CSChristophe A. T. Stevens

Christophe A. T. Stevens

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Christophe A. T. Stevens has a total of 42 co-authors. Here are the top co-authors by number of shared publications:

  • Julia Brandts

    Imperial Centre for Cardiovascular Disease Prevention, School of Public Health, Imperial College London , Stadium House, 68 Wood Lane, London W12 7RH

    4 shared publications
  • Alireza Mahani

    Quantitative Research, Davidson Kempner Capital Management , NewYork

    3 shared publications
  • Fotios Barkas

    Imperial Centre for Cardiovascular Disease Prevention, School of Public Health, Imperial College London , Stadium House, 68 Wood Lane, London W12 7RH

    3 shared publications
  • Kausik K Ray

    Department of Primary Care and Public Health, School of Public Health, Imperial College London , School of Public Health Building, 90 Wood Lane, London W12 0BZ

    3 shared publications
  • Kausik Kumar Ray

    Imperial Centre for Cardiovascular Disease Prevention, Department of Primary Care and Public Health, School of Public Health, Imperial College London, London, United Kingdom

    3 shared publications
  • Antonio J Vallejo-Vaz

    Department of Primary Care and Public Health, School of Public Health, Imperial College London , School of Public Health Building, 90 Wood Lane, London W12 0BZ

    2 shared publications

Latest Publications

  • Open Access

    Estimating the potential cardiovascular benefit of lifestyle risk factors using causal machine learning: Insights from UK Biobank

    by Christophe A.T. Stevens, Julia Brandts, Amany Elshorbagy, Fotios Barkas, Didac Llop Paredes, Kanika I. Dharmayat, Irene Karungi, Sunganani Kwilasi, Alireza Mahani, Mansour T.A. Sharabiani, et al.

  • Open Access

    Machine learning-driven prioritization of lipoprotein(a) testing: model development and validation

    by Christophe A T Stevens, Fotios Barkas, Julia Brandts, Sunganani Kwilasi, Kanika I Dharmayat, Amany Elshorbagy, Irene Karungi, Alireza Mahani, Mansour T A Sharabiani, Antonio J Vallejo-Vaz, et al.

    Aims: Elevated lipoprotein(a) [Lp(a)] is a common risk factor for cardiovascular disease affecting ∼1.4 billion people globally, with novel treatments under development. Guidelines recommend one-lifetime measurement, yet <1% are tested. Population-wide screening faces cost and implementation challenges. We developed a machine learning (ML) model to help prioritize patients for Lp(a) testing. Methods and results: Ethnicity-calibrated ML models were developed to identify individuals with elevated Lp(a) in the UK Biobank. Participants ≥37 years old (n = 438 579) were split into feature importance/selection (20%), derivation (60%), and validation (20%) datasets. Performances across risk-enhancing Lp(a) thresholds recommended by clinical guidelines (90, 125, 430 nmol/L) or entry criteria for ongoing Lp(a)-lowering trials (150, 175, 200 nmol/L) were evaluated. External validation was conducted in NHANES III. Screening 1 million people using a universal approach would identify 222 717 cases above 90 nmol/L and 1950 above 430 nmol/L. In contrast, applying ML-targeted testing using the same number of tests would identify 280 899 (+26%; 95% CI: 20–28%) and 6881 (+253%; 95% CI: 192–310%) cases, respectively. At the thresholds of 125, 150, 175, and 200 nmol/L, yield increases were 38% (95% CI: 35–40%), 51% (95% CI: 47–54%), 59% (95% CI: 55–63%), and 66% (95% CI: 61–71%). Across thresholds 90–430 nmol/L, ML-targeted testing (number needed to screen 3.6–145, AUC 0.61–0.84) required 21–72% fewer tests to identify 1 million cases. NHANES III validation demonstrated similar performance. Top 4 predictors included age, height (proxy for sex), total cholesterol, and statin use. Conclusion: An ML-guided approach to prioritize testing for elevated Lp(a) would require fewer tests to identify those above risk-enhancing thresholds or potentially eligible for emerging therapies, offering a scalable interim compromise between the low current testing rates and universal screening aspirations.


  • Open Access

    Optimizing lipid-lowering therapy for acute coronary syndrome using a decision support system: insights from a cluster randomized trial

    by Christophe A T Stevens, Jessica Smith, Julia Brandts, Fotios Barkas, Maria Moreno Morales, Leila Janani, Gaia Kiru, Nandita Kaza, Victoria Cornelius, Neil R Poulter, et al.

    Aims: Lipid-lowering therapy (LLT) after acute coronary syndrome (ACS) typically follows stepwise intensification, delaying use of combination therapies and low-density lipoprotein cholesterol (LDL-C) goal attainment. We assessed whether access to a decision support system (DSS) altered the intensity of LLT prescribing vs. standard-of-care (SoC). Methods and results: Pragmatic, multinational, parallel 1:1 cluster-randomized controlled trial of ACS patients comparing mandatory access to a DSS (providing estimates of cardiovascular events and benefits from different LLT scenarios) to SoC. The primary endpoint was the proportion receiving intensified monotherapy or initiated/escalated combination LLT by Week 16 compared to pre-admission LLT; secondary endpoints included individual components of the primary endpoint, proportions at goal (LDL-C < 1.4 mmol/L), and timing of LLT escalations. 42 sites from UK, Italy, and Spain were randomized, enrolling 1139 participants, 79% male, median age 62 years (IQR: 55, 69), 84% without prior CVD, 69% LLT-naïve at admission, and median admission LDL-C 3.0 mmol/L (IQR: 2.46, 3.75). The primary endpoint was met in 71.7% (DSS) vs. 65.7% (SoC) and risk ratio (RR) 1.11 (95%CI:0.92–1.33, P = 0.29). Intensification of monotherapy occurred in 9.0% vs. 13.1% (RR: 0.68, 95%CI: 0.46–1.00), combination LLT in 61.6% vs. 50.6% (RR: 1.35, 95%CI: 0.93–1.98). LDL-C goal achievement was 54.8% vs. 50.3% (RR 1.06, 95%CI: 0.88–1.28), with LLT escalation before discharge in 64.8% vs. 60.7%. Conclusion: Access to a DSS, in hospitals managing ACS, did not improve LLT intensification within 16 weeks or LDL-C goal attainment but revealed a favourable trend towards earlier combination LLT use, which merits larger, longer studies in other settings.


  • Open Access

    Improving the Detection of Potential Cases of Familial Hypercholesterolemia: Could Machine Learning Be Part of the Solution?

    by Christophe A. T. Stevens, Antonio J. Vallejo‐Vaz, Joana R. Chora, Fotis Barkas, Julia Brandts, Alireza Mahani, Leila Abar, Mansour T. A. Sharabiani, Kausik K. Ray

    Background: Familial hypercholesterolemia (FH), while highly prevalent, is a significantly underdiagnosed monogenic disorder. Improved detection could reduce the large number of cardiovascular events attributable to poor case finding. We aimed to assess whether machine learning algorithms outperform clinical diagnostic criteria (signs, history, and biomarkers) and the recommended screening criteria in the United Kingdom in identifying individuals with FH‐causing variants, presenting a scalable screening criteria for general populations.Methods and Results: Analysis included UK Biobank participants with whole exome sequencing, classifying them as having FH when (likely) pathogenic variants were detected in theirLDLR,APOB, orPCSK9genes. Data were stratified into 3 data sets for (1) feature importance analysis; (2) deriving state‐of‐the‐art statistical and machine learning models; (3) evaluating models' predictive performance against clinical diagnostic and screening criteria: Dutch Lipid Clinic Network, Simon Broome, Make Early Diagnosis to Prevent Early Death, and Familial Case Ascertainment Tool. One thousand and three of 454 710 participants were classified as having FH. A Stacking Ensemble model yielded the best predictive performance (sensitivity, 74.93%; precision, 0.61%; accuracy, 72.80%, area under the receiver operating characteristic curve, 79.12%) and outperformed clinical diagnostic criteria and the recommended screening criteria in identifying FH variant carriers within the validation data set (figures for Familial Case Ascertainment Tool, the best baseline model, were 69.55%, 0.44%, 65.43%, and 71.12%, respectively). Our model decreased the number needed to screen compared with the Familial Case Ascertainment Tool (164 versus 227).Conclusions: Our machine learning–derived model provides a higher pretest probability of identifying individuals with a molecular diagnosis of FH compared with current approaches. This provides a promising, cost‐effective scalable tool for implementation into electronic health records to prioritize potential FH cases for genetic confirmation.


  • Open Access

    Ensemble machine learning methods in screening electronic health records: A scoping review

    by Christophe At Stevens, Alexander Rm Lyons, Kanika I Dharmayat, Alireza Mahani, Kausik K Ray, Antonio J Vallejo-Vaz, Mansour Ta Sharabiani

    Background: Electronic health records provide the opportunity to identify undiagnosed individuals likely to have a given disease using machine learning techniques, and who could then benefit from more medical screening and case finding, reducing the number needed to screen with convenience and healthcare cost savings. Ensemble machine learning models combining multiple prediction estimates into one are often said to provide better predictive performances than non-ensemble models. Yet, to our knowledge, no literature review summarises the use and performances of different types of ensemble machine learning models in the context of medical pre-screening. Method: We aimed to conduct a scoping review of the literature reporting the derivation of ensemble machine learning models for screening of electronic health records. We searched EMBASE and MEDLINE databases across all years applying a formal search strategy using terms related to medical screening, electronic health records and machine learning. Data were collected, analysed, and reported in accordance with the PRISMA scoping review guideline. Results: A total of 3355 articles were retrieved, of which 145 articles met our inclusion criteria and were included in this study. Ensemble machine learning models were increasingly employed across several medical specialties and often outperformed non-ensemble approaches. Ensemble machine learning models with complex combination strategies and heterogeneous classifiers often outperformed other types of ensemble machine learning models but were also less used. Ensemble machine learning models methodologies, processing steps and data sources were often not clearly described. Conclusions: Our work highlights the importance of deriving and comparing the performances of different types of ensemble machine learning models when screening electronic health records and underscores the need for more comprehensive reporting of machine learning methodologies employed in clinical research.


  • Open Access

    FindMyLipidClinic.com: A global Directory of lipid clinics and patient organisations to improve dyslipidemia care: FindMyLipidClinic.com

    by Christophe A.T. Stevens, Alexander R.M. Lyons, Kanika I. Dharmayat, Julia Brandts, Antonio J. Vallejo-Vaz, Magdalena Daccord, Kausik K. Ray

    Information available on lipid clinics and patient support and advocacy groups, such as location and services provided, is limited or unknown to patients with dyslipidaemia and their family members who may also be affected, and non-specialist clinicians, hindering accessibility to appropriate healthcare. To overcome this, the European Atherosclerosis Society Familial Hypercholesterolemia Study Collaboration (EAS FHSC) led by Imperial College London has, in collaboration with the European FH Patient Network (FH Europe), developed FindMyLipidClinic.com, a global Directory of lipid clinics and patient support groups in 29 languages. Since its launch in 2020, around 4,000 visitors have conducted 12,000 searches across 1,100 locations, which may have retrieved up to 124 lipid clinics and 29 patient groups currently listed in 39 and 28 countries, respectively. Clinics and patient organisations not currently listed are encouraged to join this directory, and it would also benefit further from collaborations with other existing directories able to contribute.