Literature DB >> 30857410

Clinical Value of Predicting Individual Treatment Effects for Intensive Blood Pressure Therapy.

Tony Duan1, Pranav Rajpurkar1, Dillon Laird1, Andrew Y Ng1, Sanjay Basu2.   

Abstract

BACKGROUND: The absolute risk reduction (ARR) in cardiovascular events from therapy is generally assumed to be proportional to baseline risk-such that high-risk patients benefit most. Yet newer analyses have proposed using randomized trial data to develop models that estimate individual treatment effects. We tested 2 hypotheses: first, that models of individual treatment effects would reveal that benefit from intensive blood pressure therapy is proportional to baseline risk; and second, that a machine learning approach designed to predict heterogeneous treatment effects-the X-learner meta-algorithm-is equivalent to a conventional logistic regression approach. METHODS AND
RESULTS: We compared conventional logistic regression to the X-learner approach for prediction of 3-year cardiovascular disease event risk reduction from intensive (target systolic blood pressure <120 mm Hg) versus standard (target <140 mm Hg) blood pressure treatment, using individual participant data from the SPRINT (Systolic Blood Pressure Intervention Trial; N=9361) and ACCORD BP (Action to Control Cardiovascular Risk in Diabetes Blood Pressure; N=4733) trials. Each model incorporated 17 covariates, an indicator for treatment arm, and interaction terms between covariates and treatment. Logistic regression had lower C statistic for benefit than the X-learner (0.51 [95% CI, 0.49-0.53] versus 0.60 [95% CI, 0.58-0.63], respectively). Following the logistic regression's recommendation for individualized therapy produced restricted mean time until cardiovascular disease event of 1065.47 days (95% CI, 1061.04-1069.35), while following the X-learner's recommendation improved mean time until cardiovascular disease event to 1068.71 days (95% CI, 1065.42-1072.08). Calibration was worse for logistic regression; it over-estimated ARR attributable to intensive treatment (slope between predicted and observed ARR of 0.73 [95% CI, 0.30-1.14] versus 1.06 [95% CI, 0.74-1.32] for the X-learner, compared with the ideal of 1). Predicted ARRs using logistic regression were generally proportional to baseline pretreatment cardiovascular risk, whereas the X-learner observed-correctly-that individual treatment effects were often not proportional to baseline risk.
CONCLUSIONS: Predictions for individual treatment effects from trial data reveal that patients may experience ARRs not simply proportional to baseline cardiovascular disease risk. Machine learning methods may improve discrimination and calibration of individualized treatment effect estimates from clinical trial data. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov . Unique identifiers: NCT01206062; NCT00000620.

Entities:  

Keywords:  blood pressure; calibration; cardiovascular disease; machine learning; risk factors

Mesh:

Substances:

Year:  2019        PMID: 30857410      PMCID: PMC6756170          DOI: 10.1161/CIRCOUTCOMES.118.005010

Source DB:  PubMed          Journal:  Circ Cardiovasc Qual Outcomes        ISSN: 1941-7713


  24 in total

1.  Development of a new diabetes risk prediction tool for incident coronary heart disease events: the Multi-Ethnic Study of Atherosclerosis and the Heinz Nixdorf Recall Study.

Authors:  Joseph Yeboah; Raimund Erbel; Joseph Chris Delaney; Robin Nance; Mengye Guo; Alain G Bertoni; Matthew Budoff; Susanne Moebus; Karl-Heinz Jöckel; Gregory L Burke; Nathan D Wong; Nils Lehmann; David M Herrington; Stefan Möhlenkamp; Philip Greenland
Journal:  Atherosclerosis       Date:  2014-08-14       Impact factor: 5.162

2.  Learning About Machine Learning: The Promise and Pitfalls of Big Data and the Electronic Health Record.

Authors:  Rahul C Deo; Brahmajee K Nallamothu
Journal:  Circ Cardiovasc Qual Outcomes       Date:  2016-11-08

3.  2013 ACC/AHA guideline on the assessment of cardiovascular risk: a report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines.

Authors:  David C Goff; Donald M Lloyd-Jones; Glen Bennett; Sean Coady; Ralph B D'Agostino; Raymond Gibbons; Philip Greenland; Daniel T Lackland; Daniel Levy; Christopher J O'Donnell; Jennifer G Robinson; J Sanford Schwartz; Susan T Shero; Sidney C Smith; Paul Sorlie; Neil J Stone; Peter W F Wilson; Harmon S Jordan; Lev Nevo; Janusz Wnek; Jeffrey L Anderson; Jonathan L Halperin; Nancy M Albert; Biykem Bozkurt; Ralph G Brindis; Lesley H Curtis; David DeMets; Judith S Hochman; Richard J Kovacs; E Magnus Ohman; Susan J Pressler; Frank W Sellke; Win-Kuang Shen; Sidney C Smith; Gordon F Tomaselli
Journal:  Circulation       Date:  2013-11-12       Impact factor: 29.690

4.  The proposed 'concordance-statistic for benefit' provided a useful metric when modeling heterogeneous treatment effects.

Authors:  David van Klaveren; Ewout W Steyerberg; Patrick W Serruys; David M Kent
Journal:  J Clin Epidemiol       Date:  2017-11-11       Impact factor: 6.437

5.  Impact of Cardiovascular Risk on the Relative Benefit and Harm of Intensive Treatment of Hypertension.

Authors:  Robert A Phillips; Jiaqiong Xu; Leif E Peterson; Ryan M Arnold; Joseph A Diamond; Adam E Schussheim
Journal:  J Am Coll Cardiol       Date:  2018-03-07       Impact factor: 24.094

6.  Effects of intensive blood-pressure control in type 2 diabetes mellitus.

Authors:  William C Cushman; Gregory W Evans; Robert P Byington; David C Goff; Richard H Grimm; Jeffrey A Cutler; Denise G Simons-Morton; Jan N Basile; Marshall A Corson; Jeffrey L Probstfield; Lois Katz; Kevin A Peterson; William T Friedewald; John B Buse; J Thomas Bigger; Hertzel C Gerstein; Faramarz Ismail-Beigi
Journal:  N Engl J Med       Date:  2010-03-14       Impact factor: 91.245

7.  Using internally developed risk models to assess heterogeneity in treatment effects in clinical trials.

Authors:  James F Burke; Rodney A Hayward; Jason P Nelson; David M Kent
Journal:  Circ Cardiovasc Qual Outcomes       Date:  2014-01-14

8.  General cardiovascular risk profile for use in primary care: the Framingham Heart Study.

Authors:  Ralph B D'Agostino; Ramachandran S Vasan; Michael J Pencina; Philip A Wolf; Mark Cobain; Joseph M Massaro; William B Kannel
Journal:  Circulation       Date:  2008-01-22       Impact factor: 29.690

9.  Assessing and reporting heterogeneity in treatment effects in clinical trials: a proposal.

Authors:  David M Kent; Peter M Rothwell; John P A Ioannidis; Doug G Altman; Rodney A Hayward
Journal:  Trials       Date:  2010-08-12       Impact factor: 2.279

10.  Estimating treatment effects for individual patients based on the results of randomised clinical trials.

Authors:  Johannes A N Dorresteijn; Frank L J Visseren; Paul M Ridker; Annemarie M J Wassink; Nina P Paynter; Ewout W Steyerberg; Yolanda van der Graaf; Nancy R Cook
Journal:  BMJ       Date:  2011-10-03
View more
  7 in total

1.  Cardioinformatics: the nexus of bioinformatics and precision cardiology.

Authors:  Bohdan B Khomtchouk; Diem-Trang Tran; Kasra A Vand; Matthew Might; Or Gozani; Themistocles L Assimes
Journal:  Brief Bioinform       Date:  2020-12-01       Impact factor: 11.622

2.  Using the Causal Inference Framework to Support Individualized Drug Treatment Decisions Based on Observational Healthcare Data.

Authors:  Andreas D Meid; Carmen Ruff; Lucas Wirbka; Felicitas Stoll; Hanna M Seidling; Andreas Groll; Walter E Haefeli
Journal:  Clin Epidemiol       Date:  2020-11-02       Impact factor: 4.790

Review 3.  Artificial Intelligence and Hypertension: Recent Advances and Future Outlook.

Authors:  Thanat Chaikijurajai; Luke J Laffin; Wai Hong Wilson Tang
Journal:  Am J Hypertens       Date:  2020-11-03       Impact factor: 3.080

Review 4.  Applications of artificial intelligence for hypertension management.

Authors:  Kelvin Tsoi; Karen Yiu; Helen Lee; Hao-Min Cheng; Tzung-Dau Wang; Jam-Chin Tay; Boon Wee Teo; Yuda Turana; Arieska Ann Soenarta; Guru Prasad Sogunuru; Saulat Siddique; Yook-Chin Chia; Jinho Shin; Chen-Huan Chen; Ji-Guang Wang; Kazuomi Kario
Journal:  J Clin Hypertens (Greenwich)       Date:  2021-02-03       Impact factor: 3.738

5.  Teaching reproducible research for medical students and postgraduate pharmaceutical scientists.

Authors:  Andreas D Meid
Journal:  BMC Res Notes       Date:  2021-12-09

6.  Can Machine Learning from Real-World Data Support Drug Treatment Decisions? A Prediction Modeling Case for Direct Oral Anticoagulants.

Authors:  Andreas D Meid; Lucas Wirbka; Andreas Groll; Walter E Haefeli
Journal:  Med Decis Making       Date:  2021-12-15       Impact factor: 2.749

7.  Generalizability of heterogeneous treatment effects based on causal forests applied to two randomized clinical trials of intensive glycemic control.

Authors:  Sridharan Raghavan; Kevin Josey; Gideon Bahn; Domenic Reda; Sanjay Basu; Seth A Berkowitz; Nicholas Emanuele; Peter Reaven; Debashis Ghosh
Journal:  Ann Epidemiol       Date:  2021-07-17       Impact factor: 3.797

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.