Syed Ahmar Shah

BACKGROUND Asthma attacks remain a significant burden on primary care systems, yet predicting individual risk remains challenging. While machine learning shows promise, most existing models are derived from secondary care data or lack robust validation and assessment of clinical utility. OBJECTIVE This study aims to develop and validate machine learning models for predicting 12-month asthma attack risk using UK-wide primary care data, adhering to TRIPOD-AI and RECORD reporting guidelines. METHODS We conducted a retrospective cohort study using the Optimum Patient Care Research Database (OPCRD), comprising more than 600,000 patients with active asthma across England, Scotland, and Wales. Data were split into a training set (England) and a geographical validation/test set (Scotland and Wales). We compared five algorithms: Logistic Regression (LR) as the benchmark model, Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and neural networks (NN) (a combination of fully connected network [FCN] and long short-term memory [LSTM]). We assessed model performance using the Area Under the Receiver Operating Characteristic (ROC) curve (AUC), calibration plots, and Decision Curve Analysis (DCA) to quantify net benefit. RESULTS XGBoost emerged as the top-performing model on both the validation (AUC = 0.816) and test (AUC = 0.788) sets. It achieved 5% higher sensitivity than LR (95% vs 90%) at 62% specificity. At the same specificity (62%), XGBoost identified about five more patients per 100 who had an asthma attack within 12 months than LR, indicating a higher net benefit. Additionally, all other models outperformed LR on the test set (LR AUC: 0.754; DT: 0.770; RF: 0.783; NN: 0.786). Model calibration confirmed reliable probability estimates, and the model interpretation highlighted key predictors, including prior asthma attacks and medication use. CONCLUSIONS These findings indicate that advanced ML approaches substantially improve asthma risk prediction over a conventional regression model. Future work should focus on prospective evaluation and implementation science to determine how to integrate these models into primary care workflows to improve preventive intervention targeting and reduce asthma attacks.

Introduction: Hormonal contraceptive (HC) use has been associated with reduced risk of asthma onset, but it remains unclear whether this protection accumulates with prolonged use or varies over time. Aims: To characterise the temporal pattern of protection against asthma onset associated with HC use, and to assess whether this pattern differs by route of administration. Methods: We constructed a 15-year (2005–2019) open cohort of women aged 16–45 years from the Clinical Practice Research Datalink (N = 2,110,199). HC exposure was derived from prescription records and classified annually. Cox regression models compared alternative exposure definitions, including current use, static lifetime duration, and episode-based duration defined as time since initiation with resetting after discontinuation. Episode-based analyses were conducted overall and repeated by route of administration (oral vs other). Results: Current HC use was associated with a reduced hazard of asthma onset (HR 0.74, 95% CI 0.72–0.75). Static lifetime duration suggested a strong dose–response (≥5 years: HR 0.32, 95% CI 0.31–0.33). In contrast, episode-based analyses showed that protection against asthma onset was strongest shortly after initiation. For oral HC, the hazard of asthma onset was lowest in years 1–2 (HR 0.64, 95% CI 0.62–0.65) and attenuated with duration (≥5 years: HR 0.67, 95% CI 0.64–0.71). HC via other routes showed a similar early reduction (years 1–2: HR 0.72, 95% CI 0.66–0.79) but attenuated more rapidly toward the null. Conclusions: Protection against asthma onset associated with HC use is strongest shortly after initiation and does not appear cumulative. Apparent lifetime dose–responses likely reflect aggregation of repeated early treatment periods across an individual’s prescription history.

