Feeds:
Posts
Comments

Posts Tagged ‘aortic stenosis’


 

Application of Natural Language Processing (NLP) on ~1MM cases of semi-structured echocardiogram reports: Identification of aortic stenosis (AS) cases – Accuracy comparison to administrative diagnosis codes (IDC 9/10 codes)

Reporter: Aviva Lev-Ari, PhD, RN

Large-Scale Identification of Aortic Stenosis and its Severity Using Natural Language Processing on Electronic Health Records

Background Systematic case identification is critical to improving population health, but widely used diagnosis code-based approaches for conditions like valvular heart disease are inaccurate and lack specificity. Objective To develop and validate natural language processing (NLP) algorithms to identify aortic stenosis (AS) cases and associated parameters from semi-structured echocardiogram reports and compare its accuracy to administrative diagnosis codes. Methods Using 1,003 physician-adjudicated echocardiogram reports from Kaiser Permanente Northern California, a large, integrated healthcare system (>4.5 million members), NLP algorithms were developed and validated to achieve positive and negative predictive values >95% for identifying AS and associated echocardiographic parameters. Final NLP algorithms were applied to all adult echocardiography reports performed between 2008-2018, and compared to ICD-9/10 diagnosis code-based definitions for AS found from 14 days before to six months after the procedure date. Results A total of 927,884 eligible echocardiograms were identified during the study period among 519,967 patients. Application of the final NLP algorithm classified 104,090 (11.2%) echocardiograms with any AS (mean age 75.2 years, 52% women), with only 67,297 (64.6%) having a diagnosis code for AS between 14 days before and up to six months after the associated echocardiogram. Among those without associated diagnosis codes, 19% of patients had hemodynamically significant AS (i.e., greater than mild disease). Conclusion A validated NLP algorithm applied to a systemwide echocardiography database was substantially more accurate than diagnosis codes for identifying AS. Leveraging machine learning-based approaches on unstructured EHR data can facilitate more effective individual and population management than using administrative data alone.

Large-scale identification of aortic stenosis and its severity using natural language processing on electronic health records

Author links open overlay panel

Matthew D.SolomonMD, PhD∗†GraceTabadaMPH∗AmandaAllen∗Sue HeeSungMPH∗Alan S.GoMD∗‡§‖

Division of Research, Kaiser Permanente Northern California, Oakland, California

Department of Cardiology, Kaiser Oakland Medical Center, Oakland, California

Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, California

§

Departments of Epidemiology, Biostatistics and Medicine, University of California, San Francisco, San Francisco, California

Department of Medicine, Stanford University, Stanford, California

Available online 18 March 2021.

https://www.sciencedirect.com/science/article/pii/S2666693621000256

Background

Systematic case identification is critical to improving population health, but widely used diagnosis code–based approaches for conditions like valvular heart disease are inaccurate and lack specificity.

Objective

To develop and validate natural language processing (NLP) algorithms to identify aortic stenosis (AS) cases and associated parameters from semi-structured echocardiogram reports and compare their accuracy to administrative diagnosis codes.

Methods

Using 1003 physician-adjudicated echocardiogram reports from Kaiser Permanente Northern California, a large, integrated healthcare system (>4.5 million members), NLP algorithms were developed and validated to achieve positive and negative predictive values > 95% for identifying AS and associated echocardiographic parameters. Final NLP algorithms were applied to all adult echocardiography reports performed between 2008 and 2018 and compared to ICD-9/10 diagnosis code–based definitions for AS found from 14 days before to 6 months after the procedure date.

Results

A total of 927,884 eligible echocardiograms were identified during the study period among 519,967 patients. Application of the final NLP algorithm classified 104,090 (11.2%) echocardiograms with any AS (mean age 75.2 years, 52% women), with only 67,297 (64.6%) having a diagnosis code for AS between 14 days before and up to 6 months after the associated echocardiogram. Among those without associated diagnosis codes, 19% of patients had hemodynamically significant AS (ie, greater than mild disease).

Conclusion

A validated NLP algorithm applied to a systemwide echocardiography database was substantially more accurate than diagnosis codes for identifying AS. Leveraging machine learning–based approaches on unstructured electronic health record data can facilitate more effective individual and population management than using administrative data alone.

