scholarly journals Integrity of clinical information in radiology reports documenting pulmonary nodules

2020 ◽  
Author(s):  
Ronilda Lacson ◽  
Laila Cochon ◽  
Patrick R Ching ◽  
Eseosa Odigie ◽  
Neena Kapoor ◽  
...  
Keyword(s):  
Language Processing ◽  
Pulmonary Nodule ◽  
Medical Center ◽  
Academic Medical Center ◽  
Pulmonary Nodules ◽  
Clinical Information ◽  
Clinical Decision ◽  
Study Cohort ◽  
Radiology Reports

Abstract Objective Quantify the integrity, measured as completeness and concordance with a thoracic radiologist, of documenting pulmonary nodule characteristics in CT reports and assess impact on making follow-up recommendations. Materials and Methods This Institutional Review Board-approved, retrospective cohort study was performed at an academic medical center. Natural language processing was performed on radiology reports of CT scans of chest, abdomen, or spine completed in 2016 to assess presence of pulmonary nodules, excluding patients with lung cancer, of which 300 reports were randomly sampled to form the study cohort. Documentation of nodule characteristics were manually extracted from reports by 2 authors with 20% overlap. CT images corresponding to 60 randomly selected reports were further reviewed by a thoracic radiologist to record nodule characteristics. Documentation completeness for all characteristics were reported in percentage and compared using χ2 analysis. Concordance with a thoracic radiologist was reported as percentage agreement; impact on making follow-up recommendations was assessed using kappa. Results Documentation completeness for pulmonary nodule characteristics differed across variables (range = 2%–90%, P < .001). Concordance with a thoracic radiologist was 75% for documenting nodule laterality and 29% for size. Follow-up recommendations were in agreement in 67% and 49% of reports when there was lack of completeness and concordance in documenting nodule size, respectively. Discussion Essential pulmonary nodule characteristics were under-reported, potentially impacting recommendations for pulmonary nodule follow-up. Conclusion Lack of documentation of pulmonary nodule characteristics in radiology reports is common, with potential for compromising patient care and clinical decision support tools.

scholarly journals Preparing Clinical Text for Use in Biomedical Research

2011 ◽  
pp. 2085-2095
Author(s):  
John P. Pestian ◽  
Lukasz Itert ◽  
Charlotte Andersen
Keyword(s):  
Language Processing ◽  
Medical Center ◽  
Clinical Care ◽  
Academic Medical Center ◽  
Clinical Text ◽  
Delivery Of Care ◽  
Radiology Reports ◽  
Academic Medical ◽  
Textual Data ◽  
Regulatory Actions

Approximately 57 different types of clinical annotations construct a patient’s medical record. These annotations include radiology reports, discharge summaries, and surgical and nursing notes. Hospitals typically produce millions of text-based medical records over the course of a year. These records are essential for the delivery of care, but many are underutilized or not utilized at all for clinical research. The textual data found in these annotations is a rich source of insights into aspects of clinical care and the clinical delivery system. Recent regulatory actions, however, require that, in many cases, data not obtained through informed consent or data not related to the delivery of care must be made anonymous (as referred to by regulators as harmless), before they can be used. This article describes a practical approach with which Cincinnati Children’s Hospital Medical Center (CCHMC), a large pediatric academic medical center with more than 761,000 annual patient encounters, developed open source software for making pediatric clinical text harmless without losing its rich meaning. Development of the software dealt with many of the issues that often arise in natural language processing, such as data collection, disambiguation, and data scrubbing.

Abstract 140: Effects of Smoking Co-Morbidities and Obesity on NonHemorrhagic Stroke Outcomes

2017 ◽  
Vol 10 (suppl_3) ◽  
Author(s):  
Danielle Amato ◽  
Justin Pieper ◽  
Michael Ashamalla ◽  
Mikhail Torosoff
Keyword(s):  
Renal Disease ◽  
Hemorrhagic Stroke ◽  
Chronic Renal Disease ◽  
Medical Center ◽  
Academic Medical Center ◽  
Study Cohort ◽  
Younger Age ◽  
Social Security Death Index ◽  
The Mean

Background: Smoking is a known risk factor for ischemic stroke, while increased BMI has been associated with improved outcomes in patients with cardiovascular disease. We investigated the relationship between smoking, BMI, and outcomes in patients with non-hemorrhagic stroke. Methods: Study cohort consisted of 610 consecutive patients treated for non-hemorrhagic stroke at a single academic medical center. Retrospective chart review was conducted. Long-term outcomes were ascertained through Social Security Death Index. The study was approved by the institutional IRB. Results: The prevalence of smoking was 42%. There were more male smokers (48% vs. 35% females, p<0.001). The mean BMI was similar in smokers and non-smokers (29+/-12.7 vs. 28.8+/-14, p=0.842). Similarly, associations between smoking and hypertension, peripheral vascular disease, dyslipidemia, end-stage renal disease, and systemic evidence of atherosclerosis by TTE were not statistically significant. However, age of a smoker at the time of admission for non-hemorrhagic stroke was 5 years younger than in a non-smoker (60.7+/-15 vs. non-smokers 65.3+/-17.5, p<0.001). The mean follow up length was 51.4+/-1.3 months in smokers and 48.6+/-1.0 months in non-smokers. Observed crude mortality of 22.2% in smokers and 24.3% in non-smokers (p=0.559) was not significantly different in patients with normal, or increased BMI. However, smokers with non-hemorrhagic stroke died at significantly younger age (64.8+/-14.6 vs. 69.2+/-17.1, p=0.001). Additionally, there were trends towards increased mortality in smokers with BMI <18.5 kg/m2 (10.2 vs. 5.3% in non-smokers, p=0.226), dyslipidemia (38% vs. 24% in non-smokers, p=0.054) and chronic renal disease (64% vs. 36% in non-smokers, p=0.889). Conclusion: Smokers present with non-hemorrhagic stroke at a significantly younger age than non-smokers and die at much younger age during follow-up. While in our cohort smoking was not linked to other traditional risk factors for non-hemorrhagic stroke, it was associated with increased mortality in patients with decreased BMI, dyslipidemia, and with renal disease. “Protective” effect of increased BMI was not observed in smokers.

Automating incidental findings in radiology reports using natural language processing and machine learning to identify and classify pulmonary nodules.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e18093-e18093
Author(s):  
Christi French ◽  
Maciek Makowski ◽  
Samantha Terker ◽  
Paul Alexander Clark
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Pulmonary Nodule ◽  
Incidental Findings ◽  
Lung Nodule ◽  
Radiology Reports

e18093 Background: Pulmonary nodule incidental findings challenge providers to balance resource efficiency and high clinical quality. Incidental findings tend to be undertreated with studies reporting appropriate follow-up rates as low as 29%. Ensuring appropriate follow-up on all incidental findings is labor-intensive; requires the clinical reading and classification of radiology reports to identify high-risk lung nodules. We tested the feasibility of automating this process with natural language processing (NLP) and machine learning (ML). Methods: In cooperation with Sarah Cannon Research Institute (SCRI), we conducted a series of data science experiments utilizing NLP and ML computing techniques on 8,879 free-text, narrative CT (computerized tomography) radiology reports. Reports used were dated from Dec 8, 2015 - April 23, 2017, came from SCRI-affiliated Emergency Department, Inpatient, and Outpatient facilities and were a representative, random sample of the patient populations. Reports were divided into a development set for model training and validation, and a test set to evaluate model performance. Two models were developed - a “Nodule Model” was trained to detect the reported presence of a pulmonary nodule and a rules-based “Sizing Model” was developed to extract the size of the nodule in millimeters. Reports were bucketed into three prediction groups: > = 6 mm, < 6 mm, and no size indicated. Nodules were considered positives and placed in a queue for follow-up if the nodule was predicted > = 6 mm, or if the nodule had no size indicated and the radiology report contained the word “mass.” The Fleischner Society Guidelines and clinical review informed these definitions. Results: Precision and recall metrics were calculated for multiple model thresholds. A threshold was selected based on the validation set calculations and a success criterion of 90% queue precision was selected to minimize false positives. On the test dataset, the F1 measure of the entire pipeline (lung nodule classification model and size extraction model) was 72.9%, recall was 60.3%, and queue precision was 90.2%, exceeding success criteria. Conclusions: The experiments demonstrate the feasibility of NLP and ML technology to automate the detection and classification of pulmonary nodule incidental findings in radiology reports. This approach promises to improve healthcare quality by increasing the rate of appropriate lung nodule incidental finding follow-up and treatment without excessive labor or risking overutilization.

scholarly journals Integrity of clinical information in computerized order requisitions for diagnostic imaging

2018 ◽  
Vol 25 (12) ◽  
pp. 1651-1656 ◽  
Author(s):  
Ronilda Lacson ◽  
Romeo Laroya ◽  
Aijia Wang ◽  
Neena Kapoor ◽  
Daniel I Glazer ◽  
...  
Keyword(s):  
Medical Center ◽  
Academic Medical Center ◽  
Clinical Information ◽  
Clinical Decision ◽  
Accurate Diagnosis ◽  
Institutional Review Board ◽  
Institutional Review ◽  
Academic Medical ◽  
Potential Impact ◽  
Kappa Agreement

Abstract Objective Assess information integrity (concordance and completeness of documented exam indications from the electronic health record [EHR] imaging order requisition, compared to EHR provider notes), and assess potential impact of indication inaccuracies on exam planning and interpretation. Methods This retrospective study, approved by the Institutional Review Board, was conducted at a tertiary academic medical center. There were 139 MRI lumbar spine (LS-MRI) and 176 CT abdomen/pelvis orders performed 4/1/2016-5/31/2016 randomly selected and reviewed by 4 radiologists for concordance and completeness of relevant exam indications in order requisitions compared to provider notes, and potential impact of indication inaccuracies on exam planning and interpretation. Forty each LS-MRI and CT abdomen/pelvis were re-reviewed to assess kappa agreement. Results Requisition indications were more likely to be incomplete (256/315, 81%) than discordant (133/315, 42%) compared to provider notes (p &lt; 0.0001). Potential impact of discrepancy between clinical information in requisitions and provider notes was higher for radiologist’s interpretation than for exam planning (135/315, 43%, vs 25/315, 8%, p &lt; 0.0001). Agreement among radiologists for concordance, completeness, and potential impact was moderate to strong (Kappa 0.66-0.89). Indications in EHR order requisitions are frequently incomplete or discordant compared to physician notes, potentially impacting imaging exam planning, interpretation and accurate diagnosis. Such inaccuracies could also diminish the relevance of clinical decision support alerts if based on information in order requisitions. Conclusions Improved availability of relevant documented clinical information within EHR imaging requisition is necessary for optimal exam planning and interpretation.

scholarly journals Automate incidental findings in radiology reports using natural language processing and machine learning to identify and classify lung nodules.

2019 ◽  
Vol 5 (suppl) ◽  
pp. 49-49
Author(s):  
Christi French ◽  
Dax Kurbegov ◽  
David R. Spigel ◽  
Maciek Makowski ◽  
Samantha Terker ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Pulmonary Nodule ◽  
Incidental Findings ◽  
Free Text ◽  
Radiology Reports