Introduction: Hormone replacement therapy (HRT) has been associated with reduced risk of late-onset asthma but it is unclear whether this protection accumulates over time or is primarily linked to treatment initiation. Aims: To investigate the temporal pattern of protection against asthma onset associated with HRT use and assess differences by route of administration. Methods: We analysed a 15-year (2005–2019) open cohort of postmenopausal women aged 46–70 years using the Clinical Practice Research Datalink (N = 1,859,652). HRT exposure was derived from prescription records and classified annually. Cox regression models were used to compare current use, static lifetime duration, and episode-based duration defined as time since initiation, resetting after discontinuation. Episode-based analyses were conducted overall and repeated by route of administration (oral vs other). Results: Current HRT use was associated with a reduced hazard of asthma onset (HR 0.75, 95% CI 0.72–0.77). Static lifetime duration suggested a strong dose–response (≥5 years: HR 0.51, 95% CI 0.49–0.53). Episode-based analyses showed that protection against asthma onset was strongest in the first 1–2 years following initiation, with attenuation thereafter. Oral HRT remained protective at longer durations (≥5 years: HR 0.84, 95% CI 0.78–0.91), whereas HRT via other routes showed early protection (years 1–2: HR 0.86, 95% CI 0.77–0.97) that attenuated toward the null over time. Conclusions: Protection against asthma onset associated with HRT use is strongest shortly after initiation rather than accumulating with prolonged exposure. Episode-based exposure definitions clarify temporal risk patterns that are obscured by static lifetime summaries.

Objective: To identify and quantify key factors driving the decline in efficiency of NHS elective care, focusing on medical workforce dynamics, resource allocation and systemic inefficiencies. We hypothesised that medical workforce sickness absence and administrative turnover significantly affect productivity and backlog growth, instead medical workforce turnover has not effect. Design: This research is a national retrospective observational study using monthly panel data from NHS Digital (January 2018–December 2023). Ordinary Least Squares regression and Generalised Method of Moments models were applied to estimate the impact of workforce and resource factors on productivity and backlog indicators. These methods will account for the unobserved factors and potential reverse causality problem. Setting: The study follows secondary care across all NHS Trusts in England, with performance measured at the Trust level. Participants: All NHS Trusts delivering elective surgical services between January 2018 and December 2023. The unit of analysis was Trust-month observations, encompassing all elective surgical patients treated in each Trust. Main outcome measures: (1) Average per capita completed surgery elective cases (proxy for productivity). (2) Ratio of incomplete elective surgery to average completed elective surgery cases (proxy for additional resources needed to meet demand). Results: A one-percentage-point increase in NHS medical workforce sickness rates was associated with a 4.4% decrease in average completed elective cases (95% CI −0.0598 to −0.0272, p < 0.05). Gains in administrative staff reduced excess elective surgery incomplete cases by 14.4% (95% CI −0.155 to −0.133, p < 0.05). Findings were robust to controls for other workforce and resource-related variables. Conclusions: Workforce expansion alone will not resolve NHS elective surgery backlogs. Reducing medical sickness absence, enhancing staff wellbeing and ensuring adequate administrative capacity are critical to improving productivity and reducing waiting times.

Introduction: Cluster analysis, a machine learning-based and data-driven technique for identifying groups in data, has demonstrated its potential in a wide range of contexts. However, critical appraisal and reproducibility are often limited by insufficient reporting, ultimately hampering the interpretation and trust of key stakeholders. The present paper describes the protocol that will guide the development of a reporting guideline and checklist for studies incorporating cluster analyses—Transparent Reporting of Cluster Analyses. Methods and analysis: Following the recommended steps for developing reporting guidelines outlined by the Enhancing the QUAlity and Transparency Of health Research Network, the work will be divided into six stages. Stage 1: literature review to guide development of initial checklist. Stage 2: drafting of the initial checklist. Stage 3: internal revision of checklist. Stage 4: Delphi study in a global sample of researchers from varying fields ( n =≈) to derive consensus regarding items in the checklist and piloting of the checklist. Stage 5: consensus meeting to consolidate checklist. Stage 6: production of statement paper and explanation and elaboration paper. Stage 7: dissemination via journals, conferences, social media and a dedicated web platform. Ethics and dissemination: Due to local regulations, the planned study is exempt from the requirement of ethical review. The findings will be disseminated through peer-reviewed publications. The checklist with explanations will also be made available freely on a dedicated web platform ( troca-statement.org ) and in a repository.

