Literature DB >> 34365104

Can machine learning improve randomized clinical trial analysis?

Juan Romero1, Sharon Chiang2, Daniel M Goldenholz3.   

Abstract

PURPOSE: Recently a realistic simulator of patient seizure diaries was developed that can reproduce effects seen in randomized clinical trials (RCTs). RCTs suffer from high costs and statistical inefficiencies. Using realistic simulation and machine learning this study aimed to identify a more statistically efficient outcome metric.
METHODS: Five candidate deep learning architectures with 54 permutations of hyperparameters were compared to the traditional standard, median percent change (MPC). Each were also tested for type 1 error. All models had similar outcomes, with appropriate low levels of type 1 error.
RESULTS: The simplest model was equivalent to a logistic regression of a histogram of individual percentage changes in seizure rate, requiring 21-22% less patients to discriminate drug from placebo at 90% power. This model was referred to as LPC.
CONCLUSION: Future studies to validate LPC may enable faster, cheaper and more efficient clinical trials.
Copyright © 2021 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Machine learning; Medication; Modeling; Randomized controlled trial

Mesh:

Year:  2021        PMID: 34365104      PMCID: PMC8435025          DOI: 10.1016/j.seizure.2021.07.033

Source DB:  PubMed          Journal:  Seizure        ISSN: 1059-1311            Impact factor:   3.414


  7 in total

1.  Circadian and circaseptan rhythms in human epilepsy: a retrospective cohort study.

Authors:  Philippa J Karoly; Daniel M Goldenholz; Dean R Freestone; Robert E Moss; David B Grayden; William H Theodore; Mark J Cook
Journal:  Lancet Neurol       Date:  2018-09-12       Impact factor: 44.182

2.  Treatment Outcomes in Patients With Newly Diagnosed Epilepsy Treated With Established and New Antiepileptic Drugs: A 30-Year Longitudinal Cohort Study.

Authors:  Zhibin Chen; Martin J Brodie; Danny Liew; Patrick Kwan
Journal:  JAMA Neurol       Date:  2018-03-01       Impact factor: 18.302

3.  Does accounting for seizure frequency variability increase clinical trial power?

Authors:  Daniel M Goldenholz; Shira R Goldenholz; Robert Moss; Jacqueline French; Daniel Lowenstein; Ruben Kuzniecky; Sheryl Haut; Sabrina Cristofaro; Kamil Detyniecki; John Hixson; Philippa Karoly; Mark Cook; Alex Strashny; William H Theodore; Carl Pieper
Journal:  Epilepsy Res       Date:  2017-07-25       Impact factor: 3.045

4.  Comparing the efficacy, exposure, and cost of clinical trial analysis methods.

Authors:  Andreas Oliveira; Juan M Romero; Daniel M Goldenholz
Journal:  Epilepsia       Date:  2019-11-14       Impact factor: 5.864

Review 5.  Seizure clusters: characteristics and treatment.

Authors:  Sheryl R Haut
Journal:  Curr Opin Neurol       Date:  2015-04       Impact factor: 5.710

6.  Natural variability in seizure frequency: Implications for trials and placebo.

Authors:  Juan Romero; Phil Larimer; Bernard Chang; Shira R Goldenholz; Daniel M Goldenholz
Journal:  Epilepsy Res       Date:  2020-03-06       Impact factor: 3.045

7.  Statistical efficiency of patient data in randomized clinical trials of epilepsy treatments.

Authors:  Juan Romero; Daniel M Goldenholz
Journal:  Epilepsia       Date:  2020-07-13       Impact factor: 5.864

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.