Comparing generative and extractive approaches to information extraction from abstracts describing randomized clinical trials.

BACKGROUND: Systematic reviews of Randomized Controlled Trials (RCTs) are an important part of the evidence-based medicine paradigm. However, the creation of such systematic reviews by clinical experts is costly as well as time-consuming, and results can get quickly outdated after publication. Most RCTs are structured based on the Patient, Intervention, Comparison, Outcomes (PICO) framework and there exist many approaches which aim to extract PICO elements automatically. The automatic extraction of PICO information from RCTs has the potential to significantly speed up the creation process of systematic reviews and this way also benefit the field of evidence-based medicine. RESULTS: Previous work has addressed the extraction of PICO elements as the task of identifying relevant text spans or sentences, but without populating a structured representation of a trial. In contrast, in this work, we treat PICO elements as structured templates with slots to do justice to the complex nature of the information they represent. We present two different approaches to extract this structured information from the abstracts of RCTs. The first approach is an extractive approach based on our previous work that is extended to capture full document representations as well as by a clustering step to infer the number of instances of each template type. The second approach is a generative approach based on a seq2seq model that encodes the abstract describing the RCT and uses a decoder to infer a structured representation of a trial including its arms, treatments, endpoints and outcomes. Both approaches are evaluated with different base models on a manually annotated dataset consisting of RCT abstracts on an existing dataset comprising 211 annotated clinical trial abstracts for Type 2 Diabetes and Glaucoma. For both diseases, the extractive approach (with flan-t5-base) reached the best F 1 score, i.e. 0.547 ( ± 0.006 ) for type 2 diabetes and 0.636 ( ± 0.006 ) for glaucoma. Generally, the F 1 scores were higher for glaucoma than for type 2 diabetes and the standard deviation was higher for the generative approach. CONCLUSION: In our experiments, both approaches show promising performance extracting structured PICO information from RCTs, especially considering that most related work focuses on the far easier task of predicting less structured objects. In our experimental results, the extractive approach performs best in both cases, although the lead is greater for glaucoma than for type 2 diabetes. For future work, it remains to be investigated how the base model size affects the performance of both approaches in comparison. Although the extractive approach currently leaves more room for direct improvements, the generative approach might benefit from larger models.

Exploring the scope of post-intensive care syndrome therapy and care: engagement of non-critical care providers and survivors in a second stakeholders meeting.

BACKGROUND: Increasing numbers of survivors of critical illness are at risk for physical, cognitive, and/or mental health impairments that may persist for months or years after hospital discharge. The post-intensive care syndrome framework encompassing these multidimensional morbidities was developed at the 2010 Society of Critical Care Medicine conference on improving long-term outcomes after critical illness for survivors and their families. OBJECTIVES: To report on engagement with non-critical care providers and survivors during the 2012 Society of Critical Care Medicine post-intensive care syndrome stakeholder conference. Task groups developed strategies and resources required for raising awareness and education, understanding and addressing barriers to clinical practice, and identifying research gaps and resources, aimed at improving patient and family outcomes. PARTICIPANTS: Representatives from 21 professional associations or health systems involved in the provision of both critical care and rehabilitation of ICU survivors in the United States and ICU survivors and family members. DESIGN: Stakeholder consensus meeting. Researchers presented summaries on morbidities for survivors and their families, whereas survivors presented their own experiences. MEETING OUTCOMES: Future steps were planned regarding 1) recognizing, preventing, and treating post-intensive care syndrome, 2) building strategies for institutional capacity to support and partner with survivors and families, and 3) understanding and addressing barriers to practice. There was recognition of the need for systematic and frequent assessment for post-intensive care syndrome across the continuum of care, including explicit "functional reconciliation" (assessing gaps between a patient's pre-ICU and current functional ability at all intra- and interinstitutional transitions of care). Future post-intensive care syndrome research topic areas were identified across the continuum of recovery: characterization of at-risk patients (including recognizing risk factors, mechanisms of injury, and optimal screening instruments), prevention and treatment interventions, and outcomes research for patients and families. CONCLUSIONS: Raising awareness of post-intensive care syndrome for the public and both critical care and non-critical care clinicians will inform a more coordinated approach to treatment and support during recovery after critical illness. Continued conceptual development and engagement with additional stakeholders is required.

