Key result
AI-generated R.E.N.A.L. nephrometry scores show significant agreement with human experts and similarly predict oncologic outcomes.
Why the study?
Automating R.E.N.A.L. nephrometry scoring with artificial intelligence and comparing its predictive ability to expert human scores for oncologic and perioperative outcomes was needed.
Does an AI-generated R.E.N.A.L. nephrometry score yield comparable predictive results to human-expert scores for oncologic and perioperative outcomes in patients with suspected renal cancer?
Cohort (n=300)
Single-blind
No
Does an AI-generated R.E.N.A.L. nephrometry score yield comparable predictive results to human-expert scores for oncologic and perioperative outcomes in patients with suspected renal cancer?
Fully automated AI-generated R.E.N.A.L. scores demonstrate comparable predictive ability to human-expert scores for oncologic and perioperative outcomes in renal cancer.
Answers are grounded in this paper and cite their sources.
May support automated nephrometry for renal mass evaluation; leaves open prospective validation before clinical adoption.
PURPOSE: We sought to automate R.E.N.A.L. (for radius, exophytic/endophytic, nearness of tumor to collecting system, anterior/posterior, location relative to polar line) nephrometry scoring of preoperative computerized tomography scans and create an artificial intelligence-generated score (AI-score). Subsequently, we aimed to evaluate its ability to predict meaningful oncologic and perioperative outcomes as compared to expert human-generated nephrometry scores (H-scores). MATERIALS AND METHODS: A total of 300 patients with preoperative computerized tomography were identified from a cohort of 544 consecutive patients undergoing surgical extirpation for suspected renal cancer at a single institution. A deep neural network approach was used to automatically segment kidneys and tumors, and geometric algorithms were developed to estimate components of R.E.N.A.L. nephrometry score. Tumors were independently scored by medical personnel blinded to AI-scores. AI- and H-score agreement was assessed using Lin's concordance correlation and their predictive abilities for both oncologic and perioperative outcomes were assessed using areas under the curve. RESULTS: Median age was 60 years (IQE 51-68), and 40% were female. Median tumor size was 4.2 cm and 91.3% had malignant tumors, including 27%, 37% and 24% with high stage, grade and necrosis, respectively. There was significant agreement between H-scores and AI-scores (Lin's ⍴=0.59). Both AI- and H-scores similarly predicted meaningful oncologic outcomes (p <0.001) including presence of malignancy, necrosis, and high-grade and -stage disease (p <0.003). They also predicted surgical approach (p <0.004) and specific perioperative outcomes (p <0.05). CONCLUSIONS: Fully automated AI-generated R.E.N.A.L. scores are comparable to human-generated R.E.N.A.L. scores and predict a wide variety of meaningful patient-centered outcomes. This unambiguous artificial intelligence-based scoring is intended to facilitate wider adoption of the R.E.N.A.L. score.
No takes yet. Share an insight, caveat, or question.
A 2021 study conducted a cohort in Suspected renal cancer (n=300). AI-generated R.E.N.A.L. nephrometry score vs. Human-generated R.E.N.A.L. nephrometry score was evaluated on Agreement between AI- and H-scores and prediction of oncologic and perioperative outcomes (Lin's ⍴=0.59, p=<0.001). An AI-generated R.E.N.A.L. nephrometry score showed significant agreement with human-expert scores (Lin's ⍴=0.59) and similarly predicted meaningful oncologic outcomes (p<0.001).
Synapse has enriched 10 related papers. Consider them for comparative context: