Statistical methods for next-generation clinical trials
Lead Research Organisation:
MRC Biostatistics Unit
Abstract
Clinical trials are used to test the effectiveness and safety of new treatments. In recent years they have become more and more expensive and have high rates of failure. Methods for reducing the cost of clinical trials and improving the chances of finding the truth are important. New technology means that new approaches to clinical trials are needed. This programme will conduct research into statistical methods for improving clinical trials.
The programme will cover three main areas. The first is research for including the large amount of biological information that can be measured for patients. The purpose of this is that different patients may benefit more from a treatment than others: we would like to be able to find this if it is true. The second is to explore how clinical trials can be more efficient by allowing new treatments to be added as they go along. This will reduce the cost and provide opportunities to ensure patients on a trial get the most suitable treatment for them. A third area is to improve the statistical analysis of trials which use complicated ‘composite endpoints’ which measure several things at once. This reduces the cost of clinical trials.
By working with doctors as well as statisticians we will make sure that this research is used in real clinical trials to benefit patients and decision-makers.
The programme will cover three main areas. The first is research for including the large amount of biological information that can be measured for patients. The purpose of this is that different patients may benefit more from a treatment than others: we would like to be able to find this if it is true. The second is to explore how clinical trials can be more efficient by allowing new treatments to be added as they go along. This will reduce the cost and provide opportunities to ensure patients on a trial get the most suitable treatment for them. A third area is to improve the statistical analysis of trials which use complicated ‘composite endpoints’ which measure several things at once. This reduces the cost of clinical trials.
By working with doctors as well as statisticians we will make sure that this research is used in real clinical trials to benefit patients and decision-makers.
Technical Summary
The process of developing and testing a new treatment or intervention takes a long time, a lot of money, and often ends in failure. The high cost is primarily due to expensive clinical trials, which are required to show that the treatment is safe and effective. Improving the efficiency of clinical trials, to make maximum use of limited resources, is a priority research area.
This research programme will develop statistical methodology to ensure that clinical trials have the tools necessary to cope with current and future challenges.
The first area of focus is statistical methodology for best using the increasing amount of high-dimensional biomarker data in clinical trials. With increasing availability of routinely collected biomarker data, modern clinical trials urgently require suitable methods to incorporate them prospectively. Current approaches rely on less efficient statistical methods such as testing each variant one-by-one in a logistic regression, and classifying patients as high-risk if they are positive for a certain number of biomarker. By combining novel adaptive designs and state-of-the-art high-dimensional statistical methods such as Bayesian sparse regression we can improve on this. Through working with clinicians, this novel methodology will be available for use in real trials for areas such as cardiovascular diseases and oncology.
A second area of focus is methodology for ongoing trials that test multiple treatments and biomarkers. In an ongoing trial new treatments and biomarkers are added in continually as treatments are found sufficiently promising to move to phase III trials, or are dropped due to lack of effectiveness. Some real trials are already doing this due to the considerable logistical and administrative advantages. This programme will focus on statistical issues in ongoing trials. This includes how to optimally choose decision criteria for dropping or progressing a drug to phase III and how to optimally plan phase III trials that result. Collaborations with a multidisciplinary set of statisticians and clinicians will allow us to implement developed methods in practice.
A third area of focus is to improve the analysis of trials using composite endpoints. In this case it is possible to gain considerable power by fitting a suitable model to the data. These methods will be applied to a variety of disease areas including oncology trials, rheumatoid arthritis and lupus.
This research programme will develop statistical methodology to ensure that clinical trials have the tools necessary to cope with current and future challenges.
The first area of focus is statistical methodology for best using the increasing amount of high-dimensional biomarker data in clinical trials. With increasing availability of routinely collected biomarker data, modern clinical trials urgently require suitable methods to incorporate them prospectively. Current approaches rely on less efficient statistical methods such as testing each variant one-by-one in a logistic regression, and classifying patients as high-risk if they are positive for a certain number of biomarker. By combining novel adaptive designs and state-of-the-art high-dimensional statistical methods such as Bayesian sparse regression we can improve on this. Through working with clinicians, this novel methodology will be available for use in real trials for areas such as cardiovascular diseases and oncology.
A second area of focus is methodology for ongoing trials that test multiple treatments and biomarkers. In an ongoing trial new treatments and biomarkers are added in continually as treatments are found sufficiently promising to move to phase III trials, or are dropped due to lack of effectiveness. Some real trials are already doing this due to the considerable logistical and administrative advantages. This programme will focus on statistical issues in ongoing trials. This includes how to optimally choose decision criteria for dropping or progressing a drug to phase III and how to optimally plan phase III trials that result. Collaborations with a multidisciplinary set of statisticians and clinicians will allow us to implement developed methods in practice.
A third area of focus is to improve the analysis of trials using composite endpoints. In this case it is possible to gain considerable power by fitting a suitable model to the data. These methods will be applied to a variety of disease areas including oncology trials, rheumatoid arthritis and lupus.
Organisations
- MRC Biostatistics Unit, United Kingdom (Lead Research Organisation)
- AstraZeneca plc (Collaboration)
- Philips research cambridge (Collaboration)
- University of Queensland, Australia (Collaboration)
- Lancaster University (Collaboration)
- Fundacio Institut d'Investigacio Oncologica Vall Hebron (VHIO) (Collaboration)
- University of Cambridge, United Kingdom (Collaboration)
- University of Birmingham, United Kingdom (Collaboration)
- Kyoto University, Japan (Collaboration)
Publications

Barrett T
(2017)
The longitudinal effect of ejaculation on seminal vesicle fluid volume and whole-prostate ADC as measured on prostate MRI.
in European radiology

Fonagy P
(2018)
Multisystemic therapy versus management as usual in the treatment of adolescent antisocial behaviour (START): a pragmatic, randomised controlled, superiority trial.
in The lancet. Psychiatry

Gerety EL
(2015)
Prospective study evaluating the relative sensitivity of 18F-NaF PET/CT for detecting skeletal metastases from renal cell carcinoma in comparison to multidetector CT and 99mTc-MDP bone scintigraphy, using an adaptive trial design.
in Annals of oncology : official journal of the European Society for Medical Oncology

Grayling MJ
(2017)
Stepped wedge cluster randomized controlled trial designs: a review of reporting quality and design features.
in Trials

Grayling MJ
(2017)
Group sequential designs for stepped-wedge cluster randomised trials.
in Clinical trials (London, England)

Kunz CU
(2017)
Two-stage phase II oncology designs using short-term endpoints for early stopping.
in Statistical methods in medical research

Law LM
(2016)
Use of an embedded, micro-randomised trial to investigate non-compliance in telehealth interventions.
in Clinical trials (London, England)

Lin CJ
(2017)
Improving phase II oncology trials using best observed RECIST response as an endpoint by modelling continuous tumour measurements.
in Statistics in medicine

McMenamin M
(2018)
Improving the analysis of composite endpoints in rare disease trials.
in Orphanet journal of rare diseases

Nikolic MZ
(2015)
Noninterventional statistical comparison of BTS and CHEST guidelines for size and severity in primary pneumothorax.
in The European respiratory journal

O'Connor JP
(2017)
Imaging biomarker roadmap for cancer studies.
in Nature reviews. Clinical oncology

Pallmann P
(2018)
Adaptive designs in clinical trials: why use them, and how to run and report them.
in BMC medicine

Pandit L
(2016)
HLA associations in South Asian multiple sclerosis.
in Multiple sclerosis (Houndmills, Basingstoke, England)

Ring H
(2018)
Training nurses in a competency framework to support adults with epilepsy and intellectual disability: the EpAID cluster RCT.
in Health technology assessment (Winchester, England)


Spencer AV
(2016)
An adaptive design for updating the threshold value of a continuous biomarker.
in Statistics in medicine

Villar S
(2018)
Response-adaptive designs for binary responses: How to offer patient benefit while being robust to time trends?
in Pharmaceutical Statistics

Villar SS
(2015)
Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges.
in Statistical science : a review journal of the Institute of Mathematical Statistics

Villar SS
(2015)
Response-adaptive randomization for multi-arm clinical trials using the forward looking Gittins index rule.
in Biometrics

Wason J
(2016)
Some recommendations for multi-arm multi-stage trials.
in Statistical methods in medical research

Wason J
(2017)
A multi-stage drop-the-losers design for multi-arm clinical trials.
in Statistical methods in medical research

Wason J.M.S.
(2015)
OptGS: An R package for finding near-optimal group-sequential designs
in Journal of Statistical Software

Wason JM
(2015)
A Bayesian adaptive design for biomarker trials with linked treatments.
in British journal of cancer

Wason JM
(2016)
A review of statistical designs for improving the efficiency of phase II studies in oncology.
in Statistical methods in medical research

Wason JM
(2016)
Improving the power of clinical trials of rheumatoid arthritis by using data on continuous scales when analysing response rates: an application of the augmented binary method.
in Rheumatology (Oxford, England)
Description | New adaptive design mentioned as 'research highlight' in Nature Reviews Clinical Oncology |
Geographic Reach | National |
Policy Influence Type | Influenced training of practitioners or researchers |
URL | http://www.nature.com/nrclinonc/journal/v12/n9/full/nrclinonc.2015.138.html |
Description | Biometrika Fellowship |
Amount | £96,860 (GBP) |
Organisation | Biometrika Trust |
Sector | Private |
Country | United Kingdom |
Start | 11/2014 |
End | 09/2016 |
Description | Gates Foundation - Dora Pereira |
Amount | £5,818 (GBP) |
Organisation | Bill and Melinda Gates Foundation |
Sector | Charity/Non Profit |
Country | United States |
Start | 04/2016 |
End | 03/2018 |
Description | Health Technology Assessment |
Amount | £1,792,088 (GBP) |
Organisation | National Institute for Health Research |
Department | Health Technology Assessment Programme (HTA) |
Sector | Public |
Country | United Kingdom |
Start | 02/2017 |
End | 12/2021 |
Description | Improving the robustness of complex and structured study designd for clinical trials |
Amount | £158,598 (GBP) |
Organisation | Biometrika Trust |
Sector | Private |
Country | United Kingdom |
Start | 12/2018 |
End | 12/2021 |
Description | MRC- Alistair Coles |
Amount | £56,487 (GBP) |
Organisation | Medical Research Council (MRC) |
Sector | Academic/University |
Country | United Kingdom |
Start | 07/2016 |
End | 06/2020 |
Description | Methodology Research Programme |
Amount | £226,204 (GBP) |
Organisation | Medical Research Council (MRC) |
Department | MRC/NIHR Methodology Research Programme |
Sector | Academic/University |
Country | United Kingdom |
Start | 02/2017 |
End | 01/2020 |
Description | UCL -Peter Fonagy |
Amount | £1,459,421 (GBP) |
Organisation | National Institute for Health Research |
Sector | Public |
Country | United Kingdom |
Start | 11/2015 |
End | 10/2020 |
Description | AstraZeneca rheumatoid arthritis and SLE collaboration |
Organisation | AstraZeneca |
Country | United Kingdom |
Sector | Private |
PI Contribution | The Biostatistics unit funded a PhD student to work under my supervision on methodology for applying the augmented binary method, an improved analysis technique for composite outcomes, to rheumatoid arthritis and systemic lupus erythematosus. The PhD student, Martina McMenamin started in October 2016. |
Collaborator Contribution | AstraZeneca has provided expertise from Anna Berglind and Martin Jenkins and access to clinical trial datasets in each disease. This has helped a lot with showing the methodology is useful in real life. |
Impact | So far we have published a paper in Rheumatology, prior to Martina starting. |
Start Year | 2016 |
Description | Australian platform trial collaboration |
Organisation | University of Queensland |
Country | Australia |
Sector | Academic/University |
PI Contribution | I was invited to be a co-investigator on a clinical trial submission to the Australian Medical Research Council. I provided input to the application. My role will be to provide methodology input to the design and analysis of the trial. |
Collaborator Contribution | Professor Claire Wainwright led the application and will be the chief investigator of the trial. |
Impact | Successful application to Australian national health and medical research council, with just over $2m funding. |
Start Year | 2017 |
Description | Basket of Baskets trial |
Organisation | Fundacio Institut d'Investigacio Oncologica Vall Hebron (VHIO) |
Country | Spain |
Sector | Hospitals |
PI Contribution | VHIO are leading a European wide Basket trial which will investigate novel targeted oncology treatments for different tumour types. Cambridge Cancer Centre are involved and I am providing the statistical input to this trial. |
Collaborator Contribution | VHIO have led the development of the trial and have successfully attracted several million euros worth of funding from Roche. |
Impact | Trial has not yet started so no outcomes yet. |
Start Year | 2017 |
Description | CRUK grant |
Organisation | University of Birmingham |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I have provided expertise in efficient statistical analysis of phase II oncology trials using the RECIST criteria. |
Collaborator Contribution | Individuals at the University of Birmingham provided clinical and applied statistical expertise that has helped us jointly develop a programme of work for a grant application. |
Impact | With individuals at the University of Birmingham, I have successfully applied for a Cancer Research UK grant, to start in Jan 2015. |
Start Year | 2013 |
Description | MAMS grant |
Organisation | Lancaster University |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Provided input to multiple submitted papers, including two in 2013/2014, that covered multi-arm multi-stage trials and phase II oncology trials. I provided input into writing a grant that was funded by the MRC methodology research panel. I was a co-investigator on this grant. |
Collaborator Contribution | Dr Thomas Jaki has provided complementary expertise into the writing of papers and the grant application. |
Impact | Multiple papers published since 2012 (recorded under publications). Successful grant application. |
Start Year | 2011 |
Description | Methodology advisor for Healthy Campuses trial |
Organisation | University of Kyoto |
Country | Japan |
Sector | Academic/University |
PI Contribution | I helped advise Professor Toshi Furukawa on the design of a factorial trial in Japan, which will investigate which components of a CBT app are most beneficial to depressed undergraduate students. |
Collaborator Contribution | I contributed to the statistical design and analysis plan of the trial. |
Impact | Protocol paper is to be submitted soon. |
Start Year | 2017 |
Description | Philips Research Cambridge collaboration |
Organisation | Philips Research Cambridge |
Country | United Kingdom |
Sector | Private |
PI Contribution | I am the academic supervisor for a Ph.D. student on the subject of 'Adaptive designs for telehealth trials' |
Collaborator Contribution | Individuals at Philips Research Cambridge have provided expertise on telehealth trials and have hosted the student for a research visit. They also provided a financial contribution to the EPSRC case award that funds the studentship. |
Impact | The student (Lisa Law) started in October 2013 and has been upgraded to full Ph.D. student status in October 2014. During her time as a student, Lisa published two papers. Unfortunately Lisa chose to drop out of the PhD programme in 2016 and submitted what she had done up to that point for a MPhil degree, which she received successfully. |
Start Year | 2012 |
Description | SMARTer trial collaboration |
Organisation | University of Cambridge |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | I have provided expertise on statistical design of adaptive clinical trials to develop a suitable clinical trial design for the needs of the collaborators. |
Collaborator Contribution | Input on the design and clinical expertise. They have also written a grant application to fund the trials. |
Impact | We have submitted a paper on the trial design and a grant application to the HTA efficient trial design call (currently at outline stage). |
Start Year | 2012 |
Title | OptGS R package |
Description | This is a publically available R package for finding optimal group-sequential clinical trial designs. It is available from the CRAN repository (which involves validation steps). |
Type Of Technology | Software |
Year Produced | 2015 |
Open Source License? | Yes |
Impact | The software package description and documentation has been published in the Journal of Statistical Software. |
URL | https://cran.r-project.org/web/packages/OptGS/index.html |
Description | AZ-MRC Science Symposium 2017 on 'All Data Great and Small' |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Professional Practitioners |
Results and Impact | In conjunction with the AstraZeneca Biometrics Group, BSU organised a jointly sponsored science symposium on 'All Data Great and Small: Advancing clinical research through quantitative science'. 150 attendees from a cross-section of organisations came to the complimentary event, where various talks from external eminent speakers took place. The symposium provided an opportunity to advance knowledge and understanding on data driven research, and establish new contacts and potential new collaborations for future research. James Wason, Programme Leader Track, sat on the symposium organising committee - provided valuable ideas and contributions to develop the finalised agenda and format for the symposium. |
Year(s) Of Engagement Activity | 2017 |
Description | Armitage Lectures |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Professional Practitioners |
Results and Impact | Annual workshop and lecture created and hosted by the MRC Biostatistics Unit, to honour the immense contributions of Professor Peter Armitage who was at the unit from 1947 to 1961, and whose work is recognised throughout the world as achieving a successful balance between methodological rigour and applied commonsense, to which all statisticians aspire. An eminent medical statistician visits for a week and works with members of the unit. The highlight is the Armitage Lecture, where more than 100 delegates attend. This event raises the unit research profile and creates new collaborations. |
Year(s) Of Engagement Activity | 2016,2017 |
URL | https://www.mrc-bsu.cam.ac.uk/news-and-events/armitage-lectureships-and-workshops/ |
Description | Cambridge Science Festival |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Schools |
Results and Impact | Each year BSU participate in Cambridge Science Festival - members of the general public explore and discuss issues of scientific interest and concern, through a series of different events. The festival also aims to raise aspirations by encouraging young people to consider a career in science, technology, engineering or mathematics. BSU take part over two full days - 'Science Saturday' and the 'Cambridge Biomedical Campus' day. The unit presents a stand with 4 - 5 interactive activities that each communicate a basic statistical method or idea, representing one of the four research themes in the unit. Each year a new activity is developed and delivered requiring scientific input from staff and students across the unit. Over the two days, BSU engage with approximately 500 adults and children who visit the festival. |
Year(s) Of Engagement Activity | 2016,2017 |
Description | Imaging workshop |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | I was invited to give a talk to a mixture of PhD students and postdocs working in imaging research on "Introduction to statistics for clinical trial design". This was part of a course on clinical trials for that group. |
Year(s) Of Engagement Activity | 2015 |
Description | Media enquiry - 'Trust Me I'm a Doctor' |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Media (as a channel to the public) |
Results and Impact | James Wason, Programme Leader Track, provided background research on clinical trials research for BBC 2 documentary 'Trust Me I'm a Doctor' |
Year(s) Of Engagement Activity | 2016 |
Description | Talk at NIHR statistics group meeting |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Professional Practitioners |
Results and Impact | I was invited to give a talk on methodology research to the annual meeting of the NIHR Statistics Group |
Year(s) Of Engagement Activity | 2017 |
Description | Talk at patients event |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Patients, carers and/or patient groups |
Results and Impact | I was invited to give a talk about novel design in clinical trials to a event focused on patients with polycystic kidney disease. |
Year(s) Of Engagement Activity | 2017 |
Description | Talk to pharmaceutical statisticians meeting |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Industry/Business |
Results and Impact | I was invited to give a talk to a PSI meeting on Bayesian methods in trials. |
Year(s) Of Engagement Activity | 2018 |