Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms

Analysis of the urine flow characteristics inside catheters for intermittent catheter selection

In this study, we conducted a numerical analysis on catheter sizes using computational fluid dynamics to assess urinary flow rates during intermittent catheterization (IC). The results revealed that the fluid (urine) movement within a catheter is driven by intravesical pressure, with friction against the catheter walls being the main hindrance to fluid movement. Higher-viscosity fluids experienced increased friction with increasing intravesical pressure, resulting in reduced fluid velocity, whereas lower-viscosity fluids experienced reduced friction under similar pressure, leading to increased fluid velocity. Regarding urine characteristics, the results indicated that bacteriuria, with lower viscosity, exhibited higher flow rates, whereas glucosuria exhibited the lowest flow rates. Additionally, velocity gradients decreased with increasing catheter diameters, reducing friction and enhancing fluid speed, while the friction increased with decreasing diameters, reducing fluid velocity. These findings confirm that flow rates increased with larger catheter sizes. Furthermore, in terms of specific gravity, the results showed that a 12Fr catheter did not meet the ISO-suggested average flow rate (50 cc/min). The significance of this study lies in its application of fluid dynamics to nursing, examining urinary flow characteristics in catheterization. It is expected to aid nurses in selecting appropriate catheters for intermittent catheterization based on urinary test results.

Evaluation of diagnostic accuracy of urine neutrophil gelatinase-associated lipocalin in patients with symptoms of urinary tract infections: a meta-analysis

Introduction

Early and accurate diagnosis of urinary tract infection (UTI) can prevent serious sequelae including chronic kidney disease. Multiple individual studies have identified urine neutrophil gelatinase-associated lipocalin (uNGAL) as a promising biomarker for early diagnosis of UTI. We sought to understand the distribution and diagnostic accuracy of uNGAL values in patients presenting with UTI symptoms.

Methods

Our systematic literature reviews in PubMed, Embase, and Cochrane Reviews up to March 2024, identified 25 studies reporting mean/median, standard deviation/quartiles, and detection limits of uNGAL in symptomatic patients with and without culture-confirmed UTI. Seventeen studies were in children. Meta-analyses were performed using the quantile estimation (QE) method estimating the distributions of uNGAL, which were then compared between the UTI and non-UTI groups for identifying the best cut-off points maximizing the Youden index. Sensitivity analyses were performed on all 25 studies including adult patients.

Results

We found that uNGAL levels were significantly higher in samples with confirmed UTI compared to those without. In pediatric studies, median and 95% confidence interval (CI) of uNGAL values were 22.41 (95% CI of 9.94, 50.54) ng/mL in non-UTI group vs. 118.85 (95% CI of 43.07, 327.97) ng/mL in UTI group. We estimated the cut-off point of 48.43 ng/mL with highest sensitivity (96%) and specificity (97%) in children. Sensitivity analysis including both pediatric and adult studies yielded similar results.

Discussion

The level of uNGAL in symptomatic patients with confirmed UTI is much higher than that reported in patients without UTI. It may be used as a diagnostic tool to identify UTI early among symptomatic patients. The range of uNGAL concentrations and cut-off points reported in subjects with UTI is much lower than that reported in patients with acute intrinsic kidney injury.

Systematic Review Registration

https://www.crd.york.ac.uk/, PROSPERO (CRD42023370451).

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

Urogenital microbiota-driven virulence factor genes associated with recurrent urinary tract infection

Urinary tract infections (UTIs) are a common health issue affecting individuals worldwide. Recurrent urinary tract infections (rUTI) pose a significant clinical challenge, with limited understanding of the underlying mechanisms. Recent research suggests that the urobiome, the microbial community residing in the urinary tract, may play a crucial role in the development and recurrence of urinary tract infections. However, the specific virulence factor genes (VFGs) driven by urobiome contributing to infection recurrence remain poorly understood. Our study aimed to investigate the relationship between urobiome driven VFGs and recurrent urinary tract infections. By analyzing the VFGs composition of the urinary microbiome in patients with rUTI compared to a control group, we found higher alpha diversity in rUTI patients compared with healthy control. And then, we sought to identify specific VFGs features associated with infection recurrence. Specifically, we observed an increased abundance of certain VGFs in the recurrent infection group. We also associated VFGs and clinical data. We then developed a diagnostic model based on the levels of these VFGs using random forest and support vector machine analysis to distinguish healthy control and rUIT, rUTI relapse and rUTI remission. The diagnostic accuracy of the model was assessed using receiver operating characteristic curve analysis, and the area under the ROC curve were 0.83 and 0.75. These findings provide valuable insights into the complex interplay between the VFGs of urobiome and recurrent urinary tract infections, highlighting potential targets for therapeutic interventions to prevent infection recurrence.

