Search

Transferring and replicating predictive algorithms across healthcare systems constitutes a unique yet crucial challenge that needs to be addressed to enable the widespread adoption of machine learning in healthcare. In this study, we explored the impact of important differences across healthcare systems and the associated Electronic Health Records (EHRs) on machine-learning algorithms to predict mental health crises, up to 28 days in advance. We evaluated both the transferability and replicability of such machine learning models, and for this purpose, we trained six models using features and methods developed on EHR data from the Birmingham and Solihull Mental Health NHS Foundation Trust in the UK. These machine learning models were then used to predict the mental health crises of 2907 patients seen at the Rush University System for Health in the US between 2018 and 2020. The best one was trained on a combination of US-specific structured features and frequency features from anonymized patient notes and achieved an AUROC of 0.837. A model with comparable performance, originally trained using UK structured data, was transferred and then tuned using US data, achieving an AUROC of 0.826. Our findings establish the feasibility of transferring and replicating machine learning models to predict mental health crises across diverse hospital systems. [ABSTRACT FROM AUTHOR]

Simple Summary: Indocyanine green (ICG) is a dye that helps surgeons see the blood supply to tissues. In this study, (MIRRORS ICG) researchers wanted to see if this dye could help find cancer in women with advanced ovarian cancer undergoing robotic surgery after chemotherapy. After injecting ICG, a special camera was used to look at the whole abdomen and pelvic area. In this study, 102 tissue samples were taken to see if ICG helped identify cancerous tissue. The results showed that ICG correctly identified cancer in 91.1% of cases but had a low specificity of 13.0%, meaning it often falsely indicated cancer. This technique did not significantly help in detecting cancer in patients with widespread disease, but it showed some potential in those who had responded well to chemotherapy and had few remaining cancer spots. Molecular imaging with targeted dyes could enhance precision surgery in the future. Indocyanine green (ICG) is a fluorescent dye used for sentinel lymph node assessment and the assessment of perfusion in skin flaps and bowel anastomoses. ICG binds serum proteins and behaves as a macromolecule in the circulation. Tumour tissue has increased vascular permeability and reduced drainage, causing macromolecules to accumulate within it. MIRRORS ICG is designed to determine whether indocyanine green (ICG) helped identify metastatic deposits in women undergoing robotic interval cytoreductive surgery for advanced-stage (3c+) ovarian cancer. Peritoneal surfaces of the abdominal and pelvic cavity were inspected under white light and near-infrared light (da Vinci Si and Xi Firefly Fluorescence imaging, Intuitive Surgical Inc.) following intravenous injection of 20 mg ICG in sterile water. Visibly abnormal areas were excised and sent to histopathology, noting IGC positivity. In total, 102 biopsies were assessed using ICG. Intravenous ICG assessment following neoadjuvant chemotherapy had a sensitivity of 91.1% (95% CI [82.6–96.4%]), a specificity of 13.0% (95% CI [2.8–33.6%]), a positive predictive value of 78.3% (95% CI [68.4–86.2%]), and a negative predictive value of 30.0% (95% CI [6.7–65.2%]) False-positive samples were seen in 9/20 patients. Psammoma bodies were noted in the histopathology reports of seven of nine of these patients with false-positive results, indicating that a tumour had been present (chemotherapy-treated disease). This study demonstrates the appearance of metastatic peritoneal deposits during robotic cytoreductive surgery following the intravenous administration of ICG in women who have undergone neoadjuvant chemotherapy for stage 3c+ advanced ovarian cancer. A perfusion assessment using indocyanine green (ICG) peritoneal angiography during robotic interval cytoreductive surgery for advanced ovarian cancer did not clinically improve metastatic disease identification in patients with high-volume disease. The use of ICG in patients with excellent response to chemotherapy where few tumour deposits remained shows some promise. The potential of molecular imaging to enhance precision surgery and improve disease identification using the robotic platform is a novel avenue for future research. [ABSTRACT FROM AUTHOR]

In this study, we aimed to compare imaging-based features of brain function, measured by resting-state fMRI (rsfMRI), with individual characteristics such as age, gender, and total intracranial volume to predict behavioral measures. We developed a machine learning framework based on rsfMRI features in a dataset of 20,000 healthy individuals from the UK Biobank, focusing on temporal complexity and functional connectivity measures. Our analysis across four behavioral phenotypes revealed that both temporal complexity and functional connectivity measures provide comparable predictive performance. However, individual characteristics consistently outperformed rsfMRI features in predictive accuracy, particularly in analyses involving smaller sample sizes. Integrating rsfMRI features with demographic data sometimes enhanced predictive outcomes. The efficacy of different predictive modeling techniques and the choice of brain parcellation atlas were also examined, showing no significant influence on the results. To summarize, while individual characteristics are superior to rsfMRI in predicting behavioral phenotypes, rsfMRI still conveys additional predictive value in the context of machine learning, such as investigating the role of specific brain regions in behavioral phenotypes. Individual characteristics tend to over-perform fMRI-based metrics in the prediction of behavioral measures. However, the combination of both metrics can increase predictive accuracy, suggesting that fMRI-based metrics can successfully complement individual characteristics, mainly in large datasets. [ABSTRACT FROM AUTHOR]

Objective: To identify cortical and subcortical volume, thickness and cortical area features and the networks they constituted related to anxiety in Parkinson's disease (PD) using structural magnetic resonance imaging (sMRI), and to integrate multimodal features based on machine learning to identify PD-related anxiety. Methods: A total of 219 patients with PD were retrospectively enrolled in the study. 291 sMRI features including cortical volume, subcortical volume, cortical thickness, and cortical area, as well as 17 clinical features, were extracted. Graph theory analysis was used to explore structural networks. A support vector machine (SVM) combination model, which used both sMRI and clinical features to identify participants with PD-related anxiety, was developed and evaluated. The performance of SVM models were evaluated. The mean impact value (MIV) of the feature importance evaluation algorithm was used to rank the relative importance of sMRI features and clinical features within the model. Results: 17 significant sMRI variables associated with PD-related anxiety was used to build a brain structural network. And seven sMRI and 5 clinical features with statistically significant differences were incorporated into the SVM model. The comprehensive model achieved higher performance than clinical features or sMRI features did alone, with an accuracy of 0.88, a precision of 0.86, a sensitivity of 0.81, an F1-Score of 0.83, a macro-average of 0.85, a weightedaverage of 0.92, an AUC of 0.88, and a result of 10-fold cross-validation of 0.91 in test set. The sMRI feature right medialorbitofrontal thickness had the highest impact on the prediction model. Conclusion: We identified the brain structural features and networks related to anxiety in PD, and developed and internally validated a comprehensive model with multimodal features in identifying. [ABSTRACT FROM AUTHOR]

Real estate price prediction is crucial for informed decision making in the dynamic real estate sector. In recent years, machine learning (ML) techniques have emerged as powerful tools for enhancing prediction accuracy and data-driven decision making. However, the existing literature lacks a cohesive synthesis of methodologies, findings, and research gaps in ML-based real estate price prediction. This study addresses this gap through a comprehensive literature review, examining various ML approaches, including neural networks, ensemble methods, and advanced regression techniques. We identify key research gaps, such as the limited exploration of hybrid ML-econometric models and the interpretability of ML predictions. To validate the robustness of regression models, we conduct generalization testing on an independent dataset. Results demonstrate the applicability of regression models in predicting real estate prices across diverse markets. Our findings underscore the importance of addressing research gaps to advance the field and enhance the practical applicability of ML techniques in real estate price prediction. This study contributes to a deeper understanding of ML's role in real estate forecasting and provides insights for future research and practical implementation in the real estate industry. [ABSTRACT FROM AUTHOR]

Background: The prevalence of depression among people with chronic pain remains unclear due to the heterogeneity of study samples and definitions of depression. We aimed to identify sources of variation in the prevalence of depression among people with chronic pain and generate clinical prediction models to estimate the probability of depression among individuals with chronic pain. Methods: Participants were from the UK Biobank. The primary outcome was a "lifetime" history of depression. The model's performance was evaluated using discrimination (optimism-corrected C statistic) and calibration (calibration plot). Results: Analyses included 24,405 patients with chronic pain (mean age 64.1 years). Among participants with chronic widespread pain, the prevalence of having a "lifetime" history of depression was 45.7% and varied (25.0–66.7%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.66; good calibration on the calibration plot) included age, BMI, smoking status, physical activity, socioeconomic status, gender, history of asthma, history of heart failure, and history of peripheral artery disease. Among participants with chronic regional pain, the prevalence of having a "lifetime" history of depression was 30.2% and varied (21.4–70.6%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.65; good calibration on the calibration plot) included age, gender, nature of pain, smoking status, regular opioid use, history of asthma, pain location that bothers you most, and BMI. Conclusions: There was substantial variability in the prevalence of depression among patients with chronic pain. Clinically relevant factors were selected to develop prediction models. Clinicians can use these models to assess patients' treatment needs. These predictors are convenient to collect during daily practice, making it easy for busy clinicians to use them. [ABSTRACT FROM AUTHOR]

There are global efforts to deploy Electric Vehicles (EVs) because of the role they promise to play in energy transition. These efforts underscore the e-mobility paradigm, representing an interplay between renewable energy resources, smart technologies, and networked transportation. However, there are concerns that these initiatives could burden the electricity grid due to increased demand. Hence, the need for accurate short-term load forecasting is pivotal for the efficient planning, operation, and control of the grid and associated power systems. This study presents robust models for forecasting half-hourly and hourly loads in the UK's power system. The work leverages machine learning techniques such as Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Gaussian Process Regression (GPR) to develop robust prediction models using the net imports dataset from 2010 to 2020. The models were evaluated based on metrics like Root Mean Square Error (RMSE), Mean Absolute Prediction Error (MAPE), Mean Absolute Deviation (MAD), and the Correlation of Determination (R2). For half-hourly forecasts, SVR performed best with an R-value of 99.85%, followed closely by GPR and ANN. But, for hourly forecasts, ANN led with an R-value of 99.71%. The findings affirm the reliability and precision of machine learning methods in short-term load forecasting, particularly highlighting the superior accuracy of the SVR model for half-hourly forecasts and the ANN model for hourly forecasts. [ABSTRACT FROM AUTHOR]

