1
|
Keogh RH, Van Geloven N. Prediction Under Interventions: Evaluation of Counterfactual Performance Using Longitudinal Observational Data. Epidemiology 2024; 35:329-339. [PMID: 38630508 DOI: 10.1097/ede.0000000000001713] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/19/2024]
Abstract
Predictions under interventions are estimates of what a person's risk of an outcome would be if they were to follow a particular treatment strategy, given their individual characteristics. Such predictions can give important input to medical decision-making. However, evaluating the predictive performance of interventional predictions is challenging. Standard ways of evaluating predictive performance do not apply when using observational data, because prediction under interventions involves obtaining predictions of the outcome under conditions that are different from those that are observed for a subset of individuals in the validation dataset. This work describes methods for evaluating counterfactual performance of predictions under interventions for time-to-event outcomes. This means we aim to assess how well predictions would match the validation data if all individuals had followed the treatment strategy under which predictions are made. We focus on counterfactual performance evaluation using longitudinal observational data, and under treatment strategies that involve sustaining a particular treatment regime over time. We introduce an estimation approach using artificial censoring and inverse probability weighting that involves creating a validation dataset mimicking the treatment strategy under which predictions are made. We extend measures of calibration, discrimination (c-index and cumulative/dynamic AUCt) and overall prediction error (Brier score) to allow assessment of counterfactual performance. The methods are evaluated using a simulation study, including scenarios in which the methods should detect poor performance. Applying our methods in the context of liver transplantation shows that our procedure allows quantification of the performance of predictions supporting crucial decisions on organ allocation.
Collapse
Affiliation(s)
- Ruth H Keogh
- From the Department of Medical Statistics, London School of Hygiene & Tropical Medicine, London, United Kingdom
| | - Nan Van Geloven
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands
| |
Collapse
|
2
|
Lin L, Poppe K, Wood A, Martin GP, Peek N, Sperrin M. Making predictions under interventions: a case study from the PREDICT-CVD cohort in New Zealand primary care. FRONTIERS IN EPIDEMIOLOGY 2024; 4:1326306. [PMID: 38633209 PMCID: PMC11021700 DOI: 10.3389/fepid.2024.1326306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Accepted: 03/11/2024] [Indexed: 04/19/2024]
Abstract
Background Most existing clinical prediction models do not allow predictions under interventions. Such predictions allow predicted risk under different proposed strategies to be compared and are therefore useful to support clinical decision making. We aimed to compare methodological approaches for predicting individual level cardiovascular risk under three interventions: smoking cessation, reducing blood pressure, and reducing cholesterol. Methods We used data from the PREDICT prospective cohort study in New Zealand to calculate cardiovascular risk in a primary care setting. We compared three strategies to estimate absolute risk under intervention: (a) conditioning on hypothetical interventions in non-causal models; (b) combining existing prediction models with causal effects estimated using observational causal inference methods; and (c) combining existing prediction models with causal effects reported in published literature. Results The median absolute cardiovascular risk among smokers was 3.9%; our approaches predicted that smoking cessation reduced this to a median between a non-causal estimate of 2.5% and a causal estimate of 2.8%, depending on estimation methods. For reducing blood pressure, the proposed approaches estimated a reduction of absolute risk from a median of 4.9% to a median between 3.2% and 4.5% (both derived from causal estimation). Reducing cholesterol was estimated to reduce median absolute risk from 3.1% to between 2.2% (non-causal estimate) and 2.8% (causal estimate). Conclusions Estimated absolute risk reductions based on non-causal methods were different to those based on causal methods, and there was substantial variation in estimates within the causal methods. Researchers wishing to estimate risk under intervention should be explicit about their causal modelling assumptions and conduct sensitivity analysis by considering a range of possible approaches.
Collapse
Affiliation(s)
- Lijing Lin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - Katrina Poppe
- Schools of Population Health & Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
| | - Angela Wood
- British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom
- British Heart Foundation Centre of Research Excellence, University of Cambridge, Cambridge, United Kingdom
- National Institute for Health and Care Research Blood and Transplant Research Unit in Donor Health and Behaviour, University of Cambridge, Cambridge, United Kingdom
- Health Data Research UK Cambridge, Wellcome Genome Campus and University of Cambridge, Cambridge, United Kingdom
- Cambridge Centre of Artificial Intelligence in Medicine, University of Cambridge, Cambridge, United Kingdom
| | - Glen P. Martin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - Niels Peek
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - Matthew Sperrin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| |
Collapse
|
3
|
Fehr J, Piccininni M, Kurth T, Konigorski S. Assessing the transportability of clinical prediction models for cognitive impairment using causal models. BMC Med Res Methodol 2023; 23:187. [PMID: 37598141 PMCID: PMC10439645 DOI: 10.1186/s12874-023-02003-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 07/27/2023] [Indexed: 08/21/2023] Open
Abstract
BACKGROUND Machine learning models promise to support diagnostic predictions, but may not perform well in new settings. Selecting the best model for a new setting without available data is challenging. We aimed to investigate the transportability by calibration and discrimination of prediction models for cognitive impairment in simulated external settings with different distributions of demographic and clinical characteristics. METHODS We mapped and quantified relationships between variables associated with cognitive impairment using causal graphs, structural equation models, and data from the ADNI study. These estimates were then used to generate datasets and evaluate prediction models with different sets of predictors. We measured transportability to external settings under guided interventions on age, APOE ε4, and tau-protein, using performance differences between internal and external settings measured by calibration metrics and area under the receiver operating curve (AUC). RESULTS Calibration differences indicated that models predicting with causes of the outcome were more transportable than those predicting with consequences. AUC differences indicated inconsistent trends of transportability between the different external settings. Models predicting with consequences tended to show higher AUC in the external settings compared to internal settings, while models predicting with parents or all variables showed similar AUC. CONCLUSIONS We demonstrated with a practical prediction task example that predicting with causes of the outcome results in better transportability compared to anti-causal predictions when considering calibration differences. We conclude that calibration performance is crucial when assessing model transportability to external settings.
Collapse
Affiliation(s)
- Jana Fehr
- Digital Engineering Faculty, University of Potsdam, Potsdam, Germany.
- Digital Health and Machine Learning, Hasso-Plattner-Institute, Potsdam, Germany.
| | - Marco Piccininni
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany
- Center for Stroke Research Berlin, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Tobias Kurth
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Stefan Konigorski
- Digital Engineering Faculty, University of Potsdam, Potsdam, Germany.
- Digital Health and Machine Learning, Hasso-Plattner-Institute, Potsdam, Germany.
- Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai, New York, NY, USA.
| |
Collapse
|
4
|
Clift AK, Dodwell D, Lord S, Petrou S, Brady M, Collins GS, Hippisley-Cox J. Development and internal-external validation of statistical and machine learning models for breast cancer prognostication: cohort study. BMJ 2023; 381:e073800. [PMID: 37164379 PMCID: PMC10170264 DOI: 10.1136/bmj-2022-073800] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 03/28/2023] [Indexed: 05/12/2023]
Abstract
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.
