Development of an Automatic Interpretation Algorithm for Uroflowmetry Results: Application of Artificial Intelligence

Abstract

Purpose: To develop an automatic interpretation system for uroflowmetry (UFM) results using machine learning (ML), a form of artificial intelligence (AI).Methods: A prospectively collected 1,574 UFM results (1,031 males, 543 females) with voided volume>150 mL was labelled as normal, borderline, or abnormal by 3 urologists. If the 3 experts disagreed, the majority decision was accepted. Abnormality was defined as a condition in which a urologist judges from the UFM results that further evaluation is required and that the patient should visit a urology clinic. To develop the optimal automatic interpretation system, we applied 4 ML algorithms and 2 deep learning (DL) algorithms. ML models were trained with all UFM parameters. DL models were trained to digitally analyze 2-dimensional images of UFM curves.Results: The automatic interpretation algorithm achieved a maximum accuracy of 88.9% in males and 90.8% in females when using 6 parameters: voided volume, maximum flow rate, time to maximal flow rate, average flow rate, flow time, and voiding time. In females, the DL models showed a dramatic improvement in accuracy over the other models, reaching 95.4% accuracy in the convolutional neural network model. The performance of the DL models in clinical discrimination was outstanding in both genders, with an area under the curve of up to 0.957 in males and 0.974 in females.Conclusions: We developed an automatic interpretation algorithm for UFM results by training AI models using 6 key parameters and the shape of the curve; this algorithm agreed closely with the decisions of urology specialists.

The impact of psychological factors and anxiety on uroflowmetry results

“…Therefore, it is recommended to use repeated measurements instead of relying on a single test result to increase the reliability of the test. 4,23,24 Our study found that the patients' second UF results improved compared to the first. That may be because the patients feel more comfortable as they become familiar with the environment, recognize the health professionals, and learn how to perform the test.…”

“…That may stimulate the sympathetic nervous system, decreasing bladder capacity and potentially affecting the UF results. 4,5,9,10 Patient comfort is crucial for appropriate bladder emptying. 18 While multiple factors may affect the voiding, there is limited research on the impact of patients' emotional conditions on UF parameters.…”

“…Since this is not a natural voiding process, requiring voiding "on demand", often with low or very high bladder filling, may adversely affect UF results. 4,5 In addition, patients may feel embarrassment, discomfort, nervousness and tension due to voiding in an unfamiliar environment in the test room. 9,10 There is an amount of clinical evidence that psychological factors and anxiety affect bladder functions.…”

“…11 Therefore, some authors suggest the repetition of UF. 4 In the literature, although it is known that emotional conditions may affect bladder functions, there are limited studies examining the relationship between anxiety and UF parameters. 5 This study was conducted to determine the effect of anxiety on voiding outcomes in UF.…”

Unleashing the potential: Artificial intelligence in urology for enhanced diagnosis, treatment, and personalized care

“…In predicting benign urological conditions, CT images were used to detect urinary stones [ 5 ]. Other than image analysis, AI algorithms are expanding their range including estimations of stone-free status and uroflowmetry results [ 6 7 ]. Robot-assisted surgery is most likely to be leveraged by AI.…”