Stratifying risk of disease in haematuria patients using machine learning techniques to improve diagnostics.

Background: Detailed and invasive clinical investigations are required to identify the causes of haematuria. Highly unbalanced patient population (predominantly male) and a wide range of potential causes make the ability to correctly classify patients and identify patient-specific biomarkers a major challenge. Studies have shown that it is possible to improve the diagnosis using multi-marker analysis, even in unbalanced datasets, by applying advanced analytical methods. Here, we applied several machine learning algorithms to classify patients from the haematuria patient cohort (HaBio) by analysing multiple biomarkers and to identify the most relevant ones. Materials and methods: We applied several classification and feature selection methods (k-means clustering, decision trees, random forest with LIME explainer and CACTUS algorithm) to stratify patients into two groups: healthy (with no clear cause of haematuria) or sick (with an identified cause of haematuria e.g., bladder cancer, or infection). The classification performance of the models was compared. Biomarkers identified as important by the algorithms were also analysed in relation to their involvement in the pathological processes. Results: Results showed that a high unbalance in the datasets significantly affected the classification by random forest and decision trees, leading to the overestimation of the sick class and low model performance. CACTUS algorithm was more robust to the unbalance in the dataset. CACTUS obtained a balanced accuracy of 0.747 for both genders, 0.718 for females and 0.803 for males. The analysis showed that in the classification process for the whole dataset: microalbumin, male gender, and tPSA emerged as the most informative biomarkers. For males: age, microalbumin, tPSA, cystatin C, BTA, HAD and S100A4 were the most significant biomarkers while for females microalbumin, IL-8, pERK, and CXCL16. Conclusions: CACTUS algorithm demonstrated improved performance compared with other methods such as decision trees and random forest. Additionally, we identified the most relevant biomarkers for the specific patient group, which could be considered in the future as novel biomarkers for diagnosis. Our results have the potential to inform future research and provide new personalised diagnostic approaches tailored directly to the needs of the individuals.

Biomarkers to assess the risk of bladder cancer in patients presenting with haematuria are gender-specific.

Introduction: Haematuria is a common red flag symptom of urinary tract cancer. Bladder cancer (BC) is the most common cancer to present with haematuria. Women presenting with haematuria are often underdiagnosed. Currently, no gender-specific tests are utilized in clinical practice. Considerable healthcare resources are needed to investigate causes of haematuria and this study was set up to help identify markers of BC. The aim of the study was to define biomarker algorithms in haematuria patients using an expanded panel of biomarkers to diagnose BC and investigate if the algorithms are gender-specific. Materials and Methods: A total of n=675 patients with a history of haematuria were recruited from Northern Ireland hospitals. Patients were collected on a 2:1 ratio, non-BC (control) n=474: BC n=201. A detailed clinical history, urine and blood samples were collected. Biomarkers, known to be involved in the pathobiology underlying bladder carcinogenesis were investigated. Biomarkers differentially expressed between groups were investigated using Wilcoxon rank sum and linear regression. Results: Biomarkers were gender specific. Two biomarker-algorithms were identified to triage haematuria patients; male - u_NSE, s_PAI-1/tPA, u_midkine, u_NGAL, u_MMP-9/TIMP-1 and s_prolactin (u=urine; s=serum); sensitivity 71.8%, specificity 72.8%; AUROC 0.795; and female urine biomarkers - IL-12p70, IL-13, midkine and clusterin; sensitivity 83.7%, specificity 79.7%; AUROC 0.865. Addition of the clinical variable infection to both algorithms increased both AUROC to 0.822 (DeLong p=0.014) and to 0.923 (DeLong p=0.004) for males and females, respectively. Combining clinical risk factors with biomarker algorithms would enable application of the algorithms to triage haematuria patients. Conclusion: Using gender-specific biomarker algorithms in combination with clinical risks that are associated with BC would allow clinicians to better manage haematuria patients and potentially reduce underdiagnosis in females. In this study, we demonstrate, for the first time, that blood and urine biomarkers are gender-specific when assessing risk of BC in patients who present with blood in their urine. Combining biomarker data with clinical factors could improve triage when referring patients for further investigations.

Clinical features and predictive biomarkers for bladder cancer in patients with type 2 diabetes presenting with haematuria.

