Dataset Information

Using supervised machine learning classifiers to estimate likelihood of participating in clinical trials of a de-identified version of ResearchMatch.

ABSTRACT:

Introduction

Lack of participation in clinical trials (CTs) is a major barrier for the evaluation of new pharmaceuticals and devices. Here we report the results of the analysis of a dataset from ResearchMatch, an online clinical registry, using supervised machine learning approaches and a deep learning approach to discover characteristics of individuals more likely to show an interest in participating in CTs.

Methods

We trained six supervised machine learning classifiers (Logistic Regression (LR), Decision Tree (DT), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor Classifier (KNC), Adaboost Classifier (ABC) and a Random Forest Classifier (RFC)), as well as a deep learning method, Convolutional Neural Network (CNN), using a dataset of 841,377 instances and 20 features, including demographic data, geographic constraints, medical conditions and ResearchMatch visit history. Our outcome variable consisted of responses showing specific participant interest when presented with specific clinical trial opportunity invitations ('yes' or 'no'). Furthermore, we created four subsets from this dataset based on top self-reported medical conditions and gender, which were separately analysed.

Results

The deep learning model outperformed the machine learning classifiers, achieving an area under the curve (AUC) of 0.8105.

Conclusions

The results show sufficient evidence that there are meaningful correlations amongst predictor variables and outcome variable in the datasets analysed using the supervised machine learning classifiers. These approaches show promise in identifying individuals who may be more likely to participate when offered an opportunity for a clinical trial.

SUBMITTER: Vazquez J

PROVIDER: S-EPMC8057403 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:OBJECTIVE:We have previously found that acute psychological stress may affect mitochondria and trigger an increase in serum mitochondrial DNA, known as circulating cell-free mtDNA (ccf-mtDNA). Similar to other stress reactivity measures, there are substantial unexplained inter-individual differences in the magnitude of ccf-mtDNA reactivity, as well as within-person differences across different occasions of testing. Here, we sought to identify psychological and physiological predictors of ccf-mtDNA reactivity using machine learning-based multivariate classifiers. METHOD:We used data from serum ccf-mtDNA concentration measured pre- and post-stress in 46 healthy midlife adults tested on two separate occasions. To identify variables predicting the magnitude of ccf-mtDNA reactivity, two multivariate classification models, partial least-squares discriminant analysis (PLS-DA) and random forest (RF), were trained to discriminate between high and low ccf-mtDNA responders. Potential predictors used in the models included state variables such as physiological measures and affective states, and trait variables such as sex and personality measures. Variables identified across both models were considered to be predictors of ccf-mtDNA reactivity and selected for downstream analyses. RESULTS:Identified predictors were significantly enriched for state over trait measures (X2?=?7.03; p?=?0.008) and for physiological over psychological measures (X2?=?4.36; p?=?0.04). High responders were more likely to be male (X2?=?26.95; p?<?0.001) and differed from low-responders on baseline cardiovascular and autonomic measures, and on stress-induced reduction in fatigue (Cohen's d?=?0.38-0.73). These group-level findings also accurately accounted for within-person differences in 90% of cases. CONCLUSION:These results suggest that acute cardiovascular and psychological indices, rather than stable individual traits, predict stress-induced ccf-mtDNA reactivity. This work provides a proof-of-concept that machine learning approaches can be used to explore determinants of inter-individual and within-person differences in stress psychophysiology.

Project description:Bovine respiratory disease (BRD) is a multifactorial disease involving complex host immune interactions shaped by pathogenic agents and environmental factors. Advancements in RNA sequencing and associated analytical methods are improving our understanding of host response related to BRD pathophysiology. Supervised machine learning (ML) approaches present one such method for analyzing new and previously published transcriptome data to identify novel disease-associated genes and mechanisms. Our objective was to apply ML models to lung and immunological tissue datasets acquired from previous clinical BRD experiments to identify genes that classify disease with high accuracy. Raw mRNA sequencing reads from 151 bovine datasets (n = 123 BRD, n = 28 control) were downloaded from NCBI-GEO. Quality filtered reads were assembled in a HISAT2/Stringtie2 pipeline. Raw gene counts for ML analysis were normalized, transformed, and analyzed with MLSeq, utilizing six ML models. Cross-validation parameters (fivefold, repeated 10 times) were applied to 70% of the compiled datasets for ML model training and parameter tuning; optimized ML models were tested with the remaining 30%. Downstream analysis of significant genes identified by the top ML models, based on classification accuracy for each etiological association, was performed within WebGestalt and Reactome (FDR ≤ 0.05). Nearest shrunken centroid and Poisson linear discriminant analysis with power transformation models identified 154 and 195 significant genes for IBR and BRSV, respectively; from these genes, the two ML models discriminated IBR and BRSV with 100% accuracy compared to sham controls. Significant genes classified by the top ML models in IBR (154) and BRSV (195), but not BVDV (74), were related to type I interferon production and IL-8 secretion, specifically in lymphoid tissue and not homogenized lung tissue. Genes identified in Mannheimia haemolytica infections (97) were involved in activating classical and alternative pathways of complement. Novel findings, including expression of genes related to reduced mitochondrial oxygenation and ATP synthesis in consolidated lung tissue, were discovered. Genes identified in each analysis represent distinct genomic events relevant to understanding and predicting clinical BRD. Our analysis demonstrates the utility of ML with published datasets for discovering functional information to support the prediction and understanding of clinical BRD.

Project description:BackgroundKnee osteoarthritis is the most prevalent chronic musculoskeletal debilitating disease. Current treatments are only symptomatic, and to improve this, we need a robust prediction model to stratify patients at an early stage according to the risk of joint structure disease progression. Some genetic factors, including single nucleotide polymorphism (SNP) genes and mitochondrial (mt)DNA haplogroups/clusters, have been linked to this disease. For the first time, we aim to determine, by using machine learning, whether some SNP genes and mtDNA haplogroups/clusters alone or combined could predict early knee osteoarthritis structural progressors.MethodsParticipants (901) were first classified for the probability of being structural progressors. Genotyping included SNP genes TP63, FTO, GNL3, DUS4L, GDF5, SUPT3H, MCF2L, and TGFA; mtDNA haplogroups H, J, T, Uk, and others; and clusters HV, TJ, KU, and C-others. They were considered for prediction with major risk factors of osteoarthritis, namely, age and body mass index (BMI). Seven supervised machine learning methodologies were evaluated. The support vector machine was used to generate gender-based models. The best input combination was assessed using sensitivity and synergy analyses. Validation was performed using tenfold cross-validation and an external cohort (TASOAC).ResultsFrom 277 models, two were defined. Both used age and BMI in addition for the first one of the SNP genes TP63, DUS4L, GDF5, and FTO with an accuracy of 85.0%; the second profits from the association of mtDNA haplogroups and SNP genes FTO and SUPT3H with 82.5% accuracy. The highest impact was associated with the haplogroup H, the presence of CT alleles for rs8044769 at FTO, and the absence of AA for rs10948172 at SUPT3H. Validation accuracy with the cross-validation (about 95%) and the external cohort (90.5%, 85.7%, respectively) was excellent for both models.ConclusionsThis study introduces a novel source of decision support in precision medicine in which, for the first time, two models were developed consisting of (i) age, BMI, TP63, DUS4L, GDF5, and FTO and (ii) the optimum one as it has one less variable: age, BMI, mtDNA haplogroup, FTO, and SUPT3H. Such a framework is translational and would benefit patients at risk of structural progressive knee osteoarthritis.

Project description:BackgroundTwitter presents a valuable and relevant social media platform to study the prevalence of information and sentiment on vaping that may be useful for public health surveillance. Machine learning classifiers that identify vaping-relevant tweets and characterize sentiments in them can underpin a Twitter-based vaping surveillance system. Compared with traditional machine learning classifiers that are reliant on annotations that are expensive to obtain, deep learning classifiers offer the advantage of requiring fewer annotated tweets by leveraging the large numbers of readily available unannotated tweets.ObjectiveThis study aims to derive and evaluate traditional and deep learning classifiers that can identify tweets relevant to vaping, tweets of a commercial nature, and tweets with provape sentiments.MethodsWe continuously collected tweets that matched vaping-related keywords over 2 months from August 2018 to October 2018. From this data set of tweets, a set of 4000 tweets was selected, and each tweet was manually annotated for relevance (vape relevant or not), commercial nature (commercial or not), and sentiment (provape or not). Using the annotated data, we derived traditional classifiers that included logistic regression, random forest, linear support vector machine, and multinomial naive Bayes. In addition, using the annotated data set and a larger unannotated data set of tweets, we derived deep learning classifiers that included a convolutional neural network (CNN), long short-term memory (LSTM) network, LSTM-CNN network, and bidirectional LSTM (BiLSTM) network. The unannotated tweet data were used to derive word vectors that deep learning classifiers can leverage to improve performance.ResultsLSTM-CNN performed the best with the highest area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.93-0.98) for relevance, all deep learning classifiers including LSTM-CNN performed better than the traditional classifiers with an AUC of 0.99 (95% CI 0.98-0.99) for distinguishing commercial from noncommercial tweets, and BiLSTM performed the best with an AUC of 0.83 (95% CI 0.78-0.89) for provape sentiment. Overall, LSTM-CNN performed the best across all 3 classification tasks.ConclusionsWe derived and evaluated traditional machine learning and deep learning classifiers to identify vaping-related relevant, commercial, and provape tweets. Overall, deep learning classifiers such as LSTM-CNN had superior performance and had the added advantage of requiring no preprocessing. The performance of these classifiers supports the development of a vaping surveillance system.