Collapse
Affiliation(s)
- Ash Kieran Clift
- Cancer Research UK Oxford Centre, Oxford, UK
- Nuffield Department of Primary Care Health Sciences, Radcliffe Primary Care Building, Radcliffe Observatory Quarter, University of Oxford, Oxford OX2 6GG, UK
| | - David Dodwell
- Nuffield Department of Population Health, University of Oxford, Oxford, UK
| | - Simon Lord
- Department of Oncology, University of Oxford, Oxford, UK
| | - Stavros Petrou
- Nuffield Department of Primary Care Health Sciences, Radcliffe Primary Care Building, Radcliffe Observatory Quarter, University of Oxford, Oxford OX2 6GG, UK
| | - Michael Brady
- Department of Oncology, University of Oxford, Oxford, UK
| | - Gary S Collins
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - Julia Hippisley-Cox
- Nuffield Department of Primary Care Health Sciences, Radcliffe Primary Care Building, Radcliffe Observatory Quarter, University of Oxford, Oxford OX2 6GG, UK
| |
Collapse
|
5
|
Tanaka JRV, Sousa KHJF, Alves PJP, Guerra MJJ, Gonçalves PDB. Educational Technology on Urinary Incontinence during Pregnancy: Development and Validation of an Online Course for the Brazilian Population. AQUICHAN 2023. [DOI: 10.5294/aqui.2023.23.1.3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/24/2023] Open
Abstract
Objective: To describe the development and validation process of an online course on urinary incontinence during pregnancy in Brazil. Materials and methods: This methodological study followed an online course’s literature search, development, and validation steps. A total of 22 specialists participated in the validation step, and the content validity index (CVI) was used. Fifty-one Physical Therapy students (target audience) also participated in the Suitability Assessment of Materials. Results: The synthesis reached in the integrative review provided the basis for the course’s theoretical content, which was regarded as suitable by the specialists regarding its content, language, presentation, stimulation/motivation, and cultural adequacy (CVI = 0.99). The target audience considered the course organized, easily understandable, engaging, and motivational, with a positive response index ranging from 84.3 % to 100 %. Conclusions: The Brazilian version of the online course was considered sufficiently adequate in content and interface quality by both specialists and the target audience.
Collapse
|
6
|
Piccininni M, Rohmann JL, Wechsung M, Logroscino G, Kurth T. Should Cognitive Screening Tests Be Corrected for Age and Education? Insights From a Causal Perspective. Am J Epidemiol 2023; 192:93-101. [PMID: 36068941 PMCID: PMC9825732 DOI: 10.1093/aje/kwac159] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Revised: 07/10/2022] [Accepted: 08/31/2022] [Indexed: 01/25/2023] Open
Abstract
Cognitive screening tests such as the Mini-Mental State Examination are widely used in clinical routine to predict cognitive impairment. The raw test scores are often corrected for age and education, although documented poorer discrimination performance of corrected scores has challenged this practice. Nonetheless, test correction persists, perhaps due to the seemingly counterintuitive nature of the underlying problem. We used a causal framework to inform the long-standing debate from a more intuitive angle. We illustrate and quantify the consequences of applying the age-education correction of cognitive tests on discrimination performance. In an effort to bridge theory and practical implementation, we computed differences in discrimination performance under plausible causal scenarios using Open Access Series of Imaging Studies (OASIS)-1 data. We show that when age and education are causal risk factors for cognitive impairment and independently also affect the test score, correcting test scores for age and education removes meaningful information, thereby diminishing discrimination performance.
Collapse
Affiliation(s)
- Marco Piccininni
- Correspondence to Dr. Marco Piccininni, Institute of Public Health, Charité – Universitätsmedizin Berlin, Chariteplatz 1, Berlin, Germany 10117 (e-mail: )
| | | | | | | | | |
Collapse
|
7
|
Chan WX, Wong L. Accounting for treatment during the development or validation of prediction models. J Bioinform Comput Biol 2022; 20:2271001. [PMID: 36514873 DOI: 10.1142/s0219720022710019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Clinical prediction models are widely used to predict adverse outcomes in patients, and are often employed to guide clinical decision-making. Clinical data typically consist of patients who received different treatments. Many prediction modeling studies fail to account for differences in patient treatment appropriately, which results in the development of prediction models that show poor accuracy and generalizability. In this paper, we list the most common methods used to handle patient treatments and discuss certain caveats associated with each method. We believe that proper handling of differences in patient treatment is crucial for the development of accurate and generalizable models. As different treatment strategies are employed for different diseases, the best approach to properly handle differences in patient treatment is specific to each individual situation. We use the Ma-Spore acute lymphoblastic leukemia data set as a case study to demonstrate the complexities associated with differences in patient treatment, and offer suggestions on incorporating treatment information during evaluation of prediction models. In clinical data, patients are typically treated on a case by case basis, with unique cases occurring more frequently than expected. Hence, there are many subtleties to consider during the analysis and evaluation of clinical prediction models.
Collapse
Affiliation(s)
- Wei Xin Chan
- School of Computing, National University of Singapore, 13 Computing Drive, Singapore 117417, Singapore
| | - Limsoon Wong
- School of Computing, National University of Singapore, 13 Computing Drive, Singapore 117417, Singapore
| |
Collapse
|
8
|
Gehringer CK, Martin GP, Hyrich KL, Verstappen SM, Sergeant JC. Clinical prediction models for methotrexate treatment outcomes in patients with rheumatoid arthritis: A systematic review and meta-analysis. Semin Arthritis Rheum 2022; 56:152076. [DOI: 10.1016/j.semarthrit.2022.152076] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2022] [Revised: 07/22/2022] [Accepted: 07/26/2022] [Indexed: 11/24/2022]
|
9
|
Dickerman BA, Dahabreh IJ, Cantos KV, Logan RW, Lodi S, Rentsch CT, Justice AC, Hernán MA. Predicting counterfactual risks under hypothetical treatment strategies: an application to HIV. Eur J Epidemiol 2022; 37:367-376. [PMID: 35190946 PMCID: PMC9189026 DOI: 10.1007/s10654-022-00855-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2021] [Accepted: 02/14/2022] [Indexed: 12/23/2022]
Abstract
The accuracy of a prediction algorithm depends on contextual factors that may vary across deployment settings. To address this inherent limitation of prediction, we propose an approach to counterfactual prediction based on the g-formula to predict risk across populations that differ in their distribution of treatment strategies. We apply this to predict 5-year risk of mortality among persons receiving care for HIV in the U.S. Veterans Health Administration under different hypothetical treatment strategies. First, we implement a conventional approach to develop a prediction algorithm in the observed data and show how the algorithm may fail when transported to new populations with different treatment strategies. Second, we generate counterfactual data under different treatment strategies and use it to assess the robustness of the original algorithm's performance to these differences and to develop counterfactual prediction algorithms. We discuss how estimating counterfactual risks under a particular treatment strategy is more challenging than conventional prediction as it requires the same data, methods, and unverifiable assumptions as causal inference. However, this may be required when the alternative assumption of constant treatment patterns across deployment settings is unlikely to hold and new data is not yet available to retrain the algorithm.
Collapse
Affiliation(s)
- Barbra A Dickerman
- CAUSALab, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
| | - Issa J Dahabreh
- CAUSALab, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | | | - Roger W Logan
- CAUSALab, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Sara Lodi
- CAUSALab, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA
| | - Christopher T Rentsch
- Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, UK
- Veterans Affairs Connecticut Healthcare System, West Haven, CT, USA
- Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Amy C Justice
- Veterans Affairs Connecticut Healthcare System, West Haven, CT, USA
- Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Interdisciplinary Research on AIDS, Yale School of Public Health, New Haven, CT, USA
| | - Miguel A Hernán
- CAUSALab, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
- Harvard-MIT Division of Health Sciences and Technology, Boston, MA, USA
| |
Collapse
|
10
|
Kurth T. Continuing to Advance Epidemiology. FRONTIERS IN EPIDEMIOLOGY 2021; 1:782374. [PMID: 38455238 PMCID: PMC10910999 DOI: 10.3389/fepid.2021.782374] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 10/11/2021] [Indexed: 03/09/2024]
Affiliation(s)
- Tobias Kurth
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|
11
|
Sperrin M, Diaz-Ordaz K, Pajouheshnia R. Invited Commentary: Treatment Drop-in-Making the Case for Causal Prediction. Am J Epidemiol 2021; 190:2015-2018. [PMID: 33595073 PMCID: PMC8485150 DOI: 10.1093/aje/kwab030] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2021] [Revised: 01/25/2021] [Accepted: 02/02/2021] [Indexed: 11/12/2022] Open
Abstract
Clinical prediction models (CPMs) are often used to guide treatment initiation, with individuals at high risk offered treatment. This implicitly assumes that the probability quoted from a CPM represents the risk to an individual of an adverse outcome in absence of treatment. However, for a CPM to correctly target this estimand requires careful causal thinking. One problem that needs to be overcome is treatment drop-in: where individuals in the development data commence treatment after the time of prediction but before the outcome occurs. In this issue of the Journal, Xu et al. (Am J Epidemiol. 2021;190(10):2000-2014) use causal estimates from external data sources, such as clinical trials, to adjust CPMs for treatment drop-in. This represents a pragmatic and promising approach to address this issue, and it illustrates the value of utilizing causal inference in prediction. Building causality into the prediction pipeline can also bring other benefits. These include the ability to make and compare hypothetical predictions under different interventions, to make CPMs more explainable and transparent, and to improve model generalizability. Enriching CPMs with causal inference therefore has the potential to add considerable value to the role of prediction in healthcare.
Collapse
Affiliation(s)
- Matthew Sperrin
- Correspondence to Matthew Sperrin, Vaughan House, Portsmouth Street, University of Manchester, Manchester M13 9GB, UK (e-mail: )
| | | | | |
Collapse
|
12
|
Weissman GE, Liu VX. Algorithmic prognostication in critical care: a promising but unproven technology for supporting difficult decisions. Curr Opin Crit Care 2021; 27:500-505. [PMID: 34267077 PMCID: PMC8416806 DOI: 10.1097/mcc.0000000000000855] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW Patients, surrogate decision makers, and clinicians face weighty and urgent decisions under uncertainty in the ICU, which could be aided by risk prediction. Although emerging artificial intelligence/machine learning (AI/ML) algorithms could reduce uncertainty surrounding these life and death decisions, certain criteria must be met to ensure their bedside value. RECENT FINDINGS Although ICU severity of illness scores have existed for decades, these tools have not been shown to predict well or to improve outcomes for individual patients. Novel AI/ML tools offer the promise of personalized ICU care but remain untested in clinical trials. Ensuring that these predictive models account for heterogeneity in patient characteristics and treatments, are not only specific to a clinical action but also consider the longitudinal course of critical illness, and address patient-centered outcomes related to equity, transparency, and shared decision-making will increase the likelihood that these tools improve outcomes. Improved clarity around standards and contributions from institutions and critical care departments will be essential. SUMMARY Improved ICU prognostication, enabled by advanced ML/AI methods, offer a promising approach to inform difficult and urgent decisions under uncertainty. However, critical knowledge gaps around performance, equity, safety, and effectiveness must be filled and prospective, randomized testing of predictive interventions are still needed.
Collapse
Affiliation(s)
- Gary E Weissman
- Palliative and Advanced Illness Research (PAIR) Center
- Division of Pulmonary, Allergy, & Critical Care Medicine, Department of Medicine, Perelman School of Medicine
- Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Vincent X Liu
- Kaiser Permanente Division of Research
- The Permanente Medical Group, Oakland, California, USA
| |
Collapse
|
13
|
Xu Z, Arnold M, Stevens D, Kaptoge S, Pennells L, Sweeting MJ, Barrett J, Di Angelantonio E, Wood AM. Prediction of Cardiovascular Disease Risk Accounting for Future Initiation of Statin Treatment. Am J Epidemiol 2021; 190:2000-2014. [PMID: 33595074 PMCID: PMC8485151 DOI: 10.1093/aje/kwab031] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2020] [Revised: 12/17/2020] [Accepted: 12/18/2020] [Indexed: 12/15/2022] Open
Abstract
Cardiovascular disease (CVD) risk-prediction models are used to identify high-risk individuals and guide statin initiation. However, these models are usually derived from individuals who might initiate statins during follow-up. We present a simple approach to address statin initiation to predict “statin-naive” CVD risk. We analyzed primary care data (2004–2017) from the UK Clinical Practice Research Datalink for 1,678,727 individuals (aged 40–85 years) without CVD or statin treatment history at study entry. We derived age- and sex-specific prediction models including conventional risk factors and a time-dependent effect of statin initiation constrained to 25% risk reduction (from trial results). We compared predictive performance and measures of public-health impact (e.g., number needed to screen to prevent 1 event) against models ignoring statin initiation. During a median follow-up of 8.9 years, 103,163 individuals developed CVD. In models accounting for (versus ignoring) statin initiation, 10-year CVD risk predictions were slightly higher; predictive performance was moderately improved. However, few individuals were reclassified to a high-risk threshold, resulting in negligible improvements in number needed to screen to prevent 1 event. In conclusion, incorporating statin effects from trial results into risk-prediction models enables statin-naive CVD risk estimation and provides moderate gains in predictive ability but had a limited impact on treatment decision-making under current guidelines in this population.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | - Angela M Wood
- Correspondence to Dr. Angela M. Wood, Department of Public Health and Primary Care, University of Cambridge, Strangeways Research Laboratory, Cambridge CB1 8RN, United Kingdom (e-mail: )
| |
Collapse
|
14
|
Anikpo I, Agovi AMA, Cvitanovich MJ, Lonergan F, Johnson M, Ojha RP. The data-collection on adverse effects of anti-HIV drugs (D:A:D) model for predicting cardiovascular events: External validation in a diverse cohort of people living with HIV. HIV Med 2021; 22:936-943. [PMID: 34414654 PMCID: PMC9290794 DOI: 10.1111/hiv.13147] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Accepted: 07/07/2021] [Indexed: 11/29/2022]
Abstract
OBJECTIVES Little is known about the external validity of the Data-collection on Adverse Effects of Anti-HIV Drugs (D:A:D) model for predicting cardiovascular disease (CVD) risk among people living with HIV (PLWH). We aimed to evaluate the performance of the updated D:A:D model for 5-year CVD risk in a diverse group of PLWH engaged in HIV care. METHODS We used data from an institutional HIV registry, which includes PLWH engaged in care at a safety-net HIV clinic. Eligible individuals had a baseline clinical encounter between 1 January 2013 and 31 December 2014, with follow-up through to 31 December 2019. We estimated 5-year predicted risks of CVD as a function of the prognostic index and baseline survival of the D:A:D model, which were used to assess model discrimination (C-index), calibration and net benefit. RESULTS Our evaluable population comprised 1029 PLWH, of whom 30% were female, 50% were non-Hispanic black, and median age was 45 years. The C-index was 0.70 [95% confidence limits (CL): 0.64-0.75]. The predicted 5-year CVD risk was 3.0% and the observed 5-year risk was 8.9% (expected/observed ratio = 0.33, 95% CL: 0.26-0.54). The model had a greater net benefit than treating all or treating none at a risk threshold of 10%. CONCLUSIONS The D:A:D model was miscalibrated for CVD risk among PLWH engaged in HIV care at an urban safety-net HIV clinic, which may be related to differences in case-mix and baseline CVD risk. Nevertheless, the HIV D:A:D model may be useful for decisions about CVD intervention for high-risk patients.
Collapse
Affiliation(s)
- Ifedioranma Anikpo
- Center for Epidemiology & Healthcare Delivery Research, JPS Health Network, Fort Worth, TX, USA
| | - Afiba Manza-A Agovi
- Center for Epidemiology & Healthcare Delivery Research, JPS Health Network, Fort Worth, TX, USA.,Department of Medical Education, TCU and UNTHSC School of Medicine, Fort Worth, TX, USA
| | - Matthew J Cvitanovich
- Center for Epidemiology & Healthcare Delivery Research, JPS Health Network, Fort Worth, TX, USA
| | - Frank Lonergan
- True Worth Medical Home, JPS Health Network, Fort Worth, TX, USA
| | - Marc Johnson
- Healing Wings Clinic, JPS Health Network, Fort Worth, TX, USA
| | - Rohit P Ojha
- Center for Epidemiology & Healthcare Delivery Research, JPS Health Network, Fort Worth, TX, USA.,Department of Medical Education, TCU and UNTHSC School of Medicine, Fort Worth, TX, USA
| |
Collapse
|
15
|
van Royen FS, van Smeden M, Moons KGM, Rutten FH, Geersing GJ. Management of superficial venous thrombosis based on individual risk profiles: protocol for the development and validation of three prognostic prediction models in large primary care cohorts. Diagn Progn Res 2021; 5:15. [PMID: 34404480 PMCID: PMC8371853 DOI: 10.1186/s41512-021-00104-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/16/2021] [Accepted: 07/13/2021] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND Superficial venous thrombosis (SVT) is considered a benign thrombotic condition in most patients. However, it also can cause serious complications, such as clot progression to deep venous thrombosis (DVT) and pulmonary embolism (PE). Although most SVT patients are encountered in primary healthcare, studies on SVT nearly all were focused on patients seen in the hospital setting. This paper describes the protocol of the development and external validation of three prognostic prediction models for relevant clinical outcomes in SVT patients seen in primary care: (i) prolonged (painful) symptoms within 14 days since SVT diagnosis, (ii) for clot progression to DVT or PE within 45 days and (iii) for clot recurrence within 12 months. METHODS Data will be used from four primary care routine healthcare registries from both the Netherlands and the UK; one UK registry will be used for the development of the prediction models and the remaining three will be used as external validation cohorts. The study population will consist of patients ≥18 years with a diagnosis of SVT. Selection of SVT cases will be based on a combination of ICPC/READ/Snowmed coding and free text clinical symptoms. Predictors considered are sex, age, body mass index, clinical SVT characteristics, and co-morbidities including (history of any) cardiovascular disease, diabetes, autoimmune disease, malignancy, thrombophilia, pregnancy or puerperium and presence of varicose veins. The prediction models will be developed using multivariable logistic regression analysis techniques for models i and ii, and for model iii, a Cox proportional hazards model will be used. They will be validated by internal-external cross-validation as well as external validation. DISCUSSION There are currently no prediction models available for predicting the risk of serious complications for SVT patients presenting in primary care settings. We aim to develop and validate new prediction models that should help identify patients at highest risk for complications and to support clinical decision making for this understudied thrombo-embolic disorder. Challenges that we anticipate to encounter are mostly related to performing research in large, routine healthcare databases, such as patient selection, endpoint classification, data harmonisation, missing data and avoiding (predictor) measurement heterogeneity.
Collapse
Affiliation(s)
- F S van Royen
- Dept. General Practice, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands.
| | - M van Smeden
- Dept. Epidemiology, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - K G M Moons
- Dept. Epidemiology, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - F H Rutten
- Dept. General Practice, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - G J Geersing
- Dept. General Practice, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| |
Collapse
|
16
|
Lin L, Sperrin M, Jenkins DA, Martin GP, Peek N. A scoping review of causal methods enabling predictions under hypothetical interventions. Diagn Progn Res 2021; 5:3. [PMID: 33536082 PMCID: PMC7860039 DOI: 10.1186/s41512-021-00092-9] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/21/2020] [Accepted: 01/02/2021] [Indexed: 02/07/2023] Open
Abstract
BACKGROUND The methods with which prediction models are usually developed mean that neither the parameters nor the predictions should be interpreted causally. For many applications, this is perfectly acceptable. However, when prediction models are used to support decision making, there is often a need for predicting outcomes under hypothetical interventions. AIMS We aimed to identify published methods for developing and validating prediction models that enable risk estimation of outcomes under hypothetical interventions, utilizing causal inference. We aimed to identify the main methodological approaches, their underlying assumptions, targeted estimands, and potential pitfalls and challenges with using the method. Finally, we aimed to highlight unresolved methodological challenges. METHODS We systematically reviewed literature published by December 2019, considering papers in the health domain that used causal considerations to enable prediction models to be used for predictions under hypothetical interventions. We included both methodologies proposed in statistical/machine learning literature and methodologies used in applied studies. RESULTS We identified 4919 papers through database searches and a further 115 papers through manual searches. Of these, 87 papers were retained for full-text screening, of which 13 were selected for inclusion. We found papers from both the statistical and the machine learning literature. Most of the identified methods for causal inference from observational data were based on marginal structural models and g-estimation. CONCLUSIONS There exist two broad methodological approaches for allowing prediction under hypothetical intervention into clinical prediction models: (1) enriching prediction models derived from observational studies with estimated causal effects from clinical trials and meta-analyses and (2) estimating prediction models and causal effects directly from observational data. These methods require extending to dynamic treatment regimes, and consideration of multiple interventions to operationalise a clinical decision support system. Techniques for validating 'causal prediction models' are still in their infancy.