Long-term persistence of quality improvements for an intensive care unit communication initiative using the VALUE strategy.

PURPOSE: Communication in the intensive care unit (ICU) is an important component of quality ICU care. In this report, we evaluate the long-term effects of a quality improvement (QI) initiative, based on the VALUE communication strategy, designed to improve communication with family members of critically ill patients. MATERIALS AND METHODS: We implemented a multifaceted intervention to improve communication in the ICU and measured processes of care. Quality improvement components included posted VALUE placards, templated progress note inclusive of communication documentation, and a daily rounding checklist prompt. We evaluated care for all patients cared for by the intensivists during three separate 3 week periods, pre, post, and 3 years following the initial intervention. RESULTS: Care delivery was assessed in 38 patients and their families in the pre-intervention sample, 27 in the post-intervention period, and 41 in follow-up. Process measures of communication showed improvement across the evaluation periods, for example, daily updates increased from pre 62% to post 76% to current 84% of opportunities. CONCLUSIONS: Our evaluation of this quality improvement project suggests persistence and continued improvements in the delivery of measured aspects of ICU family communication. Maintenance with point-of-care-tools may account for some of the persistence and continued improvements.

Comparison of glomerular filtration rate determined by use of single-slice dynamic computed tomography and scintigraphy in cats.

OBJECTIVE: To compare estimation of glomerular filtration rate determined via conventional methods (ie, scintigraphy and plasma clearance of technetium Tc 99m pentetate) and dynamic single-slice computed tomography (CT). ANIMALS: 8 healthy adult cats. PROCEDURES: Scintigraphy, plasma clearance testing, and dynamic CT were performed on each cat on the same day; order of examinations was randomized. Separate observers performed GFR calculations for scintigraphy, plasma clearance testing, or dynamic CT. Methods were compared via Bland-Altman plots and considered interchangeable and acceptable when the 95% limits of agreement (mean difference between methods ± 1.96 SD of the differences) were ≤ 0.7 mL/min/kg. RESULTS: Global GFR differed < 0.7 mL/min/kg in 5 of 8 cats when comparing plasma clearance testing and dynamic CT; the limits of agreement were 1.4 and -1.7 mL/min/kg. The mean ± SD difference was -0.2 ± 0.8 mL/min/kg, and the maximum difference was 1.6 mL/min/kg. The mean ± SD difference (absolute value) for percentage filtration by individual kidneys was 2.4 ± 10.5% when comparing scintigraphy and dynamic CT; the maximum difference was 20%, and the limits of agreement were 18% and 23% (absolute value). CONCLUSIONS AND CLINICAL RELEVANCE: GFR estimation via dynamic CT exceeded the definition for acceptable clinical use, compared with results for conventional methods, which was likely attributable to sample size and preventable technical complications. Because 5 of 8 cats had comparable values between methods, further investigation of dynamic CT in a larger sample population with a wide range of GFR values should be performed.

Improving long-term outcomes after discharge from intensive care unit: report from a stakeholders' conference.