AIMS: To identify clinical features and protein biomarkers associated with bladder cancer (BC) in individuals with type 2 diabetes mellitus presenting with haematuria. MATERIALS AND METHODS: Data collected from the Haematuria Biomarker (HaBio) study was used in this analysis. A matched sub-cohort of patients with type 2 diabetes and patients without diabetes was created based on age, sex, and BC diagnosis, using approximately a 1:2 fixed ratio. Randox Biochip Array Technology and ELISA were applied for measurement of 66 candidate serum and urine protein biomarkers. Hazard ratios and 95% confidence intervals were estimated by chi-squared and Wilcoxon rank sum test for clinical features and candidate protein biomarkers. Diagnostic protein biomarker models were identified using Lasso-based binominal regression analysis. RESULTS: There was no difference in BC grade, stage, and severity between individuals with type 2 diabetes and matched controls. Incidence of chronic kidney disease (CKD) was significantly higher in patients with type 2 diabetes (p = 0.008), and CKD was significantly associated with BC in patients with type 2 diabetes (p = 0.032). A biomarker model, incorporating two serum (monocyte chemoattractant protein 1 and vascular endothelial growth factor) and three urine (interleukin 6, cytokeratin 18, and cytokeratin 8) proteins, predicted incidence of BC with an Area Under the Curve (AUC) of 0.84 in individuals with type 2 diabetes. In people without diabetes, the AUC was 0.66. CONCLUSIONS: We demonstrate the potential clinical utility of a biomarker panel, which includes proteins related to BC pathogenesis and type 2 diabetes, for monitoring risk of BC in patients with type 2 diabetes. Earlier urology referral of patients with type 2 diabetes will improve outcomes for these patients. TRIAL REGISTRATION: http://www.isrctn.com/ISRCTN25823942.

Compliance in patients with dietary hyperoxaluria: A cohort study and systematic review.

OBJECTIVE: Hyperoxaluria leads to calcium oxalate crystal formation and subsequent urolithiasis. This study aims to analyse the effect of treatment compliance in hyperoxaluria, firstly by analysis of patients with non-primary hyperoxaluria and secondly via systematic review in patients with any hyperoxaluria. METHODS: In a retrospective cohort study, adults with non-primary hyperoxaluria managed with dietary counselling in 2013 were enrolled. Twenty-four-hour (24 h) urine collections initially and at 6 months were obtained. Compliance was assessed by self-reported dietary compliance and 24 h urinary volume >2 L. Patients were followed for 24 months. Primary outcomes were urinary oxalate and calcium 24 h load at 6 months, and urolithiasis-related procedural rates at 24 months. A Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compatible systematic review of compliance among hyperoxaluric patients was performed. RESULTS: In the cohort study, of 19 eligible patients (4 female) with median age 52 years, 10 (53%) were considered compliant. Compared with the non-compliant group, these patients had significantly increased subsequent 24 h urinary volume (2250 mL vs. 1600 mL; p = 0.008) and lower procedural rates (10% vs. 56%; p = 0.033). Subsequent 24 h urinary oxalate load was non-significantly lower in compliant patients. Systematic review regarding compliance in hyperoxaluric patients revealed five studies. Only one utilised dietary counselling or analysed compliant vs. non-compliant patients, finding no difference. None examined the effect of compliance on procedural rates. CONCLUSION: Hyperoxaluria is an important cause of recurrent urolithiasis. Increasing fluid intake and reducing dietary oxalate reduce the risk of operative intervention and remain fundamental to the treatment of hyperoxaluria.

Comparability of iPad and Web-Based NIH Toolbox Cognitive Battery Administration in Veterans.

OBJECTIVE: The purpose of this study was to evaluate the comparability of National Institutes of Health Toolbox Cognitive Battery test scores across iPad application and web-based personal computer administration platforms. Original test norms were developed using a personal computer-based administration and no previous studies assessing platform comparability have been published. METHOD: Participants (N = 62; final analyzed sample n = 49) were combat-exposed post-deployment veterans without neurologic disorder, severe mental illness, current substance use disorder, or a history of moderate or severe traumatic brain injury. All participants completed both iPad and web-based versions of tests on the same day in an experimental within-subjects crossover design. Standalone validity measures were incorporated to exclude invalid performance. Outcome measures included the Dimensional Change Card Sort Test, Flanker Inhibitory Control and Attention Test, List Sorting Working Memory Test, and Pattern Comparison Processing Speed Test. RESULTS: Score differences between platforms were found on the Flanker Inhibitory Control and Attention Test. Scores were moderately correlated across tests, with the exception of low correlations for the Pattern Comparison Processing Speed Test. Most participants preferred iPad to web administration, regardless of administration order. CONCLUSIONS: Results suggest caution when interpreting iPad-acquired scores, particularly for the Flanker Inhibitory Control and Attention Test. iPad-based testing offers valuable improvements; however, the development of iPad-specific norms may be necessary to ensure valid interpretation of acquired data.

Radiofrequency Ablation of Small Renal Masses: Outcomes, Complications and Effects on Renal Function.

INTRODUCTION: To describe oncological outcomes, effects on renal function and complications with radiofrequency ablation (RFA) of T1 renal tumors in an 8-year experience. MATERIALS AND METHODS: A retrospective study of RFA in 89 consecutive patients between 2005 and 2013 was undertaken. Those with metastatic disease, incomplete follow-up, genetic pre-disposition to renal tumors and biopsy proven benign pathology were excluded, with 79 patients meeting inclusion criteria. Data was collected on demographics, oncological outcomes, complications and effects on renal function. RESULTS: We demonstrate 94% disease-free survival at median follow-up of 29 months in a population consisting of 42 T1a and 37 T1b tumors. No disease related deaths were recorded in the follow-up period. Post-RFA decline in renal function was shown to correlate with tumor size and increased age (p = 0.0009/0.0021). Pre-existing renal impairment was a risk for post-RFA function decline (p < 0.005). Two complications were encountered in the series. CONCLUSION: RFA produces durable oncological outcomes in T1 tumors with a minimal effect on renal function and low risk of complications. Patients at risk of developing renal impairment can be identified from described risk factors.

Supine Percutaneous Nephrolithotomy in the Galdako-Modified Valdivia Position: A High-Volume Single Center Experience.

OBJECTIVE: To describe the technique and outcomes of supine percutaneous nephrolithotomy (PCNL) in the Galdako-modified Valdivia position. MATERIALS AND METHODS: Prospective data were collected from 303 patients undergoing PCNL in the Galdako-modified Valdivia position at our institution between 2007 and 2015. We report our technique with outcomes of operative times, stone-free rate (SFR), and complications. RESULTS: A total of 202 solitary stones with a mean size of 17.19 ± 5.82 mm, 42 stones in multiple calices, and 57 staghorns were treated. Mean operative time was 79.79 ± 35.72 minutes. A total of 244/303 (80.5%) patients had clearance or <2 mm stone on postoperative CT. Minor complications (Clavien-Dindo Classification [CDC] 1-2) occurred in 59 (19.5%) cases and major complications (CDC ≥3) occurred in 22 (7.3%) cases. Five (1.7%) cases required postoperative blood transfusion for bleeding complications. CONCLUSION: We demonstrate that PCNL in a high-volume center to be safe and efficacious in the Galdalko-modified Valdivia position. We show equivalent SFR and complication rates to large studies of prone PCNL, with potential to decrease operative time. In particular, supine position is optimum for obese or high-risk patients with complex stone disease, because of ease of positioning and lower theoretical risk of anesthetic complications.

A Coaching by Telephone Intervention for Veterans and Care Team Engagement (ACTIVATE): A study protocol for a Hybrid Type I effectiveness-implementation randomized controlled trial.

INTRODUCTION: A large proportion of deaths and many illnesses can be attributed to three modifiable risk factors: tobacco use, overweight/obesity, and physical inactivity. Health risk assessments (HRAs) are widely available online but have not been consistently used in healthcare systems to activate patients to participate in prevention programs aimed at improving lifestyle behaviors. OBJECTIVES: The goal of this study is to test whether adding telephone-based coaching to use of a comprehensive HRA increases at-risk patients' activation and enrollment into a prevention program compared to HRA use alone. METHODS: Participants were randomized to either complete an HRA alone or in conjunction with a telephone coaching intervention. To be eligible Veterans had to have at least one modifiable risk factor (current smoker, overweight/obese, or physically inactive). The primary outcome is enrollment and participation in a prevention program by 6months. Secondary outcomes include change in a Patient Activation Measure and Framingham Risk Score. DISCUSSION: This study is the first to test a web-based health risk assessment coupled with a health coaching intervention within a large healthcare system. Results from this study will help the Veterans Health Administration (VHA) implement its national plan to include comprehensive health risk assessments as a tool to engage Veterans in prevention. The results will also inform health systems outside VHA who seek to implement Medicare's advisement that health risk assessment become a mandatory component of care under the Affordable Care Act.

Minimally Invasive management of delayed recognition iatrogenic ureteric injury.

INTRODUCTION: Iatrogenic ureteric injuries are a rare but serious complication of abdomino-pelvic surgery which can be associated with significant morbidity. 65-80% of ureteric trauma is only identified in the postoperative period. Current guidelines recommend stent insertion or urinary diversion via percutaneous nephrostomy. Good quality evidence on success and outcomes remains scant and the optimum treatment pathway unknown. METHODS: A retrospective review of all delayed presentation ureteric injuries treated in our unit between 2005 and 2013 was performed. Clinical, treatment and outcome data were collected in a custom proforma. RESULTS: 19 patients with 21 injured ureters met inclusion criteria. 16/19 (84.2%) injuries were sustained during gynaecological procedures with 10 (52.6%) of these during total abdominal hysterectomy. Suspected mechanisms from diagnostic studies was defined as partial transection in 9/21 (42.9%), complete transection in 3/21 (14.3%) and perforation in 1/21 (4.8%).Median time from injury to presentation was 16 days (IQR 7-25). 11/21 (52.4%) had successful stenting with a median time to stent placement of 25 days (IQR 18.5-42). Those with failed stenting had a median time to attempted stenting of 65 days (IQR 10-91.3). Those with successful stenting 3/11 (27.3%) had resolution requiring no further intervention. 6/11 (54.5%) required open reconstruction, with the remaining two patients unfit for reconstruction and managed with long term stents. With successful stenting median time to definitive surgery was 413 days (IQR 156-476). CONCLUSION: Success rates for stenting are similar to those reported in the literature (55% vs. 44-59%), but resolution rates are significantly lower (15% vs. 44-80%). Data for an endourological approach as a possible long-term solution is limited by heterogeneity, and a further well conducted multicentre prospective study is required.

Refugees, humanitarian aid and the right to decline vaccinations.

Recent instances of governments and others refusing humanitarian assistance to refugees and IDPs (internally-displaced persons) unless they agreed to polio immunization for their children raise difficult ethical challenges. The authors argue that states have the right and a responsibility to require such vaccinations in instances where the serious vaccine-preventable disease(s) at issue threaten others, including local populations, humanitarian workers, and others in camps or support settings.

Radiofrequency ablation of renal cell carcinoma: a follow up of outcomes.

INTRODUCTION: To present the oncological outcomes in a series of patients with cT1a renal cell carcinoma (RCC) treated with radiofrequency ablation (RFA) and its effect on the glomerular filtration rate (GFR). MATERIALS AND METHODS: Forty-five patients (48 renal units) treated at the Belfast City Hospital, over 4 years. Average age is 61.5 years (range 41-80). Eighteen patients (22 renal units) were included with American Society of Anesthesiologists (ASA) II and III. The rest were ASA I. Average tumor size was 2.63 cm (range 1.2 cm-6 cm). Renal function before and after RFA was recorded by means of the estimated glomerular filtration rate (eGFR) and the changes are presented. Oncological outcomes were established from follow up imaging. A satisfactory response was defined by disappearance or a persistence of non-enhancing lesion of smaller size at follow up. A partial response was defined by a persistent but non-enhancing similar size lesion. A failed response was defined by enlarging or persistently enhancing lesions. RESULTS: Mean follow up was 30.6 months (4-60 months). A good response was found in 33 (74%) patients. A partial response was found in 3 (8%) patients and failed response was identified in 8 (18%) patients. The average reduction in eGFR was 11 mL/min. Two patients had a 50% reduction in their eGFR. No patient required dialysis following treatment. CONCLUSION: RFA presents safe treatment choice for patients with RCC, particularly those that are high risk surgical candidates and those who refuse surgery. Short term results suggest good oncological outcomes and preservation of renal function.

Utilizing the Human, Machine, and Environment Matrix in investigations.

"How did we get into this situation?" How many times has this question been asked at the outset of an investigation, or more importantly, at the completion of an investigation? If the answer is not readily and thoroughly apparent, the investigation is not complete. Subsequently, those who will have the responsibility for correction of the conditions leading to the incident will not have all the information necessary to properly complete their task. For many years, in many writings, the Human/Machine interaction and its impact on process design has been discussed. The same impact should be examined when performing incident investigations. Consideration of the interaction of human and machine along with the environment in which they are used has long been recommended by the National Safety Council, in both design and investigation.