Artificial Intelligence in Pediatric Urology

Article Pediatrics

Neural network non-linear modeling to predict hypospadias genotype-phenotype correlation

Nicolas Fernandez et al.

Summary: This study examines the correlation between genotype and phenotype in different types of hypospadias using a neural network algorithm and suggests the potential clinical applicability of this approach.

JOURNAL OF PEDIATRIC UROLOGY (2023)

Add to Collection

Article Pediatrics

Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves

John K. Weaver et al.

Summary: The study used deep learning to extract features from postnatal kidney ultrasounds and evaluated their performance in predicting CKD progression for boys with PUV. The findings suggest that these features can improve early prediction of CKD progression, with nadir creatinine having a significant impact on the predictive models.

PEDIATRIC NEPHROLOGY (2023)

Add to Collection

Article Medicine, General & Internal

Prediction of Wilms' Tumor Susceptibility to Preoperative Chemotherapy Using a Novel Computer-Aided Prediction System

Israa Sharaby et al.

Summary: This study aims to develop a novel computer-aided prediction system for predicting the response of Wilms' tumors to preoperative chemotherapy in children. By integrating imaging markers with a machine learning classification model, the system can make early predictions about the tumor's response, leading to personalized management plans for Wilms' tumors.

DIAGNOSTICS (2023)

Add to Collection

Article Pediatrics

CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center

Yupeng Zhu et al.

Summary: This study develops a deep learning (DL) model based on computed tomography (CT) for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors. The DL model achieved high accuracy and sensitivity in discriminating nWTs from Wilms tumors (WTs).

PEDIATRIC RESEARCH (2023)

Add to Collection

Article Biology

Design of a rapid diagnostic model for bladder compliance based on real-time intravesical pressure monitoring system

Zicong Ge et al.

Summary: This study introduces a novel method to judge bladder compliance by measuring intravesical pressure during VCUG examination, showing promising classification performance in clinical trials. The method is expected to assist doctors in rapid auxiliary diagnosis of bladder diseases based on real-time data.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Pediatrics

Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves

Jethro C. C. Kwong et al.

Summary: This study successfully predicted clinically relevant outcomes in patients with posterior urethral valve using machine learning models, achieving better predictive performance than traditional statistical models.

PEDIATRIC NEPHROLOGY (2022)

Add to Collection

Article Urology & Nephrology

Machine Learning for Urodynamic Detection of Detrusor Overactivity

Kevin T. Hobbs et al.

Summary: A machine learning algorithm has been developed in this study to identify detrusor overactivity in urodynamic studies in patients with spina bifida. The model achieved good performance in detecting detrusor overactivity and has the potential to standardize UDS interpretation, enhance shared decision-making, and improve patient care.

UROLOGY (2022)

Add to Collection

Article Urology & Nephrology

Personalized application of machine learning algorithms to identify pediatric patients at risk for recurrent ureteropelvic junction obstruction after dismembered pyeloplasty

Erik Drysdale et al.

Summary: The study developed a machine learning model to predict the risk of recurrent obstruction in children after pyeloplasty, determine their survival risk score, and expected time to re-intervention. The model performed well in predicting the risk and time to re-intervention after pyeloplasty, demonstrating potential for personalized risk stratification for patients undergoing the procedure. Further real-world validation of the model is needed to confirm its effectiveness in clinical practice.

WORLD JOURNAL OF UROLOGY (2022)

Add to Collection

Article Pediatrics

A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: Methods and proof of concept

Adree Khondker et al.

Summary: This study develops a quantitative approach for grading vesicoureteral reflux (VUR) using machine learning techniques. The results demonstrate that tortuosity and ureter dilatation are predictors of high-grade VUR.

JOURNAL OF PEDIATRIC UROLOGY (2022)

Add to Collection

Article Medicine, General & Internal

Prediction of Recurrent Urinary Tract Infection in Paediatric Patients by Deep Learning Analysis of 99mTc-DMSA Renal Scan

Hyunjong Lee et al.

Summary: DL analysis of Tc-99m-DMSA renal scans can predict recurrent UTI in pediatric patients more effectively, providing an efficient supportive tool to predict poor prognosis when cortical defects are not visually demonstrable in Tc-99m-DMSA renal scans.

DIAGNOSTICS (2022)

Add to Collection

Article Urology & Nephrology

Automated Machine Learning Segmentation and Measurement of Urinary Stones on CT Scan

Rilwan Babajide et al.

Summary: The study evaluated the performance of a machine learning algorithm in identifying kidney stones and measuring their characteristics without human input. The algorithm demonstrated 100% sensitivity and specificity in detecting kidney stones, and outperformed human reviewers in accurately measuring stone features. The algorithm also provided more precise stone segmentations compared to human reviewers.

UROLOGY (2022)

Add to Collection

Article Urology & Nephrology

Identifying urethral strictures using machine learning: a proof-of-concept evaluation of convolutional neural network model

Jin Kyu Kim et al.

Summary: A CNN-based machine learning algorithm was developed to accurately distinguish between urethral strictures and normal conditions in retrograde urethrograms, showing high validation accuracy. Further development of the model may help determine stricture location and length for optimal operative repair.

WORLD JOURNAL OF UROLOGY (2022)

Add to Collection

Article Urology & Nephrology

Deep-learning segmentation of ultrasound images for automated calculation of the hydronephrosis area to renal parenchyma ratio

Sang Hoon Song et al.

Summary: This study investigated the feasibility of using a deep-learning network to measure the hydronephrosis area to renal parenchyma ratio from ultrasound images. The results showed that the deep-learning network can accurately calculate the areas of hydronephrosis and kidney, and it can assist physicians in making more accurate diagnoses of hydronephrosis.

INVESTIGATIVE AND CLINICAL UROLOGY (2022)

Add to Collection

Article Pediatrics

Application of Machine Learning Techniques for Enuresis Prediction in Children

Baran Tokar et al.

Summary: This study established a prediction model for enuresis in children using machine learning techniques, selecting 14 high feature value variables significantly affecting enuresis. The model achieved a prediction accuracy rate of 81.3% through data training.

EUROPEAN JOURNAL OF PEDIATRIC SURGERY (2021)

Add to Collection

Article Urology & Nephrology

Digital Pattern Recognition for the Identification and Classification of Hypospadias Using Artificial Intelligence vs Experienced Pediatric Urologist

Nicolas Fernandez et al.

Summary: By utilizing machine learning/image recognition, objectivity of hypospadias recognition and classification can be improved. Anatomical variables of hypospadias can predict postoperative outcomes, but there is still subjective variability among evaluators.

UROLOGY (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model

Yesim Eroglu et al.

Summary: In this study, a hybrid CNN model was developed for the diagnosis and grading of vesicoureteral reflux in voiding cystourethrography images. The proposed model achieved the highest accuracy rate of 96.9%, indicating its potential application in the diagnosis and grading of vesicoureteral reflux.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Urology & Nephrology

Pattern recognition algorithm to identify detrusor overactivity on urodynamics

Hsin-Hsiao Scott Wang et al.

Summary: The study developed a predictive model using machine learning algorithms to facilitate automated identification of DO in UDS, showing promising performance. This model could potentially standardize UDS interpretation and improve reliability. Further signal processing and machine learning interpretation of other components of UDS are planned.

NEUROUROLOGY AND URODYNAMICS (2021)

Add to Collection

Article Oncology

Deep learning enabled prediction of 5-year survival in pediatric genitourinary rhabdomyosarcoma

Hriday P. Bhambhvani et al.

Summary: A comparison study was conducted between deep learning models and conventional statistical models for predicting 5-year survival in pediatric GU-RMS patients. The results showed that the deep learning models outperformed the traditional models, potentially improving prognosis for patients with rare cancers.

SURGICAL ONCOLOGY-OXFORD (2021)

Add to Collection

Article Urology & Nephrology

A Machine Learning Model to Maximize Efficiency and Face Time in Ambulatory Clinics

Hsin-Hsiao Scott Wang et al.

Summary: A machine learning model was developed to predict pediatric urologists' clinic time, showing high accuracy in prediction and significant reduction in patient wait time, ultimately improving clinical efficiency.

UROLOGY PRACTICE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence