bn6 = nn.BatchNorm1d(n_enc_6)
  68. self.z_layer = Linear(n_enc_6, n_z)
  70. # decoder
  71. self.dec_1 = Linear(n_z, n_dec_1)
  72. self.dec_bn1 = nn.BatchNorm1d(n_dec_1)
  74. self.dec_2 = Linear(n_dec_1, n_dec_2)
  75. self.dec_bn2 = nn.BatchNorm1d(n_dec_2)
  77. self.dec_3 = Linear(n_dec_2, n_dec_3)
  78. self.dec_bn3 = nn.BatchNorm1d(n_dec_3)
  80. self.dec_4 = Linear(n_dec_3, n_dec_4)
  81. self.dec_bn4 = nn.BatchNorm1d(n_dec_4)
  83. self.dec_5 = Linear(n_dec_4, n_dec_5)
  84. self.dec_bn5 = nn.BatchNorm1d(n_dec_5)
  86. self.dec_6 = Linear(n_dec_5, n_dec_6)
  87. self.dec_bn6 = nn.BatchNorm1d(n_dec_6)
  91. self.x_bar_layer = Linear(n_dec_6, n_input)
  93. def forward(self, x):
  95. # encoder
  96. enc_h1 = self.bn1(F.relu(self.enc_1(x.type(torch.float))))
  97. enc_h2 = F.relu(self.enc_2(enc_h1))
  98. enc_h3 = F.relu(self.enc_3(enc_h2))
  99. enc_h4 = F.relu(self.enc_4(enc_h3))
  100. enc_h5 = F.relu(self.enc_5(enc_h4))
  101. enc_h6 = self.bn6(F.relu(self.enc_6(enc_h5)))
  103. z = self.z_layer(enc_h6)
  105. # decoder
  106. dec_h1 = self.dec_bn1(F.relu(self.dec_1(z)))
  107. dec_h2 = F.relu(self.dec_2(dec_h1))
  108. dec_h3 = F.relu(self.dec_3(dec_h2))
  109. dec_h4 = F.relu(self.dec_4(dec_h3))
  110. dec_h5 = F.relu(self.dec_5(dec_h4))
  111. dec_h6 = self.dec_bn6(F.relu(self.dec_6(dec_h5)))
  113. x_bar = self.x_bar_layer(dec_h6)
  115. return x_bar, z
  118. class IDEC(nn.Module):
  120. def __init__(self,n_enc_1, n_enc_2, n_enc_3, n_enc_4, n_enc_5, n_enc_6,
  121. n_dec_1, n_dec_2, n_dec_3, n_dec_4, n_dec_5, n_dec_6,
  122. n_input,
  123. n_z,
  124. n_clusters,
  125. pretrain_path='data/ae_impul.pkl'):
  126. super(IDEC, self).__init__()
  127. self.alpha = 1.0
  128. self.pretrain_path = pretrain_path
  130. self.ae = AE(
  131. n_enc_1=n_enc_1,
  132. n_enc_2=n_enc_2,
  133. n_enc_3=n_enc_3,
  134. n_enc_4=n_enc_4,
  135. n_enc_5=n_enc_5,
  136. n_enc_6=n_enc_6,
  137. n_dec_1=n_dec_1,
  138. n_dec_2=n_dec_2,
  139. n_dec_3=n_dec_3,
  140. n_dec_4=n_dec_4,
  141. n_dec_5=n_dec_5,
  142. n_dec_6=n_dec_6,
  143. n_input=n_input,
  144. n_z=n_z)
  145. # cluster layer
  146. self.cluster_layer = Parameter(torch.Tensor(n_clusters, n_z))
  147. torch.nn.init.xavier_normal_(self.cluster_layer.data)
  149. def pretrain(self, path=''):
  150. if path == '':
  151. pretrain_ae(self.ae)
  152. # load pretrain weights
  153. self.ae.load_state_dict(torch.load(self.pretrain_path))
  154. print('load pretrained ae from', path)
  156. def forward(self, x):
  158. x_bar, z = self.ae(x)
  159. # cluster
  160. q = 1.0 / (1.0 + torch.sum(
  161. torch.pow(z.unsqueeze(1) - self.cluster_layer, 2), 2) / self.alpha)
  162. q = q.pow((self.alpha + 1.0) / 2.0)
  163. q = (q.t() / torch.sum(q, 1)).t()
  164. return x_bar, q, z
  167. def target_distribution(q):
  168. weight = q**2 / q.sum(0)
  169. return (weight.t() / weight.sum(1)).t()
  172. def pretrain_ae(model):
  174. plt.ion()
  175. fig, ax = plt.subplots()
  176. ax.set_xlabel('Epoch')
  177. ax.set_ylabel('Loss')
  178. ax.set_title('Loss Curve')
  180. train_loader = DataLoader(dataset, batch_size=64, shuffle=True)
  181. print(model)
