Identifying patients with undiagnosed small intestinal neuroendocrine tumours in primary care using statistical and machine learning: model development and validation study.

BACKGROUND: Neuroendocrine tumours (NETs) are increasing in incidence, often diagnosed at advanced stages, and individuals may experience years of diagnostic delay, particularly when arising from the small intestine (SI). Clinical prediction models could present novel opportunities for case finding in primary care. METHODS: An open cohort of adults (18+ years) contributing data to the Optimum Patient Care Research Database between 1st Jan 2000 and 30th March 2023 was identified. This database collects de-identified data from general practices in the UK. Model development approaches comprised logistic regression, penalised regression, and XGBoost. Performance (discrimination and calibration) was assessed using internal-external cross-validation. Decision analysis curves compared clinical utility. RESULTS: Of 11.7 million individuals, 382 had recorded SI NET diagnoses (0.003%). The XGBoost model had the highest AUC (0.869, 95% confidence interval [CI]: 0.841-0.898) but was mildly miscalibrated (slope 1.165, 95% CI: 1.088-1.243; calibration-in-the-large 0.010, 95% CI: -0.164 to 0.185). Clinical utility was similar across all models. DISCUSSION: Multivariable prediction models may have clinical utility in identifying individuals with undiagnosed SI NETs using information in their primary care records. Further evaluation including external validation and health economics modelling may identify cost-effective strategies for case finding for this uncommon tumour.

Predicting the risk of pancreatic cancer in adults with new-onset diabetes: development and internal-external validation of a clinical risk prediction model.

BACKGROUND: The National Institute for Health and Care Excellence (NICE) recommends that people aged 60+ years with newly diagnosed diabetes and weight loss undergo abdominal imaging to assess for pancreatic cancer. More nuanced stratification could lead to enrichment of these referral pathways. METHODS: Population-based cohort study of adults aged 30-85 years at type 2 diabetes diagnosis (2010-2021) using the QResearch primary care database in England linked to secondary care data, the national cancer registry and mortality registers. Clinical prediction models were developed to estimate risks of pancreatic cancer diagnosis within 2 years and evaluated using internal-external cross-validation. RESULTS: Seven hundred and sixty-seven of 253,766 individuals were diagnosed with pancreatic cancer within 2 years. Models included age, sex, BMI, prior venous thromboembolism, digoxin prescription, HbA1c, ALT, creatinine, haemoglobin, platelet count; and the presence of abdominal pain, weight loss, jaundice, heartburn, indigestion or nausea (previous 6 months). The Cox model had the highest discrimination (Harrell's C-index 0.802 (95% CI: 0.797-0.817)), the highest clinical utility, and was well calibrated. The model's highest 1% of predicted risks captured 12.51% of pancreatic cancer cases. NICE guidance had 3.95% sensitivity. DISCUSSION: A new prediction model could have clinical utility in identifying individuals with recent onset diabetes suitable for fast-track abdominal imaging.

Predicting 10-year breast cancer mortality risk in the general female population in England: a model development and validation study.

BACKGROUND: Identifying female individuals at highest risk of developing life-threatening breast cancers could inform novel stratified early detection and prevention strategies to reduce breast cancer mortality, rather than only considering cancer incidence. We aimed to develop a prognostic model that accurately predicts the 10-year risk of breast cancer mortality in female individuals without breast cancer at baseline. METHODS: In this model development and validation study, we used an open cohort study from the QResearch primary care database, which was linked to secondary care and national cancer and mortality registers in England, UK. The data extracted were from female individuals aged 20-90 years without previous breast cancer or ductal carcinoma in situ who entered the cohort between Jan 1, 2000, and Dec 31, 2020. The primary outcome was breast cancer-related death, which was assessed in the full dataset. Cox proportional hazards, competing risks regression, XGBoost, and neural network modelling approaches were used to predict the risk of breast cancer death within 10 years using routinely collected health-care data. Death due to causes other than breast cancer was the competing risk. Internal-external validation was used to evaluate prognostic model performance (using Harrell's C, calibration slope, and calibration in the large), performance heterogeneity, and transportability. Internal-external validation involved dataset partitioning by time period and geographical region. Decision curve analysis was used to assess clinical utility. FINDINGS: We identified data for 11 626 969 female individuals, with 70 095 574 person-years of follow-up. There were 142 712 (1·2%) diagnoses of breast cancer, 24 043 (0·2%) breast cancer-related deaths, and 696 106 (6·0%) deaths from other causes. Meta-analysis pooled estimates of Harrell's C were highest for the competing risks model (0·932, 95% CI 0·917-0·946). The competing risks model was well calibrated overall (slope 1·011, 95% CI 0·978-1·044), and across different ethnic groups. Decision curve analysis suggested favourable clinical utility across all age groups. The XGBoost and neural network models had variable performance across age and ethnic groups. INTERPRETATION: A model that predicts the combined risk of developing and then dying from breast cancer at the population level could inform stratified screening or chemoprevention strategies. Further evaluation of the competing risks model should comprise effect and health economic assessment of model-informed strategies. FUNDING: Cancer Research UK.

Development and internal-external validation of statistical and machine learning models for breast cancer prognostication: cohort study.

OBJECTIVE: To develop a clinically useful model that estimates the 10 year risk of breast cancer related mortality in women (self-reported female sex) with breast cancer of any stage, comparing results from regression and machine learning approaches. DESIGN: Population based cohort study. SETTING: QResearch primary care database in England, with individual level linkage to the national cancer registry, Hospital Episodes Statistics, and national mortality registers. PARTICIPANTS: 141 765 women aged 20 years and older with a diagnosis of invasive breast cancer between 1 January 2000 and 31 December 2020. MAIN OUTCOME MEASURES: Four model building strategies comprising two regression (Cox proportional hazards and competing risks regression) and two machine learning (XGBoost and an artificial neural network) approaches. Internal-external cross validation was used for model evaluation. Random effects meta-analysis that pooled estimates of discrimination and calibration metrics, calibration plots, and decision curve analysis were used to assess model performance, transportability, and clinical utility. RESULTS: During a median 4.16 years (interquartile range 1.76-8.26) of follow-up, 21 688 breast cancer related deaths and 11 454 deaths from other causes occurred. Restricting to 10 years maximum follow-up from breast cancer diagnosis, 20 367 breast cancer related deaths occurred during a total of 688 564.81 person years. The crude breast cancer mortality rate was 295.79 per 10 000 person years (95% confidence interval 291.75 to 299.88). Predictors varied for each regression model, but both Cox and competing risks models included age at diagnosis, body mass index, smoking status, route to diagnosis, hormone receptor status, cancer stage, and grade of breast cancer. The Cox model's random effects meta-analysis pooled estimate for Harrell's C index was the highest of any model at 0.858 (95% confidence interval 0.853 to 0.864, and 95% prediction interval 0.843 to 0.873). It appeared acceptably calibrated on calibration plots. The competing risks regression model had good discrimination: pooled Harrell's C index 0.849 (0.839 to 0.859, and 0.821 to 0.876, and evidence of systematic miscalibration on summary metrics was lacking. The machine learning models had acceptable discrimination overall (Harrell's C index: XGBoost 0.821 (0.813 to 0.828, and 0.805 to 0.837); neural network 0.847 (0.835 to 0.858, and 0.816 to 0.878)), but had more complex patterns of miscalibration and more variable regional and stage specific performance. Decision curve analysis suggested that the Cox and competing risks regression models tested may have higher clinical utility than the two machine learning approaches. CONCLUSION: In women with breast cancer of any stage, using the predictors available in this dataset, regression based methods had better and more consistent performance compared with machine learning approaches and may be worthy of further evaluation for potential clinical use, such as for stratified follow-up.

Ethnic disparities in COVID-19 outcomes: a multinational cohort study of 20 million individuals from England and Canada.

BACKGROUND: Heterogeneous studies have demonstrated ethnic inequalities in the risk of SARS-CoV-2 infection and adverse COVID-19 outcomes. This study evaluates the association between ethnicity and COVID-19 outcomes in two large population-based cohorts from England and Canada and investigates potential explanatory factors for ethnic patterning of severe outcomes. METHODS: We identified adults aged 18 to 99 years in the QResearch primary care (England) and Ontario (Canada) healthcare administrative population-based datasets (start of follow-up: 24th and 25th Jan 2020 in England and Canada, respectively; end of follow-up: 31st Oct and 30th Sept 2020, respectively). We harmonised the definitions and the design of two cohorts to investigate associations between ethnicity and COVID-19-related death, hospitalisation, and intensive care (ICU) admission, adjusted for confounders, and combined the estimates obtained from survival analyses. We calculated the 'percentage of excess risk mediated' by these risk factors in the QResearch cohort. RESULTS: There were 9.83 million adults in the QResearch cohort (11,597 deaths; 21,917 hospitalisations; 2932 ICU admissions) and 10.27 million adults in the Ontario cohort (951 deaths; 5132 hospitalisations; 1191 ICU admissions). Compared to the general population, pooled random-effects estimates showed that South Asian ethnicity was associated with an increased risk of COVID-19 death (hazard ratio: 1.63, 95% CI: 1.09-2.44), hospitalisation (1.53; 1.32-1.76), and ICU admission (1.67; 1.23-2.28). Associations with ethnic groups were consistent across levels of deprivation. In QResearch, sociodemographic, lifestyle, and clinical factors accounted for 42.9% (South Asian) and 39.4% (Black) of the excess risk of COVID-19 death. CONCLUSION: International population-level analyses demonstrate clear ethnic inequalities in COVID-19 risks. Policymakers should be cognisant of the increased risks in some ethnic populations and design equitable health policy as the pandemic continues.

Preexisting Neuropsychiatric Conditions and Associated Risk of Severe COVID-19 Infection and Other Acute Respiratory Infections.

Importance: Evidence indicates that preexisting neuropsychiatric conditions confer increased risks of severe outcomes from COVID-19 infection. It is unclear how this increased risk compares with risks associated with other severe acute respiratory infections (SARIs). Objective: To determine whether preexisting diagnosis of and/or treatment for a neuropsychiatric condition is associated with severe outcomes from COVID-19 infection and other SARIs and whether any observed association is similar between the 2 outcomes. Design, Setting, and Participants: Prepandemic (2015-2020) and contemporary (2020-2021) longitudinal cohorts were derived from the QResearch database of English primary care records. Adjusted hazard ratios (HRs) with 99% CIs were estimated in April 2022 using flexible parametric survival models clustered by primary care clinic. This study included a population-based sample, including all adults in the database who had been registered with a primary care clinic for at least 1 year. Analysis of routinely collected primary care electronic medical records was performed. Exposures: Diagnosis of and/or medication for anxiety, mood, or psychotic disorders and diagnosis of dementia, depression, schizophrenia, or bipolar disorder. Main Outcomes and Measures: COVID-19-related mortality, or hospital or intensive care unit admission; SARI-related mortality, or hospital or intensive care unit admission. Results: The prepandemic cohort comprised 11 134 789 adults (223 569 SARI cases [2.0%]) with a median (IQR) age of 42 (29-58) years, of which 5 644 525 (50.7%) were female. The contemporary cohort comprised 8 388 956 adults (58 203 severe COVID-19 cases [0.7%]) with a median (IQR) age of 48 (34-63) years, of which 4 207 192 were male (50.2%). Diagnosis and/or treatment for neuropsychiatric conditions other than dementia was associated with an increased likelihood of a severe outcome from SARI (anxiety diagnosis: HR, 1.16; 99% CI, 1.13-1.18; psychotic disorder diagnosis and treatment: HR, 2.56; 99% CI, 2.40-2.72) and COVID-19 (anxiety diagnosis: HR, 1.16; 99% CI, 1.12-1.20; psychotic disorder treatment: HR, 2.37; 99% CI, 2.20-2.55). The effect estimate for severe outcome with dementia was higher for those with COVID-19 than SARI (HR, 2.85; 99% CI, 2.71-3.00 vs HR, 2.13; 99% CI, 2.07-2.19). Conclusions and Relevance: In this longitudinal cohort study, UK patients with preexisting neuropsychiatric conditions and treatments were associated with similarly increased risks of severe outcome from COVID-19 infection and SARIs, except for dementia.

The current status of risk-stratified breast screening.

Apart from high-risk scenarios such as the presence of highly penetrant genetic mutations, breast screening typically comprises mammography or tomosynthesis strategies defined by age. However, age-based screening ignores the range of breast cancer risks that individual women may possess and is antithetical to the ambitions of personalised early detection. Whilst screening mammography reduces breast cancer mortality, this is at the risk of potentially significant harms including overdiagnosis with overtreatment, and psychological morbidity associated with false positives. In risk-stratified screening, individualised risk assessment may inform screening intensity/interval, starting age, imaging modality used, or even decisions not to screen. However, clear evidence for its benefits and harms needs to be established. In this scoping review, the authors summarise the established and emerging evidence regarding several critical dependencies for successful risk-stratified breast screening: risk prediction model performance, epidemiological studies, retrospective clinical evaluations, health economic evaluations and qualitative research on feasibility and acceptability. Family history, breast density or reproductive factors are not on their own suitable for precisely estimating risk and risk prediction models increasingly incorporate combinations of demographic, clinical, genetic and imaging-related parameters. Clinical evaluations of risk-stratified screening are currently limited. Epidemiological evidence is sparse, and randomised trials only began in recent years.

Association Between Race and COVID-19 Outcomes Among 2.6 Million Children in England.

Importance: Although children mainly experience mild COVID-19 disease, hospitalization rates are increasing, with limited understanding of underlying factors. There is an established association between race and severe COVID-19 outcomes in adults in England; however, whether a similar association exists in children is unclear. Objective: To investigate the association between race and childhood COVID-19 testing and hospital outcomes. Design, Setting, Participants: In this cohort study, children (0-18 years of age) from participating family practices in England were identified in the QResearch database between January 24 and November 30, 2020. The QResearch database has individually linked patients with national SARS-CoV-2 testing, hospital admission, and mortality data. Exposures: The main characteristic of interest is self-reported race. Other exposures were age, sex, deprivation level, geographic region, household size, and comorbidities (asthma; diabetes; and cardiac, neurologic, and hematologic conditions). Main Outcomes and Measures: The primary outcome was hospital admission with confirmed COVID-19. Secondary outcomes were SARS-CoV-2-positive test result and any hospital attendance with confirmed COVID-19 and intensive care admission. Results: Of 2 576 353 children (mean [SD] age, 9.23 [5.24] years; 48.8% female), 410 726 (15.9%) were tested for SARS-CoV-2 and 26 322 (6.4%) tested positive. A total of 1853 children (0.07%) with confirmed COVID-19 attended hospital, 343 (0.01%) were admitted to the hospital, and 73 (0.002%) required intensive care. Testing varied across race. White children had the highest proportion of SARS-CoV-2 tests (223 701/1 311 041 [17.1%]), whereas Asian children (33 213/243 545 [13.6%]), Black children (7727/93 620 [8.3%]), and children of mixed or other races (18 971/147 529 [12.9%]) had lower proportions. Compared with White children, Asian children were more likely to have COVID-19 hospital admissions (adjusted odds ratio [OR], 1.62; 95% CI, 1.12-2.36), whereas Black children (adjusted OR, 1.44; 95% CI, 0.90-2.31) and children of mixed or other races (adjusted OR, 1.40; 95% CI, 0.93-2.10) had comparable hospital admissions. Asian children were more likely to be admitted to intensive care (adjusted OR, 2.11; 95% CI, 1.07-4.14), and Black children (adjusted OR, 2.31; 95% CI, 1.08-4.94) and children of mixed or other races (adjusted OR, 2.14; 95% CI, 1.25-3.65) had longer hospital admissions (≥36 hours). Conclusions and Relevance: In this large population-based study exploring the association between race and childhood COVID-19 testing and hospital outcomes, several race-specific disparities were observed in severe COVID-19 outcomes. However, ascertainment bias and residual confounding in this cohort study should be considered before drawing any further conclusions. Overall, findings of this study have important public health implications internationally.