DeSTILD: Development of a Screening Tool for Interstitial Lung Disease
Bibliographic record
Abstract
Abstract Background: Interstitial lung disease (ILD) encompasses a diverse group of pulmonary disorders characterized by inflammation and scarring of the lung interstitium. Most ILD patients get diagnosed at an advanced stage of the disease. Early diagnosis is critical for effective management and improved patient outcomes. Objective: To develop a screening tool for ILD that could be used by primary care physicians to aid in early diagnosis of ILD. Methods: We developed a screening tool that involved 4 stages; review of literature, expert interviews, content validation and derivation of tool. Important variables were listed through a comprehensive literature search, followed by interviews with 5 ILD experts to further narrow down these variables. The third step of content validation included identification of the most essential and least essential variables by 15 ILD experts. The last stage of development of tool was to build a model through a case-control study, that included 1,184 patients (619 cases and 565 controls) across 21 centres in India. Based on the data received, the scoring for each variable was derived and the sensitivity, specificity and accuracy of the tool was determined. Results: A total of 80 variables were identified through literature review phase. The 5 experts filtered out least important variables and 43 variables were finalized at this stage. Factor analysis of the scores received from the 15 ILD experts in the content validation phase, yielded a final tool comprising 10 questions with 22 variables. In the last stage of development of tool using the data from the case-control study, the significant variables were identified and the model was built using associate analysis and logistic regression. The variables and final scoring was as follows; shortness of breath: 1, dry cough: 2, exposure: 1, connective tissue disorder: 3, use of medications: 1, clubbing: 3, velcro/fine crackles: 3. Based on this scoring system, the screening tool with a cut-off score of 5 demonstrated a sensitivity of 81%, specificity of 80%, positive predictive value of 81.1%, negative predictive value of 79.1%, and overall accuracy of 80.1%. Conclusion: The development of this novel screening tool represents a significant advancement for early detection of ILD. The next steps include validation of this tool, which is currently underway.
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 | 0.009 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".