Urine biomarkers individually and as a consensus model show high sensitivity and specificity for detecting UTIs

BACKGROUND

Current diagnoses of urinary tract infection (UTI) by standard urine culture (SUC) has significant limitations in sensitivity, especially for fastidious organisms, and the ability to identify organisms in polymicrobial infections. The significant rate of both SUC "negative" or "mixed flora/contamination" results in UTI cases and the high prevalence of asymptomatic bacteriuria indicate the need for an accurate diagnostic test to help identify true UTI cases. This study aimed to determine if infection-associated urinary biomarkers can differentiate definitive UTI cases from non-UTI controls.

METHODS

Midstream clean-catch voided urine samples were collected from asymptomatic volunteers and symptomatic subjects ≥ 60 years old diagnosed with a UTI in a urology specialty setting. Microbial identification and density were assessed using a multiplex PCR/pooled antibiotic susceptibility test (M-PCR/P-AST) and SUC. Three biomarkers [neutrophil gelatinase-associated lipocalin (NGAL), and Interleukins 8 and 1β (IL-8, and IL-1β)] were also measured via enzyme-linked immunosorbent assay (ELISA). Definitive UTI cases were defined as symptomatic subjects with a UTI diagnosis and positive microorganism detection by SUC and M-PCR, while definitive non-UTI cases were defined as asymptomatic volunteers.

RESULTS

We observed a strong positive correlation (R2 > 0.90; p < 0.0001) between microbial density and the biomarkers NGAL, IL-8, and IL-1β for symptomatic subjects. Biomarker consensus criteria of two or more positive biomarkers had sensitivity 84.0%, specificity 91.2%, positive predictive value 93.7%, negative predictive value 78.8%, accuracy 86.9%, positive likelihood ratio of 9.58, and negative likelihood ratio of 0.17 in differentiating definitive UTI from non-UTI cases, regardless of non-zero microbial density. NGAL, IL-8, and IL-1β showed a significant elevation in symptomatic cases with positive microbe identification compared to asymptomatic cases with or without microbe identification. Biomarker consensus exhibited high accuracy in distinguishing UTI from non-UTI cases.

CONCLUSION

We demonstrated that positive infection-associated urinary biomarkers NGAL, IL-8, and IL-1β, in symptomatic subjects with positive SUC and/or M-PCR results was associated with definitive UTI cases. A consensus criterion with ≥ 2 of the biomarkers meeting the positivity thresholds showed a good balance of sensitivity (84.0%), specificity (91.2%), and accuracy (86.9%). Therefore, this biomarker consensus is an excellent supportive diagnostic tool for resolving the presence of active UTI, particularly if SUC and M-PCR results disagree.

The Prevalence and Association of Different Uropathogens Detected by M-PCR with Infection-Associated Urine Biomarkers in Urinary Tract Infections

Background

Many emerging uropathogens are currently identified by multiplex polymerase chain reaction (M-PCR) in suspected UTI cases. Standard urine culture (SUC) has significantly lower detection rates, raising questions about whether these organisms are associated with UTIs and truly cause inflammation.

Objective

To determine if microbes detected by M-PCR were likely causative of UTI by measuring inflammatory biomarkers in the urine of symptomatic patients.

Design Setting and Participants

Midstream voided urine was collected from subjects ≥60 years presenting to urology clinics with symptoms of UTI (n = 1132) between 01/2023 and 05/2023. Microbe detection was by M-PCR and inflammation-associated biomarker (neutrophil gelatinase-associated lipocalin, interleukin 8, and interleukin 1β) was by enzyme-linked immunosorbent assay. Biomarker positivity was measured against individual and groups of organisms, E. coli and non-E. coli cases, emerging uropathogens, monomicrobial and polymicrobial cases.

Outcome Measurements and Statistical Analysis

Distributions were compared using 2-sample Wilcoxon Rank Sum test with 2-tailed p-values < 0.05 considered statistically significant.

Results and Limitations

M-PCR was positive in 823 (72.7%) specimens with 28 of 30 (93%) microorganisms/groups detected. Twenty-six of twenty-eight detected microorganisms/groups (93%) had ≥2 biomarkers positive in >66% of cases. Both non-E. coli cases and E. coli cases had significant biomarker positivity (p < 0.05). Limitations were that a few organisms had low prevalence making inferences about their individual significance difficult.

Conclusion

The majority of microorganisms identified by M-PCR were associated with active inflammation measured by biomarker positivity, indicating they are likely causative of UTIs in symptomatic patients. This includes emerging uropathogens frequently not detected by standard urine culture.

