Emily S Blum1, Antonio R Porras2, Elijah Biggs3, Pooneh R Tabrizi3, Rachael D Sussman4, Bruce M Sprague5, Eglal Shalaby-Rana6, Massoud Majd6, Hans G Pohl5, Marius George Linguraru7. 1. Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Health System, Washington, D. C.; Division of Urology, Children's National Health System, Washington, D. C. 2. Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Health System, Washington, D. C.. Electronic address: aporraspe@childrensnational.org. 3. Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Health System, Washington, D. C. 4. Division of Urology, MedStar Georgetown University Hospital, Washington, D. C. 5. Division of Urology, Children's National Health System, Washington, D. C. 6. Department of Radiology, Children's National Health System, Washington, D. C. 7. Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Health System, Washington, D. C.; Departments of Radiology and Pediatrics, School of Medicine and Health Science, George Washington University, Washington, D. C.
Abstract
PURPOSE: We sought to define features that describe the dynamic information in diuresis renograms for the early detection of clinically significant hydronephrosis caused by ureteropelvic junction obstruction. MATERIALS AND METHODS: We studied the diuresis renogram of 55 patients with a mean ± SD age of 75 ± 66 days who had congenital hydronephrosis at initial presentation. Five patients had bilaterally affected kidneys for a total of 60 diuresis renograms. Surgery was performed on 35 kidneys. We extracted 45 features based on curve shape and wavelet analysis from the drainage curves recorded after furosemide administration. The optimal features were selected as the combination that maximized the ROC AUC obtained from a linear support vector machine classifier trained to classify patients as with or without obstruction. Using these optimal features we performed leave 1 out cross validation to estimate the accuracy, sensitivity and specificity of our framework. Results were compared to those obtained using post-diuresis drainage half-time and the percent of clearance after 30 minutes. RESULTS: Our framework had 93% accuracy, including 91% sensitivity and 96% specificity, to predict surgical cases. This was a significant improvement over the same accuracy of 82%, including 71% sensitivity and 96% specificity obtained from half-time and 30-minute clearance using the optimal thresholds of 24.57 minutes and 55.77%, respectively. CONCLUSIONS: Our machine learning framework significantly improved the diagnostic accuracy of clinically significant hydronephrosis compared to half-time and 30-minute clearance. This aids in the clinical decision making process by offering a tool for earlier detection of severe cases and it has the potential to reduce the number of diuresis renograms required for diagnosis.
PURPOSE: We sought to define features that describe the dynamic information in diuresis renograms for the early detection of clinically significant hydronephrosis caused by ureteropelvic junction obstruction. MATERIALS AND METHODS: We studied the diuresis renogram of 55 patients with a mean ± SD age of 75 ± 66 days who had congenital hydronephrosis at initial presentation. Five patients had bilaterally affected kidneys for a total of 60 diuresis renograms. Surgery was performed on 35 kidneys. We extracted 45 features based on curve shape and wavelet analysis from the drainage curves recorded after furosemide administration. The optimal features were selected as the combination that maximized the ROC AUC obtained from a linear support vector machine classifier trained to classify patients as with or without obstruction. Using these optimal features we performed leave 1 out cross validation to estimate the accuracy, sensitivity and specificity of our framework. Results were compared to those obtained using post-diuresis drainage half-time and the percent of clearance after 30 minutes. RESULTS: Our framework had 93% accuracy, including 91% sensitivity and 96% specificity, to predict surgical cases. This was a significant improvement over the same accuracy of 82%, including 71% sensitivity and 96% specificity obtained from half-time and 30-minute clearance using the optimal thresholds of 24.57 minutes and 55.77%, respectively. CONCLUSIONS: Our machine learning framework significantly improved the diagnostic accuracy of clinically significant hydronephrosis compared to half-time and 30-minute clearance. This aids in the clinical decision making process by offering a tool for earlier detection of severe cases and it has the potential to reduce the number of diuresis renograms required for diagnosis.
Authors: Antonio R Porras; Liyun Tu; Deki Tsering; Esperanza Mantilla; Albert Oh; Andinet Enquobahrie; Robert Keating; Gary F Rogers; Marius George Linguraru Journal: Plast Reconstr Surg Date: 2019-12 Impact factor: 4.730
Authors: B M Zeeshan Hameed; Aiswarya V L S Dhavileswarapu; Syed Zahid Raza; Hadis Karimi; Harneet Singh Khanuja; Dasharathraj K Shetty; Sufyan Ibrahim; Milap J Shah; Nithesh Naik; Rahul Paul; Bhavan Prasad Rai; Bhaskar K Somani Journal: J Clin Med Date: 2021-04-26 Impact factor: 4.241