Consistency Analysis of the UF-1500 and UF-5000 Automated Urine Particle Analyzers.

BACKGROUND: The aim was to evaluate the consistency of the results between the UF-1500 and UF-5000, fully automated urine particle analyzers. METHODS: A total of 554 randomly selected inpatient and outpatient urine samples were collected for analysis using the UF-1500, the UF-5000, and by manual microscopic examination. The coincidence rate, intraday repeatability, and interday reproducibility were evaluated on the UF-1500 and UF-5000. To analyze the review flags from the UF-1500, the UF-1500 results were compared to manual microscopy as the gold standard. RESULTS: The repeatability of red blood cells (RBCs), white blood cells (WBCs), epithelial cells (ECs), casts, and bacteria using the UF-1500 and UF-5000 is expressed as the relative standard deviations of the intraday and inter-day measurements. For the UF-1500, the relative standard deviation values ranged from 5.9% to 12.6% and 4.9% to 17.2% for the low and 1.6% to 9.3% and 2.3% to 16.9% for the high samples, respectively. The correlation co-efficient for RBCs, WBCs, ECs, SECs, casts, crystals, and bacteria for the UF-1500 were 0.981, 0.993, 0.968, 0.963, 0.821, 0.783, and 0.992, respectively. Review samples from the UF-1500 were confirmed by microscopic examination. Review flags for all 554 samples included 3 samples with "DEBRIS High" and 23 samples with "RBCs/YLC Abnormal classification". CONCLUSIONS: The identification of various urine components by both instruments meets laboratory requirements. These two instruments with different performances have specific characteristics and should be used based upon the needs of each laboratory.

Impact of four different extraction methods and three different reconstitution solvents on the untargeted metabolomics analysis of human and rat urine samples.

Unsuitable sample preparation may result in loss of important analytes and consequently affect the outcome of untargeted metabolomics. Due to species differences, different sample preparations may be required within the same biological matrix. The study aimed to compare the in-house sample preparation method for urine with methods from literature and to investigate the transferability of sample preparation from human urine to rat urine. A total of 12 different conditions for protein precipitation were tested, combining four different extraction solvents and three different reconstitution solvents using an untargeted liquid-chromatography high resolution mass spectrometry (LC-HRMS) metabolomics analysis. Evaluation was done based on the impact on feature count, their detectability, as well as the reproducibility of selected compounds. Results showed that a combination of methanol as extraction and acetonitrile/water (75/25) as reconstitution solvent provided improved results at least regarding the total feature count. Additionally, it was found that a higher amount of methanol was most suitable for extraction of rat urine among the tested conditions. In comparison, human urine requires significantly less volume of extraction solvent. Overall, it is recommended to systematically optimize both, the extraction method, and the reconstitution solvent for the used biofluid and the individual analytical settings.

Assessing Concordance of Results: A Comparative Study of the Manual and Automated Urinalysis Methods.

Introduction: An accurate urine analysis is a good indicator of the status of the renal and genitourinary system. However, limited studies have been done on comparing the diagnostic performance of the fully automated analyser and manual urinalysis especially in Ghana. This study evaluated the concordance of results of the fully automated urine analyser (Sysmex UN series) and the manual method urinalysis at the Komfo Anokye Teaching Hospital in Kumasi, Ghana. Methodology. Sixty-seven (67) freshly voided urine samples were analysed by the automated urine analyser Sysmex UN series and by manual examination at Komfo Anokye Teaching Hospital, Ghana. Kappa and Bland-Altman plot analyses were used to evaluate the degree of concordance and correlation of both methods, respectively. Results: Substantial (κ = 0.711, p < 0.01), slight (κ = 0.193, p = 0.004), and slight (κ = 0.109, p < 0.001) agreements were found for urine colour, appearance, and pH, respectively, between the manual and automated methods. A strong and significant correlation (r = 0.593, p < 0.001) was found between both methods for specific gravity with a strong positive linear correlation observed for red blood cell count (r = 0.951, R2 = 0.904, p < 0.001), white blood cell count (r = 0.907, R2 = 0.822, p < 0.001), and epithelial cell count (r = 0.729, R2 = 0.532, p < 0.001). A perfect agreement of urine chemistry results in both methods was observed for nitrite 67 (100%) (κ = 1.000, p < 0.001) with a fair agreement for protein 46 (68.7%) (κ = 0.395, p < 0.001). A strong agreement was found in both methods for the presence of cast 65 (97.0%) (κ = 0.734, p < 0.001) with no concordance observed for the presence of crystals (κ = 0.115, p = 0.326) and yeast-like cells (YLC) (κ = 0.171, p = 0.116). Conclusion: The automated and manual methods showed similar performances and good correlation, especially for physical and chemical examination. However, manual microscopy remains necessary to classify urine sediments, particularly for bacteria and yeast-like cells. Future research with larger samples could help validate automated urinalysis for wider clinical use and identify areas requiring improved automated detection capabilities.

Diagnostic Stewardship for Urine Cultures.

Urinary tract infections are among the most common infectious diagnoses in health care, but most urinary tract infections are diagnosed inappropriately in patients without signs or symptoms of infection. Asymptomatic bacteriuria leads to inappropriate antibiotic prescribing and negative downstream effects, including antimicrobial resistance, health care-associated infections, and adverse drug events. Diagnostic stewardship is the process of modifying the ordering, performing, or reporting of test results to improve clinical care. Diagnostic stewardship impacts the diagnostic pathway to decrease inappropriate detection and treatment of asymptomatic bacteriuria. This article reviews diagnostic stewardship methods and closes with a case study illustrating these principles in practice.

[What contribution can make artificial intelligence to urinary cytology?] / Quel apport de l'intelligence artificielle en cytologie urinaire ?

Urinary cytology using the Paris system is still the method of choice for screening high-grade urothelial carcinomas. However, the use of the objective criteria described in this terminology shows a lack of inter- and intra-observer reproducibility. Moreover, if its sensitivity is excellent on instrumented urine, it remains insufficient on voided urine samples. Urinary cytology appears to be an excellent model for the application of artificial intelligence to improve performance, since the objective criteria of the Paris system are defined at cellular level, and the resulting diagnostic approach is presented in a highly "algorithmic" way. Nevertheless, there is no commercially available morphological diagnostic aid, and very few predictive devices are still undergoing clinical validation. The analysis of different systems using artificial intelligence in urinary cytology rises clear prospects for mutual contributions.

Using the Sysmex UF-4000 urine flow cytometer for rapid diagnosis of urinary tract infection in the clinical microbiological laboratory.

BACKGROUND: Urinary tract infections are responsible for a significant worldwide disease burden. Performing urine culture is time consuming and labor intensive. Urine flow cytometry might provide a quick and reliable method to screen for urinary tract infection. METHODS: We analyzed routinely collected urine samples received between 2020 and 2022 from both inpatients and outpatients. The UF-4000 urine flow cytometer was implemented with an optimal threshold for positivity of ≥100 bacteria/µL. We thereafter validated the prognostic value to detect the presence of urinary tract infection (UTI) based on bacterial (BACT), leukocyte (WBC), and yeast-like cell (YLC) counts combined with the bacterial morphology (UF gram-flag). RESULTS: In the first phase, in 2019, the UF-4000 was implemented using 970 urine samples. In the second phase, between 2020 and 2022, the validation was performed in 42,958 midstream urine samples. The UF-4000 screen resulted in a 37% (n = 15,895) decrease in performed urine cultures. Uropathogens were identified in 18,673 (69%) positively flagged urine samples. BACT > 10.000/µL combined with a gram-negative flag had a >90% positive predictive value for the presence of gram-negative uropathogens. The absence of gram-positive flag or YLC had high negative predictive values (99% and >99%, respectively) and are, therefore, best used to rule out the presence of gram-positive bacteria or yeast. WBC counts did not add to the prediction of uropathogens. CONCLUSION: Implementation of the UF-4000 in routine practice decreased the number of cultured urine samples by 37%. Bacterial cell counts were highly predictive for the presence of UTI, especially when combined with the presence of a gram-negative flag.

Evaluation of a urine dipstick protein to urine specific gravity ratio for the detection of proteinuria in dogs and cats.

BACKGROUND: The utility of urine dipsticks for the quantification of proteinuria is limited because of the influence of urine specific gravity (USG). To circumvent the need for urine protein creatinine ratios (UPCR) some have proposed a calculated dipstick urine protein to USG ratio (DUR) for the detection of proteinuria. However, the performance of DUR has not been evaluated in veterinary patients. OBJECTIVES: Evaluate the correlation between DUR and UPCR, while also assessing the effect of urine characteristics on this relationship and evaluating the performance of DUR in detecting proteinuria. ANIMALS: Urine samples from 308 dogs and 70 cats. METHODS: Retrospective cohort study of urinalyses and UPCRs from dogs and cats collected between 2016 and 2021. RESULTS: Both canine and feline urine samples showed a positive moderate correlation between the UPCR and DUR. The correlation was not influenced by the presence of active urine sediment, glucosuria, or urine pH. In detecting canine urine samples with a UPCR >0.5, an optimal DUR of 1.4 had sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 89%, 83%, 96%, and 63%, respectively. In detecting feline urine samples with a UPCR >0.4, an optimal DUR of 2.1 had sensitivity, specificity, PPV, and NPV of 70%, 100%, 100%, and 75%, respectively. CONCLUSIONS AND CLINICAL IMPORTANCE: Use of the DUR can be a relatively reliable method for identification of proteinuria. However, given its poor NPV, the DUR cannot be recommended for exclusion of proteinuric patients.

Point-of-care image-based quantitative urinalysis with commercial reagent strips: Design and clinical evaluation.

Urinalysis is a useful test as an indicator of health or disease and as such, is a part of routine health screening. Urinalysis can be undertaken in many ways, one of which is reagent strips used in the general evaluation of health and to aid in the diagnosis and monitoring of kidney disease. To be effective, the test must be performed properly, and the results interpreted correctly. However, different light conditions and colour perception can vary between users leading to ambiguous readings. This has led to camera devices being used to capture and generate the estimated biomarker concentrations, but image colour can be affected by variations in illumination and inbuilt image processing. Therefore, a new portable device with embedded image processing techniques is presented in this study to provide quantitative measurements that are invariant to changes in illumination. The device includes a novel calibration process and uses the ratio of RGB values to compensate for variations in illumination across an image and improve the accuracy of quantitative measurements. Results show that the proposed calibration method gives consistent homogeneous illumination across the whole image. Comparisons against other existing methods and clinical results show good performance with a correlation to the clinical values. The proposed device can be used for point-of-care testing to provide reliable results consistent with clinical values.

Surface-enhanced Raman Spectroscopy in urinalysis of hypertension patients with kidney disease.

Arterial hypertension (AH) is a multifactorial and asymptomatic disease that affects vital organs such as the kidneys and heart. Considering its prevalence and the associated severe health repercussions, hypertension has become a disease of great relevance for public health across the globe. Conventionally, the classification of an individual as hypertensive or non-hypertensive is conducted through ambulatory blood pressure monitoring over a 24-h period. Although this method provides a reliable diagnosis, it has notable limitations, such as additional costs, intolerance experienced by some patients, and interferences derived from physical activities. Moreover, some patients with significant renal impairment may not present proteinuria. Accordingly, alternative methodologies are applied for the classification of individuals as hypertensive or non-hypertensive, such as the detection of metabolites in urine samples through liquid chromatography or mass spectrometry. However, the high cost of these techniques limits their applicability for clinical use. Consequently, an alternative methodology was developed for the detection of molecular patterns in urine collected from hypertension patients. This study generated a direct discrimination model for hypertensive and non-hypertensive individuals through the amplification of Raman signals in urine samples based on gold nanoparticles and supported by chemometric techniques such as partial least squares-discriminant analysis (PLS-DA). Specifically, 162 patient urine samples were used to create a PLS-DA model. These samples included 87 urine samples from patients diagnosed with hypertension and 75 samples from non-hypertensive volunteers. In the AH group, 35 patients were diagnosed with kidney damage and were further classified into a subgroup termed (RAH). The PLS-DA model with 4 latent variables (LV) was used to classify the hypertensive patients with external validation prediction (P) sensitivity of 86.4%, P specificity of 77.8%, and P accuracy of 82.5%. This study demonstrates the ability of surface-enhanced Raman spectroscopy to differentiate between hypertensive and non-hypertensive patients through urine samples, representing a significant advance in the detection and management of AH. Additionally, the same model was then used to discriminate only patients diagnosed with renal damage and controls with a P sensitivity of 100%, P specificity of 77.8%, and P accuracy of 82.5%.

Can sodium and potassium measured in timed voids be used as reference instruments for validating self-report instruments? Results from a urine calibration study.

BACKGROUND: Sodium and potassium measured in 24-h urine collections are often used as reference measurements to validate self-reported dietary intake instruments. OBJECTIVES: To evaluate whether collection and analysis of a limited number of urine voids at specified times during the day ("timed voids") can provide alternative reference measurements, and to identify their optimal number and timing. METHODS: We used data from a urine calibration study among 441 adults aged 18-39 y. Participants collected each urine void in a separate container for 24 h and recorded the collection time. For the same day, they reported dietary intake using a 24-h recall. Urinary sodium and potassium were analyzed in a 24-h composite sample and in 4 timed voids (morning, afternoon, evening, and overnight). Linear regression models were used to develop equations predicting log-transformed 24-h urinary sodium or potassium levels using each of the 4 single timed voids, 6 pairs, and 4 triples. The equations also included age, sex, race, BMI (kg/m2), and log creatinine. Optimal combinations minimizing the mean squared prediction error were selected, and the observed and predicted 24-h levels were then used as reference measures to estimate the group bias and attenuation factors of the 24-h dietary recall. These estimates were compared. RESULTS: Optimal combinations found were as follows: single voids-evening; paired voids-afternoon + overnight (sodium) and morning + evening (potassium); and triple voids-morning + evening + overnight (sodium) and morning + afternoon + evening (potassium). Predicted 24-h urinary levels estimated 24-h recall group biases and attenuation factors without apparent bias, but with less precision than observed 24-h urinary levels. To recover lost precision, it was estimated that sample sizes need to be increased by ∼2.6-2.7 times for a single void, 1.7-2.1 times for paired voids, and 1.5-1.6 times for triple voids. CONCLUSIONS: Our results provide the basis for further development of new reference biomarkers based on timed voids. CLINICAL TRIAL REGISTRY: clinicaltrials.gov as NCT01631240.

[The Paris System, 2022 edition: What is new?] / La version 2022 du Système de Paris : quoi de neuf ?

The second version of the Paris System for reporting urine cytology was published in 2022. It follows the first version of 2016, which was very successful and widely adopted by many cytopathologists from different countries. Thus, numerous publications using the Paris System have made possible to refine the criteria as well as discussing the limits. The diagnostic accuracy of urinary cytology is high for detection of high-grade urothelial carcinoma, but not for low-grade carcinoma where there are few cytological abnormalities. So, the chapter individualizing low-grade urothelial neoplasms was deleted; the latter were included in the category "negative for high-grade urothelial carcinoma". Indeed, the risk of malignancy is replaced by the risk of high-grade urothelial carcinoma. A new chapter has been devoted to urothelial tumors of the upper tract. Finally, the pitfalls linked to cellular degeneration are discussed for each category. The risk of high-grade malignancy associated with each category will help communication with the clinician and help patient care.

Diagnostic validation study of rapid urinary tract infection diagnosis kit at peripheral health facilities of West Bengal, India.

Patients reporting to the outpatient departments of peripheral health care settings in India with symptoms of urinary tract infection (UTI) receive one or the other antibiotic before culture confirmation and out of the total culture confirmed UTI cases, in less than one third cases the prescribed antibiotics matches to the antibiotic sensitivity test result. Hence, in this study, an indigenous point-of-care (POCT) rapid diagnostic kit (Rapidogram) for UTI was validated against conventional urine culture and sensitivity to understand its possible applicability at peripheral health care settings. This cross-sectional study was conducted during November 2021 to June 2022 in OPDs of two peripheral hospitals. A sample size of 300 was calculated using prevalence of urinary tract infection (UTI) as 33% for sensitivity and specificity using Buderer's formula. Urine specimens were collected following standard aseptic procedures from the recruited suspected UTI cases and transferred to laboratory maintaining the cold chain. The validation work up was done in two sections: lab validation and field validation. Out of 300 urine samples, 29 were found positive for the growth of UTI pathogen by both methods and 267 were found negative by both methods. Thus, the kit shows very high specificity (99.6%; 97.9-99.9%) and considerably high sensitivity (90.6%; 74.9-98.0%). We also observed higher PPV, NPV, test accuracy (> 96%). Diagnostic Odds Ratio and Youden index were respectively 2581 and 0.89. Clinical data showed that 44% of the suspected UTI cases were prescribed at least one antibiotic before urine test. Mostly they received Norfloxacin whereas the mostly identified organism E.coli was sensitive to Nitrofurantoin. In the context of absence of microbiology facility at peripheral setting and rampant empirical use of antibiotics in UTI, this highly specific and sensitive POCT for UTI may be used as it not only identifies the organism, also shows the antibiotic sensitivity pattern.

Microscopic urinary particle detection by different YOLOv5 models with evolutionary genetic algorithm based hyperparameter optimization.

The diagnosis of kidney disease often involves analysing urine sediment particles. Traditionally, urinalysis was performed manually by collecting urine samples and using a centrifuge, which was prone to manual errors and relied on labour-intensive processes. Automated urine sediment microscopy, based on machine learning models, requires segmentation and feature extraction, which can hinder model performance due to intrinsic characteristics of microscopic images. Deep learning models based on convolutional neural networks (CNNs) often rely on a large number of manually annotated data, making the system computationally complex. This study propose an advanced deep learning model based on YOLOv5, which offers faster performance and requires comparatively less data. The proposed model used five variants of the YOLOv5 model (YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) to detect six categories of urine particles (erythrocyte, leukocyte, crystals, cast, mycete, epithelial cells) from microscopic urine sediment images. The dataset involved 5376 images of urine sediments with 6 particles. There are 30 sets of hyperparamreteres are employed in the YOLOv5 model. To optimize the hyperparameters and fine-tune with the urine sediment dataset and for training each model, the system employed a genetic algorithm (GA) based on evolutionary principles named as Evolutionary Genetic Algorithm (EGA). Among the six categories of detected particles mycete achieved maximum performance with a mAP of 97.6 % and crystals achieved minimum performance with a mAP of 81.7 % with YOLOv5x model compared to other particles. To optimize the hyperparameters for training each model, the system employed a genetic algorithm (GA) based on evolutionary principles named as Evolutionary Genetic Algorithm (EGA). Among all the models, YOLOv5l and YOLOv5x performed the best. YOLOv5l achieved a mean average precision (mAP) of 85.8 % while YOLOv5x achieved a mAP of 85.4 % at an IoU threshold of 0.5. The detection speed per image was 23.4 ms for YOLOv5l and 28.4 ms for YOLOv5x. The proposed method developed a faster and better automated microscopic model using advanced deep learning techniques to detect urinary particles from microscopic urine sediment images for kidney disease identification. The method demonstrated strong performance in urinalysis.

Machine learning-assisted image label-free smartphone platform for rapid segmentation and robust multi-urinalysis.

This study presents a groundbreaking approach for the early detection of chronic kidney disease (CKD) and other urological disorders through an image-label-free, multi-dipstick identification method, eliminating the need for complex machinery, label libraries, or preset coordinates. Our research successfully identified reaction pads on 187 multi-dipsticks, each with 11 pads, leveraging machine learning algorithms trained on human urine data. This technique aims to surpass traditional colourimetric methods and concentration-colour curve fitting, offering more robust and precise community screening and home monitoring capabilities. The developed algorithms enhance the generalizability of machine learning models by extracting primary colours and correcting urine colours on each reaction pad. This method's cost-effectiveness and portability are significant, as it requires no additional equipment beyond a standard smartphone. The system's performance rivals professional medical equipment without auxiliary lighting or flash under regular indoor light conditions, effectively managing false positives and negatives across various categories with remarkable accuracy. In a controlled experimental setting, we found that random forest algorithms, based on a Bagging strategy and applied in the HSV colour space, showed optimal results in smartphone-assisted urinalysis. This study also introduces a novel urine colour correction method, significantly improving machine learning model performance. Additionally, ISO parameters were identified as crucial factors influencing the accuracy of smartphone-based urinalysis in the absence of additional lighting or optical configurations, highlighting the potential of this technology in low-resource settings.

[Evaluation of Sysmex UF-5000 flow cytometer flag BACT-info for Gram discrimination in urinary tract infection]. / Evaluación del parámetro BACT-info del citómetro de flujo UF-5000 (Sysmex) para la clasificación gram en infección del tracto urinario.

OBJECTIVE: Urine culture as a gold standard for the diagnosis of urinary tract infection (UTI) involves a considerable workload in Clinical Microbiology Departments, due to the high number of samples received that will ultimately be negative. Therefore, it is necessary to use screening systems that also reduce the turnaround time for UTI diagnosis. The new flow cytometer UF-5000 (Sysmex Corporation) is able to differentiate between Gram-negative and Gram-positive bacteria using the BACT-info parameter according to manufacturer. The aim of our study was to evaluate the gram discrimination ability of the UF-5000 cytometer. METHODS: A prospective study with 449 urine samples collected consecutively was conducted, in the period 7/3/2022-27/5/2022, in which the BACT-info flag was compared with urine culture as the reference method. RESULTS: The sensitivity obtained for both Gram-negative and Gram-positive bacteria was above 95%. However, for Gram-positive bacteria, the moderate Kappa index (0.49) and the low positive predictive value (37.1%) indicated that the correlation between BACT-info flag and urine culture was not acceptable and should not be reported to the requesting clinician. CONCLUSIONS: Implementation of the third generation UF-5000 cytometer represents a significant advance in the aetiological orientation of UTIs caused by Gram-negative bacteria. Reporting the Gram morphology in the urine samples reduces the response time in the microbiological diagnosis of UTI, which would have an impact on the reduction and optimisation of empirical treatment, and thus on the generation of antimicrobial resistance.

Alternative Strategies to Provide Actionable Results When a Supply of Urinalysis Strips Is Unavailable.

CONTEXT.­: Urinalysis instrument-specific dip strips offer physicians qualitative results for actionable analytes (protein, glucose, leukocyte esterase, nitrates, hemoglobin, and ketones). OBJECTIVE.­: To explain a strategy implemented to support clinical decision-making by providing urine quantification of protein, glucose, white blood cells (WBCs), and red blood cells because of urine strip shortages. DESIGN.­: During shortages, we implemented an automated algorithm that triggered sending urine samples to the automation line for quantification of protein and glucose and ensured that urine microscopy was performed to obtain WBC and red blood cell counts. The algorithm printed 2 labels so nursing staff would collect 2 specimens. We monitored the turnaround time from the specimen being received in the laboratory to result verification, ensured that the culture reflex order was triggered, and tracked complaints by physicians regarding not having usual urinalysis results. Prior to implementation, correlation between sample types for protein and glucose measurement was found acceptable. RESULTS.­: The algorithm was put in place twice during 2022. The turnaround time of urine microscopic study was identical to that obtained when the urinalysis was done with the strips; however, the quantification of glucose and protein took approximately 30 minutes more. Urine reflex cultures were triggered correctly with the algorithm, as they were derived entirely from a WBC count higher than 10 per high-power field. During the shortage period we had only 1 complaint, by a physician wanting to have results of nitrates. CONCLUSIONS.­: During urine strip shortages, we successfully implemented a diversion algorithm that provided actionable urinalysis analytes in a timely manner with minimal provider complaints.

Development and validation of artificial intelligence models to predict urinary tract infections and secondary bloodstream infections in adult patients.

BACKGROUND: Traditional culture methods are time-consuming, making it difficult to utilize the results in the early stage of urinary tract infection (UTI) management, and automated urinalyses alone show insufficient performance for diagnosing UTIs. Several models have been proposed to predict urine culture positivity based on urinalysis. However, most of them have not been externally validated or consisted solely of urinalysis data obtained using one specific commercial analyzer. METHODS: A total of 259,187 patients were enrolled to develop artificial intelligence (AI) models. AI models were developed and validated for the diagnosis of UTI and urinary tract related-bloodstream infection (UT-BSI). The predictive performance of conventional urinalysis and AI algorithms were assessed by the areas under the receiver operating characteristic curve (AUROC). We also visualized feature importance rankings as Shapley additive explanation bar plots. RESULTS: In the two cohorts, the positive rates of urine culture tests were 25.2% and 30.4%, and the proportions of cases classified as UT-BSI were 1.8% and 1.6%. As a result of predicting UTI from the automated urinalysis, the AUROC were 0.745 (0.743-0.746) and 0.740 (0.737-0.743), and most AI algorithms presented excellent discriminant performance (AUROC > 0.9). In the external validation dataset, the XGBoost model achieved the best values in predicting both UTI (AUROC 0.967 [0.966-0.968]) and UT-BSI (AUROC 0.955 [0.951-0.959]). A reduced model using ten parameters was also derived. CONCLUSIONS: We found that AI models can improve the early prediction of urine culture positivity and UT-BSI by combining automated urinalysis with other clinical information. Clinical utilization of the model can reduce the risk of delayed antimicrobial therapy in patients with nonspecific symptoms of UTI and classify patients with UT-BSI who require further treatment and close monitoring.

Validity of combined hydration self-assessment measurements to estimate a low vs. high urine concentration in a small sample of (tactical) athletes.

PURPOSE: Relationships between body weight, urine color (Uc), and thirst level (WUT) have been proposed as a simple and inexpensive self-assessment method to predict dehydration. This study aimed to determine if this method also allowed us to accurately identify a low vs. high urine concentration in (tactical) athletes. METHODS: A total of n = 19 Army Reserve Officer Training Corps cadets and club sports athletes (22.7 ± 3.8 years old, of which 13 male) were included in the analysis, providing morning body weight, thirst sensation, and Uc for five consecutive days. Each item received a score 0 or 1, resulting in a WUT score ranging from 0 (likely hydrated) to 3 (very likely dehydrated). WUT model and individual item outcomes were then compared with a ≥ 1.020 urine specific gravity (USG) cut-off indicating a high urine concentration, using descriptive comparisons, generalized linear mixed models, and logistic regression (to calculate the area under the curve (AUC)). RESULTS: WUT score was not significantly predictive of urine concentration, z = 1.59, p = 0.11. The AUC ranged from 0.54 to 0.77 for test days, suggesting a fair AUC on most days. Only Uc was significantly related to urine concentration, z = 2.49, p = 0.01. The accuracy of the WUT model for correctly classifying urine samples with a high concentration was 68% vs. 51% of samples with a low concentration, resulting in an average accuracy of 61%. CONCLUSION: This study shows that WUT scores were not predictive of urine concentration, and the method did not substantially outperform the accuracy of Uc scoring alone.