Smart Diagnosis of Urinary Tract Infections: is Artificial Intelligence the Fast-Lane Solution?

PURPOSE OF REVIEW

Artificial intelligence (AI) can significantly improve physicians' workflow when examining patients with UTI. However, most contemporary reviews are focused on examining the usage of AI with a restricted quantity of data, analyzing only a subset of AI algorithms, or performing narrative work without analyzing all dedicated studies. Given the preceding, the goal of this work was to conduct a mini-review to determine the current state of AI-based systems as a support in UTI diagnosis.

RECENT FINDINGS

There are sufficient publications to comprehend the potential applications of artificial intelligence in the diagnosis of UTIs. Existing research in this field, in general, publishes performance metrics that are exemplary. However, upon closer inspection, many of the available publications are burdened with flaws associated with the improper use of artificial intelligence, such as the use of a small number of samples, their lack of heterogeneity, and the absence of external validation. AI-based models cannot be classified as full-fledged physician assistants in diagnosing UTIs due to the fact that these limitations and flaws represent only a portion of all potential obstacles. Instead, such studies should be evaluated as exploratory, with a focus on the importance of future work that complies with all rules governing the use of AI. AI algorithms have demonstrated their potential for UTI diagnosis. However, further studies utilizing large, heterogeneous, prospectively collected datasets, as well as external validations, are required to define the actual clinical workflow value of artificial intelligence.

Inflammatory biomarker signatures in post-surgical drain fluid may detect anastomotic leaks within 48 hours of colorectal resection

BACKGROUND

The optimal treatment of colorectal cancer is surgical resection and primary anastomosis. Anastomotic leak can affect up to 20% of patients and creates significant morbidity and mortality. Current diagnosis of a leak is based on clinical suspicion and subsequent radiology. Peritoneal biomarkers have shown diagnostic utility in other conditions and could be useful in providing earlier diagnosis. This pilot study was designed to assess the practical utility of peritoneal biomarkers after abdominal surgery utilising an automated immunoassay system in routine use for quantifying cytokines.

METHODS

Patients undergoing an anterior resection for a rectal cancer diagnosis were recruited at University Hospital of Wales, Cardiff between June 2019 and June 2021. A peritoneal drain was placed in the proximity of the anastomosis during surgery, and peritoneal fluid was collected at days 1 to 3 post-operatively, and analysed using the Siemens IMMULITE platform for interleukin (IL)-1β, IL-6, IL-10, CXCL8, tumour necrosis factor alpha (TNFα) and C-reactive protein (CRP).

RESULTS

A total of 42 patients were recruited (22M:20F, median age 65). Anastomotic leak was detected in four patients and a further five patients had other intra-abdominal complications. The IMMULITE platform was able to provide robust and reliable results from the analysis of the peritoneal fluid. A metric based on the combination of peritoneal IL-6 and CRP levels was able to accurately diagnose three anastomotic leaks, whilst correctly classifying all negative control patients including those with other complications.

CONCLUSIONS

This pilot study demonstrates that a simple immune signature in surgical drain fluid could accurately diagnose an anastomotic leak at 48 h postoperatively using instrumentation that is already widely available in hospital clinical laboratories.

Applications of Artificial Intelligence in Urinalysis: Is the Future Already Here?

BACKGROUND

Artificial intelligence (AI) has emerged as a promising and transformative tool in the field of urinalysis, offering substantial potential for advancements in disease diagnosis and the development of predictive models for monitoring medical treatment responses.

CONTENT

Through an extensive examination of relevant literature, this narrative review illustrates the significance and applicability of AI models across the diverse application area of urinalysis. It encompasses automated urine test strip and sediment analysis, urinary tract infection screening, and the interpretation of complex biochemical signatures in urine, including the utilization of cutting-edge techniques such as mass spectrometry and molecular-based profiles.

SUMMARY

Retrospective studies consistently demonstrate good performance of AI models in urinalysis, showcasing their potential to revolutionize clinical practice. However, to comprehensively evaluate the real clinical value and efficacy of AI models, large-scale prospective studies are essential. Such studies hold the potential to enhance diagnostic accuracy, improve patient outcomes, and optimize medical treatment strategies. By bridging the gap between research and clinical implementation, AI can reshape the landscape of urinalysis, paving the way for more personalized and effective patient care.