49 Background: Pulmonary nodule incidental findings challenge providers to balance resource efficiency and high clinical quality. Incidental findings tend to be under evaluated with studies reporting appropriate follow-up rates as low as 29%. The efficient identification of patients with high risk nodules is foundational to ensuring appropriate follow-up and requires the clinical reading and classification of radiology reports. We tested the feasibility of automating this process with natural language processing (NLP) and machine learning (ML). Methods: In cooperation with Sarah Cannon, the Cancer Institute of HCA Healthcare, we conducted a series of experiments on 8,879 free-text, narrative CT radiology reports. A representative sample of health system ED, IP, and OP reports dated from Dec 2015 - April 2017 were divided into a development set for model training and validation, and a test set to evaluate model performance. A “Nodule Model” was trained to detect the reported presence of a pulmonary nodule and a rules-based “Size Model” was developed to extract the size of the nodule in mms. Reports were bucketed into three prediction groups: ≥ 6 mm, <6 mm, and no size indicated. Nodules were placed in a queue for follow-up if the nodule was predicted ≥ 6 mm, or if the nodule had no size indicated and the report contained the word “mass.” The Fleischner Society Guidelines and clinical review informed these definitions. Results: Precision and recall metrics were calculated for multiple model thresholds. A threshold was selected based on the validation set calculations and a success criterion of 90% queue precision was selected to minimize false positives. On the test dataset, the F1 measure of the entire pipeline was 72.9%, recall was 60.3%, and queue precision was 90.2%, exceeding success criteria. Conclusions: The experiments demonstrate the feasibility of technology to automate the detection and classification of pulmonary nodule incidental findings in radiology reports. This approach promises to improve healthcare quality by increasing the rate of appropriate lung nodule incidental finding follow-up and treatment without excessive labor or risking overutilization.

scholarly journals 164. Avoiding Complacency: Assessing the Perceived Impact and Value of Antimicrobial Stewardship at a Academic Medical Center

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S90-S91
Author(s):  
Matthew S Lee ◽  
Christopher McCoy
Keyword(s):  
Antimicrobial Stewardship ◽  
Medical Center ◽  
Academic Medical Center ◽  
Clinical Decision ◽  
Team Members ◽  
Academic Medical ◽  
Support Tools ◽  
Educational Engagement ◽  
Similar Survey ◽  
Perceived Impact

Abstract Background Multi-disciplinary engagement and education remain key measures for Antimicrobial Stewardship Programs (ASPs). Over 3 years, our ASP has undergone key changes to pre-authorization review, post-prescriptive activities, and core team members, coinciding with a 30% increase in stewardship interventions. The objectives of this study were to evaluate the familiarity of Nursing, Pharmacy and Prescribers at our academic medical center regarding ASP activities and services, as well as perceived impact on patient care and value. Secondary objectives were to determine what resources are currently utilized and areas for improvement. Methods Distinct surveys were distributed to three participant groups: Nurses, Pharmacists, and Prescribers (Housestaff, Advanced Practice Providers, and staff physicians). Questions were developed to assess familiarity, perceived value, and overall satisfaction with the ASP. Additional items included questions on the current use of ASP resources and educational engagement. Survey results were compared to a similar survey conducted 3 years amongst the same participant groups. Results The survey was delivered electronically to 3367 Prescribers, Nurses and Pharmacists. 403 responders completed the survey (208 Nurses, 181 Prescribers, and 18 Pharmacists). Familiarity was lowest amongst Nurses, but almost doubled compared to 2016 (Figure). Prescribers cited “restricted antibiotic approval”, “de-escalation”, and “alternative therapies relative to allergies” as the three most common interaction types, similar to 2016. ASP interactions continued to be rated “moderate” or “high” value (88.4% vs 89.15% in 2016), however, face-to-face interactions were preferred by only 4% of responders (unchanged compared to 2016). Prescribers also responded uncommon use of ASP online resources (20%) and clinical decision support tools (34%). 78% of responders expressed desire for increased ASP-related education. Conclusion As ASPs evolve, it is important to constantly evaluate impact and value, and identify areas for growth. Despite ASP familiarity being high and interactions valued, we need to further optimize ASP provided resources, clinical support tools, and educational offerings. Disclosures All Authors: No reported disclosures

Natural Language Processing to Identify Pulmonary Nodules and Extract Nodule Characteristics from Radiology Reports

CHEST Journal ◽  
2021 ◽  
Author(s):  
Chengyi Zheng ◽  
Brian Z. Huang ◽  
Andranik A. Agazaryan ◽  
Beth Creekmur ◽  
Thearis Osuj ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Pulmonary Nodules ◽  
Radiology Reports

scholarly journals Utility of Natural Language Processing for Clinical Quality Measures Reporting

2017 ◽  
Vol 9 (1) ◽  
Author(s):  
Dino P. Rumoro ◽  
Shital C. Shah ◽  
Gillian S. Gibbs ◽  
Marilyn M. Hallock ◽  
Gordon M. Trenholme ◽  
...  
Keyword(s):  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Medical Center ◽  
Academic Medical Center ◽  
Quality Measures ◽  
Surveillance Program ◽  
Free Text ◽  
Influenza Immunization

ObjectiveTo explain the utility of using an automated syndromic surveillanceprogram with advanced natural language processing (NLP) to improveclinical quality measures reporting for influenza immunization.IntroductionClinical quality measures (CQMs) are tools that help measure andtrack the quality of health care services. Measuring and reportingCQMs helps to ensure that our health care system is deliveringeffective, safe, efficient, patient-centered, equitable, and timely care.The CQM for influenza immunization measures the percentage ofpatients aged 6 months and older seen for a visit between October1 and March 31 who received (or reports previous receipt of) aninfluenza immunization. Centers for Disease Control and Preventionrecommends that everyone 6 months of age and older receive aninfluenza immunization every season, which can reduce influenza-related morbidity and mortality and hospitalizations.MethodsPatients at a large academic medical center who had a visit toan affiliated outpatient clinic during June 1 - 8, 2016 were initiallyidentified using their electronic medical record (EMR). The 2,543patients who were selected did not have documentation of influenzaimmunization in a discrete field of the EMR. All free text notes forthese patients between August 1, 2015 and March 31, 2016 wereretrieved and analyzed using the sophisticated NLP built withinGeographic Utilization of Artificial Intelligence in Real-Timefor Disease Identification and Alert Notification (GUARDIAN)– a syndromic surveillance program – to identify any mention ofinfluenza immunization. The goal was to identify additional cases thatmet the CQM measure for influenza immunization and to distinguishdocumented exceptions. The patients with influenza immunizationmentioned were further categorized by GUARDIAN NLP intoReceived, Recommended, Refused, Allergic, and Unavailable.If more than one category was applicable for a patient, they wereindependently counted in their respective categories. A descriptiveanalysis was conducted, along with manual review of a sample ofcases per each category.ResultsFor the 2,543 patients who did not have influenza immunizationdocumentation in a discrete field of the EMR, a total of 78,642 freetext notes were processed using GUARDIAN. Four hundred fiftythree (17.8%) patients had some mention of influenza immunizationwithin the notes, which could potentially be utilized to meet the CQMinfluenza immunization requirement. Twenty two percent (n=101)of patients mentioned already having received the immunizationwhile 34.7% (n=157) patients refused it during the study time frame.There were 27 patients with the mention of influenza immunization,who could not be differentiated into a specific category. The numberof patients placed into a single category of influenza immunizationwas 351 (77.5%), while 75 (16.6%) were classified into more thanone category. See Table 1.ConclusionsUsing GUARDIAN’s NLP can identify additional patients whomay meet the CQM measure for influenza immunization or whomay be exempt. This tool can be used to improve CQM reportingand improve overall influenza immunization coverage by using it toalert providers. Next steps involve further refinement of influenzaimmunization categories, automating the process of using the NLPto identify and report additional cases, as well as using the NLP forother CQMs.Table 1. Categorization of influenza immunization documentation within freetext notes of 453 patients using NLP

Abstract T P168: A Wake-up Call for Wake-up Strokes

Stroke ◽  
2015 ◽  
Vol 46 (suppl_1) ◽  
Author(s):  
Josephine F Huang ◽  
Jennifer E Fugate ◽  
Alejandro A Rabinstein
Keyword(s):  
Ischemic Stroke ◽  
Medical Center ◽  
Academic Medical Center ◽  
Stroke Treatment ◽  
Good Outcome ◽  
Time Period ◽  
Academic Medical ◽  
Younger Age ◽  
Stroke Mechanism

