METEOR: An Enterprise Health Informatics Environment to Support Evidence-Based Medicine

Puppala, Mamta; He, Tiancheng; Chen, Shenyi; Ogunti, Richard; Yu, Xiaohui; Li, Fuhai; Jackson, Robert E; Wong, Stephen T.C.

doi:10.1109/tbme.2015.2450181

Cited by 46 publications

(32 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have developed an NLP tool that automatically and accurately extracts mammographic findings from a large number of free text reports. A previous study using the METEOR database as well as MOTTE found an acceptable range of accuracy (96.4%) . Various NLP techniques have been used to extract clinically useful information from mammography reports.…”

Section: Discussionmentioning

confidence: 99%

“…NLP was then applied to search and retrieve established clinical parameters. MOTTE's NLP algorithm contains 5 processing steps including tokenization, stemming, stop words removal, vector space modeling, and similarity calculation, as detailed in our previous publication . Tokenization turns each clinical text report into a stream of tokens.…”

Section: Methodsmentioning

confidence: 99%

“…Because commercial NLP systems are not readily available for academic and affiliated hospitals implementing breast cancer decision support systems, we developed an NLP‐based tool, the Methodist Hospital text teaser (MOTTE). MOTTE is able to extract data reliably from millions of free text mammogram reports archived in our enterprise clinical data warehouse …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

Patel

Puppala

Ogunti

et al. 2016

Cancer

Self Cite

View full text Add to dashboard Cite

BACKGROUND: A key challenge to mining electronic health records for mammography research is the preponderance of unstructured narrative text, which strikingly limits usable output. The imaging characteristics of breast cancer subtypes have been described previously, but without standardization of parameters for data mining. METHODS: The authors searched the enterprise-wide data warehouse at the Houston Methodist Hospital, the Methodist Environment for Translational Enhancement and Outcomes Research (METEOR), for patients with Breast Imaging Reporting and Data System (BI-RADS) category 5 mammogram readings performed between January 2006 and May 2015 and an available pathology report. The authors developed natural language processing (NLP) software algorithms to automatically extract mammographic and pathologic findings from free text mammogram and pathology reports. The correlation between mammographic imaging features and breast cancer subtype was analyzed using one-way analysis of variance and the Fisher exact test. RESULTS: The NLP algorithm was able to obtain key characteristics for 543 patients who met the inclusion criteria. Patients with estrogen receptor-positive tumors were more likely to have spiculated margins (P 5.0008), and those with tumors that overexpressed human epidermal growth factor receptor 2 (HER2) were more likely to have heterogeneous and pleomorphic calcifications (P 5.0078 and P 5.0002, respectively). CONCLUSIONS: Mammographic imaging characteristics, obtained from an automated text search and the extraction of mammogram reports using NLP techniques, correlated with pathologic breast cancer subtype. The results of the current study validate previously reported trends assessed by manual data collection. Furthermore, NLP provides an automated means with which to scale up data extraction and analysis for clinical decision support.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

Patel

Puppala

Ogunti

et al. 2016

Cancer

Self Cite

View full text Add to dashboard Cite

show abstract

“…We used International Classification of Diseases, Ninth Revision (ICD‐9) codes to identify sepsis, severe sepsis and septic shock discharges between January 1, 2006, and September 09, 2015, and ICD‐10 codes to identify discharges between October 01, 2015, and June 30, 2016, We use the term sepsis as a generalizable term for all the sepsis‐related diagnoses, unless specific sepsis, severe sepsis, and septic shock related outcomes are mentioned. Data were retrieved from Houston M ethodist E nvironment for T ranslational E nhancement and O utcomes R esearch (METEOR) which is our hospital system‐wide enterprise clinical data warehouse containing admission data on over 4 million patients visits archived from 2006 . Each individual admission encounter for sepsis was reviewed.…”

Section: Methodsmentioning

confidence: 99%

Sepsis outcomes in solid organ transplant recipients

Gotur

Masud

Ezeana

et al. 2019

Transplant Infectious Dis

Self Cite

View full text Add to dashboard Cite

Background We present data on a cohort of patients diagnosed with sepsis over a 10‐year period comparing outcomes in solid organ transplant (SOT) and non–solid organ transplant (non–SOT) recipients. Methods This is a retrospective single‐center study of patients with diagnosis of sepsis from 1/1/06 to 6/30/16. Cases and controls were matched by year of sepsis diagnosis with propensity score matching. Conditional logistic regression and repeated measurement models were performed for binary outcomes. Trends over time for in‐hospital mortality were determined using the Cochran‐Armitage test. A gamma‐distributed model was performed on the continuous variables. Results Overall, there were 18 632 admission encounters with a discharge diagnosis of sepsis in 14 780 unique patients. Of those admissions, 1689 were SOT recipients. After 1:1 matching by year, there were three thousand three hundred and forty patients (1670 cases; 1670 controls) diagnosed with sepsis. There was a decreasing trend for in‐hospital mortality for sepsis over time in SOT patients and non–SOT patients (P < .05) due to early sepsis recognition and improved standard of care. Despite higher comorbidities in the SOT group, conditional logistic regression showed that in‐hospital mortality for sepsis in SOT patients was similar compared with non–SOT patients (odds ratio [OR] =1.14 [95% confidence interval {CI}, 0.95‐1.37], P = .161). However, heart and lung SOT subgroups had higher odds of dying compared with the non–SOT group (OR = 1.83 [95% CI, 1.30‐2.57], P < .001 and OR = 1.77 [95% CI, 1.34‐2.34], P < .001). On average, SOT patients had 2 days longer hospital length of stay compared with non–SOT admissions (17.00 ± 19.54 vs 15.23 ± 17.07, P < .05). Additionally, SOT patients had higher odds of hospital readmission within 30 days (OR = 1.25 [95% CI, 1.06‐1.51], P = .020), and higher odds for DIC compared with non–SOT patients (OR = 1.76 [95% CI, 1.10‐2.86], P = .021). Conclusion Sepsis in solid organ transplants and non–solid organ transplant patients have similar mortality; however, the subset of heart and lung transplant recipients with sepsis has a higher rate of mortality compared with the non–solid organ transplant recipients. SOT with sepsis as a group has a higher hospital readmission rate compared with non–transplant sepsis patients.

show abstract

“…The study was approved by the Institutional Review Board of Houston Methodist Hospital System. The METEOR (Methodist Environment for Enhancing Outcomes and Translational Research) enterprise‐wide clinical data warehouse and analytics system was queried using International Classification of Diseases‐9‐Clinical Modification (ICD‐9‐CM) codes for unique patients admitted with a primary diagnosis of heart failure (428.X) . Comorbidities present at baseline were defined by corresponding ICD‐9 codes.…”

Section: Methodsmentioning

confidence: 99%

Prevalence of in‐hospital nonsteroidal antiinflammatory drug exposure in patients with a primary diagnosis of heart failure

Álvarez

Putney

Ogunti

et al. 2017

Cardiovascular Therapeutics

Self Cite

View full text Add to dashboard Cite

show abstract

METEOR: An Enterprise Health Informatics Environment to Support Evidence-Based Medicine

Cited by 46 publications

References 16 publications

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

Sepsis outcomes in solid organ transplant recipients

Prevalence of in‐hospital nonsteroidal antiinflammatory drug exposure in patients with a primary diagnosis of heart failure

Contact Info

Product

Resources

About