Immune defenses in the urinary tract

Recent advances in preclinical modeling of urinary tract infections (UTIs) have enabled the identification of key facets of the host response that influence pathogen clearance and tissue damage. Here, we review new insights into the functions of neutrophils, macrophages, and antimicrobial peptides in innate control of uropathogens and in mammalian infection-related tissue injury and repair. We also discuss novel functions for renal epithelial cells in innate antimicrobial defense. In addition, epigenetic modifications during bacterial cystitis have been implicated in bladder remodeling, conveying susceptibility to recurrent UTI. In total, contemporary work in this arena has better defined host processes that shape UTI susceptibility and severity and might inform the development of novel preventive and therapeutic approaches for acute and recurrent UTI.

A retrospective study using machine learning to develop predictive model to identify urinary infection stones in vivo

Preoperative diagnosis of urinary infection stones is difficult, and accurate detection of stone composition can only be performed ex vivo. To provide guidance for better perioperative management and postoperative prevention of infection stones, we developed a machine learning model for preoperative identification of infection stones in vivo. The clinical data of patients with urolithiasis who underwent surgery in our hospital from January 2011 to December 2015 and January 2017 to December 2021 were retrospectively analyzed. A total of 2565 patients were included in the study, and 1168 eligible patients with urinary calculi were randomly divided into training set (70%) and test set (30%). Five machine learning algorithms (Support Vector Machine (SVM), Multilayer Perceptron (MLP), Decision Tree (DT), Random Forest Classifier (RFC), and Adaptive Boost (AdaBoost)) and 14 preoperative variables were used to construct the prediction model. The performance measure was the area under the receiver operating characteristic curve (AUC) of the validation set. The importance of 14 features in each prediction model for predicting infection stones was analyzed. A total of 89 patients (5.34%) with infection stones were included in the validation set. All the five prediction models showed strong discrimination in the validation set (AUC: 0.689-0.772). AdaBoost model was selected as the final model (AUC: 0.772(95% confidence interval, 0.657-0.887); Sensitivity: 0.522; Specificity: 0.902), UC positivity, and urine pH value were two important predictors of infection stones. We developed a predictive model through machine learning that can quickly identify infection stones in vivo with good predictive performance. It can be used for risk assessment and decision support of infection stones, optimize the disease management of urinary calculi and improve the prognosis of patients.

Prediction Framework on Early Urine Infection in IoT-Fog Environment Using XGBoost Ensemble Model

Urine infections are one of the most prevalent concerns for the healthcare industry that may impair the functioning of the kidney and other renal organs. As a result, early diagnosis and treatment of such infections are essential to avert any future complications. Conspicuously, in the current work, an intelligent system for the early prediction of urine infections has been presented. The proposed framework uses IoT-based sensors for data collection, followed by data encoding and infectious risk factor computation using the XGBoost algorithm over the fog computing platform. Finally, the analysis results along with the health-related information of users are stored in the cloud repository for future analysis. For performance validation, extensive experiments have been carried out, and results are calculated based on real-time patient data. The statistical findings of accuracy (91.45%), specificity (95.96%), sensitivity (84.79%), precision (95.49%), and f-score(90.12%) reveal the significantly improved performance of the proposed strategy over other baseline techniques.

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

Data from omics studies have been used for prediction and classification of various diseases in biomedical and bioinformatics research. In recent years, Machine Learning (ML) algorithms have been used in many different fields related to healthcare systems, especially for disease prediction and classification tasks. Integration of molecular omics data with ML algorithms has offered a great opportunity to evaluate clinical data. RNA sequence (RNA-seq) analysis has been emerged as the gold standard for transcriptomics analysis. Currently, it is being used widely in clinical research. In our present work, RNA-seq data of extracellular vesicles (EV) from healthy and colon cancer patients are analyzed. Our aim is to develop models for prediction and classification of colon cancer stages. Five different canonical ML and Deep Learning (DL) classifiers are used to predict colon cancer of an individual with processed RNA-seq data. The classes of data are formed on the basis of both colon cancer stages and cancer presence (healthy or cancer). The canonical ML classifiers, which are k-Nearest Neighbor (kNN), Logistic Model Tree (LMT), Random Tree (RT), Random Committee (RC), and Random Forest (RF), are tested with both forms of the data. In addition, to compare the performance with canonical ML models, One-Dimensional Convolutional Neural Network (1-D CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) DL models are utilized. Hyper-parameter optimizations of DL models are constructed by using genetic meta-heuristic optimization algorithm (GA). The best accuracy in cancer prediction is obtained with RC, LMT, and RF canonical ML algorithms as 97.33%. However, RT and kNN show 95.33% performance. The best accuracy in cancer stage classification is achieved with RF as 97.33%. This result is followed by LMT, RC, kNN, and RT with 96.33%, 96%, 94.66%, and 94%, respectively. According to the results of the experiments with DL algorithms, the best accuracy in cancer prediction is obtained with 1-D CNN as 97.67%. BiLSTM and LSTM show 94.33% and 93.67% performance, respectively. In classification of the cancer stages, the best accuracy is achieved with BiLSTM as 98%. 1-D CNN and LSTM show 97% and 94.33% performance, respectively. The results reveal that both canonical ML and DL models may outperform each other for different numbers of features.

What is the Diagnostic Accuracy of Novel Urine Biomarkers for Urinary Tract Infection?

Background

Urinary tract infection (UTI) affects half of women at least once in their lifetime. Current diagnosis involves urinary dipstick and urine culture, yet both methods have modest diagnostic accuracy, and cannot support decision-making in patient populations with high prevalence of asymptomatic bacteriuria, such as older adults. Detecting biomarkers of host response in the urine of hosts has the potential to improve diagnosis.

Objectives

To synthesise the evidence of the diagnostic accuracy of novel biomarkers for UTI, and of their ability to differentiate UTI from asymptomatic bacteriuria.

Design

A systematic review.

Data Sources and Methods

We searched MEDLINE, EMBASE, CINAHL and Web of Science for studies of novel biomarkers for the diagnosis of UTI. We excluded studies assessing biomarkers included in urine dipsticks as these have been well described previously. We included studies of adult patients (≥16 years) with a suspected or confirmed urinary tract infection using microscopy and culture as the reference standard. We excluded studies using clinical signs and symptoms, or urine dipstick only as a reference standard. Quality appraisal was performed using QUADAS-2. We summarised our data using point estimates and data accuracy statistics.

Results

We included 37 studies on 4009 adults measuring 66 biomarkers. Study quality was limited by case-control design and study size; only 4 included studies had a prospective cohort design. IL-6 and IL-8 were the most studied biomarkers. We found plausible evidence to suggest that IL-8, IL-6, GRO-a, sTNF-1, sTNF-2 and MCR may benefit from more rigorous evaluation of their potential diagnostic value for UTI.

Conclusions

There is insufficient evidence to recommend the use of any novel biomarker for UTI diagnosis at present. Further evaluation of the more promising candidates, is needed before they can be recommended for clinical use.

Prevalence and Associated Factors of Urinary Tract Infection in Patients with Diabetic Neuropathy: A Hospital-Based Cross-Sectional Study

Introduction

Diabetic neurogenic bladder is one of the common complications in patients with diabetic neuropathy. However, studies reporting the prevalence and associated factors of urinary tract infections (UTIs) in patients with diabetic neuropathy are rare. Therefore, the present study aimed to explore the prevalence and influencing factors of UTI in patients with diabetic neuropathy.

Methods

A hospital-based cross-sectional study that recruited patients with diabetic neuropathy was conducted from January 2019 to December 2021. Collected data included patient demographic information (age, sex, education level, body mass index), clinical data (duration of diabetes, method of administration), and laboratory tests. Multivariable logistic regression models were used to identify the factors associated with UTI risk. The strength of association was expressed as the odds ratio (OR) and 95% confidence interval (95% CI).

Results

A total of 579 patients were recruited (male, 68.2%; overall average age, 57.89 years). Using multivariate analysis with adjustment for confounding factors, female sex (odds ratio [OR]: 4.12; 95% CI: 2.24-7.60; P < 0.001), hypodermic insulin injection (OR: 2.10; 95% CI: 1.02-4.35; P = 0.045), chronic kidney disease (OR: 3.12; 95% CI: 1.11-8.80; P = 0.032), history of UTI (OR = 45.92; 95% CI: 8.62-244.76; P < 0.001), positive urinary nitrite (OR: 32.87; 95% CI: 7.37-146.70; P < 0.001), and high residual urine volume (OR: 2.19, 95% CI: 1.17-4.10; P = 0.014) were independent risk factors for UTI in patients with diabetic neuropathy. Compared with the patients aged <45 years, UTI prevalence increased 2.91-fold in patients aged 45-54 years (OR: 3.91; 95% CI: 1.02-15.03; P = 0.047) and 3.87-fold in those aged ≥65 years (OR: 4.87; 95% CI: 1.23-19.25; P = 0.024).

Conclusion

The main findings of this study showed that older age, female sex, hypodermic insulin injection, CKD, history of UTI, and positive urinary nitrite were independent risk factors for UTI in patients with diabetic neuropathy. To minimize the occurrence and resulting disease burden of UTI, knowledge regarding UTI risk factors in patients with diabetic neuropathy is critical to designate interventions.

A Step Forward for Smart Clothes─Fabric-Based Microfluidic Sensors for Wearable Health Monitoring

We report the first demonstration of fabric-based microfluidics for wearable sensing. A new technology to develop microfluidics on fabrics, as a part of an undergarment, is described here. Compared to conventional microfluidics from polydimethylsiloxane, fabric-based microfluidics are simple to make, robust, and suitable for efficient sweat delivery. Specifically, acrylonitrile butadiene styrene (ABS) films with precut microfluidic patterns were infused through fabrics to form hydrophobic areas in a specially controlled sandwich structure. Experimental tests and simulations confirmed the sweat delivery efficiency of the microfluidics. Electrodes were screen-printed onto the fabric-based microfluidic. A novel wearable potentiometer based on Arduino was also developed as the transducer and signal readouts, which was low-cost, standardized, open-source, and capable of wireless data transfer. We applied the sensor system as a standalone or as a module of a T-shirt to quantify [Ca²⁺] in a wearer's sweat, with physiological and accurate results generated. Overall, this work represents a critical step in turning regular undergarments into biochemically smart platforms for health monitoring, which will broadly benefit human healthcare.

A semi-supervised decision support system to facilitate antibiotic stewardship for urinary tract infections

Urinary Tract Infections (UTIs) are among the most frequently occurring infections in the hospital. Urinalysis and urine culture are the main tools used for diagnosis. Whereas urinalysis is sufficiently sensitive for detecting UTI, it has a relatively low specificity, leading to unnecessary treatment with antibiotics and the risk of increasing antibiotic resistance. We performed an evaluation of the current diagnostic process with an expert-based label for UTI as outcome, retrospectively established using data from the Electronic Health Records. We found that the combination of urinalysis results with the Gram stain and other readily available parameters can be used effectively for predicting UTI. Based on the obtained information, we engineered a clinical decision support system (CDSS) using the reliable semi-supervised ensemble learning (RESSEL) method, and found it to be more accurate than urinalysis or the urine culture for prediction of UTI. The CDSS provides clinicians with this prediction within hours of ordering a culture and thereby enables them to hold off on prematurely prescribing antibiotics for UTI while awaiting the culture results.

The Use of Artificial Intelligence Algorithms in the Diagnosis of Urinary Tract Infections-A Literature Review

Urinary tract infections (UTIs) are among the most common infections occurring across all age groups. UTIs are a well-known cause of acute morbidity and chronic medical conditions. The current diagnostic methods of UTIs remain sub-optimal. The development of better diagnostic tools for UTIs is essential for improving treatment and reducing morbidity. Artificial intelligence (AI) is defined as the science of computers where they have the ability to perform tasks commonly associated with intelligent beings. The objective of this study was to analyze current views regarding attempts to apply artificial intelligence techniques in everyday practice, as well as find promising methods to diagnose urinary tract infections in the most efficient ways. We included six research works comparing various AI models to predict UTI. The literature examined here confirms the relevance of AI models in UTI diagnosis, while it has not yet been established which model is preferable for infection prediction in adult patients. AI models achieve a high performance in retrospective studies, but further studies are required.

Catheter-Associated Urinary Tract Infections: Current Challenges and Future Prospects

Catheter-associated urinary tract infection (CAUTI) is the most common healthcare-associated infection and cause of secondary bloodstream infections. Despite many advances in diagnosis, prevention and treatment, CAUTI remains a severe healthcare burden, and antibiotic resistance rates are alarmingly high. In this review, current CAUTI management paradigms and challenges are discussed, followed by future prospects as they relate to the diagnosis, prevention, and treatment. Clinical and translational evidence will be evaluated, as will key basic science studies that underlie preventive and therapeutic approaches. Novel diagnostic strategies and treatment decision aids under development will decrease the time to diagnosis and improve antibiotic accuracy and stewardship. These include several classes of biomarkers often coupled with artificial intelligence algorithms, cell-free DNA, and others. New preventive strategies including catheter coatings and materials, vaccination, and bacterial interference are being developed and investigated. The antibiotic pipeline remains insufficient, and new strategies for the identification of new classes of antibiotics, and rational design of small molecule inhibitor alternatives, are under development for CAUTI treatment.

The Need to Pair Molecular Monitoring Devices with Molecular Imaging to Personalize Health

By enabling the non-invasive monitoring and quantification of biomolecular processes, molecular imaging has dramatically improved our understanding of disease. In recent years, non-invasive access to the molecular drivers of health versus disease has emboldened the goal of precision health, which draws on concepts borrowed from process monitoring in engineering, wherein hundreds of sensors can be employed to develop a model which can be used to preventatively detect and diagnose problems. In translating this monitoring regime from inanimate machines to human beings, precision health posits that continual and on-the-spot monitoring are the next frontiers in molecular medicine. Early biomarker detection and clinical intervention improves individual outcomes and reduces the societal cost of treating chronic and late-stage diseases. However, in current clinical settings, methods of disease diagnoses and monitoring are typically intermittent, based on imprecise risk factors, or self-administered, making optimization of individual patient outcomes an ongoing challenge. Low-cost molecular monitoring devices capable of on-the-spot biomarker analysis at high frequencies, and even continuously, could alter this paradigm of therapy and disease prevention. When these devices are coupled with molecular imaging, they could work together to enable a complete picture of pathogenesis. To meet this need, an active area of research is the development of sensors capable of point-of-care diagnostic monitoring with an emphasis on clinical utility. However, a myriad of challenges must be met, foremost, an integration of the highly specialized molecular tools developed to understand and monitor the molecular causes of disease with clinically accessible techniques. Functioning on the principle of probe-analyte interactions yielding a transducible signal, probes enabling sensing and imaging significantly overlap in design considerations and targeting moieties, however differing in signal interpretation and readout. Integrating molecular sensors with molecular imaging can provide improved data on the personal biomarkers governing disease progression, furthering our understanding of pathogenesis, and providing a positive feedback loop toward identifying additional biomarkers and therapeutics. Coupling molecular imaging with molecular monitoring devices into the clinical paradigm is a key step toward achieving precision health.

Development of a nomogram predicting the infection stones in kidney for better clinical management: A retrospective study

PURPOSE

To establish the first comprehensive nomogram for prediction of infection stones before treatment for better perioperative treatment and post-operative prevention of infection stones.

METHODS

A total number of 461 patients with kidney stones who underwent mini-percutaneous nephrolithotomy (mPCNL) and flexible ureteroscopy (FURS) between January 2019 to March 2021 were retrospectively analyzed. Univariable analysis and multivariable logistic regression analysis were conducted to identify the predictors for infection stones. Furthermore, the nomogram was established as a predicted model for infection stones.

RESULTS

Among 461 patients with infrared spectroscopy stone analysis, 100 (21.70%) had infection stones and 361 (78.31%) had noninfection stones. Multivariate logistic regression analysis indicated that female (OR 2.816, 95% CI 1.148-6.909, P = 0.024), recurrent kidney stones (OR 8.263, 95% CI 2.295-29.745, P = 0.001), stone burden (OR 6.872, 95% CI 2.973-15.885, P < 0.001), Hounsfield units (HU) (OR 15.208, 95% CI 6.635-34.860, P < 0.001), positive preoperative bladder urine culture (PBUC) (OR 4.899, 95% CI 1.911-12.560, P = 0.001), positive urine leukocyte esterase (ULE) (OR 3.144, 95% CI 1.114-8.870, P = 0.030), urine pH (OR 2.692, 95% CI 1.573-4.608, P < 0.001) and positive urine turbidity (OR 3.295, 95% CI 1.207-8.998, P = 0.020) were predictors for infection stone.

CONCLUSIONS

For patients with kidney stones, female, recurrent kidney stones, stone burden (>601 mm2), HU (750-1000), positive PBUC, positive ULE, urine pH and positive urine turbidity were predictors for infection stone. We established the first comprehensive model for identifying infection stones in vivo, which is extremely useful for the management of infection stones.

Point-of-care diagnostics for infectious diseases: From methods to devices

The current widespread of COVID-19 all over the world, which is caused by SARS-CoV-2 virus, has again emphasized the importance of development of point-of-care (POC) diagnostics for timely prevention and control of the pandemic. Compared with labor- and time-consuming traditional diagnostic methods, POC diagnostics exhibit several advantages such as faster diagnostic speed, better sensitivity and specificity, lower cost, higher efficiency and ability of on-site detection. To achieve POC diagnostics, developing POC detection methods and correlated POC devices is the key and should be given top priority. The fast development of microfluidics, micro electro-mechanical systems (MEMS) technology, nanotechnology and materials science, have benefited the production of a series of portable, miniaturized, low cost and highly integrated POC devices for POC diagnostics of various infectious diseases. In this review, various POC detection methods for the diagnosis of infectious diseases, including electrochemical biosensors, fluorescence biosensors, surface-enhanced Raman scattering (SERS)-based biosensors, colorimetric biosensors, chemiluminiscence biosensors, surface plasmon resonance (SPR)-based biosensors, and magnetic biosensors, were first summarized. Then, recent progresses in the development of POC devices including lab-on-a-chip (LOC) devices, lab-on-a-disc (LOAD) devices, microfluidic paper-based analytical devices (μPADs), lateral flow devices, miniaturized PCR devices, and isothermal nucleic acid amplification (INAA) devices, were systematically discussed. Finally, the challenges and future perspectives for the design and development of POC detection methods and correlated devices were presented. The ultimate goal of this review is to provide new insights and directions for the future development of POC diagnostics for the management of infectious diseases and contribute to the prevention and control of infectious pandemics like COVID-19.

Application of leukocyte esterase strip test in the screening of periprosthetic joint infections and prospects of high-precision strips

Periprosthetic joint infection (PJI) represents one of the most challenging complications after total joint arthroplasty (TJA). Despite the availability of a variety of diagnostic techniques, the diagnosis of PJI remains a challenge due to the lack of well-established diagnostic criteria. The leucocyte esterase (LE) strips test has been proved to be a valuable diagnostic tool for PJI, and its weight in PJI diagnostic criteria has gradually increased. Characterized by its convenience, speed and immediacy, leucocyte esterase strips test has a prospect of broad application in PJI diagnosis. Admittedly, the leucocyte esterase strips test has some limitations, such as imprecision and liability to interference. Thanks to the application of new technologies, such as machine reading, quantitative detection and artificial intelligence, the LE strips test is expected to overcome the limitations and improve its accuracy.

A Two-Dimensional Affinity Capture and Separation Mini-Platform for the Isolation, Enrichment, and Quantification of Biomarkers and Its Potential Use for Liquid Biopsy

Biomarker detection for disease diagnosis, prognosis, and therapeutic response is becoming increasingly reliable and accessible. Particularly, the identification of circulating cell-free chemical and biochemical substances, cellular and subcellular entities, and extracellular vesicles has demonstrated promising applications in understanding the physiologic and pathologic conditions of an individual. Traditionally, tissue biopsy has been the gold standard for the diagnosis of many diseases, especially cancer. More recently, liquid biopsy for biomarker detection has emerged as a non-invasive or minimally invasive and less costly method for diagnosis of both cancerous and non-cancerous diseases, while also offering information on the progression or improvement of disease. Unfortunately, the standardization of analytical methods to isolate and quantify circulating cells and extracellular vesicles, as well as their extracted biochemical constituents, is still cumbersome, time-consuming, and expensive. To address these limitations, we have developed a prototype of a portable, miniaturized instrument that uses immunoaffinity capillary electrophoresis (IACE) to isolate, concentrate, and analyze cell-free biomarkers and/or tissue or cell extracts present in biological fluids. Isolation and concentration of analytes is accomplished through binding to one or more biorecognition affinity ligands immobilized to a solid support, while separation and analysis are achieved by high-resolution capillary electrophoresis (CE) coupled to one or more detectors. When compared to other existing methods, the process of this affinity capture, enrichment, release, and separation of one or a panel of biomarkers can be carried out on-line with the advantages of being rapid, automated, and cost-effective. Additionally, it has the potential to demonstrate high analytical sensitivity, specificity, and selectivity. As the potential of liquid biopsy grows, so too does the demand for technical advances. In this review, we therefore discuss applications and limitations of liquid biopsy and hope to introduce the idea that our affinity capture-separation device could be used as a form of point-of-care (POC) diagnostic technology to isolate, concentrate, and analyze circulating cells, extracellular vesicles, and viruses.

Development of risk prediction models to predict urine culture growth for adults with suspected urinary tract infection in the emergency department: protocol for an electronic health record study from a single UK university hospital

BACKGROUND

Urinary tract infection (UTI) is a leading cause of hospital admissions and is diagnosed based on urinary symptoms and microbiological cultures. Due to lags in the availability of culture results of up to 72 h, and the limitations of routine diagnostics, many patients with suspected UTI are started on antibiotic treatment unnecessarily. Predictive models based on routinely collected clinical information may help clinicians to rule out a diagnosis of bacterial UTI in low-risk patients shortly after hospital admission, providing additional evidence to guide antibiotic treatment decisions.

METHODS

Using electronic hospital records from Queen Elizabeth Hospital Birmingham (QEHB) collected between 2011 and 2017, we aim to develop a series of models that estimate the probability of bacterial UTI at presentation in the emergency department (ED) among individuals with suspected UTI syndromes. Predictions will be made during ED attendance and at different time points after hospital admission to assess whether predictive performance may be improved over time as more information becomes available about patient status. All models will be externally validated for expected future performance using QEHB data from 2018/2019.

DISCUSSION

Risk prediction models using electronic health records offer a new approach to improve antibiotic prescribing decisions, integrating clinical and demographic data with test results to stratify patients according to their probability of bacterial infection. Used in conjunction with expert opinion, they may help clinicians to identify patients that benefit the most from early antibiotic cessation.