Correction: On the construction of a large-scale database of AI-assisted annotating lung ventilation-perfusion scintigraphy for pulmonary embolism (VQ4PEDB)
Bibliographic record
Abstract
A correction refers to a change to their article that the author wishes to publish after publication. The publication of this article is subject to Frontiers' editorial approval.Instructions:• Please read through all the templates before choosing • Pick the most relevant text template(s) from the following page and delete all others.• Edit the text as necessary, ensuring that the original incorrect text is included for the record, please see the below. • Please do not use any extra formatting when editing the templates, and only modify the red text unless absolutely necessary • Submit to Frontiers following the instructions on this page.When the original text contained incorrect information, to preserve the scientific record, please include that text when editing the below templates. For example:There was a mistake in the Funding statement, an incorrect number was used.The correct number is "2015C03Bd051.". The publisher apologizes for this mistake.The original version of this article has been updated. We have incorrectly opined about the performance of a private company's third party software (Segmed Inc). The performance related to Canadian zip codes as well as other types of data was due to a user error and improper configuration of the tool by the authors. We have made the following edits:[Methods, Anonymization of DICOM files and de-identification of clinical reports, second paragraph]. This paragraph should be replaced with:"For clinical report texts, we adopted and compounded the effect of the following three independent approaches as a conservative de-identification strategy: (1) Segmed Inc.'s Python-based web server was used to remove PII/PHI from clinical reports, (2) RegEx rules were used to remove Canadian formatted addresses and postal codes in Python, and (3) resulting texts were fed to a Microsoft Copilot agent that was instructed to list suspected people names, addresses, street names, 5-8 digit numbers, business names, clinic names and occupations. The agent was further prompted to ignore medical terms. The resulting terms were then manually screened for relevance, the terms were searched for in the text and then replaced with "[Anon]"."[Discussion, Data Ingestion, first paragraph]: This paragraph should be replaced with:"QA revealed our unstructured text data to be properly de-identified, highlighting the effectiveness of our multiple layers of de-identification approaches. Structured DICOM data from hospital sources proved straightforward to robustly de-identify using our strategy. Also, during our QA process, various non-structured DICOM tags, such as series description, used during splitting process were identified and addressed accordingly to preserve integrity of workflow." Accordingly, please remove reference 27.for a reason not seen here, please contact the journal's editorial office.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.116 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.005 | 0.008 |
| Insufficient payload (model declined to judge) | 0.075 | 0.048 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".