Dataset Information

Coreference resolution of medical concepts in discharge summaries by exploiting contextual information.

ABSTRACT: Patient discharge summaries provide detailed medical information about hospitalized patients and are a rich resource of data for clinical record text mining. The textual expressions of this information are highly variable. In order to acquire a precise understanding of the patient, it is important to uncover the relationship between all instances in the text. In natural language processing (NLP), this task falls under the category of coreference resolution.A key contribution of this paper is the application of contextual-dependent rules that describe relationships between coreference pairs. To resolve phrases that refer to the same entity, the authors use these rules in three representative NLP systems: one rule-based, another based on the maximum entropy model, and the last a system built on the Markov logic network (MLN) model.The experimental results show that the proposed MLN-based system outperforms the baseline system (exact match) by average F-scores of 4.3% and 5.7% on the Beth and Partners datasets, respectively. Finally, the three systems were integrated into an ensemble system, further improving performance to 87.21%, which is 4.5% more than the official i2b2 Track 1C average (82.7%).In this paper, the main challenges in the resolution of coreference relations in patient discharge summaries are described. Several rules are proposed to exploit contextual information, and three approaches presented. While single systems provided promising results, an ensemble approach combining the three systems produced a better performance than even the best single system.

SUBMITTER: Dai HJ

PROVIDER: S-EPMC3422837 | biostudies-other | 2012 Sep-Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Coreference resolution of medical concepts in discharge summaries by exploiting contextual information.

Dai Hong-Jie HJ Chen Chun-Yu CY Wu Chi-Yang CY Lai Po-Ting PT Tsai Richard Tzong-Han RT Hsu Wen-Lian WL

Journal of the American Medical Informatics Association : JAMIA 20120503 5

<h4>Objective</h4>Patient discharge summaries provide detailed medical information about hospitalized patients and are a rich resource of data for clinical record text mining. The textual expressions of this information are highly variable. In order to acquire a precise understanding of the patient, it is important to uncover the relationship between all instances in the text. In natural language processing (NLP), this task falls under the category of coreference resolution.<h4>Design</h4>A key ...[more]

PMID: 22556185

Similar Datasets

Project description:BackgroundIneffective transitions of care continue to be a source of risk for patients. Although there has been widespread implementation of electronic medical record (EMR) systems, little is currently known about hospitalists' and primary care providers' (PCPs) direct communication preferences at discharge using messaging capabilities in a shared EMR system.ObjectiveWe examined how hospitalists and PCPs with a shared EMR prefer to directly communicate at the time of hospital discharge by identifying preferred modes, information prioritization, challenges, facilitators, and proposed solutions.DesignA sequential, explanatory mixed methods study with surveys and semi-structured interviews.ParticipantsThirty-eight academic hospitalists and 63 PCPs working in outpatient clinics in a single safety net hospital system with a shared EMR.Main approachDescriptive statistics were used to analyze survey responses. Interviews were analyzed using immersion/crystallization and a mixture of inductive and deductive thematic analysis.Key resultsPCPs preferred direct communication at discharge through a message within the EMR while hospitalists preferred a message within the EMR and email. Qualitative results identified key themes related to patient care and direct communication: value of direct communication, safety, social determinants of health, and clinical judgment. Both groups prioritized direct communication for high-risk medications, pending and follow-up studies, and high-risk patients that hospitalists were concerned about. Overall, both hospitalists and PCPs reported that ensuring patient safety, flagging patients with social challenges, and expressing concerns about patients based on clinical judgment were key communication priorities.ConclusionsHospitalists and primary care providers report considerable overlap in preferences for direct communication at the time of hospital discharge through a shared EMR. Specifically, both groups reported similar concerns regarding patient safety and continuity during transitions. Direct messaging within the EMR could enable "closed loop" communication that helps ensure safe transitions of care for high-risk patients.

Project description:Discharge summaries are a vital tool to communicate information from Hospital to Primary Care teams; updating GPs about what happened during an admission, and handing over care detailing any follow up care required. Historically, Discharge Summaries have been posted to hospitals, increasing costs for hospitals, creating administrative work for GP practices receiving the letters, and resulting in some letters being lost or delayed in reaching the GP, with implications for patient safety if follow up requests are not received and acted upon. In an effort to improve patient care, the Clinical Commissioning Group in Surrey drew up a contract with Ashford and St Peter's Foundation Trust, aiming to increase the percentage of discharge summaries sent electronically from the rate of 9% sent within 24 hours, to over 75%. This contract set targets of 50% in May, 65% in June, and 80% in July. Financial penalties would be imposed if targets were not achieved, starting in June 2013. The Trust set up a working group comprising of doctors, IT personnel and ward PAs to devise a multi-pronged solution to achieve this target. The electronic discharge summary system was reviewed and improvements were designed and developed to make the process of signing off letters easier, and transmission of signed off letters became automated rather than requiring manual transmission by ward PAs. Presentations and leaflets to explain the importance of prompt completion and transmission of discharge summaries were given to Doctors to improve compliance using the revised IT system. Figures on transmission rates were automatically emailed to key stakeholders every day (Ward PAs, Divisional Leads) showing performance on each ward. This helped identify areas requiring more intervention. Areas (e.g. Day Surgery) that had not used electronic discharge summaries were engaged with, and persuaded to take part. As a result, transmission rates of Discharge Summaries within 24 hours of patient discharge increased from 9% on May 11th 2013, to 76% by June 29th 2013. This has improved communication with GPs, led to more reliable handover of care, and reduced costs for the Trust (both in processing and postage costs, and by avoiding fines).

Project description:BackgroundAcute kidney injury (AKI) increases the risk of hospital readmission, chronic kidney disease, and death. Therefore, effective communication in discharge summaries is essential for safe transitions of care.ObjectiveThe objectives of this study were to determine the quality of discharge summaries in AKI survivors and identify predictors of higher quality discharge summaries.DesignRetrospective chart review.SettingTertiary care academic center in Ontario, Canada.PatientsWe examined the discharge summary quality of 300 randomly selected adult patients who survived a hospitalization with AKI at our tertiary care hospital, stratified by AKI severity. We included 150 patients each from 2015 to 2016 and 2018 to 2019, before and after introduction of a post-AKI clinic in 2017.MeasurementsWe reviewed charts for 9 elements of AKI care to create a composite score summarizing discharge summary quality.MethodsWe used multivariable logistic regression to identify predictors of discharge summary quality.ResultsThe median discharge summary composite score was 4/9 (interquartile range, 2-6). The least frequently mentioned elements were baseline creatinine (n = 55, 18%), AKI-specific follow-up labs (n = 66, 22%), and medication recommendations (n = 80, 27%). The odds of having a higher quality discharge summary (composite score ≥4/9) was greater for every increase in baseline creatinine of 25 μmol/L (adjusted odds ratio [aOR]: 1.27; 95% confidence interval [CI]: 1.03, 1.56), intrarenal etiology (aOR: 2.32; 95% CI: 1.26, 4.27), and increased AKI severity (stage 2 aOR: 2.57; 95% CI: 1.35, 4.91 and stage 3 aOR: 3.36; 95% CI: 1.56, 7.22). There was no association between discharge summary quality and the years before and after introduction of a post-AKI clinic (aOR: 0.77; 95% CI: 0.46, 1.29).LimitationsThe single-center study design limits generalizability.ConclusionsMost discharge summaries are missing key AKI elements, even in patients with severe AKI. These gaps suggest several opportunities exist to improve discharge summary communication following AKI.

Project description:Quality of documentation is harder to quantify and incentivise, but it has a significant impact on patient care. Good discharge summaries facilitate continuity between secondary and primary care. The junior doctors' forum led this project to improve the quality of electronic discharge summaries (eDS). Baseline measurement revealed significant room for improvement. We measured the quality of 10 summaries per month (across all inpatient specialties), against 23 indicators from the revised Academy of Medical Royal Colleges (AoMRC) standards (2013) that were prioritised by GPs as a "minimum dataset". Junior doctors felt that the Trust's dual eDS systems were responsible for great variation in quality. This was confirmed by the results of a comparison audit of the systems in April 2014: one system greatly outperformed the other (57% mean compliance with iSoft clinical management (iCM) based system vs. 77% with InfoPath-based system). We recommended that the Trust move to a single eDS system, decommissioning the iCM-based system, and this proposal was approved by several Trust committees. We worked with information services, junior doctors, general practitioners and hospital physicians to develop and implement a generic template to further improve compliance with AoMRC standards. In August 2014, the iCM-based system was withdrawn, the new template went live, and training was delivered, coinciding with the changeover of junior doctors to minimise disruption. Median compliance increased from 66.7% to 77.8%. Quality of discharge summaries had improved across the specialties. There was a reduction in the number of complaints and positive qualitative feedback from general practitioners and junior doctors. Completion of discharge summaries within 24 hours was not affected by this change. There is still more to be done to improve quality; average compliance with the full AoMRC standards (39 indicators) is 59.5%. With the approval of the Trust executive committee further plan, do, study, act (PDSA) cycles are underway, working to improve the remaining specialty-specific templates.

Dataset Information

Coreference resolution of medical concepts in discharge summaries by exploiting contextual information.

Publications

Coreference resolution of medical concepts in discharge summaries by exploiting contextual information.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets