AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
Incorrect electronic health records data that is put to secondary uses can lead to erroneous inferences and poor insurance coverage or other health-related policies

Medical Big Data And Big Data Quality Problems

CONNECTICUT INSURANCE LAW JOURNAL, no. 1 (2014): 289-316

Cited by: 0|Views7
Full Text
Bibtex
Weibo

Abstract

Medical big data has generated much excitement in recent years and for good reason. It can be an invaluable resource for researchers in general and insurers in particular. This Article, however, argues that users of medical big data must proceed with caution and recognize the data's considerable limitations and shortcomings. These include...More

Code:

Data:

Introduction
  • The term “big data” is suddenly pervasive. The New York Times deemed this the “Age of Big Data” in a 2012 article,[1] and a Google search for the term yields over 15 million hits. “Big data” is difficult to define precisely, but it is characterized by three attributes known as “the three Vs”: its large volume, its variety, and its velocity, that is, the frequency with which it is generated.[2].
  • One of the largest is scheduled to become operational in September 2015 and to link information from hospitals, academic centers, community clinics, insurers, and others sources.
  • This data repository, funded by the.
  • 11 Chad Terhune, They Know What’s in Your Medicine Cabinet, BLOOMBERG BUSINESSWEEK (July 22, 2008), http://www.businessweek.com/stories/2008-0722/they-know-whats-in-your-medicine-cabinet; David Lazarus, Your Prescription History Is Their Business, L.A. TIMES (Oct. 21, 2013), http://articles.
  • The PPACA applies only to health insurers and does not extend to life, long-term care, or disability insurers.[19]
Highlights
  • The term “big data” is suddenly pervasive
  • *** Medical big data has generated much excitement in recent years and for good reason. It can be an invaluable resource for researchers in general and insurers in particular. This Article, argues that users of medical big data must proceed with caution and recognize the data’s considerable limitations and shortcomings
  • The Patient Protection and Affordable Care Act (PPACA), severely limits the discretion of health insurers operating in the individual market
  • 22 Episodes are attributed to particular physicians based on attribution rules, as seen in the rule that dictates “responsibility is assigned to a physician who accounts for 30% or more of professional and prescribing costs included in the episode.”
  • Incorrect electronic health records (EHR) data that is put to secondary uses can lead to erroneous inferences and poor insurance coverage or other health-related policies
  • It is critical that vendors, health care providers, and government authorities aggressively attack the challenges of data quality
Results
  • 22 Episodes are attributed to particular physicians based on attribution rules, as seen in the rule that dictates “responsibility is assigned to a physician who accounts for 30% or more of professional and prescribing costs included in the episode.”.
Conclusion
  • Medical big data is a growing resource for insurance analysts and other researchers.
  • Incorrect EHR data that is put to secondary uses can lead to erroneous inferences and poor insurance coverage or other health-related policies.
  • It is critical that vendors, health care providers, and government authorities aggressively attack the challenges of data quality.
  • It is only with significant improvements that the great potential of medical big data can be realized
Funding
  • 22 Episodes are attributed to particular physicians based on attribution rules, as seen in the rule that dictates “responsibility is assigned to a physician who accounts for 30% or more of professional and prescribing costs included in the episode.”
Study subjects and analysis
individuals: 150
Such errors are particularly likely in hospitals. During a typical hospitalization, approximately 150 individuals view each patient’s chart, and multiple records may be handled at once in nursing stations.34. 32 Id. (the $2.13 billion figure is in 2007 dollars)

randomly selected hospital admissions: 100
Copy and paste is very commonly used. In a study of 100 randomly selected hospital admissions, copied text was found in seventy–. eight percent of medical residents’ sign-out notes (written when their shift ended) and fifty-four percent of patient progress notes.[40]

admissions: 629
Another publication found an average error rate of 9.76 percent.44. Australian researchers who audited 629 admissions at two Sydney hospitals identified 1,164 prescribing errors in. 41 AM

admissions: 100
43 Id. at 243–44. those patients’ records, equivalent to 185 errors per 100 admissions.45. They noted, however, that error rates had decreased significantly since the hospitals transitioned from paper medical records to EHRs, dropping from

admissions: 100
They noted, however, that error rates had decreased significantly since the hospitals transitioned from paper medical records to EHRs, dropping from. 625 inaccuracies per 100 admissions to 212 at one hospital and from 362 to 185 errors per 100 admissions at the other.46. EHR data is often incomplete, lacking elements that would be valuable for secondary uses.[47]

Reference
  • 1 Steve Lohr, The Age of Big Data, N.Y. TIMES (Feb. 11, 2012), http://www.nytimes.com/2012/02/12/sunday-review/big-datas-impact-in-theworld.html?pagewanted=all&_r=0.
    Locate open access versionFindings
  • 2 Philip Russom, Big Data Analytics, TDWI BEST PRACTICES REPORT 1, 6 (4th Quarter 2011).
    Google ScholarFindings
  • 3 Ariana Eunjung Cha, Scientists Embark on Unprecedented Effort to Connect Millions of Patient Medical Records, WASH. POST (Apr. 15, 2014), http://www.washingtonpost.com/national/health-science/scientists-embark-on-unprecedentedeffort-to-connect-millions-of-patient-medical-records/2014/04/15/ea7c966a-b12e11e3-9627-c65021d6d572_story.html.
    Locate open access versionFindings
  • 4 Sharona Hoffman & Andy Podgurski, The Use and Misuse of Biomedical Data: Is Bigger Really Better? 39 AM. J.L. & MED. 497, 506–15 (2013).
    Google ScholarLocate open access versionFindings
  • 5 Taxiarchis Botsis et al., Secondary Use of EHR: Data Quality Issues and Informatics Opportunities, AMIA JOINT SUMMITS TRANSLATIONAL SCI. PROC. 1, 1 (2010); Jessica S. Ancker et al., Root Causes Underlying Challenges to Secondary Use of Data, AMIA ANN. SYMP. PROC. 57, 57 (2011).
    Google ScholarLocate open access versionFindings
  • 6 Brian J. Wells et al., Strategies for Handling Missing Data in Electronic Health Record Derived Data, 1 EGEMS 1, 1 (2013), available at http://repository.academyhealth.org/egems/vol1/iss3/7/.
    Findings
  • 8 Health Insurance Coverage of the Total Population, THE HENRY J. KAISER FAMILY FOUND. (2012), http://kff.org/other/state-indicator/total-population/.
    Locate open access versionFindings
  • 10 Fact Sheet 8: Introduction to Medical and Health Information Privacy, PRIVACY RIGHTS CLEARINGHOUSE (Aug. 2014), https://www.privacyrights.org/medical-records-privacy.
    Locate open access versionFindings
  • 11 Chad Terhune, They Know What’s in Your Medicine Cabinet, BLOOMBERG BUSINESSWEEK (July 22, 2008), http://www.businessweek.com/stories/2008-0722/they-know-whats-in-your-medicine-cabinet; David Lazarus, Your Prescription History Is Their Business, L.A. TIMES (Oct.21, 2013), http://articles.latimes.com/2013/oct/21/business/la-fi-lazarus-20131022.
    Findings
  • 21 See Anna D. Sinaiko & Meredith B. Rosenthal, The Impact of Tiered Physician Networks on Patient Choice, HEALTH SERVS. RES. 1348, 1357 (2014), available at http://onlinelibrary.wiley.com/doi/10.1111/1475-6773.12165/pdf.
    Locate open access versionFindings
  • 27 See Hian Chye Koh & Gerald Tan, Data Mining Applications in Healthcare, 19 J. HEALTHCARE INFO MGMT. 64 (2005).
    Google ScholarLocate open access versionFindings
  • 28 K. Bruce Bayley et al., Challenges in Using Electronic Health Record Data for CER Experience of 4 Learning Organizations and Solutions Applied, 51 MED. CARE S80, S81 (2013); George Hripcsak & David J. Albers, Next-Generation Phenotyping of Electronic Health Records, 20 J. AM. MED. INFORMATICS ASS’N 117, 117–18 (2013).
    Google ScholarLocate open access versionFindings
  • 29 See Andrew Gottschalk & Susan A. Flocke, Time Spent in Face-to-Face Patient Care and Work Outside the Examination Room, 3 ANNALS FAM. MED. 488, 491 (2005) (finding that the average time per patient was 13.3 minutes); Kimberly S. H. Yarnall et al., Family Physicians as Team Leaders: See “Time” to Share the Care, PREVENTING CHRONIC DISEASE: PUB. HEALTH RES. PRAC. & POL’Y 1, 6, Apr. 2009, http://www.cdc.gov/pcd/issues/2009/apr/08_0023.htm (finding that the mean length for an acute care visit is 17.3 minutes, the mean for a chronic disease care visit is 19.3 minutes, and the average for a preventive care visit is 21.4 minutes, and that of total clinical time spent by physicians, these comprise 45.8%, 37.4%, and 16.8%respectively); Kevin Fiscella & Ronald M. Epstein, So Much to Do, So Little Time: Care for the Socially Disadvantaged and the 15-Minute Visit, 168 ARCHIVES INTERNAL MED.1843, 1843 (2008) (“The average office visit in the United States lasts for about 16 minutes.”).
    Locate open access versionFindings
  • 30 Farah Magrabi et al., An Analysis of Computer-Related Patient Safety Incidents to Inform the Development of A Classification, 17 J. AM. MED. INFORMATICS ASS’N. 663, 665, 669 (2010); Sharona Hoffman & Andy Podgurski, E-Health Hazards: Provider Liability and Electronic Health Record Systems, 24 BERKELEY TECH. L. J. 1523, 1544–45 (2009) (discussing input errors); Botsis et al., supra note 5, at 1; Ancker et al., supra note 5, at 57.
    Google ScholarLocate open access versionFindings
  • 31 Christopher S. Brunt, CPT Fee Differentials and Visit Upcoding Under Medicare Part B, 20 HEALTH ECON. 831, 840 (2011).
    Google ScholarLocate open access versionFindings
  • 33 Elizabeth Borycki, Trends in Health Information Technology Safety: From Technology-Induced Errors to Current Approaches for Ensuring Technology Safety, 19 HEALTH INF. RES. 69, 70 (2013).
    Google ScholarLocate open access versionFindings
  • 35 Eugenia L. Siegler & Ronald Adelman, Copy and Paste: A Remediable Hazard of Electronic Health Records, 122 AM. J. MED. 495, 495–96 (2009) (cautioning that cut and paste functions can lead to patient problem lists never changing, notes and errors being copied by multiple staff members, and loss of accurate narrative).
    Google ScholarLocate open access versionFindings
  • 36 Lena Mamykina et al., Clinical Documentation: Composition or Synthesis?, 19 J. AM. MED. INFORMATICS ASS’N. 1025, 1027 (2012).
    Google ScholarLocate open access versionFindings
  • 37 Kevin B. O’Reilly, EHRs: “Sloppy and Paste” Endures Despite Patient Safety Risk, AM. MED. NEWS (Feb. 4, 2013), http://www.amednews.com/article/20130204/profession/130209993/2/.
    Findings
  • 42 Saveli I. Goldberg et al., Analysis of Data Errors in Clinical Research Databases, AMIA 2008 ANN. SYMP. PROC. 242, 242–43 (2008) (attributing errors to data entry mistakes, misinterpretation of hard-copy documents when information was typed into the database, and perpetuation of errors that were contained in the original paper documents and were not corrected during the transition to EHRs).
    Google ScholarLocate open access versionFindings
  • 44 Meredith L. Nahm, Quantifying Data Quality for Clinical Trials Using Electronic Data Capture, PLOS ONE, AUG. 2008, at 1 (discussing a literature review of “42 articles that provided source-to-database error rates, primarily from registries” and finding that the “average error rate across these publications was 976 errors per 10,000 fields”); see also James J. Cimino et al., Use of Clinical Alerting to Improve the Collection of Clinical Research Data, AMIA 2009 SYMP. PROC. 218, 218 (2009) (discussing data error rates pertaining to research databases).
