Purpose To explore the value of the clinical radiomics nomogram based on ultrasound in evaluating the degree of fibrosis in chronic kidney disease(CKD).Materials and Methods This retrospective study included 350 patients with CKD in Nanchong Central Hospital from January 2014 to July 2022 who underwent renal biopsy.The patients were categorized by the tubule atrophy with interstitial fibrosis(TA/IF)and divided into a training cohort(n=245)and test cohort(n=105).The patient demographics were evaluated to establish a clinical prediction model.The XGBoost machine learning model was constructed by extracting the radiomics features from the ultrasound images.The clinical radiomics nomogram prediction model was constructed by combining the radiomics score(Rad score)and important clinical features.The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis.Results Among the 350 patients with CKD,226 had TA/IF 0 and 124 had TA/IF 1.Based on the clinical characteristics and Rad score,the clinical radiomics nomogram prediction model had the highest area under the curve in the training and testing cohorts,with the area under the curve of 0.938(95%CI 0.909-0.969)and 0.933(95%CI 0.891-0.980),respectively.Conclusion The ultrasound-based radiomics prediction model has potential value for the noninvasive diagnosis of TA/IF in CKD.Nomogram prediction models based on renal Rad scores and clinic may help clinicians to manage patients.

Purpose To explore the value of the clinical radiomics nomogram based on ultrasound in evaluating the degree of fibrosis in chronic kidney disease(CKD).Materials and Methods This retrospective study included 350 patients with CKD in Nanchong Central Hospital from January 2014 to July 2022 who underwent renal biopsy.The patients were categorized by the tubule atrophy with interstitial fibrosis(TA/IF)and divided into a training cohort(n=245)and test cohort(n=105).The patient demographics were evaluated to establish a clinical prediction model.The XGBoost machine learning model was constructed by extracting the radiomics features from the ultrasound images.The clinical radiomics nomogram prediction model was constructed by combining the radiomics score(Rad score)and important clinical features.The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis.Results Among the 350 patients with CKD,226 had TA/IF 0 and 124 had TA/IF 1.Based on the clinical characteristics and Rad score,the clinical radiomics nomogram prediction model had the highest area under the curve in the training and testing cohorts,with the area under the curve of 0.938(95%CI 0.909-0.969)and 0.933(95%CI 0.891-0.980),respectively.Conclusion The ultrasound-based radiomics prediction model has potential value for the noninvasive diagnosis of TA/IF in CKD.Nomogram prediction models based on renal Rad scores and clinic may help clinicians to manage patients.

INTRODUCTION: We aimed to investigate the intergrader and intragrader reliability of human graders and an automated algorithm for vertical cup-disc ratio (CDR) grading in colour fundus photographs. MATERIALS AND METHODS: Two-hundred fundus photographs were selected from a database of 3000 photographs of patients screened at a tertiary ophthalmology referral centre. The graders included glaucoma specialists (n = 3), general ophthalmologists (n = 2), optometrists (n = 2), family physicians (n = 2) and a novel automated algorithm (AA). In total, 2 rounds of CDR grading were held for each grader on 2 different dates, with the photographs presented in random order. The CDR values were graded as 0.1-1.0 or ungradable. The grading results of the 2 senior glaucoma specialists were used as the reference benchmarks for comparison. RESULTS: The intraclass correlation coefficient values ranged from 0.37-0.74 and 0.47-0.97 for intergrader and intragrader reliability, respectively. There was no significant correlation between the human graders' level of reliability and their years of experience in grading CDR ( = 0.91). The area under the curve (AUC) value of the AA was 0.847 (comparable to AUC value of 0.876 for the glaucoma specialist). Bland Altman plots demonstrated that the AA's performance was at least comparable to a glaucoma specialist. CONCLUSION The results suggest that AA is comparable to and may have more consistent performance than human graders in CDR grading of fundus photographs. This may have potential application as a screening tool to help detect asymptomatic glaucoma-suspect patients in the community.