Diagnostic predictive evaluation of pneumocystis jirovecii pneumonia using digital chest CT analysis combined with clinical features
Bibliographic record
Abstract
Background: Pneumocystis jirovecii pneumonia (PJP) is a serious form of pneumonia characterized by non-specific symptoms. Diagnosis is challenging due to overlapping clinical and laboratory features with bacterial pneumonia (BP). This study aimed to develop a diagnostic prediction model integrating digital chest CT analysis with clinical and laboratory parameters to enable early identification of PJP. Methods: A retrospective analysis was performed on patients with confirmed PJP or BP at two medical centers between May 2020 and June 2024. Patient history, clinical symptoms, and laboratory test results were compared between cohorts. Chest CT images were analyzed using AI-assisted tools. Predictive factors were identified through univariate and multivariate logistic regression analyses, and a diagnostic nomogram was constructed. External validation was conducted using an independent cohort. Results: Multivariate analysis identified previous immunomodulator use, procalcitonin levels, inflammatory lesion volume/total lung volume, whole lung -700 to -450 HU pneumonia lesion volume, and whole lung -450 to -300 HU pneumonia lesion volume as independent predictors of PJP. The constructed nomogram achieved AUCs of 0.898 and 0.820 in the training and validation cohorts, respectively, with sensitivity of 74.5% and specificity of 90.4% in the training cohort, and sensitivity of 73.5% and specificity of 79.4% in the validation cohort. Calibration curves and decision curve analyses confirmed the model's predictive accuracy and clinical utility. Conclusion: The model provides a valuable tool for differentiating PJP from BP, demonstrating that AI-assisted recognition of chest CT images can effectively support pathogen identification. Its application has the potential to improve early diagnosis of PJP and enhance patient outcomes.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".