Generic medical concept embedding and time decay for diverse patient outcome prediction tasks.
Ontology highlight
ABSTRACT:
SUBMITTER: Li Y
PROVIDER: S-EPMC9418804 | biostudies-literature | 2022 Sep
REPOSITORIES: biostudies-literature
Publications
Generic medical concept embedding and time decay for diverse patient outcome prediction tasks.
Li Yupeng Y Dong Wei W Ru Boshu B Black Adam A Zhang Xinyuan X Guan Yuanfang Y
iScience 20220804 9
Many fields, including Natural Language Processing (NLP), have recently witnessed the benefit of pre-training with large generic datasets to improve the accuracy of prediction tasks. However, there exist key differences between the longitudinal healthcare data (<i>e.g.</i>, claims) and NLP tasks, which make the direct application of NLP pre-training methods to healthcare data inappropriate. In this article, we developed a pre-training scheme for longitudinal healthcare data that leverages the pa ...[more]
Similar Datasets
Project description:ObjectiveFeature 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 methodsWe 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.ResultsAmong 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.ConclusionMCE 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.
| S-EPMC8206403 | biostudies-literature
Project description:Thanks to recent advances in sequencing and computational technologies, many researchers with biological and/or medical backgrounds are now producing multiple data sets with an embedded temporal dimension. Multi-modalities enable researchers to explore and investigate different biological and physico-chemical processes with various technologies. Motivated to explore multi-omics data and time-series multi-omics specifically, the exploration process has been hindered by the separation introduced by each omics-type. To effectively explore such temporal data sets, discover anomalies, find patterns, and better understand their intricacies, expertise in computer science and bioinformatics is required. Here we present MOVIS, a modular time-series multi-omics exploration tool with a user-friendly web interface that facilitates the data exploration of such data. It brings into equal participation each time-series omic-type for analysis and visualization. As of the time of writing, two time-series multi-omics data sets have been integrated and successfully reproduced. The resulting visualizations are task-specific, reproducible, and publication-ready. MOVIS is built on open-source software and is easily extendable to accommodate different analytical tasks. An online version of MOVIS is available under https://movis.mathematik.uni-marburg.de/ and on Docker Hub (https://hub.docker.com/r/aanzel/movis).
| S-EPMC8886009 | biostudies-literature
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:BackgroundThe widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention.ObjectiveWe aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI).MethodsMedical concepts, including patients' age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score.ResultsCompared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice.ConclusionsThe introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.
| S-EPMC9386580 | biostudies-literature
Project description:ObjectiveThe reasonable classification of a large number of distinct diagnosis codes can clarify patient diagnostic information and help clinicians to improve their ability to assign and target treatment for primary diseases. Our objective is to identify and predict a unifying diagnosis (UD) from electronic medical records (EMRs).MethodsWe screened 4,418 sepsis patients from a public MIMIC-III database and extracted their diagnostic information for UD identification, their demographic information, laboratory examination information, chief complaint, and history of present illness information for UD prediction. We proposed a data-driven UD identification and prediction method (UDIPM) embedding the disease ontology structure. First, we designed a set similarity measure method embedding the disease ontology structure to generate a patient similarity matrix. Second, we applied affinity propagation clustering to divide patients into different clusters, and extracted a typical diagnosis code co-occurrence pattern from each cluster. Furthermore, we identified a UD by fusing visual analysis and a conditional co-occurrence matrix. Finally, we trained five classifiers in combination with feature fusion and feature selection method to unify the diagnosis prediction.ResultsThe experimental results on a public electronic medical record dataset showed that the UDIPM could extracted a typical diagnosis code co-occurrence pattern effectively, identified and predicted a UD based on patients' diagnostic and admission information, and outperformed other fusion methods overall.ConclusionsThe accurate identification and prediction of the UD from a large number of distinct diagnosis codes and multi-source heterogeneous patient admission information in EMRs can provide a data-driven approach to assist better coding integration of diagnosis.
| S-EPMC8811031 | biostudies-literature
Project description:IntroductionThe In-patient Medication Order Entry System (IPMOE) was first implemented in the medical ward of Princess Margaret Hospital, Hong Kong. It was a local developed close-loop system including prescription, dispensing and administration modules. Evaluation on its impact on nursing tasks would be important for practice improvement and subsequent system enhancement.ObjectiveThe study was conducted to quantify the nursing times across medication-associated tasks for paper-based MAR and computer-based IPMOE, including change in the tasks and time patterns before and after IPMOE implementation.MethodsThis was a prospective observation study in medical wards before (Jan 2014-Jun 2014) and after (Mar 2015-Jun 2015) the implementation of IPMOE. We conducted 8-hr observation studies of individual nurses with a customized application to time various pre-categorized nursing tasks. Statistical inferences and interrupted time series analysis was performed to identify the change in the intercept and trends over time after implementation.ResultThe average number of medication-related tasks was significantly reduced from 61.07 to 29.81, a reduction of 31.26 episodes per duty (P < 0.001, 95% CI 22.9-39.63). The time for the medication-related tasks was reduced from 32 min (SD = 21.57) to 26.57 min (SD = 11.35) and the medication administration time increased from 37.93 min (SD = 14.78) to 44.37 min (SD = 19.45), but there was no overall significant difference in the time spent on each duty (P = 0.315) between the two groups. An improving trend in the delayed effect was observed (P = 0.03), which indicated a run-in period for new application was needed in clinical setting.ConclusionOur study had shown the time motion observation could be applied to measure the impact of the IPMOE in a busy clinical setting. Through classification of activities, validation, objective measurement and longitudinal evaluation, the method could be applied in various systems as well as different clinical settings in measure efficiency.
| S-EPMC6626216 | biostudies-literature
Project description:BackgroundRubrics are frequently used to assess competencies in outcome-based medical education (OBE). The implementation of assessment systems using rubrics is usually realised through years of involvement in projects with various stakeholders. However, for countries or specialities new to OBE, faster and more simplified processes are required. In March 2019, Japan introduced nine competencies and generic rubrics of competencies for medical residents. We explored the local adaptation of these generic rubrics and its consequences for assessors.MethodsThe study followed three steps. First, we locally adapted the generic rubrics. This was followed by conducting mixed-method research to explore the effect of the local adaptation. In step two, we examined the correlations between the scores in the locally adapted assessment sheets for supervising doctors and generic rubrics. In step three, we conducted interviews with supervising doctors. The study was conducted in the General Internal Medicine Department of Nagoya University, Japan. In the first step, doctors in the Medical Education Center and other medical departments, clerks, and residents participated. Supervising doctors in the General Internal Medicine Department participated in the second and third steps.ResultsA locally adapted assessment system was developed and implemented in seven months. The scores of the generic rubrics and the adapted assessment tool completed by the supervising doctors showed good correlations in some items as opposed to others, assessed mainly with other tools. Participant interviews revealed that local adaptation decreased their cognitive load leading to consistent ratings, increased writing of comments, and promoting reflection on instruction.ConclusionsThis adaptation process is a feasible way to begin the implementation of OBE. Local adaptation has advantages over direct use of generic rubrics.
| S-EPMC8996613 | biostudies-literature
Project description:Truck pulling is one of the common manual materials handling tasks which contribute to musculoskeletal disorders. The maximum endurance time (MET) for two-handed truck pulling tasks has been rarely discussed in the literature. The objectives of this study were to explore the development of muscular fatigue when performing two-handed pulling task and to establish models to predict the MET. A simulated pallet truck pulling experiment was conducted. Sixteen healthy adults including eight females and eight males participated. The participants pulled a handle simulating that of a pallet truck using two hands until they could not pull any longer under two postures. The forces applied for females and males were 139.65 N and 170.03 N, respectively. The maximum voluntary contractions (MVC) of the pulling strength both before and after the simulated pull were measured. After each trial, both the MET and subjective ratings of muscular fatigue on body segments were recorded. The results showed that posture significantly affected MVC of pull both before and after the trial. It was found that foot/shank of the front leg had higher subjective ratings of muscular fatigue than the other body segments. The MET equations employing both power and logarithmic functions were developed to predict the MET of the two-handed pulling tasks. Predictive models established in this study may be used to assess the MET for two-handed pulling tasks.
| S-EPMC6239301 | biostudies-literature
Project description:PurposeThe added value of measuring patient-reported outcomes (PROs) for delivering patient-centered care and assessment of healthcare quality is increasingly evident. However, healthcare system wide data collection initiatives are hampered by the proliferation of patient-reported outcome measures (PROMs) and conflicting data collection standards. As part of a national initiative of the Dutch Ministry of Health, Welfare and Sport we developed a consensus-based standard set of generic PROs and PROMs to be implemented across Dutch medical specialist care.MethodsA working group of mandated representatives of umbrella organizations involved in Dutch medical specialist care, together with PROM experts and patient organizations worked through a structured, consensus-driven co-creation process. This included literature reviews, online expert and working group meetings, and feedback from national patient- and umbrella organizations. The 'PROM-cycle' methodology was used to select feasible, valid, and reliable PROMs to obtain domain scores for each of the PROs included in the set.ResultsEight PROs across different domains of health were ultimately endorsed: symptoms (pain & fatigue), functioning (physical, social/participation, mental [anxiety & depression]), and overarching (quality of life & perceived overall health). A limited number of generic PROMs was endorsed. PROMIS short forms were selected as the preferred instruments for all PROs. Several recommendations were formulated to facilitate healthcare system level adoption and implementation of the standard set.ConclusionsWe developed a consensus-based standard set of Generic PROMs and a set of recommendations to facilitate healthcare system wide implementation across Dutch medical specialist care.
| S-EPMC10172289 | biostudies-literature
Project description:Background: The substitution of generic drugs can effectively alleviate the rapid growth of drug costs; however, the clinical effectiveness and medical costs of originator products and generics were barely studied in China. Objectives: To compare the effectiveness of antihypertensive drugs and hypertension-related medical costs between originator and generic initiators in Yinzhou, China. Methods: We conducted a population-based retrospective cohort study using the Chinese Electronic Health Records Research in Yinzhou (CHERRY), from July 1, 2011, to December 31, 2018. Hypertension patients initiating with originator products were compared with patients initiating with generic counterparts. We used 1:1 propensity score matching to pair the two groups based on sociodemographic, clinical, and health service utilization variables. Cox proportional regression was adopted to compare the rate of hospitalization for hypertension-related cardiovascular disease between matched originator and generic initiators. Wilcoxon matched-pairs signed-rank test was used to compare annual hypertension-related medical costs. Results: Matched pairs (10,535) of patients were included in the comparative study of originator products and generics, corresponding to seven antihypertensive drugs including amlodipine, felodipine, nifedipine, irbesartan, losartan, valsartan, and metoprolol. The average age of patients included in the analysis was around 60 years (originator vs. generics initiators: from 59.0 vs. 59.1 years in losartan to 62.9 vs. 63.6 years in nifedipine). Higher hospitalization rates among originator initiators were observed for three calcium channel blockers (hazard ratio[95% CI]: amlodipine, 3.18[1.43, 7.11]; felodipine, 3.60[1.63, 7.98]; and nifedipine, 3.86[1.26, 11.81]; respectively). The remaining four out of seven drugs of the clinical endpoint estimates showed comparable outcomes between originator products and generics (hazard ratio[95% CI]: irbesartan, 1.19[0.50, 2.84]; losartan, 1.84[0.84, 4.07]; valsartan, 2.04[0.72, 5.78]; and metoprolol, 1.25[0.56, 2.80]; respectively). Higher median annual hypertension-related medical costs were observed in originator initiators (all p < 0.001), except for metoprolol (p = 0.646). Conclusion: We observed comparable or even better clinical outcomes and less medical cost associated with the use of antihypertensive generics compared to originator counterparts. This could help increase patient and provider confidence in the efficacy of generic medicines to manage hypertension diseases.
| S-EPMC8920543 | biostudies-literature