BACKGROUND: Millions of patients are discharged from intensive care units annually. These intensive care survivors and their families frequently report a wide range of impairments in their health status which may last for months and years after hospital discharge. OBJECTIVES: To report on a 2-day Society of Critical Care Medicine conference aimed at improving the long-term outcomes after critical illness for patients and their families. PARTICIPANTS: Thirty-one invited stakeholders participated in the conference. Stakeholders represented key professional organizations and groups, predominantly from North America, which are involved in the care of intensive care survivors after hospital discharge. DESIGN: Invited experts and Society of Critical Care Medicine members presented a summary of existing data regarding the potential long-term physical, cognitive and mental health problems after intensive care and the results from studies of postintensive care unit interventions to address these problems. Stakeholders provided reactions, perspectives, concerns and strategies aimed at improving care and mitigating these long-term health problems. MEASUREMENTS AND MAIN RESULTS: Three major themes emerged from the conference regarding: (1) raising awareness and education, (2) understanding and addressing barriers to practice, and (3) identifying research gaps and resources. Postintensive care syndrome was agreed upon as the recommended term to describe new or worsening problems in physical, cognitive, or mental health status arising after a critical illness and persisting beyond acute care hospitalization. The term could be applied to either a survivor or family member. CONCLUSIONS: Improving care for intensive care survivors and their families requires collaboration between practitioners and researchers in both the inpatient and outpatient settings. Strategies were developed to address the major themes arising from the conference to improve outcomes for survivors and families.

Bayesian brain source imaging based on combined MEG/EEG and fMRI using MCMC.

A number of brain imaging techniques have been developed in order to investigate brain function and to develop diagnostic tools for various brain disorders. Each modality has strengths as well as weaknesses compared to the others. Recent work has explored how multiple modalities can be integrated effectively so that they complement one another while maintaining their individual strengths. Bayesian inference employing Markov Chain Monte Carlo (MCMC) techniques provides a straightforward way to combine disparate forms of information while dealing with the uncertainty in each. In this paper we introduce methods of Bayesian inference as a way to integrate different forms of brain imaging data in a probabilistic framework. We formulate Bayesian integration of magnetoencephalography (MEG) data and functional magnetic resonance imaging (fMRI) data by incorporating fMRI data into a spatial prior. The usefulness and feasibility of the method are verified through testing with both simulated and empirical data.

Probabilistic forward model for electroencephalography source analysis.

Source localization by electroencephalography (EEG) requires an accurate model of head geometry and tissue conductivity. The estimation of source time courses from EEG or from EEG in conjunction with magnetoencephalography (MEG) requires a forward model consistent with true activity for the best outcome. Although MRI provides an excellent description of soft tissue anatomy, a high resolution model of the skull (the dominant resistive component of the head) requires CT, which is not justified for routine physiological studies. Although a number of techniques have been employed to estimate tissue conductivity, no present techniques provide the noninvasive 3D tomographic mapping of conductivity that would be desirable. We introduce a formalism for probabilistic forward modeling that allows the propagation of uncertainties in model parameters into possible errors in source localization. We consider uncertainties in the conductivity profile of the skull, but the approach is general and can be extended to other kinds of uncertainties in the forward model. We and others have previously suggested the possibility of extracting conductivity of the skull from measured electroencephalography data by simultaneously optimizing over dipole parameters and the conductivity values required by the forward model. Using Cramer-Rao bounds, we demonstrate that this approach does not improve localization results nor does it produce reliable conductivity estimates. We conclude that the conductivity of the skull has to be either accurately measured by an independent technique, or that the uncertainties in the conductivity values should be reflected in uncertainty in the source location estimates.

Spatiotemporal noise covariance estimation from limited empirical magnetoencephalographic data.

The performance of parametric magnetoencephalography (MEG) and electroencephalography (EEG) source localization approaches can be degraded by the use of poor background noise covariance estimates. In general, estimation of the noise covariance for spatiotemporal analysis is difficult mainly due to the limited noise information available. Furthermore, its estimation requires a large amount of storage and a one-time but very large (and sometimes intractable) calculation or its inverse. To overcome these difficulties, noise covariance models consisting of one pair or a sum of multi-pairs of Kronecker products of spatial covariance and temporal covariance have been proposed. However, these approaches cannot be applied when the noise information is very limited, i.e., the amount of noise information is less than the degrees of freedom of the noise covariance models. A common example of this is when only averaged noise data are available for a limited prestimulus region (typically at most a few hundred milliseconds duration). For such cases, a diagonal spatiotemporal noise covariance model consisting of sensor variances with no spatial or temporal correlation has been the common choice for spatiotemporal analysis. In this work, we propose a different noise covariance model which consists of diagonal spatial noise covariance and Toeplitz temporal noise covariance. It can easily be estimated from limited noise information, and no time-consuming optimization and data-processing are required. Thus, it can be used as an alternative choice when one-pair or multi-pair noise covariance models cannot be estimated due to lack of noise information. To verify its capability we used Bayesian inference dipole analysis and a number of simulated and empirical datasets. We compared this covariance model with other existing covariance models such as conventional diagonal covariance, one-pair and multi-pair noise covariance models, when noise information is sufficient to estimate them. We found that our proposed noise covariance model yields better localization performance than a diagonal noise covariance, while it performs slightly worse than one-pair or multi-pair noise covariance models - although these require much more noise information. Finally, we present some localization results on median nerve stimulus empirical MEG data for our proposed noise covariance model.

Improving source detection and separation in a spatiotemporal Bayesian inference dipole analysis.

Most existing spatiotemporal multi-dipole approaches for MEG/EEG source localization assume that the dipoles are active for the full time range being analysed. If the actual time range of activity of sources is significantly shorter than the time range being analysed, the detectability, localization and time-course determination of such sources may be adversely affected, especially for weak sources. In order to improve detectability and reconstruction of such sources, it is natural to add active time range information (starting time point and ending time point of source activation) for each candidate source as unknown parameters in the analysis. However, this adds additional nonlinear free parameters that could burden the analysis and could be unfeasible for some methods. Recently, we described a spatiotemporal Bayesian inference multi-dipole analysis for the MEG/EEG inverse problem. This approach treated the number of dipoles as a free parameter, produced realistic uncertainty estimates using a Markov chain Monte Carlo numerical sampling of the posterior distribution and included a method to reduce the unwanted effects of local minima. In this paper, our spatiotemporal Bayesian inference multi-dipole analysis is extended to incorporate active time range parameters of starting and stopping time points. The properties of this analysis in comparison to the previous one without active time range parameters are demonstrated through extensive studies using both simulated and empirical MEG data.

Spatiotemporal Bayesian inference dipole analysis for MEG neuroimaging data.

Recently, we described a Bayesian inference approach to the MEG/EEG inverse problem that used numerical techniques to estimate the full posterior probability distributions of likely solutions upon which all inferences were based [Schmidt, D.M., George, J.S., Wood, C.C., 1999. Bayesian inference applied to the electromagnetic inverse problem. Human Brain Mapping 7, 195; Schmidt, D.M., George, J.S., Ranken, D.M., Wood, C.C., 2001. Spatial-temporal bayesian inference for MEG/EEG. In: Nenonen, J., Ilmoniemi, R. J., Katila, T. (Eds.), Biomag 2000: 12th International Conference on Biomagnetism. Espoo, Norway, p. 671]. Schmidt et al. (1999) focused on the analysis of data at a single point in time employing an extended region source model. They subsequently extended their work to a spatiotemporal Bayesian inference analysis of the full spatiotemporal MEG/EEG data set. Here, we formulate spatiotemporal Bayesian inference analysis using a multi-dipole model of neural activity. This approach is faster than the extended region model, does not require use of the subject's anatomical information, does not require prior determination of the number of dipoles, and yields quantitative probabilistic inferences. In addition, we have incorporated the ability to handle much more complex and realistic estimates of the background noise, which may be represented as a sum of Kronecker products of temporal and spatial noise covariance components. This reduces the effects of undermodeling noise. In order to reduce the rigidity of the multi-dipole formulation which commonly causes problems due to multiple local minima, we treat the given covariance of the background as uncertain and marginalize over it in the analysis. Markov Chain Monte Carlo (MCMC) was used to sample the many possible likely solutions. The spatiotemporal Bayesian dipole analysis is demonstrated using simulated and empirical whole-head MEG data.