Diagnostic performance of artificial intelligence in detection of renal cell carcinoma: a systematic review and meta-analysis
Bibliographic record
Abstract
OBJECTIVES: The detection of renal cell carcinoma (RCC) tumors in the earlier stages is of great importance for more effective treatment. Encouraged by the key role of imaging in the management of RCC, we conducted a systematic review and meta-analysis of the studies that made use of artificial intelligence (AI) for the detection of RCC to quantitatively determine the performance of AI for distinguishing related renal lesions. MATERIALS AND METHODS: PubMed, Scopus, CENTRAL, and Embase electronic databases were systematically searched in November 2024 to identify studies that applied AI for the detection or classification of RCC. We conducted a meta-analysis to evaluate the diagnostic performance of utilized algorithms. Moreover, meta-regression was conducted over suspected covariates to evaluate potential sources of inter-study heterogeneity. Publication bias and quality assessment were also done for the included studies. RESULTS: Sixty-four studies were included in this systematic review, of which 31 studies were selected for meta-analysis. The studies assessing algorithms' performance on internal validation showed pooled sensitivity and specificity of 85% (95% confidence interval [CI], 82 to 87) and 76% (95% CI, 70 to 80), respectively. Moreover, externally validated Al algorithms had a pooled sensitivity and specificity of 80% (95% CI, 73 to 84) and 90% (95% CI, 84 to 93), respectively. Studies that performed internal validation for clinician performance had a pooled sensitivity of 79% (95% CI, 72 to 85) and specificity of 60% (95% CI, 49 to 70). CONCLUSION: The findings of the present study validate the acceptable performance of AI algorithms when contrasted with medical professionals in the identification and categorization of RCC. Nevertheless, the presence of heterogeneity between studies and the absence of coherence in the results underscore the necessity for the cautious interpretation of these results and additional prospective studies.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.008 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".