Dataset Information

Can machine learning improve randomized clinical trial analysis?

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.

SUBMITTER: Romero J

PROVIDER: S-EPMC8435025 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Can machine learning improve randomized clinical trial analysis?

Romero Juan J Chiang Sharon S Goldenholz Daniel M DM

Seizure 20210802

<h4>Purpose</h4>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.<h4>Methods</h4>Five candidate deep learning architectures with 54 permutations of hyperparameters were compared to the traditional standard, median percent ch ...[more]

PMID: 34365104

Similar Datasets

Project description:BackgroundColorectal cancer (CRC) is a common intestinal malignancy worldwide, posing a serious threat to public health. Due to its high heterogeneity, prognosis and drug response of different CRC patients vary widely, limiting the effectiveness of traditional treatment. Therefore, this study aims to construct a novel CRC prognostic signature using machine learning algorithms to assist in making informed clinical decisions and improving treatment outcomes.MethodsGene expression matrix and clinical information of CRC patients were obtained from the The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Then, genes with prognostic value were identified through univariate Cox regression analysis. Next, nine machine learning algorithms, including least absolute shrinkage and selection operator (LASSO), gradient boosting machine (GBM), CoxBoost, plsRcox, Ridge, Enet, StepCox, SuperPC and survivalSVM were integrated to form 97 combinations, which was employed to screen the best strategy for building a prognostic model based on the average C-index in the three CRC cohorts. Kaplan Meier survival analysis, receiver operating curve (ROC) analysis and multivariate regression analysis were conducted to assess the predictive performance of the constructed signature. Furthermore, the CIBERSORT and ESTIMATE algorithms were utilized to quantify the infiltration level of immune cells. Besides, a nomogram were developed to predict 1-, 2-, and 3-year overall survival (OS) probabilities for individual patient.ResultsA prognostic signature consisting of 13 genes was developed utilizing LASSO Cox regression and GBM methods. Across both the training and validation datasets, the performance evaluation consistently indicated the signature's capacity to accurately predict the prognosis of CRC patients. Especially, compared with 30 published signatures, the 13-gene model exhibited dramatically superior predictive power. Even within clinical subgroups, it could still precisely stratify the prognosis. Functional analysis revealed a robust association between the signature and the immune status as well as chemotherapy response in CRC patients. Furthermore, a nomogram was created based on the signature-derived risk score, which demonstrated a strong predictive ability for OS in CRC patients.ConclusionsThe 13-gene prognostic signature is expected to be a valuable tool for risk stratification, survival prediction, and treatment evaluation of patients with CRC.

Project description:Few randomized controlled trials (RCTs) report interventions targeting improvement of frailty status as an outcome.This RCT enrolled 117 older adults (65-79?years of age) in Toufen, Taiwan who scored 3-6 on The Chinese Canadian Study of Health and Aging Clinical Frailty Scale Telephone Version and then score ?1 on the Cardiovascular Health Study Phenotypic Classification of Frailty (CHS_PCF). With a two by two factorial design, subjects were randomly assigned to interventions (Exercise and nutrition, EN, n?=?55 or problem solving therapy, PST, n?=?57) or controls (non-EN, n?=?62 or non-PST, n?=?60). Educational booklets were provided to all. EN group subjects received nutrition consultation and a thrice-weekly exercise-training program while PST group subjects received 6 sessions in 3?month. Subjects were followed at 3, 6, and 12?months. Primary outcome was improvement of the CHS_PCF by at least one category (from pre-frail to robust, or from frail to pre-frail or robust) from baseline assessments. One hundred and one completed final assessments. Intention-to-treat analysis with the generalized estimating equation model was applied with adjustment for time and treatment-by-time interactions.Mean age was 71.4?±?3.7?years, with 59% females. Baseline characteristic were generally comparable between groups. EN group subjects had a higher improvement rate on the primary outcome than non-EN group subjects (45% vs 27%, adjusted p?=?0.008) at 3?months, but not 6 or 12?months. They also had more increase of serum 25(OH) vitamin D level (4.9?±?7.7 vs 1.2?±?5.4, p?=?0.006) and lower percentage of osteopenia (74% vs 89% p?=?0.042) at 12?months. PST group subjects had better improvement (2.7?±?6.1 vs 0.2?±?6.7, p?=?0.035, 6-month) and less deterioration (-3.5?±?9.7 vs -7.1?±?8.7, p?=?0.036, 12-month) of dominant leg extension power than non-PST subjects. Some secondary outcomes were also improved in control groups (non-EN or non-PST). No adverse effects were reported.The three-month EN intervention resulted in short-term (3-month) frailty status improvement and long-term effect on bone mineral density and serum vitamin D (12-month) among Taiwanese community-dwelling elders. The effect of PST was less pronounced.ClinicalTrials.gov: EC0970301

Dataset Information

Can machine learning improve randomized clinical trial analysis?

Purpose

Methods

Results

Conclusion

Publications

Can machine learning improve randomized clinical trial analysis?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets