Comparative effectiveness of medical concept embedding for feature engineering in phenotyping.
Ontology highlight
ABSTRACT: Objective
Feature engineering is a major bottleneck in phenotyping. Properly learned medical concept embeddings (MCEs) capture the semantics of medical concepts, thus are useful for retrieving relevant medical features in phenotyping tasks. We compared the effectiveness of MCEs learned from knowledge graphs and electronic healthcare records (EHR) data in retrieving relevant medical features for phenotyping tasks.Materials and methods
We implemented 5 embedding methods including node2vec, singular value decomposition (SVD), LINE, skip-gram, and GloVe with 2 data sources: (1) knowledge graphs obtained from the observational medical outcomes partnership (OMOP) common data model; and (2) patient-level data obtained from the OMOP compatible electronic health records (EHR) from Columbia University Irving Medical Center (CUIMC). We used phenotypes with their relevant concepts developed and validated by the electronic medical records and genomics (eMERGE) network to evaluate the performance of learned MCEs in retrieving phenotype-relevant concepts. Hits@k% in retrieving phenotype-relevant concepts based on a single and multiple seed concept(s) was used to evaluate MCEs.Results
Among all MCEs, MCEs learned by using node2vec with knowledge graphs showed the best performance. Of MCEs based on knowledge graphs and EHR data, MCEs learned by using node2vec with knowledge graphs and MCEs learned by using GloVe with EHR data outperforms other MCEs, respectively.Conclusion
MCE enables scalable feature engineering tasks, thereby facilitating phenotyping. Based on current phenotyping practices, MCEs learned by using knowledge graphs constructed by hierarchical relationships among medical concepts outperformed MCEs learned by using EHR data.
SUBMITTER: Lee J
PROVIDER: S-EPMC8206403 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:In this study, we propose to use machine learning to understand terminated clinical trials. Our goal is to answer two fundamental questions: (1) what are common factors/markers associated to terminated clinical trials? and (2) how to accurately predict whether a clinical trial may be terminated or not? The answer to the first question provides effective ways to understand characteristics of terminated trials for stakeholders to better plan their trials; and the answer to the second question can direct estimate the chance of success of a clinical trial in order to minimize costs. By using 311,260 trials to build a testbed with 68,999 samples, we use feature engineering to create 640 features, reflecting clinical trial administration, eligibility, study information, criteria etc. Using feature ranking, a handful of features, such as trial eligibility, trial inclusion/exclusion criteria, sponsor types etc., are found to be related to the clinical trial termination. By using sampling and ensemble learning, we achieve over 67% Balanced Accuracy and over 0.73 AUC (Area Under the Curve) scores to correctly predict clinical trial termination, indicating that machine learning can help achieve satisfactory prediction results for clinical trial study.
| S-EPMC7876037 | biostudies-literature
Project description:BACKGROUND:There has been an increasing interest in learning low-dimensional vector representations of medical concepts from Electronic Health Records (EHRs). Vector representations of medical concepts facilitate exploratory analysis and predictive modeling of EHR data to gain insights about the patterns of care and health outcomes. EHRs contain structured data such as diagnostic codes and laboratory tests, as well as unstructured free text data in form of clinical notes, which provide more detail about condition and treatment of patients. METHODS:In this work, we propose a method that jointly learns vector representations of medical concepts and words. This is achieved by a novel learning scheme based on the word2vec model. Our model learns those relationships by integrating clinical notes and sets of accompanying medical codes and by defining joint contexts for each observed word and medical code. RESULTS:In our experiments, we learned joint representations using MIMIC-III data. Using the learned representations of words and medical codes, we evaluated phenotypes for 6 diseases discovered by our and baseline method. The experimental results show that for each of the 6 diseases our method finds highly relevant words. We also show that our representations can be very useful when predicting the reason for the next visit. CONCLUSIONS:The jointly learned representations of medical concepts and words capture not only similarity between codes or words themselves, but also similarity between codes and words. They can be used to extract phenotypes of different diseases. The representations learned by the joint model are also useful for construction of patient features.
| S-EPMC6290514 | biostudies-other
Project description:BackgroundThe protection of private data is a key responsibility for research studies that collect identifiable information from study participants. Limiting the scope of data collection and preventing secondary use of the data are effective strategies for managing these risks. An ideal framework for data collection would incorporate feature engineering, a process where secondary features are derived from sensitive raw data in a secure environment without a trusted third party.ObjectiveThis study aimed to compare current approaches based on how they maintain data privacy and the practicality of their implementations. These approaches include traditional approaches that rely on trusted third parties, and cryptographic, secure hardware, and blockchain-based techniques.MethodsA set of properties were defined for evaluating each approach. A qualitative comparison was presented based on these properties. The evaluation of each approach was framed with a use case of sharing geolocation data for biomedical research.ResultsWe found that approaches that rely on a trusted third party for preserving participant privacy do not provide sufficiently strong guarantees that sensitive data will not be exposed in modern data ecosystems. Cryptographic techniques incorporate strong privacy-preserving paradigms but are appropriate only for select use cases or are currently limited because of computational complexity. Blockchain smart contracts alone are insufficient to provide data privacy because transactional data are public. Trusted execution environments (TEEs) may have hardware vulnerabilities and lack visibility into how data are processed. Hybrid approaches combining blockchain and cryptographic techniques or blockchain and TEEs provide promising frameworks for privacy preservation. For reference, we provide a software implementation where users can privately share features of their geolocation data using the hybrid approach combining blockchain with TEEs as a supplement.ConclusionsBlockchain technology and smart contracts enable the development of new privacy-preserving feature engineering methods by obviating dependence on trusted parties and providing immutable, auditable data processing workflows. The overlap between blockchain and cryptographic techniques or blockchain and secure hardware technologies are promising fields for addressing important data privacy needs. Hybrid blockchain and TEE frameworks currently provide practical tools for implementing experimental privacy-preserving applications.
| S-EPMC6712958 | biostudies-literature
Project description:Today, novel candidate therapeutics are identified in an environment which is intrinsically different from the clinical context in which they are ultimately evaluated. We present a strategy that allows biological relevance to be assessed in the early stages of drug discovery. Using molecular phenotyping and an in vitro model of diabetic cardiomyopathy, we show that by quantifying pathway reporter gene expression, molecular phenotyping can cluster compounds based on pathway profiles and dissect associations between pathway activities and disease phenotypes simultaneously. Molecular phenotyping identified a class of calcium-signaling modulators that can reverse disease-regulated pathways and phenotypes, which was validated by structurally distinct compounds of relevant classes. The technique was applicable to compounds with a range of binding specificities and detected false-positive hits missed by classical phenotypic assays. Our results advocate application of molecular phenotyping in drug discovery, promoting biological relevance as a key selection criterion early in the drug development cascade.
2017-05-24 | GSE89972 | GEO
Project description:Evidence-based medicine depends on the timely synthesis of research findings. An important source of synthesized evidence resides in systematic reviews. However, a bottleneck in review production involves dual screening of citations with titles and abstracts to find eligible studies. For this research, we tested the effect of various kinds of textual information (features) on performance of a machine learning classifier. Based on our findings, we propose an automated system to reduce screeing burden, as well as offer quality assurance.We built a database of citations from 5 systematic reviews that varied with respect to domain, topic, and sponsor. Consensus judgments regarding eligibility were inferred from published reports. We extracted 5 feature sets from citations: alphabetic, alphanumeric(+), indexing, features mapped to concepts in systematic reviews, and topic models. To simulate a two-person team, we divided the data into random halves. We optimized the parameters of a Bayesian classifier, then trained and tested models on alternate data halves. Overall, we conducted 50 independent tests.All tests of summary performance (mean F3) surpassed the corresponding baseline, P<0.0001. The ranks for mean F3, precision, and classification error were statistically different across feature sets averaged over reviews; P-values for Friedman's test were .045, .002, and .002, respectively. Differences in ranks for mean recall were not statistically significant. Alphanumeric(+) features were associated with best performance; mean reduction in screening burden for this feature type ranged from 88% to 98% for the second pass through citations and from 38% to 48% overall.A computer-assisted, decision support system based on our methods could substantially reduce the burden of screening citations for systematic review teams and solo reviewers. Additionally, such a system could deliver quality assurance both by confirming concordant decisions and by naming studies associated with discordant decisions for further consideration.
| S-EPMC3903545 | biostudies-other
Project description:This paper describes evidence that led to the concept of biological embedding and research approaches designed to elucidates its mechanisms. Biological embedding occurs when experience gets under the skin and alters human biological and developmental processes; when systematic differences in experience in different social environments in society lead to systematically different biological and developmental states; when these differences are stable and long term; and, finally, when they have the capacity to influence health, well-being, learning, or behavior over the life course. Biological embedding emerged from insights in population health on the unique characteristics of socioeconomic gradients: Ubiquity in poor and postscarcity societies alike; gradient seen regardless of whether socioeconomic status is measured by income, education, or occupation; cutting widely across health, well-being, learning, and behavior outcomes; replicating itself on new conditions entering society; and, often, showing that flatter gradients mean better overall societal outcomes. Most important, the gradient begins the life course as a gradient in developmental health, suggesting that the emergence of a multifaceted resilience/vulnerability early in life is the best place to look for evidence of biological embedding. To understand its character, the metaphor of the "archeology of biological embedding" has been used, wherein the surficial stratum of the "dig" is experience and behavior, the shallow stratum is organ system and cellular function, and the deep stratum is gene function. We are now ready to address the fundamental question of biological embedding: How do early childhood environments work together with genetic variation and epigenetic regulation to generate gradients in health and human development across the life course?
| S-EPMC3477385 | biostudies-other
Project description:In 2014, we assessed the effectiveness of Medical Taping Concept (MTC) in Primary Dysmenorrhoea (PD) with a single-blind, two-armed clinical trial (NCT02114723, ClinicalTrials.gov) with a follow-up of 4 menstrual cycles (pre-intervention: 2 months; post-intervention: 2 months) in a sample formed by 129 Spanish women aged 18-30 years with PD. We had two groups: intervention group (75), MTC covering T-11 and T-12 dermatomes; control group (54), another taping in both greater trochanter areas. Our main outcome measures were: pre-intervention and post-intervention increase in pain difference measured 2 hours after commencement (2-h pain - 0-h pain); difference between the number of tablets ingested post-intervention and pre-intervention; and associated symptoms in post-intervention (fatigue, vomiting, diarrhoea, nausea and others). Pain was assessed in: abdomen, legs, head and lower back. We found significant differences (p < 0.05) for number of tablets, abdominal and leg pain. In conclusion, the intervention group had less abdominal and leg pain when pharmacological therapy was not started. Furthermore, the intervention resulted in a lower intake of tablets. Nevertheless, more studies are needed to corroborate our results and to analyze the MTC effectiveness if women do not take any tablets during the entire menstrual period.
| S-EPMC4643292 | biostudies-literature
Project description:ObjectivePhenotyping algorithms are capable of accurately identifying patients with specific phenotypes from within electronic medical records systems. However, developing phenotyping algorithms in a scalable way remains a challenge due to the extensive human resources required. This paper introduces a high-throughput unsupervised feature selection method, which improves the robustness and scalability of electronic medical record phenotyping without compromising its accuracy.MethodsThe proposed Surrogate-Assisted Feature Extraction (SAFE) method selects candidate features from a pool of comprehensive medical concepts found in publicly available knowledge sources. The target phenotype's International Classification of Diseases, Ninth Revision and natural language processing counts, acting as noisy surrogates to the gold-standard labels, are used to create silver-standard labels. Candidate features highly predictive of the silver-standard labels are selected as the final features.ResultsAlgorithms were trained to identify patients with coronary artery disease, rheumatoid arthritis, Crohn's disease, and ulcerative colitis using various numbers of labels to compare the performance of features selected by SAFE, a previously published automated feature extraction for phenotyping procedure, and domain experts. The out-of-sample area under the receiver operating characteristic curve and F -score from SAFE algorithms were remarkably higher than those from the other two, especially at small label sizes.ConclusionSAFE advances high-throughput phenotyping methods by automatically selecting a succinct set of informative features for algorithm training, which in turn reduces overfitting and the needed number of gold-standard labels. SAFE also potentially identifies important features missed by automated feature extraction for phenotyping or experts.
| S-EPMC6080726 | biostudies-literature
Project description:OBJECTIVE:Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS:SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS:SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION:SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.
| S-EPMC6424621 | biostudies-literature
Project description:BackgroundMicroorganisms can be metabolically engineered to produce a wide range of commercially important chemicals. Advancements in computational strategies for strain design and synthetic biological techniques to construct the designed strains have facilitated the generation of large libraries of potential candidates for chemical production. Consequently, there is a need for high-throughput laboratory scale techniques to characterize and screen these candidates to select strains for further investigation in large scale fermentation processes. Several small-scale fermentation techniques, in conjunction with laboratory automation have enhanced the throughput of enzyme and strain phenotyping experiments. However, such high throughput experimentation typically entails large operational costs and generate massive amounts of laboratory plastic waste.ResultsIn this work, we develop an eco-friendly automation workflow that effectively calibrates and decontaminates fixed-tip liquid handling systems to reduce tip waste. We also investigate inexpensive methods to establish anaerobic conditions in microplates for high-throughput anaerobic phenotyping. To validate our phenotyping platform, we perform two case studies-an anaerobic enzyme screen, and a microbial phenotypic screen. We used our automation platform to investigate conditions under which several strains of E. coli exhibit the same phenotypes in 0.5 L bioreactors and in our scaled-down fermentation platform. We also propose the use of dimensionality reduction through t-distributed stochastic neighbours embedding (t-SNE) in conjunction with our phenotyping platform to effectively cluster similarly performing strains at the bioreactor scale.ConclusionsFixed-tip liquid handling systems can significantly reduce the amount of plastic waste generated in biological laboratories and our decontamination and calibration protocols could facilitate the widespread adoption of such systems. Further, the use of t-SNE in conjunction with our automation platform could serve as an effective scale-down model for bioreactor fermentations. Finally, by integrating an in-house data-analysis pipeline, we were able to accelerate the 'test' phase of the design-build-test-learn cycle of metabolic engineering.
| S-EPMC8461876 | biostudies-literature