Keywords

Aortic stenosis Echocardiography Machine learning Population health Quality and outcomes Valvular heart disease

SOURCE

https://www.sciencedirect.com/science/article/pii/S2666693621000256

Read Full Post »


The presence of any Valvular Heart Disease (VHD) did not influence the comparison of Dabigatran [Pradaxa, Boehringer Ingelheim] with Warfarin

Reporter: Aviva Lev-Ari, PhD, RN

 

UPDATED on 10/22/2018

Dabigatran (Pradaxa) was no better than aspirin for prevention of recurrent stroke among patients with an embolic stroke of undetermined source in the RE-SPECT ESUS trial reported at the World Stroke Congress.

 

Pradaxa® (dabigatran etexilate)
Clinical experience of Pradaxa® equates to over 9 million patient-years in all licensed indications worldwide. Pradaxa® has been in the market for more than ten years and is approved in over 100 countries.15
Currently approved indications for Pradaxa® are:16,17
  • Prevention of stroke and systemic embolism in patients with non-valvular atrial fibrillation and a risk factor for stroke
  • Primary prevention of venous thromboembolic events in patients undergoing elective total hip replacement surgery or total knee replacement surgery
  • Treatment of deep vein thrombosis (DVT) and pulmonary embolism (PE) and the prevention of recurrent DVT and recurrent PE in adults
Dabigatran, a direct thrombin inhibitor (DTI), was the first widely approved drug in a new generation of direct oral anticoagulants, available to target a high unmet medical need in the prevention and treatment of acute and chronic thromboembolic diseases.18,19,20
REFERENCES

SOURCE

https://www.boehringer-ingelheim.com/press-release/Results-from-two-Pradaxa-trials-to-be-presented-at-WSC

 

 

Event Rate and Outcome Risk, With vs Without Valvular Heart Disease

Outcome Valvular heart disease, event rate/y, % No valvular heart disease, event rate/y, % HR (95% CI)* P
Stroke, systemic embolic event 1.61 1.41 1.09 (0.88–1.33) 0.43
Major bleeding 4.36 2.84 1.32 (1.16–1.33) <0.001
Intracranial hemorrhage 0.51 0.41 1.20 (0.83–1.74) 0.32
All-cause mortality 4.45 3.67 1.09 (0.96–1.23) 0.18
*Adjusted using propensity scores

ORIGINAL RESEARCH ARTICLE

Comparison of Dabigatran versus Warfarin in Patients with Atrial Fibrillation and Valvular Heart Disease: The RE-LY Trial

Michael D. Ezekowitz, Rangadham Nagarakanti, Herbert Noack, Martina Brueckmann, Claire Litherland, Mark Jacobs, Andreas Clemens,Paul A. Reilly, Stuart J. Connolly, Salim Yusuf and Lars Wallentin

 http://dx.doi.org/10.1161/CIRCULATIONAHA.115.020950

 

Results—There were 3950 patients with any VHD:

  • 3101 had mitral regurgitation,
  • 1179 tricuspid regurgitation,
  • 817 aortic regurgitations,
  • 471 aortic stenosis and
  • 193 mild mitral stenosis.

At baseline patients with any VHD had more

  • heart failure,
  • coronary disease,
  • renal impairment and
  • persistent atrial fibrillation.

Patients with any VHD had higher rates of

  • major bleeds (HR 1.32; 95% CI 1.16-1.5)

but similar

  • stroke or systemic embolism (SEE) rates (HR 1.09; 95% CI 0.88-1.33).

For D110 patients, major bleed rates were lower than warfarin (HR 0.73; 95% CI 0.56-0.95 with and HR 0.84; 95% CI 0.71-0.99 without VHD) and

For D150 similar to warfarin in patients with (HR 0.82; 95% CI 0.64-1.06) or without VHD (HR 0.98; 95% CI 0.83-1.15).

For D150 patients stroke/SEE rates were lower versus warfarin with (HR 0.59; 95% CI 0.37-0.93) and without VHD (HR 0.67; 95% CI 0.52-0.86) and similar to warfarin for D110 irrespective of presence of VHD (HR 0.97 CI 0.65-1.45 and 0.85 CI 0.70-1.10).

For intracranial bleeds and death rates for D150 and D110 were lower vs warfarin independent of presence of VHD.

Conclusions—The presence of any VHD did not influence the comparison of dabigatran with warfarin.

Clinical Trial Registration—URL: http://clinicaltrials.gov. Unique Identifier: NCT00262600.

SOURCES

http://circ.ahajournals.org/content/early/2016/08/05/CIRCULATIONAHA.115.020950

http://www.medscape.com/viewarticle/867482?nlid=108872_3866&src=WNL_mdplsfeat_160816_mscpedit_card&uac=93761AJ&spon=2&impID=1179558&faf=1

 

Read Full Post »