Collapse
Affiliation(s)
- Lijing Lin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK.
| | - Matthew Sperrin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
| | - David A Jenkins
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
- NIHR Greater Manchester Patient Safety Translational Research Centre, The University of Manchester, Manchester, UK
| | - Glen P Martin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
| | - Niels Peek
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
- NIHR Greater Manchester Patient Safety Translational Research Centre, The University of Manchester, Manchester, UK
- NIHR Manchester Biomedical Research Centre, The University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
| |
Collapse
|
17
|
Sisk R, Lin L, Sperrin M, Barrett JK, Tom B, Diaz-Ordaz K, Peek N, Martin GP. Informative presence and observation in routine health data: A review of methodology for clinical risk prediction. J Am Med Inform Assoc 2021; 28:155-166. [PMID: 33164082 PMCID: PMC7810439 DOI: 10.1093/jamia/ocaa242] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2020] [Accepted: 09/17/2020] [Indexed: 12/20/2022] Open
Abstract
Objective Informative presence (IP) is the phenomenon whereby the presence or absence of patient data is potentially informative with respect to their health condition, with informative observation (IO) being the longitudinal equivalent. These phenomena predominantly exist within routinely collected healthcare data, in which data collection is driven by the clinical requirements of patients and clinicians. The extent to which IP and IO are considered when using such data to develop clinical prediction models (CPMs) is unknown, as is the existing methodology aiming at handling these issues. This review aims to synthesize such existing methodology, thereby helping identify an agenda for future methodological work. Materials and Methods A systematic literature search was conducted by 2 independent reviewers using prespecified keywords. Results Thirty-six articles were included. We categorized the methods presented within as derived predictors (including some representation of the measurement process as a predictor in the model), modeling under IP, and latent structures. Including missing indicators or summary measures as predictors is the most commonly presented approach amongst the included studies (24 of 36 articles). Discussion This is the first review to collate the literature in this area under a prediction framework. A considerable body relevant of literature exists, and we present ways in which the described methods could be developed further. Guidance is required for specifying the conditions under which each method should be used to enable applied prediction modelers to use these methods. Conclusions A growing recognition of IP and IO exists within the literature, and methodology is increasingly becoming available to leverage these phenomena for prediction purposes. IP and IO should be approached differently in a prediction context than when the primary goal is explanation. The work included in this review has demonstrated theoretical and empirical benefits of incorporating IP and IO, and therefore we recommend that applied health researchers consider incorporating these methods in their work.
Collapse
Affiliation(s)
- Rose Sisk
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, University of Manchester, Manchester, United Kingdom
| | - Lijing Lin
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, University of Manchester, Manchester, United Kingdom
| | - Matthew Sperrin
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, University of Manchester, Manchester, United Kingdom
| | - Jessica K Barrett
- MRC Biostatistics Unit, University of Cambridge, Cambridge, United Kingdom.,Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom
| | - Brian Tom
- MRC Biostatistics Unit, University of Cambridge, Cambridge, United Kingdom
| | - Karla Diaz-Ordaz
- Department of Medical Statistics, London School of Hygiene and Tropical Medicine, London, United Kingdom
| | - Niels Peek
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, University of Manchester, Manchester, United Kingdom.,NIHR Biomedical Research Centre, Manchester Academic Health Science Centre, University of Manchester, Manchester, United Kingdom.,Alan Turing Institute, University of Manchester, London, United Kingdom
| | - Glen P Martin
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, University of Manchester, Manchester, United Kingdom
| |
Collapse
|
18
|
Martin GP, Sperrin M, Sotgiu G. Performance of prediction models for COVID-19: the Caudine Forks of the external validation. Eur Respir J 2020; 56:13993003.03728-2020. [PMID: 33060155 PMCID: PMC7562696 DOI: 10.1183/13993003.03728-2020] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Accepted: 10/06/2020] [Indexed: 02/06/2023]
Abstract
Healthcare systems worldwide have observed significant changes to meet demands due to the coronavirus disease 2019 (COVID-19) pandemic. The uncertainty surrounding optimal treatment, the rapid public health urgency and clinical emergencies have caused a chaotic disruption of the cases and their related contacts at inpatient and outpatient settings. Developing more tailored healthcare plans based on the currently available scientific evidence, could help improve clinical efficacy, treatment outcomes, prognosis, and health efficiency. Existing evidence suggests that none of the COVID-19 prediction models can be supported for clinical use. Here we discuss “what next” in COVID-19 prediction.https://bit.ly/2SMtoLV
Collapse
Affiliation(s)
- Glen P Martin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
| | - Matthew Sperrin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
| | - Giovanni Sotgiu
- Clinical Epidemiology and Medical Statistics Unit, Dept of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| |
Collapse
|
19
|
Pate A, van Staa T, Emsley R. An assessment of the potential miscalibration of cardiovascular disease risk predictions caused by a secular trend in cardiovascular disease in England. BMC Med Res Methodol 2020; 20:289. [PMID: 33256644 PMCID: PMC7706224 DOI: 10.1186/s12874-020-01173-x] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2020] [Accepted: 11/23/2020] [Indexed: 12/31/2022] Open
Abstract
Background A downwards secular trend in the incidence of cardiovascular disease (CVD) in England was identified through previous work and the literature. Risk prediction models for primary prevention of CVD do not model this secular trend, this could result in over prediction of risk for individuals in the present day. We evaluate the effects of modelling this secular trend, and also assess whether it is driven by an increase in statin use during follow up. Methods We derived a cohort of patients (1998–2015) eligible for cardiovascular risk prediction from the Clinical Practice Research Datalink with linked hospitalisation and mortality records (N = 3,855,660). Patients were split into development and validation cohort based on their cohort entry date (before/after 2010). The calibration of a CVD risk prediction model developed in the development cohort was tested in the validation cohort. The calibration was also assessed after modelling the secular trend. Finally, the presence of the secular trend was evaluated under a marginal structural model framework, where the effect of statin treatment during follow up is adjusted for. Results Substantial over prediction of risks in the validation cohort was found when not modelling the secular trend. This miscalibration could be minimised if one was to explicitly model the secular trend. The reduction in risk in the validation cohort when introducing the secular trend was 35.68 and 33.24% in the female and male cohorts respectively. Under the marginal structural model framework, the reductions were 33.31 and 32.67% respectively, indicating increasing statin use during follow up is not the only the cause of the secular trend. Conclusions Inclusion of the secular trend into the model substantially changed the CVD risk predictions. Models that are being used in clinical practice in the UK do not model secular trend and may thus overestimate the risks, possibly leading to patients being treated unnecessarily. Wider discussion around the modelling of secular trends in a risk prediction framework is needed. Supplementary Information The online version contains supplementary material available at 10.1186/s12874-020-01173-x.
Collapse
Affiliation(s)
- Alexander Pate
- Division of Imaging, Informatics and Data Science, School of Health Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Oxford Road, Manchester, M13 9PL, UK.
| | - Tjeerd van Staa
- Division of Imaging, Informatics and Data Science, School of Health Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Oxford Road, Manchester, M13 9PL, UK
| | - Richard Emsley
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, De Crispigny Park, London, SE5 8AF, UK
| |
Collapse
|
20
|
Cooray SD, Boyle JA, Soldatos G, Zamora J, Fernández Félix BM, Allotey J, Thangaratinam S, Teede HJ. Protocol for development and validation of a clinical prediction model for adverse pregnancy outcomes in women with gestational diabetes. BMJ Open 2020; 10:e038845. [PMID: 33154055 PMCID: PMC7646337 DOI: 10.1136/bmjopen-2020-038845] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Abstract
INTRODUCTION Gestational diabetes (GDM) is a common yet highly heterogeneous condition. The ability to calculate the absolute risk of adverse pregnancy outcomes for an individual woman with GDM would allow preventative and therapeutic interventions to be delivered to women at high-risk, sparing women at low-risk from unnecessary care. The Prediction for Risk-Stratified care for women with GDM (PeRSonal GDM) study will develop, validate and evaluate the clinical utility of a prediction model for adverse pregnancy outcomes in women with GDM. METHODS AND ANALYSIS We undertook formative research to conceptualise and design the prediction model. Informed by these findings, we will conduct a model development and validation study using a retrospective cohort design with participant data collected as part of routine clinical care across three hospitals. The study will include all pregnancies resulting in births from 1 July 2017 to 31 December 2018 coded for a diagnosis of GDM (estimated sample size 2430 pregnancies). We will use a temporal split-sample development and validation strategy. A multivariable logistic regression model will be fitted. The performance of this model will be assessed, and the validated model will also be evaluated using decision curve analysis. Finally, we will explore modes of model presentation suited to clinical use, including electronic risk calculators. ETHICS AND DISSEMINATION This study was approved by the Human Research Ethics Committee of Monash Health (RES-19-0000713 L). We will disseminate results via presentations at scientific meetings and publication in peer-reviewed journals. TRIAL REGISTRATION DETAILS Systematic review proceeding this work was registered on PROSPERO (CRD42019115223) and the study was registered on the Australian and New Zealand Clinical Trials Registry (ACTRN12620000915954); Pre-results.
Collapse
Affiliation(s)
- Shamil D Cooray
- Monash Centre for Health Research and Implementation, School of Public Health and Preventative Medicine, Monash University, Clayton, Victoria, Australia
- Diabetes Unit, Monash Health, Clayton, Victoria, Australia
| | - Jacqueline A Boyle
- Monash Centre for Health Research and Implementation, School of Public Health and Preventative Medicine, Monash University, Clayton, Victoria, Australia
- Monash Women's Program, Monash Health, Clayton, Victoria, Australia
| | - Georgia Soldatos
- Monash Centre for Health Research and Implementation, School of Public Health and Preventative Medicine, Monash University, Clayton, Victoria, Australia
- Diabetes and Endocrinology Units, Monash Health, Clayton, Victoria, Australia
| | - Javier Zamora
- CIBER Epidemiology and Public Health, Madrid, Comunidad de Madrid, Spain
- Clinical Biostatistics Unit, Hospital Ramon y Cajal, Madrid, Madrid, Spain
| | - Borja M Fernández Félix
- CIBER Epidemiology and Public Health, Madrid, Comunidad de Madrid, Spain
- Clinical Biostatistics Unit, Hospital Universitario Ramon y Cajal, Madrid, Madrid, Spain
| | - John Allotey
- WHO Collaborating Centre for Global Women's Health, Institute of Metabolism and Systems Research, University of Birmingham, Birmingham, Birmingham, UK
| | - Shakila Thangaratinam
- WHO Collaborating Centre for Global Women's Health, Institute of Metabolism and Systems Research, University of Birmingham, Birmingham, Birmingham, UK
| | - Helena J Teede
- Monash Centre for Health Research and Implementation, School of Public Health and Preventative Medicine, Monash University, Clayton, Victoria, Australia
- Diabetes and Endocrinology Units, Monash Health, Clayton, Victoria, Australia
| |
Collapse
|
21
|
Dickerman BA, Hernán MA. Counterfactual prediction is not only for causal inference. Eur J Epidemiol 2020; 35:615-617. [PMID: 32623620 DOI: 10.1007/s10654-020-00659-8] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Affiliation(s)
- Barbra A Dickerman
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
| | - Miguel A Hernán
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA.,Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.,Harvard-MIT Division of Health Sciences and Technology, Boston, MA, USA
| |
Collapse
|
22
|
Abstract
Reasons to be cautious
Collapse
Affiliation(s)
- Matthew Sperrin
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Brian McMillan
- Centre for Primary Care and Health Services Research, Division of Population Health, Health Services Research and Primary Care, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| |
Collapse
|
23
|
Piccininni M, Konigorski S, Rohmann JL, Kurth T. Directed acyclic graphs and causal thinking in clinical risk prediction modeling. BMC Med Res Methodol 2020; 20:179. [PMID: 32615926 PMCID: PMC7331263 DOI: 10.1186/s12874-020-01058-z] [Citation(s) in RCA: 32] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2020] [Accepted: 06/19/2020] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND In epidemiology, causal inference and prediction modeling methodologies have been historically distinct. Directed Acyclic Graphs (DAGs) are used to model a priori causal assumptions and inform variable selection strategies for causal questions. Although tools originally designed for prediction are finding applications in causal inference, the counterpart has remained largely unexplored. The aim of this theoretical and simulation-based study is to assess the potential benefit of using DAGs in clinical risk prediction modeling. METHODS We explore how incorporating knowledge about the underlying causal structure can provide insights about the transportability of diagnostic clinical risk prediction models to different settings. We further probe whether causal knowledge can be used to improve predictor selection in clinical risk prediction models. RESULTS A single-predictor model in the causal direction is likely to have better transportability than one in the anticausal direction in some scenarios. We empirically show that the Markov Blanket, the set of variables including the parents, children, and parents of the children of the outcome node in a DAG, is the optimal set of predictors for that outcome. CONCLUSIONS Our findings provide a theoretical basis for the intuition that a diagnostic clinical risk prediction model including causes as predictors is likely to be more transportable. Furthermore, using DAGs to identify Markov Blanket variables may be a useful, efficient strategy to select predictors in clinical risk prediction models if strong knowledge of the underlying causal structure exists or can be learned.
Collapse
Affiliation(s)
- Marco Piccininni
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
| | - Stefan Konigorski
- Digital Health & Machine Learning Research Group, Hasso Plattner Institute for Digital Engineering, Potsdam, Germany
- Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, USA
| | - Jessica L Rohmann
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Tobias Kurth
- Institute of Public Health, Charité - Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|
24
|
van Geloven N, Swanson SA, Ramspek CL, Luijken K, van Diepen M, Morris TP, Groenwold RHH, van Houwelingen HC, Putter H, le Cessie S. Prediction meets causal inference: the role of treatment in clinical prediction models. Eur J Epidemiol 2020; 35:619-630. [PMID: 32445007 PMCID: PMC7387325 DOI: 10.1007/s10654-020-00636-1] [Citation(s) in RCA: 45] [Impact Index Per Article: 11.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2020] [Accepted: 04/18/2020] [Indexed: 11/29/2022]
Abstract
In this paper we study approaches for dealing with treatment when developing a clinical prediction model. Analogous to the estimand framework recently proposed by the European Medicines Agency for clinical trials, we propose a 'predictimand' framework of different questions that may be of interest when predicting risk in relation to treatment started after baseline. We provide a formal definition of the estimands matching these questions, give examples of settings in which each is useful and discuss appropriate estimators including their assumptions. We illustrate the impact of the predictimand choice in a dataset of patients with end-stage kidney disease. We argue that clearly defining the estimand is equally important in prediction research as in causal inference.