Wearable inertial measurement units (IMUs) are being used to quantify gait characteristics that are associated with increased fall risk, but the current limitation is the lack of contextual information that would clarify IMU data. Use of wearable video-based cameras would provide a comprehensive understanding of an individual's habitual fall risk, adding context to clarify abnormal IMU data. Generally, there is taboo when suggesting the use of wearable cameras to capture real-world video, clinical and patient apprehension due to ethical and privacy concerns. This perspective proposes that routine use of wearable cameras could be realized within digital medicine through AI-based computer vision models to obfuscate/blur/shade sensitive information while preserving helpful contextual information for a comprehensive patient assessment. Specifically, no person sees the raw video data to understand context, rather AI interprets the raw video data first to blur sensitive objects and uphold privacy. That may be more routinely achieved than one imagines as contemporary resources exist. Here, to showcase/display the potential an exemplar model is suggested via off-the-shelf methods to detect and blur sensitive objects (e.g., people) with an accuracy of 88%. Here, the benefit of the proposed approach includes a more comprehensive understanding of an individual's free-living fall risk (from free-living IMU-based gait) without compromising privacy. More generally, the video and AI approach could be used beyond fall risk to better inform habitual experiences and challenges across a range of clinical cohorts. Medicine is becoming more receptive to wearables as a helpful toolbox, camera-based devices should be plausible instruments. [ABSTRACT FROM AUTHOR]

Polygenic risk score (PRS) predictions often show bias toward the population of available genome-wide association studies (GWASs), which is typically of European ancestry. This study aimed to assess the performance differences of ancestry-specific PRS and test the implementation of multi-ancestry PRS to enhance the generalizability of low-density lipoprotein (LDL) cholesterol predictions in the East Asian (EAS) population. In this study, we computed ancestry-specific and multi-ancestry PRSs for LDL using data obtained from the Global Lipid Genetics Consortium, while accounting for population-specific linkage disequilibrium patterns using the PRS-CSx method in the United Kingdom Biobank dataset (UKB, n = 423,596) and Taiwan Biobank dataset (TWB, n = 68,978). Population-specific PRSs were able to predict LDL levels better within the target population, whereas multi-ancestry PRSs were more generalizable. In the TWB dataset, covariate-adjusted R2 values were 9.3% for ancestry-specific PRS, 6.7% for multi-ancestry PRS, and 4.5% for European-specific PRS. Similar trends (8.6%, 7.8%, and 6.2%) were observed in the smaller EAS population of the UKB (n = 1,480). Consistent with R2 values, PRS stratification in EAS regions (TWB) effectively captured a heterogenous variability in LDL blood cholesterol levels across PRS strata. The mean difference in LDL levels between the lowest and highest EAS-specific PRS (EAS_PRS) deciles was 0.82, compared to 0.59 for European-specific PRS (EUR_PRS) and 0.76 for multi-ancestry PRS. Notably, the mean LDL values in the top decile of multi-ancestry PRS were comparable to those of EAS_PRS (3.543 vs. 3.541, p = 0.86). Our analysis of the PRS prediction model for LDL cholesterol further supports the issue of PRS generalizability across populations. Our targeted analysis of the EAS population revealed that integrating non-European genotyping data with a powerful European-based GWAS can enhance the generalizability of LDL PRS. [ABSTRACT FROM AUTHOR]

Context The adrenocorticotropin hormone stimulation test (AST) is used to diagnose adrenal insufficiency, and is often repeated in patients when monitoring recovery of the hypothalamo–pituitary–adrenal axis. Objective To develop and validate a prediction model that uses previous AST results with new baseline cortisol to predict the result of a new AST. Methods This was a retrospective, longitudinal cohort study in patients who had undergone at least 2 ASTs, using polynomial regression with backwards variable selection, at a Tertiary UK adult endocrinology center. Model was developed from 258 paired ASTs over 5 years in 175 adults (mean age 52.4 years, SD 16.4), then validated on data from 111 patients over 1 year (51.8, 17.5) from the same center, data collected after model development. Candidate prediction variables included previous test baseline adrenocorticotropin hormone (ACTH), previous test baseline and 30-minute cortisol, days between tests, and new baseline ACTH and cortisol used with calculated cortisol/ACTH ratios to assess 8 candidate predictors. The main outcome measure was a new test cortisol measured 30 minutes after Synacthen administration. Results Using 258 sequential ASTs from 175 patients for model development and 111 patient tests for model validation, previous baseline cortisol, previous 30-minute cortisol and new baseline cortisol were superior at predicting new 30-minute cortisol (R 2 = 0.71 [0.49-0.93], area under the curve [AUC] = 0.97 [0.94-1.0]) than new baseline cortisol alone (R 2 = 0.53 [0.22-0.84], AUC = 0.88 [0.81-0.95]). Conclusion Results of a previous AST can be objectively combined with new early-morning cortisol to predict the results of a new AST better than new early-morning cortisol alone. An online calculator is available at https://endocrinology.shinyapps.io/sheffield%5fsst%5fcalculator/ for external validation. [ABSTRACT FROM AUTHOR]

Pancreatic cancer (PaCa) is a lethal cancer with an increasing incidence, highlighting the need for early prevention strategies. There is a lack of a comprehensive PaCa predictive model derived from large prospective cohorts. Therefore, we have developed an integrated PaCa risk prediction model for PaCa using data from the UK Biobank, incorporating lifestyle-related, genetic-related, and medical history-related variables for application in healthcare settings. We used a machine learning-based random forest approach and a traditional multivariable logistic regression method to develop a PaCa predictive model for different purposes. Additionally, we employed dynamic nomograms to visualize the probability of PaCa risk in the prediction model. The top five influential features in the random forest model were age, PRS, pancreatitis, DM, and smoking. The significant risk variables in the logistic regression model included male gender (OR = 1.17), age (OR = 1.10), non-O blood type (OR = 1.29), higher polygenic score (PRS) (Q5 vs. Q1, OR = 2.03), smoking (OR = 1.82), alcohol consumption (OR = 1.27), pancreatitis (OR = 3.99), diabetes (DM) (OR = 2.57), and gallbladder-related disease (OR = 2.07). The area under the receiver operating curve (AUC) of the logistic regression model is 0.78. Internal validation and calibration performed well in both models. Our integrative PaCa risk prediction model with the PRS effectively stratifies individuals at future risk of PaCa, aiding targeted prevention efforts and supporting community-based cancer prevention initiatives. [ABSTRACT FROM AUTHOR]

Background: A prediction tool was developed and internally validated to aid the diagnosis of Cushing's syndrome in dogs attending UK primary‐care practices. External validation is an important part of model validation to assess model performance when used in different populations. Objectives: To assess the original prediction model's transportability, applicability, and diagnostic performance in a secondary‐care practice in the Netherlands. Animals: Two hundred thirty client‐owned dogs. Methods: Retrospective observational study. Medical records of dogs under investigation of Cushing's syndrome between 2011 and 2020 were reviewed. Dogs diagnosed with Cushing's syndrome by the attending internists and fulfilling ALIVE criteria were defined as cases, others as non‐cases. All dogs were scored using the aforementioned prediction tool. Dog characteristics and predictor‐outcome effects in development and validation data sets were compared to assess model transportability. Calibration and discrimination were examined to assess model performance. Results: Eighty of 230 dogs were defined as cases. Significant differences in dog characteristics were found between UK primary‐care and Dutch secondary‐care populations. Not all predictors from the original model were confirmed to be significant predictors in the validation sample. The model systematically overestimated the probability of having Cushing's syndrome (a = −1.10, P <.001). Calibration slope was 1.35 and discrimination proved excellent (area under the receiver operating curve = 0.83). Conclusions and Clinical Importance: The prediction model had moderate transportability, excellent discriminatory ability, and overall overestimated probability of having Cushing's syndrome. This study confirms its utility, though emphasizes that ongoing validation efforts of disease prediction tools are a worthwhile effort. [ABSTRACT FROM AUTHOR]

Aims Left ventricular systolic dysfunction (LSVD) is a heterogeneous condition with several factors influencing prognosis. Better phenotyping of asymptomatic individuals can inform preventative strategies. This study aims to explore the clinical phenotypes of LVSD in initially asymptomatic subjects and their association with clinical outcomes and cardiovascular abnormalities through multi-dimensional data clustering. Methods and results Clustering analysis was performed on 60 clinically available variables from 1563 UK Biobank participants without pre-existing heart failure (HF) and with left ventricular ejection fraction (LVEF) < 50% on cardiovascular magnetic resonance (CMR) assessment. Risks of developing HF, other cardiovascular events, death, and a composite of major adverse cardiovascular events (MACE) associated with clusters were investigated. Cardiovascular imaging characteristics, not included in the clustering analysis, were also evaluated. Three distinct clusters were identified, differing considerably in lifestyle habits, cardiovascular risk factors, electrocardiographic parameters, and cardiometabolic profiles. A stepwise increase in risk profile was observed from Cluster 1 to Cluster 3, independent of traditional risk factors and LVEF. Compared with Cluster 1, the lowest risk subset, the risk of MACE ranged from 1.42 [95% confidence interval (CI): 1.03–1.96; P < 0.05] for Cluster 2 to 1.72 (95% CI: 1.36–2.35; P < 0.001) for Cluster 3. Cluster 3, the highest risk profile, had features of adverse cardiovascular imaging with the greatest LV re-modelling, myocardial dysfunction, and decrease in arterial compliance. Conclusions Clustering of clinical variables identified three distinct risk profiles and clinical trajectories of LVSD amongst initially asymptomatic subjects. Improved characterization may facilitate tailored interventions based on the LVSD sub-type and improve clinical outcomes. [ABSTRACT FROM AUTHOR]

Background Since the outbreak of COVID-19, data on its psychosocial predictors are limited. We therefore aimed to explore psychosocial predictors of COVID-19 infection at the UK Biobank (UKB). Methods This was a prospective cohort study conducted among UKB participants. Results The sample size was N  = 104 201, out of which 14 852 (14.3%) had a positive COVID-19 test. The whole sample analysis showed significant interactions between sex and several predictor variables. Among females, absence of college/university degree [odds ratio (OR) 1.55, 95% confidence interval (CI) 1.45–1.66] and socioeconomic deprivation (OR 1.16 95% CI 1.11–1.21) were associated with higher odds of COVID-19 infection, while history of psychiatric consultation (OR 0.85 95% CI 0.77–0.94) with lower odds. Among males, absence of college/university degree (OR 1.56, 95% CI 1.45–1.68) and socioeconomic deprivation (OR 1.12, 95% CI 1.07–1.16) were associated with higher odds, while loneliness (OR 0.87, 95% CI 0.78–0.97), irritability (OR 0.91, 95% CI 0.83–0.99) and history of psychiatric consultation (OR 0.85, 95% CI 0.75–0.97) were associated with lower odds. Conclusion Sociodemographic factors predicted the odds of COVID-19 infection equally among male and female participants, while psychological factors had differential impacts. [ABSTRACT FROM AUTHOR]

Background: Both genetic and early life risk factors play important roles in the pathogenesis and progression of adult depression. However, the interplay between these risk factors and their added value to risk prediction models have not been fully elucidated. Methods: Leveraging a meta-analysis of major depressive disorder genome-wide association studies (N = 45,591 cases and 97,674 controls), we developed and optimized a polygenic risk score for depression using LDpred in a model selection dataset from the UK Biobank (N = 130,092 European ancestry individuals). In a UK Biobank test dataset (N = 278,730 European ancestry individuals), we tested whether the polygenic risk score and early life risk factors were associated with each other and compared their associations with depression phenotypes. Finally, we conducted joint predictive modeling to combine this polygenic risk score with early life risk factors by stepwise regression, and assessed the model performance in identifying individuals at high risk of depression. Results: In the UK Biobank test dataset, the polygenic risk score for depression was moderately associated with multiple early life risk factors. For instance, a one standard deviation increase in the polygenic risk score was associated with 1.16-fold increased odds of frequent domestic violence (95% CI: 1.14-1.19) and 1.09-fold increased odds of not having access to medical care as a child (95% CI: 1.05-1.14). However, the polygenic risk score was more strongly associated with depression phenotypes than most early life risk factors. A joint predictive model integrating the polygenic risk score, early life risk factors, age and sex achieved an AUROC of 0.6766 for predicting strictly defined major depressive disorder, while a model without the polygenic risk score and a model without any early life risk factors had an AUROC of 0.6593 and 0.6318, respectively. Conclusion: We have developed a polygenic risk score to partly capture the genetic liability to depression. Although genetic and early life risk factors can be correlated, joint predictive models improved risk stratification despite limited improvement in magnitude, and may be explored as tools to better identify individuals at high risk of depression. [ABSTRACT FROM AUTHOR]

As findings on the epidemiological and genetic risk factors for coronavirus disease-19 (COVID-19) continue to accrue, their joint power and significance for prospective clinical applications remains virtually unexplored. Severity of symptoms in individuals affected by COVID-19 spans a broad spectrum, reflective of heterogeneous host susceptibilities across the population. Here, we assessed the utility of epidemiological risk factors to predict disease severity prospectively, and interrogated genetic information (polygenic scores) to evaluate whether they can provide further insights into symptom heterogeneity. A standard model was trained to predict severe COVID-19 based on principal component analysis and logistic regression based on information from eight known medical risk factors for COVID-19 measured before 2018. In UK Biobank participants of European ancestry, the model achieved a relatively high performance (area under the receiver operating characteristic curve ~90%). Polygenic scores for COVID-19 computed from summary statistics of the Covid19 Host Genetics Initiative displayed significant associations with COVID-19 in the UK Biobank (p-values as low as 3.96e-9, all with R2 under 1%), but were unable to robustly improve predictive performance of the non-genetic factors. However, error analysis of the non-genetic models suggested that affected individuals misclassified by the medical risk factors (predicted low risk but actual high risk) display a small but consistent increase in polygenic scores. Overall, the results indicate that simple models based on health-related epidemiological factors measured years before COVID-19 onset can achieve high predictive power. Associations between COVID-19 and genetic factors were statistically robust, but currently they have limited predictive power for translational settings. Despite that, the outcomes also suggest that severely affected cases with a medical history profile of low risk might be partly explained by polygenic factors, prompting development of boosted COVID-19 polygenic models based on new data and tools to aid risk-prediction. [ABSTRACT FROM AUTHOR]

The polygenic risk score (PRS) could be used to stratify individuals with high risk of diseases and predict complex trait of individual in a population. Previous studies developed a PRS-based prediction model using linear regression and evaluated the predictive performance of the model using the R2 value. One of the key assumptions of linear regression is that the variance of the residual should be constant at each level of the predictor variables, called homoscedasticity. However, some studies show that PRS models exhibit heteroscedasticity between PRS and traits. This study analyzes whether heteroscedasticity exists in PRS models of diverse disease-related traits and, if any, it affects the accuracy of PRS-based prediction in 354,761 Europeans from the UK Biobank. We constructed PRSs for 15 quantitative traits using LDpred2 and estimated the existence of heteroscedasticity between PRSs and 15 traits using three different tests of the Breusch-Pagan (BP) test, score test, and F test. Thirteen out of fifteen traits show significant heteroscedasticity. Further replication using new PRSs from the PGS catalog and independent samples (N = 23,620) from the UK Biobank confirmed the heteroscedasticity in ten traits. As a result, ten out of fifteen quantitative traits show statistically significant heteroscedasticity between the PRS and each trait. There was a greater variance of residuals as PRS increased, and the prediction accuracy at each level of PRS tended to decrease as the variance of residuals increased. In conclusion, heteroscedasticity was frequently observed in the PRSbased prediction models of quantitative traits, and the accuracy of the predictive model may differ according to PRS values. Therefore, prediction models using the PRS should be constructed by considering heteroscedasticity. [ABSTRACT FROM AUTHOR]

During the outbreak of a disease caused by a pathogen with unknown characteristics, the uncertainty of its progression parameters can be reduced by devising methods that, based on rational assumptions, exploit available information to provide actionable insights. In this study, performed a few (~6) weeks into the outbreak of COVID-19 (caused by SARS-CoV-2), one of the most important disease parameters, the average time-to-recovery, was calculated using data publicly available on the internet (daily reported cases of confirmed infections, deaths, and recoveries), and fed into an algorithm that matches confirmed cases with deaths and recoveries. Unmatched cases were adjusted based on the matched cases calculation. The mean time-to-recovery, calculated from all globally reported cases, was found to be 18.01 days (SD 3.31 days) for the matched cases and 18.29 days (SD 2.73 days) taking into consideration the adjusted unmatched cases as well. The proposed method used limited data and provided experimental results in the same region as clinical studies published several months later. This indicates that the proposed method, combined with expert knowledge and informed calculated assumptions, could provide a meaningful calculated average time-to-recovery figure, which can be used as an evidence-based estimation to support containment and mitigation policy decisions, even at the very early stages of an outbreak. [ABSTRACT FROM AUTHOR]

Background: Mortality prediction is critical on long-term kidney replacement therapy (KRT), both for individual treatment decisions and resource planning. Many mortality prediction models already exist, but as a major shortcoming most of them have only been validated internally. This leaves reliability and usefulness of these models in other KRT populations, especially foreign, unknown. Previously two models were constructed for one- and two-year mortality prediction of Finnish patients starting long-term dialysis. These models are here internationally validated in KRT populations of the Dutch NECOSAD Study and the UK Renal Registry (UKRR). Methods: We validated the models externally on 2051 NECOSAD patients and on two UKRR patient cohorts (5328 and 45493 patients). We performed multiple imputation for missing data, used c-statistic (AUC) to assess discrimination, and evaluated calibration by plotting average estimated probability of death against observed risk of death. Results: Both prediction models performed well in the NECOSAD population (AUC 0.79 for the one-year model and 0.78 for the two-year model). In the UKRR populations, performance was slightly weaker (AUCs: 0.73 and 0.74). These are to be compared to the earlier external validation in a Finnish cohort (AUCs: 0.77 and 0.74). In all tested populations, our models performed better for PD than HD patients. Level of death risk (i.e., calibration) was well estimated by the one-year model in all cohorts but was somewhat overestimated by the two-year model. Conclusions: Our prediction models showed good performance not only in the Finnish but in foreign KRT populations as well. Compared to the other existing models, the current models have equal or better performance and fewer variables, thus increasing models' usability. The models are easily accessible on the web. These results encourage implementing the models into clinical decision-making widely among European KRT populations. [ABSTRACT FROM AUTHOR]

This research is devoted to the determination of hidden dependencies between the flow of particles that come from the Sun and precipitation-induced floods in the United Kingdom (UK). The analysis covers 20 flood events during the period from October 2001 to December 2019. The parameters of solar activity were used as model input data, while precipitations data in the period 10 days before and during each flood event were used as model output. The time lag of 0–9 days was taken into account in the research. Correlation analysis was conducted to determine the degree of randomness for the time series of input and output parameters. For establishing a potential causative link, machine learning classification predictive modeling was applied. Two approaches, the decision tree, and the random forest were used. We analyzed the accuracy of classification models forecast from 0 to 9 days in advance. It was found that the most important factors for flood forecasting are proton density with a time lag of 9, differential proton flux in the range of 310–580 keV, and ion temperature. Research in this paper has shown that the decision tree model is more accurate and adequate in predicting the appearance of precipitation-induced floods up to 9 days ahead with an accuracy of 91%. The results of this study confirmed that by increasing technical capabilities, using improved machine learning techniques and large data sets, it is possible to improve the understanding of the physical link between the solar wind and tropospheric weather and help improve severe weather forecasting. [ABSTRACT FROM AUTHOR]

In the previous research on traffic flow prediction models, most of the models mainly studied the time series of traffic flow, and the spatial correlation of traffic flow was not fully considered. To solve this problem, this paper proposes a method to predict the spatio-temporal characteristics of short-term traffic flow by combining the k-nearest neighbor algorithm and bidirectional long short-term memory network model. By selecting the real-time traffic flow data observed on high-speed roads in the United Kingdom, the K-nearest neighbor algorithm is used to spatially screen the station data to determine the points with high correlation and then input the BILSTM model for prediction. The experimental results show that compared with SVR, LSTM, GRU, KNN-LSTM, and CNN-LSTM models, the model proposed in this paper has better prediction accuracy, and its performance has been improved by 77%, 19%, 18%, 22%, and 13%, respectively. The proposed K-nearest neighbor-bidirectional long short-time memory model shows better prediction performance. [ABSTRACT FROM AUTHOR]

There is a multitude of pathological conditions that affect human health, yet we currently lack a predictive model for most diseases, and underlying mechanisms that are shared by multiple diseases are poorly understood. We leveraged baseline clinical biomarker data and long-term disease outcomes in UK Biobank to build prognostic multivariate survival models for over 200 most common diseases. We construct a similarity map between biomarker-disease hazard ratios and demonstrate broad patterns of shared similarity in biomarker profiles across the entire disease space. Further aggregation of risk profiles through density based clustering showed that biomarker-risk profiles can be partitioned into few distinct clusters with characteristic patterns representative of broad disease categories. To confirm these risk patterns we built disease co-occurrence networks in the UK Biobank and US HCUP hospitalization databases, and compared similarity in biomarker risk profiles to disease co-occurrence. We show that proximity in the biomarker-disease space is strongly related to the occurrence of disease comorbidity, suggesting biomarker profile patterns can be used for both predicting future outcomes as well as a sensitive mechanism for detecting under-diagnosed disease states. [ABSTRACT FROM AUTHOR]

Background: Bronchopulmonary dysplasia (BPD) is a chronic disease that affects the immature lungs of preterm infants. Infants born before 32 weeks of gestation are at a greater risk of developing BPD due to the need for respiratory support with higher oxygen requirement. Pulmonary vascular remodelling in early BPD can impose an additional burden on the right ventricle (RV) and RV dysfunction. This protocol outlines the study design and aims to formulate a prediction model to identify early BPD through the data generated from echo scans analysis. Methods: The mixed-methods observational cohort feasibility study, which comprises three work-packages (WPs), will be conducted at the regional neonatal unit, University Hospital Plymouth, Plymouth, UK. WP-I will recruit 40 preterm infants; each participant will have two heart scans performed in the first ten days after birth (DABs). WP-II will collect the documentation of the participating preterm infants' parents in the study neonatal unit diaries in the first 10 DABs. WP-III will involve semi-structured interviews of 10–15 parents of participating preterm infants and 10–15 health professionals who participated in WP-I. The study recruitment will be conducted over 18-months. The start date is 01 June 2022. WP-I and WP-II recruitment will occur during this period, while WP-III recruitment will occur during the second half. The results are expected to be submitted for publication by mid-2024. Discussion: This paper outlines the study design. If the study successfully identifies the most sensitive echo parameter in recognising the RV dysfunction associated with early BPD, it will be an important finding in constructing an early BPD prediction model. Trial registration: ClinicalTrials.gov Identifier is NCT05235399 [ABSTRACT FROM AUTHOR]

Cardiorespiratory fitness is an established predictor of metabolic disease and mortality. Fitness is directly measured as maximal oxygen consumption (VO2max), or indirectly assessed using heart rate responses to standard exercise tests. However, such testing is costly and burdensome because it requires specialized equipment such as treadmills and oxygen masks, limiting its utility. Modern wearables capture dynamic real-world data which could improve fitness prediction. In this work, we design algorithms and models that convert raw wearable sensor data into cardiorespiratory fitness estimates. We validate these estimates' ability to capture fitness profiles in free-living conditions using the Fenland Study (N=11,059), along with its longitudinal cohort (N = 2675), and a third external cohort using the UK Biobank Validation Study (N = 181) who underwent maximal VO2max testing, the gold standard measurement of fitness. Our results show that the combination of wearables and other biomarkers as inputs to neural networks yields a strong correlation to ground truth in a holdout sample (r = 0.82, 95CI 0.80–0.83), outperforming other approaches and models and detects fitness change over time (e.g., after 7 years). We also show how the model's latent space can be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment. These results demonstrate the value of wearables for fitness estimation that today can be measured only with laboratory tests. [ABSTRACT FROM AUTHOR]

Simple Summary: Oesophago-gastric cancer is one of the commonest cancers worldwide, yet it can be particularly difficult to diagnose given that initial symptoms are often non-specific and routine screening is not available. Cancer risk-assessment tools, which calculate cancer risk based on symptoms and other risk factors present in the primary care record, can aid decisions on referrals for cancer investigations, facilitating earlier diagnosis. Diagnosing common cancers earlier could help improve survival rates. Using UK primary care electronic health record data, we compared five different machine learning techniques for probabilistic classification of cancer patients against a current widely used UK primary care cancer risk-assessment tool. The machine learning algorithms outperformed the current risk-assessment tool, with a higher overall accuracy and an ability to reasonably identify 11–25% more cancer patients. We conclude that machine-learning-based risk-assessment tools could help better identify suitable patients for further investigation and support earlier diagnosis. Oesophago-gastric cancer is difficult to diagnose in the early stages given its typical non-specific initial manifestation. We hypothesise that machine learning can improve upon the diagnostic performance of current primary care risk-assessment tools by using advanced analytical techniques to exploit the wealth of evidence available in the electronic health record. We used a primary care electronic health record dataset derived from the UK General Practice Research Database (7471 cases; 32,877 controls) and developed five probabilistic machine learning classifiers: Support Vector Machine, Random Forest, Logistic Regression, Naïve Bayes, and Extreme Gradient Boosted Decision Trees. Features included basic demographics, symptoms, and lab test results. The Logistic Regression, Support Vector Machine, and Extreme Gradient Boosted Decision Tree models achieved the highest performance in terms of accuracy and AUROC (0.89 accuracy, 0.87 AUROC), outperforming a current UK oesophago-gastric cancer risk-assessment tool (ogRAT). Machine learning also identified more cancer patients than the ogRAT: 11.0% more with little to no effect on false positives, or up to 25.0% more with a slight increase in false positives (for Logistic Regression, results threshold-dependent). Feature contribution estimates and individual prediction explanations indicated clinical relevance. We conclude that machine learning could improve primary care cancer risk-assessment tools, potentially helping clinicians to identify additional cancer cases earlier. This could, in turn, improve survival outcomes. [ABSTRACT FROM AUTHOR]

Background: The fatty liver index (FLI) is frequently used as a non-invasive clinical marker for research, prognostic and diagnostic purposes. It is also used to stratify individuals with hepatic steatosis such as non-alcoholic fatty liver disease (NAFLD), and to detect the presence of type 2 diabetes or cardiovascular disease. The FLI is calculated using a combination of anthropometric and blood biochemical variables; however, it reportedly excludes 8.5-16.7% of individuals with NAFLD. Moreover, the FLI cannot quantitatively predict liver fat, which might otherwise render an improved diagnosis and assessment of fatty liver, particularly in longitudinal studies. We propose FLI+ using predictive regression modelling, an improved index reflecting liver fat content that integrates 12 routinely-measured variables, including the original FLI. Methods and findings: We evaluated FLI+ on a dataset from the UK Biobank containing 28,796 individual estimates of proton density fat fraction derived from magnetic resonance imaging across normal to severe levels and interpolated to align with the original FLI range. The results obtained for FLI+ outperform the original FLI by delivering a lower mean absolute error by approximately 47%, a lower standard deviation by approximately 20%, and an increased adjusted R2 statistic by approximately 49%, reflecting a more accurate representation of liver fat content. Conclusions: Our proposed model predicting FLI+ has the potential to improve diagnosis and provide a more accurate stratification than FLI between absent, mild, moderate and severe levels of hepatic steatosis. [ABSTRACT FROM AUTHOR]

Objectives: Psoriatic arthritis (PsA) has a strong genetic component, and the identification of genetic risk factors could help identify the ~30% of psoriasis patients at high risk of developing PsA. Our objectives were to identify genetic risk factors and pathways that differentiate PsA from cutaneous‐only psoriasis (PsC) and to evaluate the performance of PsA risk prediction models. Methods: Genome‐wide meta‐analyses were conducted separately for 5,065 patients with PsA and 21,286 healthy controls and separately for 4,340 patients with PsA and 6,431 patients with PsC. The heritability of PsA was calculated as a single‐nucleotide polymorphism (SNP)–based heritability estimate (h2SNP) and biologic pathways that differentiate PsA from PsC were identified using Priority Index software. The generalizability of previously published PsA risk prediction pipelines was explored, and a risk prediction model was developed with external validation. Results: We identified a novel genome‐wide significant susceptibility locus for the development of PsA on chromosome 22q11 (rs5754467; P = 1.61 × 10−9), and key pathways that differentiate PsA from PsC, including NF‐κB signaling (adjusted P = 1.4 × 10−45) and Wnt signaling (adjusted P = 9.5 × 10−58). The heritability of PsA in this cohort was found to be moderate (h2SNP = 0.63), which was similar to the heritability of PsC (h2SNP = 0.61). We observed modest performance of published classification pipelines (maximum area under the curve 0.61), with similar performance of a risk model derived using the current data. Conclusion: Key biologic pathways associated with the development of PsA were identified, but the investigation of risk classification revealed modest utility in the available data sets, possibly because many of the PsC patients included in the present study were receiving treatments that are also effective in PsA. Future predictive models of PsA should be tested in PsC patients recruited from primary care. [ABSTRACT FROM AUTHOR]

Bicuspid aortic valve disease (BAV) is the most common congenital heart condition, and early detection can improve outcomes for patients. In this case–control study, patients with a diagnosis of BAV were identified from their electronic primary-care records in the UK's Clinical Practice Research Datalink (CPRD). Each case was propensity-score matched to up to five controls. The clinical features recorded before diagnosis were compared. The proposed clinical features shown to be associated with BAV (p < 0.05) were incorporated into a multivariable regression model. We identified 2898 cases. The prevalence of BAV in the CPRD was 1 in 5181, significantly lower than expected, suggesting that diagnosis and/or recording could be improved. The following biologically plausible clinical features were associated with a subsequent diagnosis of BAV: palpitations (OR: 2.86 (95% CI: 1.60, 3.16)), atrial fibrillation (AF) (OR: 2.25 (95% CI: 1.60, 3.16)) and hypertension (OR: 1.72 (1.48, 2.00)). The best model had an AUC of 0.669 (95% CI: 0.658 to 0.680), a positive predictive value (PPV) of 5.9% (95% CI: 4.0% to 8.7%) and a negative predictive value (NPV) of 99% (95% CI: 99% to 99%) at a population prevalence of 1%. This study indicates that palpitations, hypertension and AF should trigger a clinical suspicion of BAV and assessment via echocardiography. It also demonstrates the potential to develop a prediction model for BAV to stratify patients for echocardiography screening. [ABSTRACT FROM AUTHOR]

Machine learning for hospital operations is under-studied. We present a prediction pipeline that uses live electronic health-records for patients in a UK teaching hospital's emergency department (ED) to generate short-term, probabilistic forecasts of emergency admissions. A set of XGBoost classifiers applied to 109,465 ED visits yielded AUROCs from 0.82 to 0.90 depending on elapsed visit-time at the point of prediction. Patient-level probabilities of admission were aggregated to forecast the number of admissions among current ED patients and, incorporating patients yet to arrive, total emergency admissions within specified time-windows. The pipeline gave a mean absolute error (MAE) of 4.0 admissions (mean percentage error of 17%) versus 6.5 (32%) for a benchmark metric. Models developed with 104,504 later visits during the Covid-19 pandemic gave AUROCs of 0.68–0.90 and MAE of 4.2 (30%) versus a 4.9 (33%) benchmark. We discuss how we surmounted challenges of designing and implementing models for real-time use, including temporal framing, data preparation, and changing operational conditions. [ABSTRACT FROM AUTHOR]

Pipe failure prediction models are essential for informing proactive management decisions. This study aims to establish a reliable prediction model returning the probability of pipe failure using a gradient boosted tree model, and a specific segmentation and grouping of pipes on a 1 km grid that associates localised characteristics. The model is applied to an extensive UK network with approximately 40,000 km of pipeline and a 14-year failure history. The model was evaluated using the Receiver Operator Curve and Area Under the Curve (0.89), briers score (0.007) and Mathews Correlation Coefficient (0.27) for accuracy, indicating acceptable predictions. A weighted risk analysis is used to identify the consequence of a pipe failure and provide a graphical representation of high-risk pipes for decision makers. The weighted risk analysis provided an important step to understanding the consequences of the predicted failure. The model can be used directly in strategic planning, which sets long-term key decisions regarding maintenance and potential replacement of pipes. [ABSTRACT FROM AUTHOR]

As patient health information is highly regulated due to privacy concerns, most machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however less attention has been given to adopting ready-made models in new settings. We introduce three methods to do this—(1) applying a ready-made model "as-is" (2); readjusting the decision threshold on the model's output using site-specific data and (3); finetuning the model using site-specific data via transfer learning. Using a case study of COVID-19 diagnosis across four NHS Hospital Trusts, we show that all methods achieve clinically-effective performances (NPV > 0.959), with transfer learning achieving the best results (mean AUROCs between 0.870 and 0.925). Our models demonstrate that site-specific customization improves predictive performance when compared to other ready-made approaches. [ABSTRACT FROM AUTHOR]

Model Predictive Control (MPC) emerges as a promising solution to address the substantial greenhouse gas emissions from the building sector. By employing advanced control strategies, such as MPC, for peak energy shifting, there is a significant potential to enhance energy efficiency and reduce emissions through effective demand response within a smart grid. Although MPC has been the subject of extensive research, the practical implementation of cost-effective and easily deployable solutions in buildings remains limited. This study proposes a cost-effective MPC approach, employing the Internet of Things (IoT) and dynamic pricing. The control strategy, developed in MATLAB, is locally deployed on Raspberry Pi hardware via WiFi. The proposed MPC was tested in a controlled environment at the University of Nottingham, UK, where it regulated a radiator heating device to maintain indoor comfort in response to dynamic hourly electricity prices, using real-time indoor temperature feedback. The results confirmed the proposed MPC's accuracy in predicting indoor temperature responses and controlling indoor temperature within setpoints over a typical winter week. Performance analysis further revealed that the proposed MPC strategy resulted in a 20% electricity cost reduction compared to a conventional control strategy. Additionally, alongside the proposed MPC strategy, a Phase Change Material (PCM) wallboard system was integrated into a co-simulation platform. The developed PCM wallboard model underwent a verification and validation process, utilizing both numerical simulations and experimental data. The results demonstrate that the proposed MPC-controlled PCM wallboard system saved 35% on electricity cost compared with the original case study room. This study provides valuable insights into the development of intelligent localized demand response control for the built environment, offering a range of choices for IoT equipment. [Display omitted] • Proposed low-cost, IoT-based model predictive control (MPC) strategy for buildings. • MPC strategy implemented in real-world settings using Raspberry Pi hardware. • Integrated PCM wallboard system, achieving 35% electricity cost savings. • Co-simulation platform for interactive modelling of MPC and PCM-integrated buildings. • Peak energy shifting using MPC in PCM-integrated buildings. [ABSTRACT FROM AUTHOR]

While the Flynn effect is a well-recognised phenomenon impacting tests of cognitive ability, limited research has been conducted into its relevance for tests of premorbid ability. Consequently, we aimed to investigate whether estimated FSIQ scores from four commonly used word reading tasks (the NART, the NART2, the WTAR, and the TOPF) were influenced by the Flynn effect. We administered the NART, WTAR, and TOPF to 120 healthy community-dwelling adults. Using these raw scores we calculated estimated FSIQ scores using the predictive models published in the relevant manuals and compared these with scores obtained on the WASI-II. We found a linear increase in estimated FSIQ, with the oldest reading task, the NART, returning the highest scores and the most recent, the TOPF, the lowest. The NART, WTAR US, and TOPF US overestimated intellectual ability compared to current functioning measured by the WASI-II. Our findings indicated tests of premorbid functioning appear to be subject to the Flynn effect, and clinicians should exercise caution in using older word reading tasks such as the NART. Our results support the need for Australian standardisations of these instruments. KEY POINTS What is already known about this topic: The Flynn effect is the well-known observation that population intelligence is increasing by 3 IQ points per decade. Word reading tasks reliably and validly estimate premorbid intellectual functioning in patients with neuropsychological impairment. There is some evidence indicating word reading tasks might be impacted by the Flynn effect. What this topic adds: We replicated previous research and found results that were consistent with the Flynn effect in estimating premorbid intellectual functioning across the TOPF, WTAR and NART2 and NART. Our results confirmed older tests such as the NART are likely to significantly overestimate premorbid intellectual functioning and should be used with caution. Differences in predicted FSIQ scores based on UK and US norms point to a need for future Australian standardisations of these tests. [ABSTRACT FROM AUTHOR]

Based on the high incidence of chronic kidney disease (CKD) in recent years, a better early prediction model for identifying high-risk individuals before end-stage renal failure (ESRD) occurs is needed. We conducted a nested case–control study in 348 subjects (116 cases and 232 controls) from the "Tianjin Medical University Chronic Diseases Cohort". All subjects did not have CKD at baseline, and they were followed up for 5 years until August 2018. Using multivariate Cox regression analysis, we found five nongenetic risk factors associated with CKD risks. Logistic regression was performed to select single nucleotide polymorphisms (SNPs) from which we obtained from GWAS analysis of the UK Biobank and other databases. We used a logistic regression model and natural logarithm OR value weighting to establish CKD genetic/nongenetic risk prediction models. In addition, the final comprehensive prediction model is the arithmetic sum of the two optimal models. The AUC of the prediction model reached 0.894, while the sensitivity was 0.827, and the specificity was 0.801. We found that age, diabetes, and normal high values of urea nitrogen, TGF-β, and ADMA were independent risk factors for CKD. A comprehensive prediction model was also established, which may help identify individuals who are most likely to develop CKD early. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVDs) are the primary cause of all death globally. Timely and accurate identification of people at risk of developing an atherosclerotic CVD and its sequelae is a central pillar of preventive cardiology. One widely used approach is risk prediction models; however, currently available models consider only a limited set of risk factors and outcomes, yield no actionable advice to individuals based on their holistic medical state and lifestyle, are often not interpretable, were built with small cohort sizes or are based on lifestyle data from the 1960s, e.g. the Framingham model. The risk of developing atherosclerotic CVDs is heavily lifestyle dependent, potentially making many occurrences preventable. Providing actionable and accurate risk prediction tools to the public could assist in atherosclerotic CVD prevention. Accordingly, we developed a benchmarking pipeline to find the best set of data preprocessing and algorithms to predict absolute 10-year atherosclerotic CVD risk. Based on the data of 464,547 UK Biobank participants without atherosclerotic CVD at baseline, we used a comprehensive set of 203 consolidated risk factors associated with atherosclerosis and its sequelae (e.g. heart failure). Our two best performing absolute atherosclerotic risk prediction models provided higher performance, (AUROC: 0.7573, 95% CI: 0.755–0.7595) and (AUROC: 0.7544, 95% CI: 0.7522–0.7567), than Framingham (AUROC: 0.680, 95% CI: 0.6775–0.6824) and QRisk3 (AUROC: 0.725, 95% CI: 0.7226–0.7273). Using a subset of 25 risk factors identified with feature selection, our reduced model achieves similar performance (AUROC 0.7415, 95% CI: 0.7392–0.7438) while being less complex. Further, it is interpretable, actionable and highly generalizable. The model could be incorporated into clinical practice and might allow continuous personalized predictions with automated intervention suggestions. [ABSTRACT FROM AUTHOR]

