AI Science Tracker
EN

Dalian Medical University

2 discoveries from 2023 to 2026

Discoveries

Real-Time Influenza Surveillance Using DeepSeek-Augmented BERT Classification on Chinese Social Media: Infodemiology Study.

Source check: Source checked. Not independent scientific confirmation.

Finding: Social-media classifier produced an influenza signal leading the official series by about a week; first-version and final results support that limited claim.

Technology: LLM pseudo-labeling plus chronological BERT test set; index correlations with CDC ILI and lead-time analysis reported; no lab confirmation or multi-season test.

Family DeepSeek: profile · models page

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
LLM pseudo-labeling plus chronological BERT test set; index correlations with CDC ILI and lead-time analysis reported; no lab confirmation or multi-season test.
Test and result
Validation basis and its limits: LLM pseudo-labeling plus chronological BERT test set; index correlations with CDC ILI and lead-time analysis reported; no lab confirmation or multi-season test.
Limitation / still unknown
The reviewed source does not establish prospective benefit, broad external validity, or replication beyond the reported study.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://doi.org/10.2196/98164

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Learned mitochondrial expression patterns associate with kidney cancer survival

Source check: Source checked. Not independent scientific confirmation.

Finding: Consensus clustering and Boruta selection separated mitochondrial-expression patterns in TCGA clear-cell renal cancer data, with different recorded overall survival. Iterative LASSO and survival forests also produced exploratory prognostic models fitted to these data. This is a retrospective association; optimized survival cutoffs and model selection make performance optimistic, and predicted drug sensitivity does not establish treatment response or a therapeutic mechanism.

Technology: Consensus clustering; Boruta; iterative LASSO; random survival forest

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Unsupervised clustering and forest-based feature selection learn mitochondrial-expression patterns that can be compared with recorded survival.
Test and result
Outcome associations of unsupervised expression groups and exploratory supervised prognostic fitting using recorded TCGA survival data.
Limitation / still unknown
Independent prognostic validation, causal mitochondrial mechanisms and clinical treatment utility remain unestablished; no held-out cohort is described for the reported model performance.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC10657316/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 21 Nov 2026. Review scope: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.