  182. optimizer = Adam(model.parameters(), lr=args.lr)
  183. for epoch in range(iter_n):
  184. total_loss = 0.
  185. for batch_idx, (x, _, _) in enumerate(train_loader):
  186. x = x.to(device)
  187. x = x.type(torch.float)
  188. optimizer.zero_grad()
  189. x_bar, z = model(x)
  190. loss = F.mse_loss(x_bar, x)
  191. total_loss += loss.item()
  193. loss.backward()
  194. optimizer.step()
  196. ax.plot(epoch, total_loss/ (batch_idx + 1), 'bo')
  197. ax.figure.canvas.draw()
  198. ax.figure.canvas.flush_events()
  200. print("epoch {} loss={:.4f}".format(epoch,
  201. total_loss / (batch_idx + 1)))
  202. torch.save(model.state_dict(), args.pretrain_path)
  204. if total_loss/(batch_idx + 1) <0.001:
  205. break
  207. plt.ioff()
  208. plt.savefig('z=10/loss_curve_pretrainAE.png')
  209. print("model saved to {}.".format(args.pretrain_path))
  212. def train_idec():
  214. model = IDEC(
  215. n_enc_1=4096,
  216. n_enc_2=2048,
  217. n_enc_3=1024,
  218. n_enc_4=512,
  219. n_enc_5=128,
  220. n_enc_6=64,
  221. n_dec_1=64,
  222. n_dec_2=128,
  223. n_dec_3=512,
  224. n_dec_4=1024,
  225. n_dec_5=2048,
  226. n_dec_6=4096,
  227. n_input=args.n_input,
  228. n_z=args.n_z,
  229. n_clusters=args.n_clusters,
  230. alpha=1.0,
  231. pretrain_path=args.pretrain_path).to(device)
  233. model.pretrain('z=10/pretrian_model_loop.pkl')
  235. train_loader = DataLoader(
  236. dataset, batch_size=args.batch_size, shuffle=False)
  237. optimizer = Adam(model.parameters(), lr=args.lr)
  239. # cluster parameter initiate
  240. data = dataset.x
  241. y = dataset.y
  242. data = torch.Tensor(data).to(device)
  243. x_bar, hidden = model.ae(data)
  245. kmeans = KMeans(n_clusters=args.n_clusters)
  246. y_pred = kmeans.fit_predict(hidden.data.cpu().numpy())
  248. nmi_k = nmi_score(y_pred, y)
  249. print("nmi score={:.4f}".format(nmi_k))
  251. hidden = None
  252. x_bar = None
  254. y_pred_last = y_pred
  255. model.cluster_layer.data = torch.tensor(kmeans.cluster_centers_).to(device)
  257. model.train()
  258. y_all = []
  260. plt.ion()
  261. fig, ax = plt.subplots()
  262. ax.set_xlabel('Epoch')
  263. ax.set_ylabel('Loss')
  264. ax.set_title('Loss Curve')
  266. num_losses = 2
  267. losses = [[] for _ in range(num_losses)]
  268. total_losses = []
  269. SSE_all =[]
  270. totle_p = 0
  271. for epoch in range(400):
  273. if epoch % args.update_interval == 0:
  275. _, tmp_q, hidden = model(data)
  277. center_cluters = model.cluster_layer.data
  278. sse, y_pred = SSE_distance(hidden, center_cluters)
  279. SSE_all.append(sse)
  280. print("SSE: ", sse)
  282. # # update target distribution p
  283. tmp_q = tmp_q.data
  284. p = target_distribution(tmp_q)
  286. y_pred_last = y_pred
  288. if epoch % 20 == 0:
  289. y_all.append(y_pred_last)
  292. totle_loss = 0
  293. totle_reconstr_loss, totle_kl, totle_p = 0, 0, 0
  294. for batch_idx, (x, _, idx) in enumerate(train_loader):
  296. x = x.to(device)
  297. idx = idx.to(device)
  299. x = x.type(torch.float)
  300. x_bar, q, z = model(x)
  302. reconstr_loss = F.mse_loss(x_bar, x)
  303. kl_loss = F.kl_div(q.log(), p[idx.type(torch.long)])