INTRODUCTION: Studies suggest 8%-28% of ischemic strokes present as wake-up strokes (WUS). The unknown time of symptom onset precludes these patients from approved treatments for acute ischemic stroke, but a substantial proportion of patients may be deemed candidates for treatment if other factors are considered. The aim of this study was to identify characteristics associated with clinical outcomes of WUS patients. METHODS: We retrospectively reviewed the medical record of patients with ischemic stroke admitted to a large academic medical center between January 2011 and May 2012. We identified patients with stroke symptoms upon awakening or those who were found with stroke symptoms with an unknown time of onset. Baseline demographics, stroke mechanism, presenting NIHSS, Alberta Stroke Program Early Computed Tomography Score (ASPECTS), and modified Rankin Scale (mRS) scores on discharge and at 3-month follow-up were obtained. A good outcome was defined as mRS 0-2. RESULTS: WUS patients comprised 22% (162/731) of all patients with ischemic stroke at our institution during this time period. Median age was 74 years (range 15-100), median presenting NIHSS was 5 (range 0-28), and median initial ASPECTS 10 (range 0-10). A cardioembolic mechanism was identified in 68 patients (42%). Predictors of good outcome at hospital discharge were lower initial NIHSS (3.5 versus 12.0, p<0.0001) and higher ASPECTS (9.8 versus 8.1, p=0.0002). The predictors of good outcomes at 3 months were younger age (69.1 versus 75.8, p=0.009), lower initial NIHSS (5.0 versus 12.6, p<0.0001), and higher ASPECTS (9.5 versus 8.1, p=0.0006). One hundred and eleven patients (68.5%) had initial ASPECTS of 10. Of those, 19 had NIHSS≥10 and 7 were treated with acute recanalization therapies. Four of the 7 treated patients had good outcomes, and 2 of the 12 untreated patients had good outcomes. CONCLUSIONS: Few patients with strokes of unknown onset and severe deficits have good outcomes without acute stroke treatment. Patients with NIHSS≥10 and ASPECTS 10 may be candidates for acute recanalization therapy.

Engaging Housestaff as Informatics Collaborators: Educational and Operational Opportunities

2021 ◽  
Vol 12 (05) ◽  
pp. 1150-1156
Author(s):  
Jared A. Shenson ◽  
Ivana Jankovic ◽  
Hyo Jung Hong ◽  
Benjamin Weia ◽  
Lee White ◽  
...  
Keyword(s):  
Positive Impact ◽  
Care Delivery ◽  
Medical Center ◽  
Academic Medical Center ◽  
Clinical Information ◽  
Lessons Learned ◽  
First Year ◽  
Hospital Governance ◽  
Staff Members ◽  
It Systems

Abstract Background In academic hospitals, housestaff (interns, residents, and fellows) are a core user group of clinical information technology (IT) systems, yet are often relegated to being recipients of change, rather than active partners in system improvement. These information systems are an integral part of health care delivery and formal efforts to involve and educate housestaff are nascent. Objective This article develops a sustainable forum for effective engagement of housestaff in hospital informatics initiatives and creates opportunities for professional development. Methods A housestaff-led IT council was created within an academic medical center and integrated with informatics and graduate medical education leadership. The Council was designed to provide a venue for hands-on clinical informatics educational experiences to housestaff across all specialties. Results In the first year, five housestaff co-chairs and 50 members were recruited. More than 15 projects were completed with substantial improvements made to clinical systems impacting more than 1,300 housestaff and with touchpoints to nearly 3,000 staff members. Council leadership was integrally involved in hospital governance committees and became the go-to source for housestaff input on informatics efforts. Positive experiences informed members' career development toward informatics roles. Key lessons learned in building for success are discussed. Conclusion The council model has effectively engaged housestaff as learners, local champions, and key informatics collaborators, with positive impact for the participating members and the institution. Requiring few resources for implementation, the model should be replicable at other institutions.

Sign in / Sign up

Export Citation Format

Share Document