A population-based study exploring phenotypic clusters and clinical outcomes in stroke using unsupervised machine learning approach.

Individuals developing stroke have varying clinical characteristics, demographic, and biochemical profiles. This heterogeneity in phenotypic characteristics can impact on cardiovascular disease (CVD) morbidity and mortality outcomes. This study uses a novel clustering approach to stratify individuals with incident stroke into phenotypic clusters and evaluates the differential burden of recurrent stroke and other cardiovascular outcomes. We used linked clinical data from primary care, hospitalisations, and death records in the UK. A data-driven clustering analysis (kamila algorithm) was used in 48,114 patients aged ≥ 18 years with incident stroke, from 1-Jan-1998 to 31-Dec-2017 and no prior history of serious vascular events. Cox proportional hazards regression was used to estimate hazard ratios (HRs) for subsequent adverse outcomes, for each of the generated clusters. Adverse outcomes included coronary heart disease (CHD), recurrent stroke, peripheral vascular disease (PVD), heart failure, CVD-related and all-cause mortality. Four distinct phenotypes with varying underlying clinical characteristics were identified in patients with incident stroke. Compared with cluster 1 (n = 5,201, 10.8%), the risk of composite recurrent stroke and CVD-related mortality was higher in the other 3 clusters (cluster 2 [n = 18,655, 38.8%]: hazard ratio [HR], 1.07; 95% CI, 1.02-1.12; cluster 3 [n = 10,244, 21.3%]: HR, 1.20; 95% CI, 1.14-1.26; and cluster 4 [n = 14,014, 29.1%]: HR, 1.44; 95% CI: 1.37-1.50). Similar trends in risk were observed for composite recurrent stroke and all-cause mortality outcome, and subsequent recurrent stroke outcome. However, results were not consistent for subsequent risk in CHD, PVD, heart failure, CVD-related mortality, and all-cause mortality. In this proof of principle study, we demonstrated how a heterogenous population of patients with incident stroke can be stratified into four relatively homogenous phenotypes with differential risk of recurrent and major cardiovascular outcomes. This offers an opportunity to revisit the stratification of care for patients with incident stroke to improve patient outcomes.

Sex disparity in subsequent outcomes in survivors of coronary heart disease.

OBJECTIVE: Evidence on sex differences in outcomes after developing coronary heart disease (CHD) has focused on recurrent CHD, all-cause mortality or revascularisation. We assessed sex disparities in subsequent major adverse cardiovascular events (MACE) in adults surviving their first-time CHD. METHODS: Using a population-based cohort obtained from the Clinical Practice Research Datalink (CPRD GOLD) linked to hospitalisation and death records in the UK, we identified 143 702 adults (aged ≥18 years) between 1 January 1998 and 31 December 2017 with no prior history of MACE. MACE outcome was a composite of recurrent CHD, stroke, peripheral vascular disease, heart failure and cardiovascular-related mortality. Multivariable models (Cox and competing risks regressions) were used to assess differences between sexes. RESULTS: There were 143 702 adults with any incident CHD (either angina, myocardial infarction or coronary revascularisation). Women (n=63 078, 43.9%) were older than men (median age, 73 vs 66 years). First subsequent MACE outcome was observed in 91 706 (63.8%). Women had a significantly lower risk of MACE (hazard ratio (HR), 0.68 (95% CI 0.67 to 0.69); sub-hazard ratio (HRsd), 0.71 (0.70 to 0.72), respectively) and recurrent CHD (n=66 543, 46.3%) (HR, 0.60 (0.59 to 0.61); HRsd, 0.62 (0.61 to 0.63)) when compared with men after incident CHD. However, women had a significantly higher risk of stroke (n=5740, 4.0%) (HR, 1.26 (1.19 to 1.33); HRsd, 1.32 (1.25 to 1.39)), heart failure (n=7905, 5.5%) (HR, 1.09 (1.04 to 1.15); HRsd, 1.13 (1.07 to 1.18)) and all-cause mortality (n=29 503, 20.5%) (HR, 1.05 (1.02 to 1.07); HRsd, 1.11 (1.08 to 1.13)). CONCLUSIONS: After incident CHD, women have lower risk of composite MACE and recurrent CHD outcomes but higher risk of stroke, heart failure, and all-cause mortality compared with men.

Strategies for screening for familial hypercholesterolaemia in primary care and other community settings.

BACKGROUND: Familial hypercholesterolaemia is a common inherited condition that is associated with premature cardiovascular disease. The increased cardiovascular morbidity and mortality, resulting from high levels of cholesterol since birth, can be prevented by starting lipid-lowering therapy. However, the majority of patients in the UK and worldwide remain undiagnosed. Established diagnostic criteria in current clinical practice are the Simon-Broome and Dutch Lipid Clinical network criteria and patients are classified as having probable, possible or definite familial hypercholesterolaemia. OBJECTIVES: To assess the effectiveness of healthcare interventions strategies to systematically improve identification of familial hypercholesterolaemia in primary care and other community settings compared to usual care (incidental approaches to identify familial hypercholesterolaemia in primary care and other community settings). SEARCH METHODS: We searched the Cochrane Inborn Errors of Metabolism Trials Register. Date of last search: 13 September 2021. We also searched databases (Cochrane Central Register of Controlled Trials (CENTRAL), Ovid MEDLINE, PubMed, Embase, CINAHL, Web of Science, and SCOPUS) as well as handsearching relevant conference proceedings, reference lists of included articles, and the grey literature. Date of last searches: 05 March 2020.  SELECTION CRITERIA: As per the Effective Practice and Organisation of Care (EPOC) Group guidelines, we planned to include randomised controlled trials (RCTs), cluster-RCTs and non-randomised studies of interventions (NRSI). Eligible NRSI were non-randomised controlled trials, prospective cohort studies, controlled before-and-after studies, and interrupted-time-series studies. We planned to selected studies with healthcare interventions strategies that aimed to systematically identify people with possible or definite clinical familial hypercholesterolaemia, in primary care and other community settings. These strategies would be compared with usual care or no intervention. We considered participants of any age from the general population who access primary care and other community settings. DATA COLLECTION AND ANALYSIS: Two authors planned to independently select studies according to the inclusion criteria, to extract data and assess for risk of bias and the certainty of the evidence (according to the GRADE criteria). We contacted corresponding study authors in order to obtain further information for all the studies considered in the review. MAIN RESULTS: No eligible RCTs or NRSIs were identified for inclusion, however, we excluded 28 studies. AUTHORS' CONCLUSIONS: Currently, there are no RCTs or controlled NRSI evidence to determine the most appropriate healthcare strategy to systematically identify possible or definite clinical familial hypercholesterolaemia in primary care or other community settings. Uncontrolled before-and-after studies were identified, but were not eligible for inclusion. Further studies assessing healthcare strategies of systematic identification of familial hypercholesterolaemia need to be conducted with diagnosis confirmed by genetic testing or validated through clinical phenotype (or both).

Case-finding and genetic testing for familial hypercholesterolaemia in primary care.

OBJECTIVE: Familial hypercholesterolaemia (FH) is a common inherited disorder that remains mostly undetected in the general population. Through FH case-finding and direct access to genetic testing in primary care, this intervention study described the genetic and lipid profile of patients found at increased risk of FH and the outcomes in those with positive genetic test results. METHODS: In 14 Central England general practices, a novel case-finding tool (Familial Hypercholetserolaemia Case Ascertainment Tool, FAMCAT1) was applied to the electronic health records of 86 219 patients with cholesterol readings (44.5% of total practices' population), identifying 3375 at increased risk of FH. Of these, a cohort of 336 consenting to completing Family History Questionnaire and detailed review of their clinical data, were offered FH genetic testing in primary care. RESULTS: Genetic testing was completed by 283 patients, newly identifying 16 with genetically confirmed FH and 10 with variants of unknown significance. All 26 (9%) were recommended for referral and 19 attended specialist assessment. In a further 153 (54%) patients, the test suggested polygenic hypercholesterolaemia who were managed in primary care. Total cholesterol and low-density lipoprotein-cholesterol levels were higher in those patients with FH-causing variants than those with other genetic test results (p=0.010 and p=0.002). CONCLUSION: Electronic case-finding and genetic testing in primary care could improve identification of FH; and the better targeting of patients for specialist assessment. A significant proportion of patients identified at risk of FH are likely to have polygenic hypercholesterolaemia. There needs to be a clearer management plan for these individuals in primary care. TRIAL REGISTRATION NUMBER: NCT03934320.

Obesity and long-term outcomes after incident stroke: a prospective population-based cohort study.

BACKGROUND: The association between obesity, major adverse cardiovascular events (MACE), and mortality in patients with incident stroke is not well established. We assessed the relationship between body mass index (BMI) and MACE in patients with incident stroke. METHODS: The population-based cohort study identified 30 702 individuals from the Clinical Practice Research Datalink (CPRD GOLD) and Hospital Episode Statistics (HES) databases from the United Kingdom. Individuals were aged ≥18 years with incident stroke between 1-1-1998 and 31-12-2017, a BMI recorded within 24 months before incident stroke, and no prior history of MACE. BMI was categorized as underweight (<18.5 kg/m2 ), normal (18.5-24.9 kg/m2 ), overweight (25.0-29.9 kg/m2 ), obesity class I (30.0-34.9 kg/m2 ), class II (35.0-39.9 kg/m2 ) and class III (≥40 kg/m2). MACE was defined as a composite of incident coronary heart disease, recurrent stroke, peripheral vascular disease (PVD), heart failure, and cardiovascular-related mortality. Multivariable Cox regression was used to assess differences in MACE risk between BMI categories. RESULTS: At baseline, 1217 (4.0%) were underweight, 10 783 (35.1%) had a normal BMI, 10 979 (35.8%) had overweight, 5206 (17.0%) had obesity Class I, 1749 (5.7%) Class II, and 768 (2.5%) Class III. In multivariable analysis, higher BMI were associated with lower risk of subsequent MACE [overweight: HR 0.96, 95% CI 0.93-0.99)]; PVD [overweight: 0.65 (0.49-0.85); obesity Class III: 0.19 (0.50-0.77)]; cardiovascular-related death [overweight: 0.80 (0.74-0.86); obesity Class I: 0.79 (0.71-0.88); Class II: 0.80 (0.67-0.96)]; and all-cause mortality [overweight: 0.75 (0.71-0.79); obesity Class I: 0.75 (0.70-0.81); Class II: 0.77 (0.68-0.86)] when compared to those with normal BMI. The results were similar irrespective of sex, diabetes mellitus, smoking or cancer at time of incident stroke. CONCLUSIONS: In patients with incident stroke, overweight or obesity were associated with a more favourable prognosis for subsequent MACE, PVD, and mortality, irrespective of sex, diabetes mellitus, smoking, or cancer at baseline. As with other cohort studies, our study demonstrates an association. Randomized control trials should be considered to robustly evaluate the impact of weight management recommendations on subsequent cardiovascular outcomes in stroke survivors.

Assessing the severity of cardiovascular disease in 213 088 patients with coronary heart disease: a retrospective cohort study.

OBJECTIVE: Most current cardiovascular disease (CVD) risk stratification tools are for people without CVD, but very few are for prevalent CVD. In this study, we developed and validated a CVD severity score in people with coronary heart disease (CHD) and evaluated the association between severity and adverse outcomes. METHODS: Primary and secondary care data for 213 088 people with CHD in 398 practices in England between 2007 and 2017 were used. The cohort was randomly divided into training and validation datasets (80%/20%) for the severity model. Using 20 clinical severity indicators (each assigned a weight=1), baseline and longitudinal CVD severity scores were calculated as the sum of indicators. Adjusted Cox and competing-risk regression models were used to estimate risks for all-cause and cause-specific hospitalisation and mortality. RESULTS: Mean age was 64.5±12.7 years, 46% women, 16% from deprived areas, baseline severity score 1.5±1.2, with higher scores indicating a higher burden of disease. In the training dataset, 138 510 (81%) patients were hospitalised at least once, and 39 944 (23%) patients died. Each 1-unit increase in baseline severity was associated with 41% (95% CI 37% to 45%, area under the receiver operating characteristics (AUROC) curve=0.79) risk for 1 year for all-cause mortality; 59% (95% CI 52% to 67%, AUROC=0.80) for cardiovascular (CV)/diabetes mortality; 27% (95% CI 26% to 28%) for any-cause hospitalisation and 37% (95% CI 36% to 38%) for CV/diabetes hospitalisation. Findings were consistent in the validation dataset. CONCLUSIONS: Higher CVD severity score is associated with higher risks for any-cause and cause-specific hospital admissions and mortality in people with CHD. Our reproducible score based on routinely collected data can help practitioners better prioritise management of people with CHD in primary care.

Sex, Age, and Socioeconomic Differences in Nonfatal Stroke Incidence and Subsequent Major Adverse Outcomes.

BACKGROUND AND PURPOSE: Data about variations in stroke incidence and subsequent major adverse outcomes are essential to inform secondary prevention and prioritizing resources to those at the greatest risk of major adverse end points. We aimed to describe the age, sex, and socioeconomic differences in the rates of first nonfatal stroke and subsequent major adverse outcomes. METHODS: The cohort study used linked Clinical Practice Research Datalink and Hospital Episode Statistics data from the United Kingdom. The incidence rate (IR) ratio of first nonfatal stroke and subsequent major adverse outcomes (composite major adverse cardiovascular events, recurrent stroke, cardiovascular disease-related, and all-cause mortality) were calculated and presented by year, sex, age group, and socioeconomic status based on an individual's location of residence, in adults with incident nonfatal stroke diagnosis between 1998 and 2017. RESULTS: A total of 82 774 first nonfatal stroke events were recorded in either primary care or hospital data-an IR of 109.20 per 100 000 person-years (95% CI, 108.46-109.95). Incidence was significantly higher in women compared with men (IR ratio, 1.13 [95% CI, 1.12-1.15]; P<0.001). Rates adjusted for age and sex were higher in the lowest compared with the highest socioeconomic status group (IR ratio, 1.10 [95% CI, 1.08-1.13]; P<0.001). For subsequent major adverse outcomes, the overall incidence for major adverse cardiovascular event was 38.05 per 100 person-years (95% CI, 37.71-38.39) with a slightly higher incidence in women compared with men (38.42 versus 37.62; IR ratio, 1.02 [95% CI, 1.00-1.04]; P=0.0229). Age and socioeconomic status largely accounted for the observed higher incidence of adverse outcomes in women. CONCLUSIONS: In the United Kingdom, incidence of initial stroke and subsequent major adverse outcomes are higher in women, older populations, and people living in socially deprived areas.

Performance and clinical utility of supervised machine-learning approaches in detecting familial hypercholesterolaemia in primary care.

Familial hypercholesterolaemia (FH) is a common inherited disorder, causing lifelong elevated low-density lipoprotein cholesterol (LDL-C). Most individuals with FH remain undiagnosed, precluding opportunities to prevent premature heart disease and death. Some machine-learning approaches improve detection of FH in electronic health records, though clinical impact is under-explored. We assessed performance of an array of machine-learning approaches for enhancing detection of FH, and their clinical utility, within a large primary care population. A retrospective cohort study was done using routine primary care clinical records of 4,027,775 individuals from the United Kingdom with total cholesterol measured from 1 January 1999 to 25 June 2019. Predictive accuracy of five common machine-learning algorithms (logistic regression, random forest, gradient boosting machines, neural networks and ensemble learning) were assessed for detecting FH. Predictive accuracy was assessed by area under the receiver operating curves (AUC) and expected vs observed calibration slope; with clinical utility assessed by expected case-review workload and likelihood ratios. There were 7928 incident diagnoses of FH. In addition to known clinical features of FH (raised total cholesterol or LDL-C and family history of premature coronary heart disease), machine-learning (ML) algorithms identified features such as raised triglycerides which reduced the likelihood of FH. Apart from logistic regression (AUC, 0.81), all four other ML approaches had similarly high predictive accuracy (AUC > 0.89). Calibration slope ranged from 0.997 for gradient boosting machines to 1.857 for logistic regression. Among those screened, high probability cases requiring clinical review varied from 0.73% using ensemble learning to 10.16% using deep learning, but with positive predictive values of 15.5% and 2.8% respectively. Ensemble learning exhibited a dominant positive likelihood ratio (45.5) compared to all other ML models (7.0-14.4). Machine-learning models show similar high accuracy in detecting FH, offering opportunities to increase diagnosis. However, the clinical case-finding workload required for yield of cases will differ substantially between models.