  304. loss = args.gamma * kl_loss + reconstr_loss
  306. totle_reconstr_loss += reconstr_loss.item()
  307. totle_kl += kl_loss.item()
  308. totle_loss += loss.item()
  310. optimizer.zero_grad()
  311. loss.backward()
  312. optimizer.step()
  314. losses[0].append(totle_reconstr_loss/ (batch_idx + 1))
  315. losses[1].append(totle_kl/ (batch_idx + 1))
  316. total_losses.append(totle_loss/ (batch_idx + 1))
  317. ax.clear()
  318. for i in range(num_losses):
  319. ax.plot(range(epoch + 1), losses[i], label=f'Loss {i + 1}')
  320. ax.plot(range(epoch + 1), total_losses, label='Total Loss')
  321. ax.figure.canvas.draw()
  322. ax.figure.canvas.flush_events()
  323. plt.ioff()
  325. plt.savefig('z=10/loss_curve.png')
  326. print("epoch {} loss={:.4f} reconstr_loss={:.4f} kl_loss={:.6f}".format(epoch, totle_loss / (batch_idx + 1),
  327. totle_reconstr_loss / (batch_idx + 1),
  328. totle_kl / (batch_idx + 1)))
  330. torch.save(model.state_dict(), args.idec_path)
  331. return np.min(SSE_all), y_pred_last, SSE_all, center_cluters.cpu().detach().numpy(), hidden.cpu().detach().numpy()
  333. if __name__ == "__main__":
  335. parser = argparse.ArgumentParser(
  336. description='train',
  337. formatter_class=argparse.ArgumentDefaultsHelpFormatter)
  339. parser.add_argument('--lr', type=float, default=0.0001)
  340. parser.add_argument('--n_clusters', default=6, type=int)
  341. parser.add_argument('--batch_size', default=64, type=int)
  342. parser.add_argument('--n_z', default=10, type=int)
  343. parser.add_argument('--dataset', type=str, default='impul')
  344. parser.add_argument('--pretrain_path', type=str, default='data/ae_impul')
  345. parser.add_argument(
  346. '--gamma',
  347. default=0.5,
  348. type=float,
  349. help='coefficient of clustering loss')
  350. parser.add_argument('--update_interval', default=1, type=int)
  351. parser.add_argument('--tol', default=0.001, type=float)
  352. parser.add_argument('--idec_path', type=str, default='')
  353. args = parser.parse_args()
  354. args.cuda = torch.cuda.is_available()
  355. print("use cuda: {}".format(args.cuda))
  356. device = torch.device("cuda" if args.cuda else "cpu")
  358. if args.dataset == 'impul':
  359. args.pretrain_path = 'z=10/pretrian_model_loop.pkl'
  360. args.n_clusters = n_clusters
  361. args.n_input = index_number
  362. dataset = MnistDataset()
  363. print(args)
  365. # loop multiple time
  366. n = 1
  367. SSE_loop = []
  368. SSE_multi = []
  369. labels = np.zeros((n, sub_n))
  370. y_all = []
  371. centers = []
  372. hiddens = []
  373. for i in range(n):
  374. args.idec_path = 'z=10/idec_model_loop' + str(n) + '.pkl'
  375. min_SSE, label, SSE_all, center, hidden_last = train_idec()
  376. SSE_multi.append(min_SSE)
  377. y_all.append(label)
  378. labels[i, :] = label
  379. SSE_loop.append(SSE_all)
  380. centers.append(center)
  381. hiddens.append(hidden_last)
  382. print('mean SSE: ', np.mean(SSE_multi))
  384. print('labels', labels)
  386. import pandas as pd
  387. df = pd.DataFrame(data=labels)
  389. df.to_excel('labels.xlsx', index=False, header=False)

idec_model.py at commit cd260d3, no license · at the source

Overview

Authors: Xinwen Wen1, Jiahao Zhao1, Zhe Du1, Xiao Yu1, Dongcheng Wang1, Boxun Fu2, Mengjiao Ge3, Haichao Zhao3, Hongmei Wang4, Fu Li2, Dahua Yu5, Qinghua He3, Kai Yuan1,5,6,7,8
ORCID iDs: Mengjiao Ge
  1. School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710126 China
  2. School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi 710126 People’s Republic of China
  3. Faculty of Psychology, MOE Key Laboratory of Cognition and Personality, Southwest University, Chongqing, China
  4. Department of Medical Imaging, Inner Mongolia People’s Hospital, Hohhot, 010017 China
  5. School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia 014010 China
  6. Engineering Research Center of Molecular and Neuroimaging, Ministry of Education, Xi’an, Shaanxi People’s Republic of China
  7. Hainan Free Trade Port Health Medical Research Institute, Baoting, Hainan 572300 People’s Republic of China
  8. Ganzhou City Key Laboratory of Mental Health, The Third People’s Hospital of Ganzhou City, Ganzhou, Jiangxi 341000 People’s Republic of China
Institutions: Xidian University (China); Southwest University (China); Inner Mongolia People's Hospital (China); Inner Mongolia University of Science and Technology (China)
Journal: BMC medicine, volume 24, issue 1, article 290
Dates: received 9 October 2025; accepted 23 March 2026; published online 26 March 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1186/s12916-026-04825-9 · PMID 41888807 · PMCID PMC13141395 · OpenAlex W7140798817
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: fMRI (modality), human (organism), other condition (population), systems (subfield)
Methods: Statistics, Connectivity, fMRI & imaging, Smoothing, state filtering, decompositions
Keywords: Internet gaming disorder, Impulsivity, Resting-state functional connectivity, Deep clustering, Subtyping
MeSH: Brain*, Impulsive Behavior*, Internet Addiction Disorder*, Video Games*, Adolescent, Cross-Sectional Studies, Female, Humans, Internet, Longitudinal Studies, Magnetic Resonance Imaging, Male, Young Adult (* major topic)
Topic: Impact of Technology on Adolescents (Sociology and Political Science, Social Sciences), according to OpenAlex
Funding: National Natural Science Foundation of China (82371500, U22A20303, 82260359); Central Guide Local Science and Technology Development Fund Project (2025ZY0033); Central Government-funded Projects to Guide Local Technological Development (2025ZY0033)
Citations: not cited yet (Europe PMC); 47 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.

Vic-coding-NA/IGD_risk_idec

License: none: the authors keep all their rights
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: cd260d3484df200f9d369b46be10d3d3dfd9bc06, 18 March 2026
Languages: Python (2)
Size: 2 files, 2 scripts
Software Heritage: not archived
Found in: “Data availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (2 files), pandas (2 files), PyTorch (2 files), Matplotlib (1 file), scikit-learn (1 file), SciPy (1 file)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
2 files
At the source: github.com/Vic-coding-NA/IGD_risk_idec

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 2 scripts, each with its path and the digest of its content;
  • 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Code and data availability statement

The paper has a code and data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1186/s12916-026-04825-9.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 13 authors, 5 keywords, 13 MeSH terms, 3 funders, 43 references.

Cite

This paper

Wen, X., Zhao, J., Du, Z., Yu, X., Wang, D., Fu, B., Ge, M., Zhao, H., Wang, H., Li, F., Yu, D., He, Q., & Yuan, K. (2026). Risk classification of internet gaming disorder based on neurobiological subtyping from impulsivity-linked resting-state functional connectivity: a longitudinal design study. BMC medicine, 24(1), 290. https://doi.org/10.1186/s12916-026-04825-9

BibTeX

@article{wen2026risk,
author = {Wen, Xinwen and Zhao, Jiahao and Du, Zhe and Yu, Xiao and Wang, Dongcheng and Fu, Boxun and Ge, Mengjiao and Zhao, Haichao and Wang, Hongmei and Li, Fu and Yu, Dahua and He, Qinghua and Yuan, Kai},
title = {{Risk classification of internet gaming disorder based on neurobiological subtyping from impulsivity-linked resting-state functional connectivity: a longitudinal design study}},
journal = {BMC medicine},
year = {2026},
month = mar,
volume = {24},
number = {1},
pages = {290},
publisher = {BMC},
issn = {1741-7015},
doi = {10.1186/s12916-026-04825-9},
url = {https://doi.org/10.1186/s12916-026-04825-9},
pmid = {41888807},
pmcid = {PMC13141395}
}

RIS

TY - JOUR
AU - Wen, Xinwen
AU - Zhao, Jiahao
AU - Du, Zhe
AU - Yu, Xiao
AU - Wang, Dongcheng
AU - Fu, Boxun
AU - Ge, Mengjiao
AU - Zhao, Haichao
AU - Wang, Hongmei
AU - Li, Fu
AU - Yu, Dahua
AU - He, Qinghua
AU - Yuan, Kai
TI - Risk classification of internet gaming disorder based on neurobiological subtyping from impulsivity-linked resting-state functional connectivity: a longitudinal design study
T2 - BMC medicine
J2 - BMC Med
PY - 2026
DA - 2026/03/26
VL - 24
IS - 1
SP - 290
SN - 1741-7015
PB - BMC
DO - 10.1186/s12916-026-04825-9
UR - https://doi.org/10.1186/s12916-026-04825-9
LA - en
ER -

CSL-JSON

{
"id": "10.1186/s12916-026-04825-9",
"type": "article-journal",
"title": "Risk classification of internet gaming disorder based on neurobiological subtyping from impulsivity-linked resting-state functional connectivity: a longitudinal design study",
"container-title": "BMC medicine",
"author": [
{
"family": "Wen",
"given": "Xinwen"
},
{
"family": "Zhao",
"given": "Jiahao"
},
{
"family": "Du",
"given": "Zhe"
},
{
"family": "Yu",
"given": "Xiao"
},
{
"family": "Wang",
"given": "Dongcheng"
},
{
"family": "Fu",
"given": "Boxun"
},
{
"family": "Ge",
"given": "Mengjiao"
},
{
"family": "Zhao",
"given": "Haichao"
},
{
"family": "Wang",
"given": "Hongmei"
},
{
"family": "Li",
"given": "Fu"
},
{
"family": "Yu",
"given": "Dahua"
},
{
"family": "He",
"given": "Qinghua"
},
{
"family": "Yuan",
"given": "Kai"
}
],
"container-title-short": "BMC Med",
"volume": "24",
"issue": "1",
"page": "290",
"DOI": "10.1186/s12916-026-04825-9",
"PMID": "41888807",
"PMCID": "PMC13141395",
"ISSN": "1741-7015",
"publisher": "BMC",
"URL": "https://doi.org/10.1186/s12916-026-04825-9",
"language": "en",
"issued": {
"date-parts": [
[
2026,
3,
26
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1556/2006.2025.00103 [code]
Connectome-based predictive modelling of problematic gaming in youth from the ABCD study.
Journal: Journal of behavioral addictions
In common: scikit-learn, pandas, SciPy, 1 other tool, fMRI, other condition, 4 references
[2] doi:10.1016/j.neuroimage.2026.121829 [code]
Connectome-based prediction of problematic use of social media in adolescents: Findings from the ABCD study.
Journal: NeuroImage
In common: scikit-learn, pandas, SciPy, 1 other tool, fMRI, other condition, 2 references
[3] doi:10.1016/j.bpsgos.2025.100485 [code]
Transformative Effects of Mindfulness Meditation Training on the Dynamic Reconfiguration of Executive and Default Mode Networks in Internet Gaming Disorder.
Journal: Biological psychiatry global open science
In common: 4 references
[4] doi:10.1038/s41380-026-03457-y [code]
Connectome-based growth models reveal individual heterogeneity and neurophysiological subtypes of subthreshold depression.
Journal: Molecular psychiatry
In common: scikit-learn, pandas, SciPy, 2 other tools, 2 references
[5] doi:10.1038/s41467-025-57682-0 [code]
Major depressive disorder on a neuromorphic continuum.
Journal: Nature communications
In common: scikit-learn, pandas, SciPy, 2 other tools, 2 references
[6] doi:10.3389/fnins.2022.984647 [code]
Neural mechanisms of brand love relationship dynamics: Is the development of brand love relationships the same as that of interpersonal romantic love relationships?
Journal: Frontiers in neuroscience
In common: scikit-learn, pandas, SciPy, 2 other tools, 2 references
[7] doi:10.1038/s41366-026-02018-1 [code]
The neural pathways of change: an fMRI study of the effects of behavioral change suggestions on value-based dietary decision-making.
Journal: International journal of obesity (2005)
In common: scikit-learn, pandas, SciPy, 2 other tools, fMRI, other condition, 1 reference
[8] doi:10.1002/advs.202514044 [code]
Light Therapy Alleviates Addiction-Related Symptoms and Reshapes Habenula and Midbrain Pathways.
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
In common: scikit-learn, pandas, SciPy, 2 other tools, fMRI, other condition, 1 reference
[9] doi:10.1038/s41467-026-71719-y [code]
Brain functional-structural gradient coupling reflects development, behavior and genetic influences.
Journal: Nature communications
In common: PyTorch, scikit-learn, pandas, 3 other tools, 1 reference
[10] doi:10.1002/hbm.70139 [code]
Reward Decision Network Disconnection in Poststroke Apathy: A Prospective Multimodality Imaging Study.
Journal: Human brain mapping
In common: scikit-learn, pandas, NumPy, fMRI, 2 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9.svg)](https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9.svg
   :target: https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9"><img src="https://openscicode.org/badge/doi/10.1186/s12916-026-04825-9.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.