The management of myeloma in the elderly is shifting its focus towards reducing the risk of under-treating fit patients and the risk of over-treating frail patients. Frailty assessment is required in this patient group in order to individualise treatment decisions. In addition to the proven prognostic values of the International Myeloma Working Group (IMWG) frailty score and the revised Myeloma Co-morbidity Index (R-MCI), a new easy-to-use frailty-based risk profile score (high-risk (i.e. frail), medium risk (i.e. intermediate-fitness) and low-risk (i.e. fit)) named Myeloma Risk Profile (MRP) was shown to be predictive of survival in the clinical trial setting. In this retrospective real-world study, we set out to evaluate the frailty characteristics and clinical outcomes according to the different MRP scoring algorithm categories (frail vs. intermediate vs fit), in a high risk cohort of elderly newly diagnosed myeloma patients treated with the fixed-duration triplet therapy VCD (bortezomib with cyclophosphamide and dexamethasone). Clinical outcomes included: reason for treatment discontinuation, overall response rate (ORR), overall survival (OS), progression-free survival (PFS), and adverse events (AEs). Out of 100 patients, 62 were frail, 27 were intermediate and 11 were fit, according to MRP scores. To enable meaningful comparisons between comparable numbers, subgroups analyses for ORR, OS, PFS, and AEs focused on frail (n = 62) versus intermediate or fit (n = 38) patients. The proportion of patients in each subgroup who were able to complete the planned course of treatment was (frail: 43.5% vs. intermediate or fit: 55.3%). A higher proportion in the frail subgroup discontinued therapy due to progressive disease (19.4% vs. 2.6%). Discontinuation due to toxicity was comparable across subgroups (14.5% vs. 15.8%), ORR in the total cohort was 75%, and this was comparable between subgroups (frail: 74.2% vs. intermediate or fit: 76.3%). There was a trend for a shorter median OS in the frail subgroup but without a statistical significance: (frail vs. intermediate or fit): (46 months vs. not reached, HR: 1.94, 95% CI 0.89–4.2, p = 0.094). There was no difference in median PFS between subgroups: (frail vs. intermediate or fit): (11.8 vs. 9.9 months, HR: 0.99, 95% CI: 0.61–1.61, P = 0.982). This cohort demonstrated a higher incidence rate of AEs in frail patients compared to those in the intermediate or fit group: patients with at least one any grade toxicity (85.5% vs. 71.1%), patients with at least one ≥G3 AE (37.1% vs. 21.1%). In conclusion, our study is to the first to evaluate clinical outcomes according to MRP in a high risk real-world cohort of patients treated exclusively with the proteasome inhibitor-based VCD therapy. Our study demonstrated a trend for worse OS in addition to worse AE outcomes in the frail group, but no difference in PFS with this fixed-duration therapy. MRP is an easy-to-use tool in clinical practice; its prognostic value was validated in the real-world in a large cohort of patients from the Danish Registry. Further evaluation of MRP in the real-world when continuous therapies are used, can further support the generalisability of its prognostic value in elderly myeloma patients. [ABSTRACT FROM AUTHOR]

We wanted to assess if "Explainable AI" in the form of extreme gradient boosting (XGBoost) could outperform traditional logistic regression in predicting myocardial infarction (MI) in a large cohort. Two machine learning methods, XGBoost and logistic regression, were compared in predicting risk of MI. The UK Biobank is a population-based prospective cohort including 502 506 volunteers with active consent, aged 40 to 69 years at recruitment from 2006 to 2010. These subjects were followed until end of 2019 and the primary outcome was myocardial infarction. Both models were trained using 90% of the cohort. The remaining 10% was used as a test set. Both models were equally precise, but the regression model classified more of the healthy class correctly. XGBoost was more accurate in identifying individuals who later suffered a myocardial infarction. Receiver operator characteristic (ROC) scores are class size invariant. In this metric XGBoost outperformed the logistic regression model, with ROC scores of 0.86 (accuracy 0.75 (CI ±0.00379) and 0.77 (accuracy 0.77 (CI ± 0.00369) respectively. Secondly, we demonstrate how SHAPley values can be used to visualize and interpret the predictions made by XGBoost models, both for the cohort test set and for individuals. The XGBoost machine learning model shows very promising results in evaluating risk of MI in a large and diverse population. This model can be used, and visualized, both for individual assessments and in larger cohorts. The predictions made by the XGBoost models, points toward a future where "Explainable AI" may help to bridge the gap between medicine and data science. [ABSTRACT FROM AUTHOR]

Statistical models for clinical risk prediction are often derived using data from primary care databases; however, they are frequently used outside of clinical settings. The use of prediction models in epidemiological studies without external validation may lead to inaccurate results. We use the example of applying the QRISK3 model to data from the United Kingdom (UK) Biobank study to illustrate the challenges and provide suggestions for future authors. The QRISK3 model is recommended by the National Institute for Health and Care Excellence (NICE) as a tool to aid cardiovascular risk prediction in English and Welsh primary care patients aged between 40 and 74. QRISK3 has not been externally validated for use in studies where data is collected for more general scientific purposes, including the UK Biobank study. This lack of external validation is important as the QRISK3 scores of participants in UK Biobank have been used and reported in several publications. This paper outlines: (i) how various publications have used QRISK3 on UK Biobank data and (ii) the ways that the lack of external validation may affect the conclusions from these publications. We then propose potential solutions for addressing these challenges; for example, model recalibration and considering alternative models, for the application of traditional statistical models such as QRISK3, in cohorts without external validation. [ABSTRACT FROM AUTHOR]

Background: Timely interventions in women presenting with preterm labour can substantially improve health outcomes for preterm babies. However, establishing such a diagnosis is very challenging, as signs and symptoms of preterm labour are common and can be nonspecific. We aimed to develop and externally validate a risk prediction model using concentration of vaginal fluid fetal fibronectin (quantitative fFN), in combination with clinical risk factors, for the prediction of spontaneous preterm birth and assessed its cost-effectiveness.Methods and Findings: Pregnant women included in the analyses were 22+0 to 34+6 weeks gestation with signs and symptoms of preterm labour. The primary outcome was spontaneous preterm birth within 7 days of quantitative fFN test. The risk prediction model was developed and internally validated in an individual participant data (IPD) meta-analysis of 5 European prospective cohort studies (2009 to 2016; 1,783 women; mean age 29.7 years; median BMI 24.8 kg/m2; 67.6% White; 11.7% smokers; 51.8% nulliparous; 10.4% with multiple pregnancy; 139 [7.8%] with spontaneous preterm birth within 7 days). The model was then externally validated in a prospective cohort study in 26 United Kingdom centres (2016 to 2018; 2,924 women; mean age 28.2 years; median BMI 25.4 kg/m2; 88.2% White; 21% smokers; 35.2% nulliparous; 3.5% with multiple pregnancy; 85 [2.9%] with spontaneous preterm birth within 7 days). The developed risk prediction model for spontaneous preterm birth within 7 days included quantitative fFN, current smoking, not White ethnicity, nulliparity, and multiple pregnancy. After internal validation, the optimism adjusted area under the curve was 0.89 (95% CI 0.86 to 0.92), and the optimism adjusted Nagelkerke R2 was 35% (95% CI 33% to 37%). On external validation in the prospective UK cohort population, the area under the curve was 0.89 (95% CI 0.84 to 0.94), and Nagelkerke R2 of 36% (95% CI: 34% to 38%). Recalibration of the model's intercept was required to ensure overall calibration-in-the-large. A calibration curve suggested close agreement between predicted and observed risks in the range of predictions 0% to 10%, but some miscalibration (underprediction) at higher risks (slope 1.24 (95% CI 1.23 to 1.26)). Despite any miscalibration, the net benefit of the model was higher than "treat all" or "treat none" strategies for thresholds up to about 15% risk. The economic analysis found the prognostic model was cost effective, compared to using qualitative fFN, at a threshold for hospital admission and treatment of ≥2% risk of preterm birth within 7 days. Study limitations include the limited number of participants who are not White and levels of missing data for certain variables in the development dataset.Conclusions: In this study, we found that a risk prediction model including vaginal fFN concentration and clinical risk factors showed promising performance in the prediction of spontaneous preterm birth within 7 days of test and has potential to inform management decisions for women with threatened preterm labour. Further evaluation of the risk prediction model in clinical practice is required to determine whether the risk prediction model improves clinical outcomes if used in practice.Trial Registration: The study was approved by the West of Scotland Research Ethics Committee (16/WS/0068). The study was registered with ISRCTN Registry (ISRCTN 41598423) and NIHR Portfolio (CPMS: 31277). [ABSTRACT FROM AUTHOR]

Most existing tools for constructing genetic prediction models begin with the assumption that all genetic variants contribute equally towards the phenotype. However, this represents a suboptimal model for how heritability is distributed across the genome. Therefore, we develop prediction tools that allow the user to specify the heritability model. We compare individual-level data prediction tools using 14 UK Biobank phenotypes; our new tool LDAK-Bolt-Predict outperforms the existing tools Lasso, BLUP, Bolt-LMM and BayesR for all 14 phenotypes. We compare summary statistic prediction tools using 225 UK Biobank phenotypes; our new tool LDAK-BayesR-SS outperforms the existing tools lassosum, sBLUP, LDpred and SBayesR for 223 of the 225 phenotypes. When we improve the heritability model, the proportion of phenotypic variance explained increases by on average 14%, which is equivalent to increasing the sample size by a quarter. Existing genetic prediction tools typically assume that genetic variants contribute equally towards the phenotype. The authors develop eight prediction tools that allow the user to specify the heritability model, and show that these tools enable substantially improved prediction of complex traits. [ABSTRACT FROM AUTHOR]

Background: Dietary assessments in research and clinical settings are largely reliant on self-reported questionnaires. It is acknowledged that these are subject to measurement error and biases and that objective approaches would be beneficial. Dietary biomarkers have been purported as a complementary approach to improve the accuracy of dietary assessments. Tentative biomarkers have been identified for many individual fruits and vegetables (FVs), but an objective total FV intake assessment tool has not been established.Objectives: To derive and validate a prediction model of total FV intake (TFVpred) to inform future biomarker studies.Methods: Data from the National Diet and Nutrition Survey (NDNS) were used for this analysis. A modeling group (MG) consisting of participants aged >11 years from the NDNS years 5-6 was created (n = 1746). Intake data for 96 FVs were analyzed by stepwise regression to derive a model that satisfied 3 selection criteria: SEE ≤80, R2 >0.7, and ≤10 predictors. The TFVpred model was validated using comparative data from a validation group (VG) created from the NDNS years 7-8 (n = 1865). Pearson's correlation coefficients were assessed between observed and predicted values in the MG and VG. Bland-Altman plots were used to assess agreement between TFVpred estimates and total FV intake.Results: A TFVpred model, comprised of tomatoes, apples, carrots, bananas, pears, strawberries, and onions, satisfied the selection criteria (R2 = 0.761; SEE = 78.81). Observed and predicted total FV intake values were positively correlated in the MG (r = 0.872; P < 0.001; R2 = 0.761) and the VG (r = 0.838; P < 0.001; R2 = 0.702). In the MG and VG, 95.0% and 94.9%, respectively, of TFVpred model residuals were within the limits of agreement.Conclusions: Intakes of a concise FV list can be used to predict total FV intakes in a UK population. The individual FVs included in the TFVpred model present targets for biomarker discovery aimed at objectively assessing total FV intake. [ABSTRACT FROM AUTHOR]

Objective: To establish a polyexposure score (PXS) for type 2 diabetes (T2D) incorporating 12 nongenetic exposures and examine whether a PXS and/or a polygenic risk score (PGS) improves diabetes prediction beyond traditional clinical risk factors.Research Design and Methods: We identified 356,621 unrelated individuals from the UK Biobank of White British ancestry with no prior diagnosis of T2D and normal HbA1c levels. Using self-reported and hospital admission information, we deployed a machine learning procedure to select the most predictive and robust factors out of 111 nongenetically ascertained exposure and lifestyle variables for the PXS in prospective T2D. We computed the clinical risk score (CRS) and PGS by taking a weighted sum of eight established clinical risk factors and >6 million single nucleotide polymorphisms, respectively.Results: In the study population, 7,513 had incident T2D. The C-statistics for the PGS, PXS, and CRS models were 0.709, 0.762, and 0.839, respectively. Individuals in the top 10% of PGS, PXS, and CRS had 2.00-, 5.90-, and 9.97-fold greater risk, respectively, compared to the remaining population. Addition of PGS and PXS to CRS improved T2D classification accuracy, with a continuous net reclassification index of 15.2% and 30.1% for cases, respectively, and 7.3% and 16.9% for controls, respectively.Conclusions: For T2D, the PXS provides modest incremental predictive value over established clinical risk factors. However, the concept of PXS merits further consideration in T2D risk stratification and is likely to be useful in other chronic disease risk prediction models. [ABSTRACT FROM AUTHOR]

Accurate risk assessment of an individuals' propensity to develop cardiovascular diseases (CVDs) is crucial for the prevention of these conditions. Numerous published risk prediction models used for CVD risk assessment are based on conventional risk factors and include only a limited number of biomarkers. The addition of novel biomarkers can boost the discriminative ability of risk prediction models for CVDs with different pathogenesis. The present study reports the development of risk prediction models for a range of heterogeneous CVDs, including coronary artery disease (CAD), stroke, deep vein thrombosis (DVT), and abdominal aortic aneurysm (AAA), as well as for Type 2 diabetes mellitus (DM2), a major CVD risk factor. In addition to conventional risk factors, the models incorporate various blood biomarkers and comorbidities to improve both individual and population stratification. An automatic variable selection approach was developed to generate the best set of explanatory variables for each model from the initial panel of risk factors. In total, up to 254,220 UK Biobank participants (ranging from 215,269 to 254,220 for different CVDs and DM2) were included in the analyses. The derived prediction models utilizing Cox proportional hazards regression achieved consistent discrimination performance (C-index) for all diseases: CAD, 0.794 (95% CI, 0.787–0.801); DM2, 0.909 (95% CI, 0.903–0.916); stroke, 0.778 (95% CI, 0.756–0.801); DVT, 0.743 (95% CI, 0.737–0.749); and AAA, 0.893 (95% CI, 0.874–0.912). When validated on various subpopulations, they demonstrated higher discrimination in healthier and middle-age individuals. In general, calibration of a five-year risk of developing the CVDs and DM2 demonstrated incremental overestimation of disease-related conditions amongst the highest decile of risk probabilities. In summary, the risk prediction models described were validated with high discrimination and good calibration for several CVDs and DM2. These models incorporate multiple shared predictor variables and may be integrated into a single platform to enhance clinical stratification to impact health outcomes. [ABSTRACT FROM AUTHOR]

Background: Antimicrobial resistance is driven by the overuse of antibiotics. This study aimed to develop and validate clinical prediction models for the risk of infection-related hospital admission with upper respiratory infection (URTI), lower respiratory infection (LRTI) and urinary tract infection (UTI). These models were used to investigate whether there is an association between the risk of an infection-related complication and the probability of receiving an antibiotic prescription.Methods: The study used electronic health record data from general practices contributing to the Clinical Practice Research Datalink (CPRD GOLD) and Welsh Secure Anonymised Information Linkage (SAIL), both linked to hospital records. Patients who visited their general practitioner with an incidental URTI, LRTI or UTI were included and followed for 30 days for hospitalisation due to infection-related complications. Predictors included age, gender, clinical and medication risk factors, ethnicity and socioeconomic status. Cox proportional hazards regression models were used with predicted risks independently validated in SAIL.Results: The derivation and validation cohorts included 8.1 and 2.7 million patients in CPRD and SAIL, respectively. A total of 7125 (0.09%) hospital admissions occurred in CPRD and 7685 (0.28%) in SAIL. Important predictors included age and measures of comorbidity. Initial attempts at validating in SAIL (i.e. transporting the models with no adjustment) indicated the need to recalibrate the models for age and underlying incidence of infections; internal bootstrap validation of these updated models yielded C-statistics of 0.63 (LRTI), 0.69 (URTI) and 0.73 (UTI) indicating good calibration. For all three infection types, the rate of antibiotic prescribing was not associated with patients' risk of infection-related hospital admissions.Conclusion: The risk for infection-related hospital admissions varied substantially between patients, but prescribing of antibiotics in primary care was not associated with risk of hospitalisation due to infection-related complications. Our findings highlight the potential role of clinical prediction models to help inform decisions of prescribing of antibiotics in primary care. [ABSTRACT FROM AUTHOR]

Objective: To develop enhanced prediction models to update the QUiPP App prototype, a tool providing individualized risk of spontaneous preterm birth (sPTB), for use in women with symptoms of threatened preterm labor (TPTL), incorporating risk factors, transvaginal ultrasound assessment of cervical length (CL) and cervicovaginal fluid quantitative fetal fibronectin (qfFN) test results.Methods: Participants were pregnant women between 23 + 0 and 34 + 6 weeks' gestation with symptoms of TPTL, recruited as part of four prospective cohort studies carried out at 16 UK hospitals between October 2010 and October 2017. The training set comprised all women whose outcomes were known in May 2017 (n = 1032). The validation set comprised women whose outcomes were gathered between June 2017 and March 2018 (n = 506). Parametric survival models were developed for three combinations of predictors: risk factors plus qfFN test results alone, risk factors plus CL alone, and risk factors plus both qfFN and CL. The best models were selected using the Akaike and Bayesian information criteria. The estimated probability of sPTB < 30, < 34 or < 37 weeks' gestation and within 1 or 2 weeks of testing was calculated and receiver-operating-characteristics (ROC) curves were created to demonstrate the diagnostic ability of the prediction models.Results: Predictive statistics were similar between the training and the validation sets at most outcome time points and for each combination of predictors. Areas under the ROC curves (AUC) demonstrated that all three algorithms had good accuracy for the prediction of sPTB at < 30, < 34 and < 37 weeks' gestation and within 1 and 2 weeks' post-testing in the validation set, particularly the model combining risk factors plus qfFN alone (AUC: 0.96 at < 30 weeks; 0.85 at < 34 weeks; 0.77 at < 37 weeks; 0.91 at < 1 week from testing; and 0.92 at < 2 weeks from testing).Conclusions: Validation of the new prediction models suggests that the QUiPP App v.2 can reliably calculate risk of sPTB in women with TPTL. Use of the QUiPP App in practice could lead to better targeting of intervention, while providing reassurance and avoiding unnecessary intervention in women at low risk. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd. [ABSTRACT FROM AUTHOR]

Objectives: Accurate mid-pregnancy prediction of spontaneous preterm birth (sPTB) is essential to ensure appropriate surveillance of high-risk women. Advancing the QUiPP App prototype, QUiPP App v.2 aimed to provide individualized risk of delivery based on cervical length (CL), quantitative fetal fibronectin (qfFN) or both tests combined, taking into account further risk factors, such as multiple pregnancy. Here we report development of the QUiPP App v.2 predictive models for use in asymptomatic high-risk women, and validation using a distinct dataset in order to confirm the accuracy and transportability of the QUiPP App, overall and within specific clinically relevant time frames.Methods: This was a prospective secondary analysis of data of asymptomatic women at high risk of sPTB recruited in 13 UK preterm birth clinics. Women were offered longitudinal qfFN testing every 2-4 weeks and/or transvaginal ultrasound CL measurement between 18 + 0 and 36 + 6 weeks' gestation. A total of 1803 women (3878 visits) were included in the training set and 904 women (1400 visits) in the validation set. Prediction models were created based on the training set for use in three groups: patients with risk factors for sPTB and CL measurement alone, with risk factors for sPTB and qfFN measurement alone, and those with risk factors for sPTB and both CL and qfFN measurements. Survival analysis was used to identify the significant predictors of sPTB, and parametric structures for survival models were compared and the best selected. The estimated overall probability of delivery before six clinically important time points (< 30, < 34 and < 37 weeks' gestation and within 1, 2 and 4 weeks after testing) was calculated for each woman and analyzed as a predictive test for the actual occurrence of each event. This allowed receiver-operating-characteristics curves to be plotted, and areas under the curve (AUC) to be calculated. Calibration was performed to measure the agreement between expected and observed outcomes.Results: All three algorithms demonstrated high accuracy for the prediction of sPTB at < 30, < 34 and < 37 weeks' gestation and within 1, 2 and 4 weeks of testing, with AUCs between 0.75 and 0.90 for the use of qfFN and CL combined, between 0.68 and 0.90 for qfFN alone, and between 0.71 and 0.87 for CL alone. The differences between the three algorithms were not statistically significant. Calibration confirmed no significant differences between expected and observed rates of sPTB within 4 weeks and a slight overestimation of risk with the use of CL measurement between 22 + 0 and 25 + 6 weeks' gestation.Conclusions: The QUiPP App v.2 is a highly accurate prediction tool for sPTB that is based on a unique combination of biomarkers, symptoms and statistical algorithms. It can be used reliably in the context of communicating to patients the risk of sPTB. Whilst further work is required to determine its role in identifying women requiring prophylactic interventions, it is a reliable and convenient screening tool for planning follow-up or hospitalization for high-risk women. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd. [ABSTRACT FROM AUTHOR]

Background: External validation of risk models is critical for risk-stratified breast cancer prevention. We used the Individualized Coherent Absolute Risk Estimation (iCARE) as a flexible tool for risk model development and comparative model validation and to make projections for population risk stratification.Methods: Performance of two recently developed models, one based on the Breast and Prostate Cancer Cohort Consortium analysis (iCARE-BPC3) and another based on a literature review (iCARE-Lit), were compared with two established models (Breast Cancer Risk Assessment Tool and International Breast Cancer Intervention Study Model) based on classical risk factors in a UK-based cohort of 64 874 white non-Hispanic women (863 patients) age 35-74 years. Risk projections in a target population of US white non-Hispanic women age 50-70 years assessed potential improvements in risk stratification by adding mammographic breast density (MD) and polygenic risk score (PRS).Results: The best calibrated models were iCARE-Lit (expected to observed number of cases [E/O] = 0.98, 95% confidence interval [CI] = 0.87 to 1.11) for women younger than 50 years, and iCARE-BPC3 (E/O = 1.00, 95% CI = 0.93 to 1.09) for women 50 years or older. Risk projections using iCARE-BPC3 indicated classical risk factors can identify approximately 500 000 women at moderate to high risk (>3% 5-year risk) in the target population. Addition of MD and a 313-variant PRS is expected to increase this number to approximately 3.5 million women, and among them, approximately 153 000 are expected to develop invasive breast cancer within 5 years.Conclusions: iCARE models based on classical risk factors perform similarly to or better than BCRAT or IBIS in white non-Hispanic women. Addition of MD and PRS can lead to substantial improvements in risk stratification. However, these integrated models require independent prospective validation before broad clinical applications. [ABSTRACT FROM AUTHOR]

Introduction: Cardiopulmonary exercise testing (CPET) is widely used within the United Kingdom for preoperative risk stratification. Despite this, CPET's performance in predicting adverse events has not been systematically evaluated within the framework of classifier performance. Methods: After prospective registration on PROSPERO (CRD42018095508) we systematically identified studies where CPET was used to aid in the prognostication of mortality, cardiorespiratory complications, and unplanned intensive care unit (ICU) admission in individuals undergoing non-cardiopulmonary surgery. For all included studies we extracted or calculated measures of predictive performance whilst identifying and critiquing predictive models encompassing CPET derived variables. Results: We identified 36 studies for qualitative review, from 27 of which measures of classifier performance could be calculated. We found studies to be highly heterogeneous in methodology and quality with high potential for bias and confounding. We found seven studies that presented risk prediction models for outcomes of interest. Of these, only four studies outlined a clear process of model development; assessment of discrimination and calibration were performed in only two and only one study undertook internal validation. No scores were externally validated. Systematically identified and calculated measures of test performance for CPET demonstrated mixed performance. Data was most complete for anaerobic threshold (AT) based predictions: calculated sensitivities ranged from 20-100% when used for predicting risk of mortality with high negative predictive values (96-100%). In contrast, positive predictive value (PPV) was poor (2.9-42.1%). PPV appeared to be generally higher for cardiorespiratory complications, with similar sensitivities. Similar patterns were seen for the association of Peak VO2 (sensitivity 85.7-100%, PPV 2.7-5.9%) and VE/VCO2 (Sensitivity 27.8%-100%, PPV 3.4-7.1%) with mortality. Conclusions: In general CPET's 'rule-out' capability appears better than its ability to 'rule-in' complications. Poor PPV may reflect the frequency of complications in studied populations. Our calculated estimates of classifier performance suggest the need for a balanced interpretation of the pros and cons of CPET guided pre-operative risk stratification. [ABSTRACT FROM AUTHOR]

[Display omitted] • This study assessed the benefits of EU, UK and city level policies on PM 2.5. • Over 99% of UK area was predicted to meet the WHO PM 2.5 target of 10 μg m−3 by 2030. • PM 2.5 at kerbside in major cities still risks exceeding 10 μg m−3 by 2030. • Interpreting future PM 2.5 forecasts requires knowledge of model uncertainty. • These findings and recommendations could be applicable to other European cities. The recent United Kingdom (UK) Environment Act consultation had the intention of setting two targets for PM 2.5 (particles with an aerodynamic diameter less than 2.5 μm), one related to meeting an annual average concentration and the second to reducing population exposure. As part of the consultation, predictions of PM 2.5 concentrations in 2030 were made by combining European Union (EU) and UK government's emissions forecasts, with the Climate Change Committee's (CCC) Net Zero vehicle forecasts, and in London with the addition of local policies based on the London Environment Strategy (LES). Predictions in 2018 showed 6.4% of the UK's area and 82.6% of London's area had PM 2.5 concentrations above the World Health Organization (WHO) interim target of 10 μg m−3, but by 2030, over 99% of the UK's area was predicted to be below it. However, kerbside concentrations in London and other major cities were still at risk of exceeding 10 μg m−3. With local action on PM 2.5 in London, population weighted concentrations showed full compliance with the WHO interim target of 10 μg m−3 in 2030. However, predicting future PM 2.5 concentrations and interpreting the results will always be difficult and uncertain for many reasons, such as imperfect models and the difficulty in estimating future emissions. To help understand the sensitivity of the model's PM 2.5 predictions in 2030, current uncertainty was quantified using PM 2.5 measurements and showed large areas in the UK that were still at risk of exceeding the WHO interim target despite the model predictions being below 10 μg m−3. Our results do however point to the benefits that policy at EU, UK and city level can have on achieving the WHO interim target of 10 μg m−3. These results were submitted to the UK Environment Act consultation. Nevertheless, the issues addressed here could be applicable to other European cities. [ABSTRACT FROM AUTHOR]

Background: Atrial fibrillation (AF) is caused by different mechanisms but current treatment strategies do not target these mechanisms. Stratified therapy based on mechanistic drivers and biomarkers of AF have the potential to improve AF prevention and management outcomes. We will integrate mechanistic insights with known pathophysiological drivers of AF in models predicting recurrent AF and prevalent AF to test hypotheses related to AF mechanisms and response to rhythm control therapy.Methods: We will harmonise and combine baseline and outcome data from 12 studies collected by six centres from the United Kingdom, Germany, France, Spain, and the Netherlands which assess prevalent AF or recurrent AF. A Delphi process and statistical selection will be used to identify candidate clinical predictors. Prediction models will be developed in patients with AF for AF recurrence and AF-related outcomes, and in patients with or without AF at baseline for prevalent AF. Models will be used to test mechanistic hypotheses and investigate the predictive value of plasma biomarkers.Discussion: This retrospective, harmonised, individual patient data analysis will use information from 12 datasets collected in five European countries. It is envisioned that the outcome of this analysis would provide a greater understanding of the factors associated with recurrent and prevalent AF, potentially allowing development of stratified approaches to prevention and therapy management. [ABSTRACT FROM AUTHOR]