The aim of this study was to develop and validate a decision support model using a machine learning algorithm to predict treatment success after single session shock wave lithotripsy in ureteral stone cases. Of the 1,803 patients treated with shock wave lithotripsy we selected those with ureteral stones who had preoperative computerized tomography available. Treatment success after single session shock wave lithotripsy was defined as freedom from stones or residual stone fragments less than 2 mm long on computerized tomography or plain x-ray of the kidneys, ureters and bladder 2 weeks later. Decision tree analysis was done using a machine learning algorithm to identify relevant parameters. A decision support model was developed to calculate the probability of treatment success. A total of 791 patients were enrolled in study. Mean ± SD stone length was 5.9 ± 2.3 mm and mean stone volume was 89.3 ± 140.0 mm3. The overall treatment success rate after SWL was 64.4% (509 cases). The rate for upper, middle and lower ureter stones was 59.8%, 65.5% and 69.6%, respectively. On decision tree analysis the top 3 performance criteria factors were volume, length and HU. Decision models were constructed with all possible combinations of factors. The model with 15 factors had greater than 92% accuracy and an average ROC AUC of 0.951. We applied a machine learning algorithm, a subfield of artificial intelligence, to predict the outcome after single session shock wave lithotripsy for ureteral stones. A 92.29% accurate decision model was developed with 15 factors and an average ROC AUC of 0.951.
To evaluate risk factors for deterioration of lower urinary tract symptoms (LUTS) in elderly men in a community-based, prospective longitudinal cohort study. In a suburban area in Korea, 1,514 subjects aged ≥45 years were randomly selected by systematic sampling. A total of 918 elderly subjects were enrolled in this in-depth clinical study in 2004. Of these, 547 participants were followed up for 3 years and the data was analyzed in 2014. Standard questionnaires were administered face-to-face by trained interviewers. After excluding women, 224 male participants with complete data including transrectal ultrasonography were included in the final analysis. LUTS were diagnosed using the International Prostate Symptom Score (IPSS) questionnaire. Symptom deterioration was defined as a score of ≥8 points during the 3-year follow-up period. LUTS prevalence increased to 13.1% and the mean IPSS increased by 2.6 points during the 3-year period. After adjusting for confounders, a smoking history of ≥50 pack-years was an independent risk factor for deterioration of LUTS and storage subsymptoms compared with no history of smoking (3.1 and 5.1 odds, respectively). Physical activity had a protective effect on voiding subsymptoms. However, high protein diet and alcohol intake were not associated with LUTS deterioration. The LUTS prevalence among elderly men living in a suburban area increased to 13.1% and the IPSS increased by 2.6 points during the 3-year period. A history of heavy smoking, low physical activity, and high protein intake were associated with LUTS deterioration. However, there was no significant association between alcohol intake and LUTS deterioration.