Machine Learning and External Validation of the IDENTIFY Risk Calculator for Patients with Haematuria Referred to Secondary Care for Suspected Urinary Tract Cancer.

BACKGROUND: The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups. OBJECTIVE: To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms. DESIGN, SETTING, AND PARTICIPANTS: Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined. RESULTS AND LIMITATIONS: There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups. CONCLUSIONS: The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer. PATIENT SUMMARY: We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.

Metabolic profiling of prostate cancer in skeletal microenvironments identifies G6PD as a key mediator of growth and survival.

The spread of cancer to bone is invariably fatal, with complex cross-talk between tumor cells and the bone microenvironment responsible for driving disease progression. By combining in silico analysis of patient datasets with metabolomic profiling of prostate cancer cells cultured with bone cells, we demonstrate the changing energy requirements of prostate cancer cells in the bone microenvironment, identifying the pentose phosphate pathway (PPP) as elevated in prostate cancer bone metastasis, with increased expression of the PPP rate-limiting enzyme glucose-6-phosphate dehydrogenase (G6PD) associated with a reduction in progression-free survival. Genetic and pharmacologic manipulation demonstrates that G6PD inhibition reduces prostate cancer growth and migration, associated with changes in cellular redox state and increased chemosensitivity. Genetic blockade of G6PD in vivo results in reduction of tumor growth within bone. In summary, we demonstrate the metabolic plasticity of prostate cancer cells in the bone microenvironment, identifying the PPP and G6PD as metabolic targets for the treatment of prostate cancer bone metastasis.

Metabolism in the Tumour-Bone Microenvironment.

PURPOSE OF REVIEW: For solid tumours such as breast and prostate cancer, and haematological malignancies such as myeloma, bone represents a supportive home, where the cellular crosstalk is known to underlie both tumour growth and survival, and the development of the associated bone disease. The importance of metabolic reprogramming is becoming increasingly recognised, particularly within cancer biology, enabling tumours to adapt to changing environments and pressures. This review will discuss our current understanding of metabolic requirements and adaptations within the tumour-bone microenvironment. RECENT FINDINGS: The bone provides a unique metabolic microenvironment, home to highly energy-intensive processes such as bone resorption and bone formation, both of which are dysregulated in the presence of cancer. Approaches such as metabolomics demonstrate metabolic plasticity in patients with advanced disease. Metabolic crosstalk between tumour cells and surrounding stroma supports disease pathogenesis. There is increasing evidence for a key role for metabolic reprogramming within the tumour-bone microenvironment to drive disease progression. As such, understanding these metabolic adaptations should reveal new therapeutic targets and approaches.

Diagnosis of celiac disease is being missed in over 80% of children particularly in those from socioeconomically deprived backgrounds.

Population-based screening studies have documented prevalence of celiac disease (CD) at 1% at age 7 years, but 90% of children remain undiagnosed. This prospective cohort study aims to examine whether observed differences in diagnosis rates of CD exist between children from different socioeconomic groups and how this has changed over a 12-year period. All children aged ≤15 years with a postcode within South West of England (SWE) diagnosed with CD during a 12-year period (1999-2010) when all diagnoses were based on endoscopic histology were included in the study. The incidence rates in socioeconomic groups were determined using the Index of Multiple Deprivation Score and Office of National Statistics population data. Four hundred fifteen children were diagnosed with CD; 65 within the City of Bristol (CoB). Diagnosis rate rose 4.2 times in SWE and 3.1 times in CoB between the first and last 4 years of the study. The rate was 1.6 times higher in the least socioeconomically deprived compared to most deprived (2.2 times in CoB), and the gap widened over the 12 years. Missed cases estimates for CoB and SWE are at least 83% and 91%, respectively.Conclusion: These findings suggest that while incidence of diagnosed CD in children has increased over a 12-year period, 83-91% remained undiagnosed. Socioeconomically deprived children are more likely to be underdiagnosed, and the gap between the least and most deprived has widened. To fully address massive underdiagnosis, further strategies including pilot studies using finger prick serological mass screening for CD in children entering primary schools are needed. What is Known: • Epidemiological studies record a 1% prevalence of celiac disease (CD), but up to 90% of children may remain undiagnosed. • Previous studies have documented an increased incidence of CD in higher socioeconomic groups, but proposed reasons remain conflicting. What is New: • Incidence of diagnosed CDhas gone up across all social classes but more so in higher socioeconomic groups and there is an increasing health/wealth gap. • This study estimates that 83-91% of children with CD are still being missed despite improved and easily available serological testing and suggest that population screening should be reconsidered.

Metformin and Prostate Cancer: a New Role for an Old Drug.

PURPOSE OF REVIEW: Since epidemiological studies first demonstrated a potential positive effect of metformin in reducing cancer incidence and mortality, there has been an increased interest in not only better understanding metformin's mechanisms of action but also in exploring its potential anti-cancer effects. In this review, we aim to summarise the current evidence exploring a role for metformin in prostate cancer therapy. RECENT FINDINGS: Preclinical studies have demonstrated a number of antineoplastic biological effects via a range of molecular mechanisms. Data from retrospective epidemiological studies in prostate cancer has been mixed; however, there are several clinical trials currently underway evaluating metformin's role as an anti-cancer agent. Early studies have shown benefits of metformin to inhibit cancer cell proliferation and improve metabolic syndrome in prostate cancer patients receiving androgen deprivation therapy (ADT). While the body of evidence to support a role for metformin in prostate cancer therapy is rapidly growing, there is still insufficient data from randomised trials, which are currently still ongoing. However, evidence so far suggests metformin could be a useful adjuvant agent, particularly in patients on ADT.

Recognising serious umbilical cord anomalies.

Umbilical vessel catheterisation is a common intervention in neonatal care. Many complications are recognised, some of which are life-threatening. We report the case of a term neonate who was compromised at birth following antepartum haemorrhage with evidence of multiorgan ischaemic injury. Following resuscitation and umbilical vessel catheterisation, she developed pneumoperitoneum. At laparotomy, a patent vitellointestinal duct was identified and resected. Intestinal perforation was found in the duct wall, most plausibly explained by the unintentional catheterisation of the duct via the umbilicus. Learning to recognise umbilical cord anomalies, such as patent vitellointestinal duct, can be simple and could prevent potentially serious complications.