Collapse
Affiliation(s)
- Nan van Geloven
- Department of Biomedical Data Sciences, Leiden University Medical Center, Zone S5-P, PO Box 9600, 2300 RC, Leiden, The Netherlands.
| | - Sonja A Swanson
- Department of Epidemiology, Erasmus MC, Rotterdam, The Netherlands
- Department of Epidemiology, Harvard T. H. Chan School of Public Health, Boston, USA
| | - Chava L Ramspek
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Kim Luijken
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Merel van Diepen
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Tim P Morris
- MRC Clinical Trials Unit, UCL London, London, UK
| | - Rolf H H Groenwold
- Department of Biomedical Data Sciences, Leiden University Medical Center, Zone S5-P, PO Box 9600, 2300 RC, Leiden, The Netherlands
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Hans C van Houwelingen
- Department of Biomedical Data Sciences, Leiden University Medical Center, Zone S5-P, PO Box 9600, 2300 RC, Leiden, The Netherlands
| | - Hein Putter
- Department of Biomedical Data Sciences, Leiden University Medical Center, Zone S5-P, PO Box 9600, 2300 RC, Leiden, The Netherlands
| | - Saskia le Cessie
- Department of Biomedical Data Sciences, Leiden University Medical Center, Zone S5-P, PO Box 9600, 2300 RC, Leiden, The Netherlands
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
25
|
Sperrin M, Martin GP, Sisk R, Peek N. Missing data should be handled differently for prediction than for description or causal explanation. J Clin Epidemiol 2020; 125:183-187. [PMID: 32540389 DOI: 10.1016/j.jclinepi.2020.03.028] [Citation(s) in RCA: 42] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2019] [Revised: 03/10/2020] [Accepted: 03/18/2020] [Indexed: 12/26/2022]
Abstract
Missing data are much studied in epidemiology and statistics. Theoretical development and application of methods for handling missing data have mostly been conducted in the context of prospective research data and with a goal of description or causal explanation. However, it is now common to build predictive models using routinely collected data, where missing patterns may convey important information, and one might take a pragmatic approach to optimizing prediction. Therefore, different methods to handle missing data may be preferred. Furthermore, an underappreciated issue in prediction modeling is that the missing data method used in model development may not match the method used when a model is deployed. This may lead to overoptimistic assessments of model performance. For prediction, particularly with routinely collected data, methods for handling missing data that incorporate information within the missingness pattern should be explored and further developed. Where missing data methods differ between model development and model deployment, the implications of this must be explicitly evaluated. The trade-off between building a prediction model that is causally principled, and building a prediction model that maximizes the use of all available information, should be carefully considered and will depend on the intended use of the model.
Collapse
Affiliation(s)
- Matthew Sperrin
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK.
| | - Glen P Martin
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Rose Sisk
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Niels Peek
- Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| |
Collapse
|
26
|
Sperrin M, Jenkins D, Martin GP, Peek N. Explicit causal reasoning is needed to prevent prognostic models being victims of their own success. J Am Med Inform Assoc 2020; 26:1675-1676. [PMID: 31722385 PMCID: PMC6857504 DOI: 10.1093/jamia/ocz197] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2019] [Accepted: 10/18/2019] [Indexed: 11/14/2022] Open
Affiliation(s)
- Matthew Sperrin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - David Jenkins
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - Glen P Martin
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| | - Niels Peek
- Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom
| |
Collapse
|
27
|
Beesley LJ, Salvatore M, Fritsche LG, Pandit A, Rao A, Brummett C, Willer CJ, Lisabeth LD, Mukherjee B. The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities. Stat Med 2020; 39:773-800. [PMID: 31859414 PMCID: PMC7983809 DOI: 10.1002/sim.8445] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2018] [Revised: 09/10/2019] [Accepted: 11/16/2019] [Indexed: 01/03/2023]
Abstract
Biobanks linked to electronic health records provide rich resources for health-related research. With improvements in administrative and informatics infrastructure, the availability and utility of data from biobanks have dramatically increased. In this paper, we first aim to characterize the current landscape of available biobanks and to describe specific biobanks, including their place of origin, size, and data types. The development and accessibility of large-scale biorepositories provide the opportunity to accelerate agnostic searches, expedite discoveries, and conduct hypothesis-generating studies of disease-treatment, disease-exposure, and disease-gene associations. Rather than designing and implementing a single study focused on a few targeted hypotheses, researchers can potentially use biobanks' existing resources to answer an expanded selection of exploratory questions as quickly as they can analyze them. However, there are many obvious and subtle challenges with the design and analysis of biobank-based studies. Our second aim is to discuss statistical issues related to biobank research such as study design, sampling strategy, phenotype identification, and missing data. We focus our discussion on biobanks that are linked to electronic health records. Some of the analytic issues are illustrated using data from the Michigan Genomics Initiative and UK Biobank, two biobanks with two different recruitment mechanisms. We summarize the current body of literature for addressing these challenges and discuss some standing open problems. This work complements and extends recent reviews about biobank-based research and serves as a resource catalog with analytical and practical guidance for statisticians, epidemiologists, and other medical researchers pursuing research using biobanks.
Collapse
Affiliation(s)
| | | | | | - Anita Pandit
- University of Michigan, Department of Biostatistics
| | - Arvind Rao
- University of Michigan, Department of Computational Medicine and Bioinformatics
| | - Chad Brummett
- University of Michigan, Department of Anesthesiology
| | - Cristen J. Willer
- University of Michigan, Department of Computational Medicine and Bioinformatics
| | | | | |
Collapse
|
28
|
van Bussel EF, Hoevenaar-Blom MP, Poortvliet RKE, Gussekloo J, van Dalen JW, van Gool WA, Richard E, Moll van Charante EP. Predictive value of traditional risk factors for cardiovascular disease in older people: A systematic review. Prev Med 2020; 132:105986. [PMID: 31958478 DOI: 10.1016/j.ypmed.2020.105986] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/13/2019] [Revised: 01/08/2020] [Accepted: 01/12/2020] [Indexed: 01/21/2023]
Abstract
With increasing age, associations between traditional risk factors (TRFs) and cardiovascular disease (CVD) shift. It is unknown which mid-life risk factors remain relevant predictors for CVD in older people. We systematically searched PubMed and EMBASE on August 16th 2019 for studies assessing predictive ability of >1 of fourteen TRFs for fatal and non-fatal CVD, in the general population aged 60+. We included 12 studies, comprising 11 unique cohorts. TRF were evaluated in 2 to 11 cohorts, and retained in 0-70% of the cohorts: age (70%), diabetes (64%), male sex (57%), systolic blood pressure (SBP) (50%), smoking (36%), high-density lipoprotein cholesterol (HDL) (33%), left ventricular hypertrophy (LVH) (33%), total cholesterol (22%), diastolic blood pressure (20%), antihypertensive medication use (AHM) (20%), body mass index (BMI) (0%), hypertension (0%), low-density lipoprotein cholesterol (0%). In studies with low to moderate risk of bias, systolic blood pressure (SBP) (80%), smoking (80%) and HDL cholesterol (60%) were more often retained. Model performance was moderate with C-statistics ranging from 0.61 to 0.77. Compared to middle-aged adults, in people aged 60+ different risk factors predict CVD and current prediction models perform only moderate at best. According to most studies, age, sex and diabetes seem valuable predictors of CVD in old-age. SBP, HDL cholesterol and smoking may also have predictive value. Other blood pressure and cholesterol related variables, BMI, and LVH seem of very limited or no additional value. Without competing risk analysis, predictors are overestimated.
Collapse
Affiliation(s)
- E F van Bussel
- Department of General Practice, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100DD Amsterdam, the Netherlands.
| | - M P Hoevenaar-Blom
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100 DD Amsterdam, the Netherlands; Department of Neurology, Donders Centre for Brain, Behaviour and Cognition, Radboud University Medical Center, Geert Grooteplein 10, 6525 GA Nijmegen, the Netherlands.
| | - R K E Poortvliet
- Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands.
| | - J Gussekloo
- Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands; Department of Gerontology and Geriatrics, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, Netherlands.
| | - J W van Dalen
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100 DD Amsterdam, the Netherlands; Department of Neurology, Donders Centre for Brain, Behaviour and Cognition, Radboud University Medical Center, Geert Grooteplein 10, 6525 GA Nijmegen, the Netherlands.
| | - W A van Gool
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100 DD Amsterdam, the Netherlands.
| | - E Richard
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100 DD Amsterdam, the Netherlands; Department of Neurology, Donders Centre for Brain, Behaviour and Cognition, Radboud University Medical Center, Geert Grooteplein 10, 6525 GA Nijmegen, the Netherlands.
| | - E P Moll van Charante
- Department of General Practice, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1100DD Amsterdam, the Netherlands.
| |
Collapse
|
29
|
Pajouheshnia R, Schuster NA, Groenwold RHH, Rutten FH, Moons KGM, Peelen LM. Accounting for time‐dependent treatment use when developing a prognostic model from observational data: A review of methods. STAT NEERL 2019. [DOI: 10.1111/stan.12193] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Affiliation(s)
- Romin Pajouheshnia
- Julius Center for Health Sciences and Primary CareUniversity Medical Center Utrecht Utrecht The Netherlands
- Division of Pharmacoepidemiology and Clinical PharmacologyUtrecht Institute for Pharmaceutical Sciences, Utrecht University Utrecht The Netherlands
| | - Noah A. Schuster
- Julius Center for Health Sciences and Primary CareUniversity Medical Center Utrecht Utrecht The Netherlands
| | - Rolf H. H. Groenwold
- Department of Clinical EpidemiologyLeiden University Medical Center Leiden The Netherlands
| | - Frans H. Rutten
- Julius Center for Health Sciences and Primary CareUniversity Medical Center Utrecht Utrecht The Netherlands
| | - Karel G. M. Moons
- Julius Center for Health Sciences and Primary CareUniversity Medical Center Utrecht Utrecht The Netherlands
| | - Linda M. Peelen
- Julius Center for Health Sciences and Primary CareUniversity Medical Center Utrecht Utrecht The Netherlands
| |
Collapse
|
30
|
Pajouheshnia R, Groenwold RHH, Peelen LM, Reitsma JB, Moons KGM. When and how to use data from randomised trials to develop or validate prognostic models. BMJ 2019; 365:l2154. [PMID: 31142454 DOI: 10.1136/bmj.l2154] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Affiliation(s)
- Romin Pajouheshnia
- Julius Centre for Health Sciences and Primary Care, University Medical Centre Utrecht, Utrecht University, 3508 GA Utrecht, Netherlands
- Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, Netherlands
| | - Rolf H H Groenwold
- Department of Clinical Epidemiology, Leiden University Medical Centre, Leiden, Netherlands
| | - Linda M Peelen
- Julius Centre for Health Sciences and Primary Care, University Medical Centre Utrecht, Utrecht University, 3508 GA Utrecht, Netherlands
| | - Johannes B Reitsma
- Julius Centre for Health Sciences and Primary Care, University Medical Centre Utrecht, Utrecht University, 3508 GA Utrecht, Netherlands
- Cochrane Netherlands, Utrecht, Netherlands
| | - Karel G M Moons
- Julius Centre for Health Sciences and Primary Care, University Medical Centre Utrecht, Utrecht University, 3508 GA Utrecht, Netherlands
- Cochrane Netherlands, Utrecht, Netherlands
| |
Collapse
|
31
|
Sperrin M, Martin GP, Pate A, Van Staa T, Peek N, Buchan I. Using marginal structural models to adjust for treatment drop-in when developing clinical prediction models. Stat Med 2018; 37:4142-4154. [PMID: 30073700 PMCID: PMC6282523 DOI: 10.1002/sim.7913] [Citation(s) in RCA: 27] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2017] [Revised: 05/31/2018] [Accepted: 06/25/2018] [Indexed: 01/19/2023]
Abstract
Clinical prediction models (CPMs) can inform decision making about treatment initiation, which requires predicted risks assuming no treatment is given. However, this is challenging since CPMs are usually derived using data sets where patients received treatment, often initiated postbaseline as "treatment drop-ins." This study proposes the use of marginal structural models (MSMs) to adjust for treatment drop-in. We illustrate the use of MSMs in the CPM framework through simulation studies that represent randomized controlled trials and real-world observational data and the example of statin initiation for cardiovascular disease prevention. The simulations include a binary treatment and a covariate, each recorded at two timepoints and having a prognostic effect on a binary outcome. The bias in predicted risk was examined in a model ignoring treatment, a model fitted on treatment-naïve patients (at baseline), a model including baseline treatment, and the MSM. In all simulation scenarios, all models except the MSM underestimated the risk of outcome given absence of treatment. These results were supported in the statin initiation example, which showed that ignoring statin initiation postbaseline resulted in models that significantly underestimated the risk of a cardiovascular disease event occurring within 10 years. Consequently, CPMs that do not acknowledge treatment drop-in can lead to underallocation of treatment. In conclusion, when developing CPMs to predict treatment-naïve risk, researchers should consider using MSMs to adjust for treatment drop-in, and also seek to exploit the ability of MSMs to allow estimation of individual treatment effects.
Collapse
Affiliation(s)
- Matthew Sperrin
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
| | - Glen P. Martin
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
| | - Alexander Pate
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
| | - Tjeerd Van Staa
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
| | - Niels Peek
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
| | - Iain Buchan
- Farr Institute, Faculty of Biology, Medicine and HealthUniversity of Manchester, Manchester Academic Health Science CentreManchesterUK
- Microsoft ResearchCambridgeUK
| |
Collapse
|