Predicting major adverse cardiovascular events for secondary prevention: protocol for a systematic review and meta-analysis of risk prediction models.

INTRODUCTION: Cardiovascular disease (CVD) is the leading cause of morbidity and mortality globally. With advances in early diagnosis and treatment of CVD and increasing life expectancy, more people are surviving initial CVD events. However, models for stratifying disease severity risk in patients with established CVD for effective secondary prevention strategies are inadequate. Multivariable prognostic models to stratify CVD risk may allow personalised treatment interventions. This review aims to systematically review the existing multivariable prognostic models for the recurrence of CVD or major adverse cardiovascular events in adults with established CVD diagnosis. METHODS AND ANALYSIS: Bibliographic databases (Ovid MEDLINE, EMBASE, PsycINFO and Web of Science) will be searched, from database inception to April 2020, using terms relating to the clinical area and prognosis. A hand search of the reference lists of included studies will also be done to identify additional published studies. No restrictions on language of publications will be applied. Eligible studies present multivariable models (derived or validated) of adults (aged 16 years and over) with an established diagnosis of CVD, reporting at least one of the components of the primary outcome of major adverse cardiovascular events (defined as either coronary heart disease, stroke, peripheral artery disease, heart failure or CVD-related mortality). Reviewing will be done by two reviewers independently using the pre-defined criteria. Data will be extracted for included full-text articles. Risk of bias will be assessed using the Prediction model study Risk Of Bias ASsessment Tool (PROBAST). Prognostic models will be summarised narratively. If a model is tested in multiple validation studies, the predictive performance will be summarised using a random-effects meta-analysis model to account for any between-study heterogeneity. ETHICS AND DISSEMINATION: Ethics approval is not required. The results of this study will be submitted to relevant conferences for presentation and a peer-reviewed journal for publication. PROSPERO REGISTRATION NUMBER: CRD42019149111.

Correction to: The comorbidity burden of type 2 diabetes mellitus: patterns, clusters and predictions from a large English primary care cohort.

The original article [1] contains an omitted grant acknowledgement and affiliation as relates to the contribution of co-author, Rafael Perera-Salazar. As such, the following two amendments should apply to the original article.

The comorbidity burden of type 2 diabetes mellitus: patterns, clusters and predictions from a large English primary care cohort.

BACKGROUND: The presence of additional chronic conditions has a significant impact on the treatment and management of type 2 diabetes (T2DM). Little is known about the patterns of comorbidities in this population. The aims of this study are to quantify comorbidity patterns in people with T2DM, to estimate the prevalence of six chronic conditions in 2027 and to identify clusters of similar conditions. METHODS: We used the Clinical Practice Research Datalink (CPRD) linked with the Index of Multiple Deprivation (IMD) data to identify patients diagnosed with T2DM between 2007 and 2017. 102,394 people met the study inclusion criteria. We calculated the crude and age-standardised prevalence of 18 chronic conditions present at and after the T2DM diagnosis. We analysed longitudinally the 6 most common conditions and forecasted their prevalence in 2027 using linear regression. We used agglomerative hierarchical clustering to identify comorbidity clusters. These analyses were repeated on subgroups stratified by gender and deprivation. RESULTS: More people living in the most deprived areas had ≥ 1 comorbidities present at the time of diagnosis (72% of females; 64% of males) compared to the most affluent areas (67% of females; 59% of males). Depression prevalence increased in all strata and was more common in the most deprived areas. Depression was predicted to affect 33% of females and 15% of males diagnosed with T2DM in 2027. Moderate clustering tendencies were observed, with concordant conditions grouped together and some variations between groups of different demographics. CONCLUSIONS: Comorbidities are common in this population, and high between-patient variability in comorbidity patterns emphasises the need for patient-centred healthcare. Mental health is a growing concern, and there is a need for interventions that target both physical and mental health in this population.

Sub-optimal cholesterol response to initiation of statins and future risk of cardiovascular disease.

OBJECTIVE: To assess low-density lipoprotein cholesterol (LDL-C) response in patients after initiation of statins, and future risk of cardiovascular disease (CVD). METHODS: Prospective cohort study of 165 411 primary care patients, from the UK Clinical Practice Research Datalink, who were free of CVD before statin initiation, and had at least one pre-treatment LDL-C within 12 months before, and one post-treatment LDL-C within 24 months after, statin initiation. Based on current national guidelines, <40% reduction in baseline LDL-C within 24 months was classified as a sub-optimal statin response. Cox proportional regression and competing-risks survival regression models were used to determine adjusted hazard ratios (HRs) and sub-HRs for incident CVD outcomes for LDL-C response to statins. RESULTS: 84 609 (51.2%) patients had a sub-optimal LDL-C response to initiated statin therapy within 24 months. During 1 077 299 person-years of follow-up (median follow-up 6.2 years), there were 22 798 CVD events (12 142 in sub-optimal responders and 10 656 in optimal responders). In sub-optimal responders, compared with optimal responders, the HR for incident CVD was 1.17 (95% CI 1.13 to 1.20) and 1.22 (95% CI 1.19 to 1.25) after adjusting for age and baseline untreated LDL-C. Considering competing risks resulted in lower but similar sub-HRs for both unadjusted (1.13, 95% CI 1.10 to 1.16) and adjusted (1.19, 95% CI 1.16 to 1.23) cumulative incidence function of CVD. CONCLUSIONS: Optimal lowering of LDL-C is not achieved within 2 years in over half of patients in the general population initiated on statin therapy, and these patients will experience significantly increased risk of future CVD.

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches.

BACKGROUND: Prognostic modelling using standard methods is well-established, particularly for predicting risk of single diseases. Machine-learning may offer potential to explore outcomes of even greater complexity, such as premature death. This study aimed to develop novel prediction algorithms using machine-learning, in addition to standard survival modelling, to predict premature all-cause mortality. METHODS: A prospective population cohort of 502,628 participants aged 40-69 years were recruited to the UK Biobank from 2006-2010 and followed-up until 2016. Participants were assessed on a range of demographic, biometric, clinical and lifestyle factors. Mortality data by ICD-10 were obtained from linkage to Office of National Statistics. Models were developed using deep learning, random forest and Cox regression. Calibration was assessed by comparing observed to predicted risks; and discrimination by area under the 'receiver operating curve' (AUC). FINDINGS: 14,418 deaths (2.9%) occurred over a total follow-up time of 3,508,454 person-years. A simple age and gender Cox model was the least predictive (AUC 0.689, 95% CI 0.681-0.699). A multivariate Cox regression model significantly improved discrimination by 6.2% (AUC 0.751, 95% CI 0.748-0.767). The application of machine-learning algorithms further improved discrimination by 3.2% using random forest (AUC 0.783, 95% CI 0.776-0.791) and 3.9% using deep learning (AUC 0.790, 95% CI 0.783-0.797). These ML algorithms improved discrimination by 9.4% and 10.1% respectively from a simple age and gender Cox regression model. Random forest and deep learning achieved similar levels of discrimination with no significant difference. Machine-learning algorithms were well-calibrated, while Cox regression models consistently over-predicted risk. CONCLUSIONS: Machine-learning significantly improved accuracy of prediction of premature all-cause mortality in this middle-aged population, compared to standard methods. This study illustrates the value of machine-learning for risk prediction within a traditional epidemiological study design, and how this approach might be reported to assist scientific verification.

Preconception risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease.

BACKGROUND: Globally, about five per cent of children are born with congenital or genetic disorders. The most common autosomal recessive conditions are thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease, with higher carrier rates in specific patient populations. Identifying and counselling couples at genetic risk of the conditions before pregnancy enables them to make fully informed reproductive decisions, with some of these choices not being available if genetic counselling is only offered in an antenatal setting. This is an update of a previously published review. OBJECTIVES: To assess the effectiveness of systematic preconception genetic risk assessment to improve reproductive outcomes in women and their partners who are identified as carriers of thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease in healthcare settings when compared to usual care. SEARCH METHODS: We searched the Cochrane Cystic Fibrosis and Genetic Disorders Group's Trials Registers. In addition, we searched for all relevant trials from 1970 (or the date at which the database was first available if after 1970) to date using electronic databases (MEDLINE, Embase, CINAHL, PsycINFO), clinical trial databases (National Institutes of Health, Clinical Trials Search portal of the World Health Organization, metaRegister of controlled clinical trials), and hand searching of key journals and conference abstract books from 1998 to date (European Journal of Human Genetics, Genetics in Medicine, Journal of Community Genetics). We also searched the reference lists of relevant articles, reviews and guidelines and also contacted subject experts in the field to request any unpublished or other published trials.Date of latest search of the registers: 20 June 2017.Date of latest search of all other sources: 16 November 2017. SELECTION CRITERIA: Any randomised or quasi-randomised controlled trials (published or unpublished) comparing reproductive outcomes of systematic preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease when compared to usual care. DATA COLLECTION AND ANALYSIS: We identified 25 papers, describing 16 unique trials which were potentially eligible for inclusion in the review. However, after assessment, no randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease were found. MAIN RESULTS: No randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease were included. One ongoing trial has been identified which may potentially eligible for inclusion once completed. AUTHORS' CONCLUSIONS: As no randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis, or Tay-Sachs disease were found for inclusion in this review, the research evidence for current policy recommendations is limited to non-randomised studies.Information from well-designed, adequately powered, randomised trials is desirable in order to make more robust recommendations for practice. However, such trials must also consider the legal, ethical, and cultural barriers to implementation of preconception genetic risk assessment.

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

BACKGROUND: Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. METHODS: Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the 'receiver operating curve' (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). FINDINGS: 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723-0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739-0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755-0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755-0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759-0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. CONCLUSIONS: Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others.

The value of aspartate aminotransferase and alanine aminotransferase in cardiovascular disease risk assessment.

OBJECTIVE: Aspartate aminotransferase to alanine aminotransferase (AST/ALT) ratio, reflecting liver disease severity, has been associated with increased risk of cardiovascular disease (CVD). The aim of this study was to evaluate whether the AST/ALT ratio improves established risk prediction tools in a primary care population. METHODS: Data were analysed from a prospective cohort of 29 316 UK primary care patients, aged 25-84 years with no history of CVD at baseline. Cox proportional hazards regression was used to derive 10-year multivariate risk models for the first occurrence of CVD based on two established risk prediction tools (Framingham and QRISK2), with and without including the AST/ALT ratio. Overall, model performance was assessed by discriminatory accuracy (AUC c-statistic). RESULTS: During a total follow-up of 120 462 person-years, 782 patients (59% men) experienced their first CVD event. Multivariate models showed that elevated AST/ALT ratios were significantly associated with CVD in men (Framingham: HR 1.37, 95% CI 1.05 to 1.79; QRISK2: HR 1.40, 95% CI 1.04 to 1.89) but not in women (Framingham: HR 1.06, 95% CI 0.78 to 1.43; QRISK2: HR 0.97, 95% CI 0.70 to 1.35). Including the AST/ALT ratio with all Framingham risk factors (AUC c-statistic: 0.72, 95% CI 0.71 to 0.74) or QRISK2 risk factors (AUC c-statistic: 0.73, 95% CI 0.71 to 0.74) resulted in no change in discrimination from the established risk prediction tools. Limiting analysis to those individuals with raised ALT showed that discrimination could improve by 5% and 4% with Framingham and QRISK2 risk factors, respectively. CONCLUSIONS: Elevated AST/ALT ratio is significantly associated with increased risk of developing CVD in men but not women. However, the ratio does not confer any additional benefits over established CVD risk prediction tools in the general population, but may have clinical utility in certain subgroups.

Preconception risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease.

BACKGROUND: Globally, about five per cent of children are born with congenital or genetic disorders. The most common autosomal recessive conditions are thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease, with higher carrier rates in specific patient populations. Identifying and counselling couples at genetic risk of the conditions before pregnancy enables them to make fully informed reproductive decisions, with some of these choices not being available if genetic counselling is only offered in an antenatal setting. OBJECTIVES: To assess the effectiveness of systematic preconception genetic risk assessment to improve reproductive outcomes in women and their partners who are identified as carriers of thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease in healthcare settings when compared to usual care. SEARCH METHODS: We searched the Cochrane Cystic Fibrosis and Genetic Disorders Group's Trials Registers. In addition, we searched for all relevant trials from 1970 (or the date at which the database was first available if after 1970) to date using electronic databases (MEDLINE, Embase, CINAHL, PsycINFO), clinical trial databases (National Institutes of Health, Clinical Trials Search portal of the World Health Organization, metaRegister of controlled clinical trials), and hand searching of key journals and conference abstract books from 1998 to date (European Journal of Human Genetics, Genetics in Medicine, Journal of Community Genetics). We also searched the reference lists of relevant articles, reviews and guidelines and also contacted subject experts in the field to request any unpublished or other published trials.Date of latest search of the registers: 25 June 2015.Date of latest search of all other sources: 10 December 2014. SELECTION CRITERIA: Any randomised or quasi-randomised control trials (published or unpublished) comparing reproductive outcomes of systematic preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease when compared to usual care. DATA COLLECTION AND ANALYSIS: We identified 19 papers, describing 13 unique trials which were potentially eligible for inclusion in the review. However, after assessment, no randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease were found. MAIN RESULTS: No randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis and Tay-Sachs disease were found. AUTHORS' CONCLUSIONS: As no randomised controlled trials of preconception genetic risk assessment for thalassaemia, sickle cell disease, cystic fibrosis, or Tay-Sachs disease were found for inclusion in this review, the research evidence for current policy recommendations is limited to non-randomised studies.Information from well-designed, adequately powered, randomised trials is desirable in order to make more robust recommendations for practice. However, such trials must also consider the legal, ethical, and cultural barriers to implementation of preconception genetic risk assessment.

Improving identification of familial hypercholesterolaemia in primary care: derivation and validation of the familial hypercholesterolaemia case ascertainment tool (FAMCAT).

OBJECTIVE: Heterozygous familial hypercholesterolaemia (FH) is a common autosomal dominant disorder. The vast majority of affected individuals remain undiagnosed, resulting in lost opportunities for preventing premature heart disease. Better use of routine primary care data offers an opportunity to enhance detection. We sought to develop a new predictive algorithm for improving identification of individuals in primary care who could be prioritised for further clinical assessment using established diagnostic criteria. METHODS: Data were analysed for 2,975,281 patients with total or LDL-cholesterol measurement from 1 Jan 1999 to 31 August 2013 using the Clinical Practice Research Datalink (CPRD). Included in this cohort study were 5050 documented cases of FH. Stepwise logistic regression was used to derive optimal multivariate prediction models. Model performance was assessed by its discriminatory accuracy (area under receiver operating curve [AUC]). RESULTS: The FH prediction model (FAMCAT), consisting of nine diagnostic variables, showed high discrimination (AUC 0.860, 95% CI 0.848-0.871) for distinguishing cases from non-cases. Sensitivity analysis demonstrated no significant drop in discrimination (AUC 0.858, 95% CI 0.845-0.869) after excluding secondary causes of hypercholesterolaemia. Removing family history variables reduced discrimination (AUC 0.820, 95% CI 0.807-0.834), while incorporating more comprehensive family history recording of myocardial infraction significantly improved discrimination (AUC 0.894, 95% CI 0.884-0.904). CONCLUSION: This approach offers the opportunity to enhance detection of FH in primary care by identifying individuals with greatest probability of having the condition. Such cases can be prioritised for further clinical assessment, appropriate referral and treatment to prevent premature heart disease.