Objectives SARS-CoV-2 infection provides protection against reinfection and severe COVID-19 disease; however, this protective effect may diminish over time. We assessed waning of natural immunity conferred by previous infection against severe disease and symptomatic reinfection in Brazil and Scotland. Design We undertook a test-negative design study and nested case–control analysis to estimate waning of natural immunity against severe COVID-19 outcomes and symptomatic reinfection using national linked datasets. We used logistic regression to estimate ORs with 95% CIs. A stratified analysis assessed immunity during the Omicron dominant period in Brazil. Setting and participants We included data from the adult populations of Brazil and Scotland from 1 June 2020 to 30 April 2022. Outcome measures Severe COVID-19 was defined as hospitalisation or death. Reinfection was defined as reverse-transcriptase PCR or rapid antigen test confirmed at least 120 days after primary infection. Results From Brazil, we included 30 881 873 tests and 1 301 665 severe COVID-19 outcomes, and from Scotland, we included 1 520 201 tests and 7988 severe COVID-19 outcomes. Against severe outcomes, sustained protection was observed for at least 12 months after primary SARS-CoV-2 infection with little evidence of waning: 12 months postprimary infection: Brazil OR 0.12 (95% CI 0.10 to 0.14), Scotland OR 0.03 (95% CI 0.02 to 0.04). For symptomatic reinfection, Brazilian data demonstrated evidence of waning in the 12 months following primary infection, although some residual protection remained beyond 12 months: 12 months postprimary infection: OR 0.42 (95% CI 0.40 to 0.43). The greatest reduction in risk of SARS-CoV-2 infection was in individuals with hybrid immunity (history of previous infection and vaccination), with sustained protection against severe outcomes at 12 months postprimary infection. During the Omicron dominant period in Brazil, odds of symptomatic reinfection were higher and increased more quickly over time when compared with the overall study period, although protection against severe outcomes was sustained at 12 months postprimary infection (whole study: OR 0.12 (95% CI 0.10 to 0.14); Omicron phase: OR 0.15 (95% CI 0.12 to 0.19)). Conclusion Cross-national analyses demonstrate sustained protection against severe COVID-19 disease for at least 12 months following natural SARS-CoV-2 infection, with vaccination further enhancing protection. Protection against symptomatic reinfection was lower with evidence of waning, but there remained a protective effect beyond 12 months from primary infection.

See related article

Introduction The role of female sex hormones and their influence on asthma’s development and natural history remain uncertain. Our study aims to enhance understanding of exogenous sex hormones’ role in asthma development and manifestation, considering phenotypic heterogeneity and focusing on metabolic syndrome-linked asthma that has shown increased severity in females. Methods and analysis A cohort study using primary care data from the Clinical Practice Research Datalink (CPRD) databases linked with additional data sources (Hospital Episode Statistics, ethnicity and deprivation) will include individuals aged 16–70 years, spanning 1 January 2005 to 31 December 2019. We will use appropriate statistical learning methods depending on the outcome: extended Cox regression for late-onset asthma; Poisson or negative binomial regression for asthma exacerbations; binary logistic regression for asthma control; and ordered logistic regression for asthma severity. Asthma exacerbation will be defined based on the American Thoracic Society/European Respiratory Society Task Force definition as the presence of either one of an asthma-related accident and emergency department visit, an asthma-related (unscheduled) hospital admission or an acute course of oral corticosteroids (OCS) with evidence of asthma-related medical event and/or review within 2 weeks of OCS prescription. Poor asthma control in any given month will be defined by the occurrence of an exacerbation episode or use of short-acting beta agonist. Asthma severity will be defined based on the British Thoracic Society asthma severity steps. Asthma phenotypes will be identified using k-means clustering. Analyses will be undertaken using both GOLD and Aurum to ensure coverage across UK nations. Ethics and dissemination CPRD has received ethics approval from the Health Research Authority (East Midlands—Derby, REC reference number 21/EM/065) to support research using anonymised data. Approval to conduct this study was obtained through CPRD’s Research Data Governance process. The results will be disseminated through academic publications and conference presentations, contributing to the understanding and practice of asthma management, particularly in the context of the impacts of exogenous sex steroid hormones.