AUTOMATED KIDNEY STONE DETECTION FROM CORONAL CT IMAGES USING DEEP VGG-19 MODEL

PD35-02 APPLICATION OF ARTIFICIAL INTELLIGENCE TOOL TO IDENTIFY PATIENTS AT HIGH RISK FOR SYMPTOMATIC KIDNEY STONE RECURRENCE

An innovative, prospective, randomized multicenter study regarding the diagnosis of kidney stones with ultrasound and CT including more than 2700 patients was recently published in the highly respected New England Journal of Medicine 1 . The study showed that in the case of clinical suspicion of nephrolithiasis the results of those primarily examined with ultrasound and those primarily examined with CT did not differ with respect to diagnoses, complications, pain, frequency of repeat presentation at the emergency room and hospitalization over 30 days, and not even with respect to missed diagnoses during a 6-month follow-up period. For the detection of kidney stones, there were as slightly lower sensitivity and a higher specificity for US compared to CT. As expected, the radiation exposure and costs in the ultrasound arm were lower. Approximately 40 % of the ultrasound patients underwent CT in the following 6 months. The study results are certainly surprising to many colleagues who saw unenhanced low-dose CT as the diagnostic gold standard in a strict method comparison 2 3 . No wonder that the frequency of CT examinations for suspected kidney stones has increased in the USA tenfold from 1996 – 2007 4 . However, in light of earlier ultrasound publications regarding kidney stone diagnosis, this result is not surprising. The importance of ultrasound for kidney stone diagnosis 5 6 and the equivalence of US and intravenous urography even for the detection of ureteral stones have long been known in Europe 7 8 9 . We know even German publications cannot be widely read and even English publications require an accepted publication medium or they remain virtually unknown. A prospective study including 100 patients in the discontinued EJU publication from Elsevier showed equivalence of ultrasound and intravenous urography for kidney and ureteral stones and superiority of US over plain radiography of the kidneys 9 . Today, numerous studies are available, primarily comparisons between US and CT with very different results. As in the past, the results primarily depend on the quality of the examination technique 10 11 12 13 14 15 . The study by Smith-Bindman et al. 1 shows the high value of ultrasound diagnosis when used directly in the clinical setting. The concept of continuing the physical examination with technical means was introduced in Germany in 1976 16 . The additional inclusion of the medical history was performed as part of “clinical sonography” in Europe. This approach was named “point of care ultrasound” in the USA and for approximately 15 years American colleagues in emergency units have been using the ultrasound probe with great success in this regard. In the USA this new development was based less on European experiences than on increasing economic pressure and the rapid development of US equipment. The discussion regarding CT-based increased radiation exposure and the possible increase in malignant diseases that was started by Brenner et al. 17 and is still ongoing may have also had an impact. This discussion has basically not yet reached Germany. What can we learn from this new study? The study in NEJM should provide the impetus for the primary use of ultrasound in the case of clinical suspicion of nephrolithiasis. The majority of the use of CT and excretory urography could be decreased by approximately 80 % for this common medical problem, thus making a significant contribution to radiation hygiene. Moreover, we can learn how to perform excellent, clinically relevant studies with cooperation and relatively simple means. To ensure a high level of significance for ultrasound diagnostics, more clinical and sonografic competence and intensive ultrasound training is necessary. In addition, we need a greater number of significant studies that should be published as prominently as possible.

This study evaluated possible predictors of long-term opioid usage among patients with ureteric stones who received ureteroscopy (URS) or shockwave lithotripsy (SWL). We also assessed opioid usage characteristics of URS and SWL recipients. This retrospective study used IQVIA PharMetrics® Plus for Academicsadministrative claims database from years 2006-2020 to identify patients with a diagnosis of kidney or ureteral stones who were treated with either SWL or URS. We performed unadjusted bivariate analyses to compare opioid use characteristics of URS and SWL recipients, and performed logistic regression to determine demographic and clinical factors associated with becoming a long-term opioid user. The study population consisted of opioid naive individuals having a diagnosis of a kidney stone who underwent URS (N = 9407) or SWL (N = 4894). About 6.7% (N = 964) of study subjects were long-term opioid users. Unadjusted bivariate associations showed that compared to non-long-term opioid users, long-term opioid users had significantly greater total days' supply, total morphine milliequivalents (MME) supplied, and claims per month. A similar trend was observed for URS (vs. SWL) recipients. However, compared to SWL recipients, URS recipients had 14.3% (1.2-25.6%; p = 0.034) lower odds of becoming long-term users. Total days' supply (OR: 1.041 (95% CI 1.030-1.052; p < 0.001) and total MME supplied (OR 1.001 (95% CI 1.000-1.001; p < 0.001) were significantly associated with long-term usage. Higher total days' supply and total MME supplied as well as SWL were identified as risk factors for becoming long-term opioid users.

Previous studies examining the association between kidney stone disease (KSD) and arterial stiffness have been limited. Both age and gender have been found to have an impact on KSD, but their influence on the relationship between KSD and increased arterial stiffness is unclear. This study included 6694 subjects from October 2006 to August 2009. The diagnosis of kidney stone was based on the results of ultrasonographic examination. Increased arterial stiffness was defined as right-sided brachial-ankle pulse wave velocity (baPWV) ≥ 14 m/s. Associations between KSD and increased arterial stiffness were analyzed using multiple logistic regression models. KSD was positively related to increased arterial stiffness in both male and female groups (males: odds ratio [OR], 1.306; 95% confidence interval [CI], 1.035–1.649; females: OR, 1.585; 95% CI, 1.038–2.419) after adjusting for confounding factors. Subgroup analysis by age group (<50 and ≥50 years) showed a significant positive relationship only in the groups ≥ 50 years for both genders (males: OR, 1.546; 95% CI, 1.111–2.151; females: OR, 1.783; 95% CI, 1.042–3.054), but not in the groups < 50 years. In conclusion, KSD is associated with a higher risk of increased arterial stiffness in individuals aged ≥ 50 years, but not in those aged < 50 years for both genders.

Whether a link exists between kidney stone disease and osteoporosis or fractures remains an open question. In this retrospective cohort study, we sought to determine the prevalence of osteoporosis and fractures and rate of bone mineral density screening by dual-energy X-ray absorptiometry (DXA) in patients with kidney stone disease. We examined nationwide data from the Veterans Health Administration and identified 531,431 patients with kidney stone disease between 2007 and 2015. Nearly 1 in 4 patients (23.6%, 95% confidence interval [CI] 23.5-23.7) with kidney stone disease had a prevalent diagnosis of osteoporosis or fracture. In patients with no prior history of osteoporosis or bone mineral density assessment before a kidney stone diagnosis, 9.1% were screened with DXA after their kidney stone diagnosis, of whom 20% were subsequently diagnosed with osteoporosis. Our findings provide support for wider use of bone mineral density screening in patients with kidney stone disease, including middle-aged and older men, a group less well recognized as at risk for osteoporosis or fractures. © 2021 American Society for Bone and Mineral Research (ASBMR).

Kidney stone disease is a common syndrome and a recurring one, where it bears a 50% chance of being manifested again within ten years and may lead to serious complications like ureteral obstruction and unbearable pain. If timely intervention is considered of paramount importance for a timely intervention, early and accurate detection using computed tomography (CT) scans is also critical to this process. Existing diagnostic systems are being challenged by factors like noise in images, low contrast, and class imbalance, and these might hamper the performance of existing systems. This work focuses on developing an optimized framework of deep learning for the detection of kidney stones in CT images to deal with these drawbacks. The overall proposed approach consists of a preprocessing scheme to normalize the data using Wang-Mendel (WM) de-noising and enhancing contrast globally, followed by data augmentation with the use of SdSmote to overcome an imbalance in the classes. The pre-processed images will be fed into a modified Bidirectional Recurrent Neural Network (BRNN), which will undergo optimization of the weights and biases using a newly implemented Bald Eagle Search (BES) algorithm, with quasi-oppositional learning and chaotic initialization introduced to increase convergence and global search capability. The proposed method is applied to the public CT Kidney Dataset, compared with state-of-the-art techniques like ensemble learning, Exemplar Darknet19, DE/SVM, and Decision Tree solutions. The proposed means attained better performance, showing 96.96% accuracy, 95.62% sensitivity, 91.67% specificity, 94.38% precision, 94.99% F1-score, and 91.61% in the Jaccard Index, thereby confirming the effectiveness and robustness of the proposed model in clinical decision-making concerning kidney stone diagnosis.

BackgroundInsulin response may significantly contribute to the formation of kidney stones. Diets can modulate the insulin response and we hypothesize that high insulinemic potential diets may increase the kidney stones risk.MethodsData were from the US National Health and Nutrition Examination Survey. Diets were assessed by 24-hour dietary recall. Two empirical dietary indices for insulin resistance (EDIR) and hyperinsulinemia (EDIH) were used to reflect the dietary insulinemic potential. Diagnosis of kidney stones was based on self-report. Logistic regression was employed to calculate ORs and 95% CIs while adjusting for variables identified through a directed acyclic graph (DAG).ResultsHigher EDIR [ORTertile 3 vs. Tertile 1 = 1.31 (95% CI: 1.13–1.53); ORPer−standard deviation increase= 1.11 (95% CI: 1.05–1.18); ptrend = 0.001] and EDIH [ORTertile 3 vs. Tertile 1 = 1.26 (95% CI: 1.08–1.47); ORPer−standard deviation increase= 1.10 (95% CI: 1.04–1.16); ptrend = 0.001] scores were both positively associated with kidney stones. The conclusion remains unchanged in the sensitivity analysis after adjusting for potential mediating factors that were identified from the DAG, including BMI, hypertension, and diabetes. Subgroup analysis showed that results in most subgroups were consistent with the main analysis.ConclusionsThis study indicates that the insulinemic potential of diet may partly underlie the influence of dietary patterns on kidney stones, emphasizing the importance of avoiding dietary patterns with insulinemic potential.Clinical trial numberNot applicable.

Diet is an important contributor to kidney stone formation, but there are limited data regarding long-term changes in dietary factors after a kidney stone. We analyzed data from three longitudinal cohorts, the Health Professionals Follow-Up Study and Nurses' Health Study I and II, comparing changes in dietary factors in participants with and without kidney stones during follow-up. The daily intake of dietary calcium, supplemental calcium, animal protein, caffeine, fructose, potassium, sodium, oxalate, phytate, vitamin D, vitamin C, sugar-sweetened beverages, fluids, net endogenous acid production, and Dietary Approaches to Stop Hypertension score were assessed by repeat food frequency questionnaires and computed as absolute differences; a difference-in-differences approach was used to account for temporal changes using data from participants without kidney stones from the same calendar period. Included were 184,398 participants with no history of kidney stones, 7095 of whom became confirmed stone formers. Several intakes changed significantly over time in stone formers, with some showing a relative increase up to 8 years later, including caffeine (difference in differences, 8.8 mg/d; 95% confidence interval [95% CI], 3.4 to 14.1), potassium (23.4 mg/d; 95% CI, 4.6 to 42.3), phytate (12.1 mg/d; 95% CI, 2.5 to 21.7), sodium (43.1 mg/d; 95% CI, 19.8 to 66.5), and fluids (47.1 ml/d; 95% CI, 22.7 to 71.5). Other dietary factors showed a significant decrease, such as oxalate (-7.3 mg/d; 95% CI, -11.4 to -3.2), vitamin C (-34.2 mg/d; 95% CI, -48.8 to -19.6), and vitamin D (-18.0 IU/d; 95% CI, -27.9 to -8.0). A significant reduction was observed in sugar-sweetened beverages intake of -0.5 (95% CI, -0.8 to -0.3) and -1.4 (95% CI, -1.8 to -1.0) servings per week and supplemental calcium of -105.1 (95% CI, -135.4 to -74.7) and -69.4 (95% CI, -95.4 to -43.4) mg/d for women from Nurses' Health Study I and II, respectively. Animal protein, dietary calcium, fructose intake, Dietary Approaches to Stop Hypertension score, and net endogenous acid production did not change significantly over time. After the first episode of a kidney stone, mild and inconsistent changes were observed concerning dietary factors associated with kidney stone formation.

Objective To investigate the effects of conventional submarine environment on kidney stone and blood uric acid. Methods A retrospective analysis was made on the health examination results of the commissioned officers and enlisted, who underwent health examination in No. 113 Hospital from January 1, 2015 to December 31, 2017. The subjects were divided into the submarine group and the shore service group, by depending on whether they worked onboard the submarine or on shore, and they were further divided into different age groups in accordance with age: i. e. the junior age group (≤30 years), the mid age group (31years< age<40 years) and the senior age group (≥40 years). The diagnosis of kidney stone was verified by ultrasonography (GE LOGIQ-E9 Color Ultrasonograph). Results A total of 1 010 naval personnel were finally included in the study. The incidence of kidney stone in the submarine group (n=710) and the shore service group (n=300) was 3.2% and 2.7% respectively (P>0.05). The blood uric acid levels were respectively (352.1±67.3)μmol/L and (350.2±67.0)μmol/L(P>0.05). The incidence of hyperuricemia was respectively 13.7% and 15.3% (P>0.05). However, if comparisons were made by age groups, no statististical differences could be noticed in the incidence of kidney stone, the level of blood uric acid, the incidence of hyperuricemia in the submarine and the shore service groups (P>0.05). Conclusions Conventional submarine environment seems to have no significant effects on the formation of kidney stone and the level of blood uric acid. However, this initial conclusion demands verification through further detailed study. Key words: Submarine; Kidney stone; Uric acid

To evaluate the impact of extensive surgery on urine profile, serum exams and stone composition of complicated IBD patients. Patients with IBD and a history of total proctocolectomy (TPC) with fecal diversion (end ileostomy or ileal pouch anal anastomosis-IPAA) were selected. Only patients with at least one complete 24-h urine profile were included. A case-control study was performed selecting patients with kidney stone disease in a random way who had also at least on complete 24-h urine profile. Case and controls were matched for age, gender, and body mass index (BMI). Groups were compared to urine profile, serum exams and stone composition. Sixty-eight patients were enrolled in this study, 34 patients with IBD who underwent TPC and had diagnosis of kidney stones and 34 matched patients with only kidney stones. IBD patients had a significantly lower urine volume, urine citrate and urine sodium. Regarding serum exams, only serum bicarbonate was statistically significant lower. In both groups, calcium oxalate stone was the most common. Patients with IBD with TPC and kidney stones have a low urine volume and low urine citrate as main risk factors for kidney stone formation. As seen in the general population, calcium oxalate is the most common stone composition.

BackgroundKidney stones have become a worldwide public health problem. The purpose of this research is to study the relationship between plasma cadmium level and the prevalence of kidney stones in an adult population.MethodsThe data of this study were based on a current survey conducted from December 2018 to November 2019 in Gongcheng Yao Autonomous County, Guangxi, China. A total of 940 study subjects of the same sex and age (within 2 years of each other) according to 1:1 matching were selected for a case–control study. The diagnosis of kidney stones was based on the presence of strong light spots, patches, clusters, or bands within the renal sinus region, followed by an echo-free bundle of acoustic images. Plasma metal elements were determined by the metal plasma method. The relationship between plasma cadmium concentration and the prevalence of kidney stones was assessed using logistic regression and restricted cubic spline regression.ResultsThe crude ratio for kidney stones in the highest quartile of plasma cadmium was 1.164 (95% CI, 1.121 to 2.324) compared with the lowest quartile. A positive correlation was found between the two (P for trend = 0.039). After adjusting for potential confounders, the ratio of plasma cadmium to kidney stones in the highest quartile was 1.606 (95% CI, 1.100 to 2.344) compared with the lowest quartile, and the findings remained unchanged.ConclusionThe odds of kidney stones in adults increased with increasing plasma cadmium exposure, and high plasma cadmium may be a risk factor for kidney stones.

Deep learning model for automated kidney stone detection using coronal CT images

Kidney Stone Prevalence Based on Self-Report and Electronic Health Records: Insight into the Prevalence of Active Medical Care for Kidney Stones

PUK22 - ESTIMATES OF KIDNEY STONES COSTS. AN ANALYSIS OF CLINICAL AND ADMINISTRATIVE DATA TO MEASURE THE BURDEN OF KIDNEY STONES IN ITALY

Kidney stones are increasingly recognized as a systemic disorder with a high global prevalence. However, large proteomics studies are lacking. An individual-level proteomics study with rigorous adjustments was performed on 35,331 UK Biobank participants to uncover the independent associations between 2922 circulating proteins and prevalent kidney stone disease. Mendelian randomization (MR) analysis was utilized to assess causal relationships. Findings were validated using genomic data from the Mayo Clinic Biobank (MCBB, N=43,744), concentration-response analysis, transcriptomics analyses, and additional genome-wide association studies (GWAS). Nine plasma proteins were independently associated with a kidney stone diagnosis, including reduced uromodulin (UMOD; β = -0.10, 95% CI: [-0.15, -0.05]) and elevated scavenger receptor cysteine-rich domain-containing group B protein (SSC4D; β = 0.28, 95% CI: [0.17, 0.38]), and were enriched in extracellular matrix pathways. MR analysis revealed kidney stone presence contributes to elevated levels of matrix metalloproteinase 7. Conversely, lower plasma UMOD (OR = 0.93, 95% CI: [0.90, 0.97]) and higher plasma SSC4D (OR = 1.10, 95% CI: [1.02, 1.18]) were associated with a kidney stone risk. These associations were consistently replicated in the MCBB dataset (UMOD: OR = 0.92, 95% CI: [0.86, 0.98]; SSC4D: OR = 1.13, 95% CI: [1.01, 1.27]) and further validated by a concentration-response analysis. Single-nucleus RNA sequencing and quantitative trait loci analyses confirmed consistent associations between thick ascending limb UMOD expression and stone former status, and with blood and urine UMOD concentrations. GWAS analysis, adjusted for eGFR, suggested that the protective role of UMOD against kidney stones was independent of kidney function. This study highlights significant associations between concentrations of specific blood proteins and a history of kidney stones. Several implicated proteins are related to kidney stone matrix, with UMOD independently associated with lower risk and SSC4D with higher risk of kidney stones.