    Google ScholarLocate open access versionFindings
  • 45 Johanna I. Westbrook et al., The Safety of Electronic Prescribing: Manifestations, Mechanisms, and Rates of System-Related Errors Associated with Two Commercial Systems in Hospitals, 20 J. AM. MED. INFORMATICS ASS’N 1159, 1161 (2013).
    Google ScholarLocate open access versionFindings
  • 49 Craig Newgard et al., Electronic Versus Manual Data Processing: Evaluating the Use of Electronic Health Records in Out-of-Hospital Clinical Research, 19 ACAD. EMERGENCY MED. 217, 225 (2012).
    Google ScholarLocate open access versionFindings
  • 50 David S. Sanders et al., Electronic Health Record Systems in Ophthalmology: Impact on Clinical Documentation, 120 AM. ACAD. OPHTHALMOLOGY 1745, 1751–53 (2013).
    Google ScholarLocate open access versionFindings
  • 51 Kitty S. Chan et al., Review: Electronic Health Records and the Reliability and Validity of Quality Measures: A Review of the Literature, 67 MED. CARE RES. & REV. 503, 506 (2010).
    Google ScholarLocate open access versionFindings
  • 53 Joseph L. Goulet et al., Measuring Performance Directly Using the Veterans Health Administration Electronic Medical Record: A Comparison with External Peer Review, 45 MED. CARE 73, 81 (2007).
    Google ScholarLocate open access versionFindings
  • 54 See, e.g., Susan Rea et al., Bias in Recording of Body Mass Index Data in the Electronic Health Record, AMIA SUMMITS ON TRANSLATIONAL SCI. PROC. 214, 217 (2013) (“[T]he BMI on higher disease status patients was also demonstrated when comparing the frequencies of patients having particular diagnoses between subgroups having versus not having a BMI recorded.”); Nicole G. Weiskopf, Sick Patients Have More Data: The Non-Random Completeness of Electronic Health Records, AMIA SUMMITS ON TRANSLATIONAL SCI. PROC., 1472, 1476 (2013) (“Sicker patients tend to have more complete records and healthier patients tend to have records that are less complete.”).
    Google ScholarLocate open access versionFindings
  • 55 For an example of selection bias, see generally KENNETH J. ROTHMAN ET AL., MODERN EPIDEMIOLOGY 135–36 (3d ed. 2008) (explaining selection bias in the context of epidemiologic studies).
    Google ScholarLocate open access versionFindings
  • 57 See generally William R. Hersh et al., Caveats for the Use of Operational Electronic Health Record Data in Comparative Effectiveness Research, 51 MED. CARE S30, S33 (2013) (“The most commonly known problematic transformation of data occurs when data are coded, often for billing purposes”).
    Google ScholarLocate open access versionFindings
  • 61 Christopher G. Chute, Medical Concept Representation, in MEDICAL INFORMATICS: KNOWLEDGE MANAGEMENT AND DATA MINING IN BIOMEDICINE 170 tbl.6-1 (Hsinchun Chen et al. eds., 2005).
    Google ScholarLocate open access versionFindings
  • 62 Wells, supra note 6, at 2 (“[T]he free text areas of the patient chart... are difficult to analyze quantitatively due to the breadth of human expression, grammatical errors, “the use of acronyms and abbreviations, and the potential for different interpretations of the same phrase depending on context.”); Nicole Gray Weiskopf & Chunhua Weng, Methods and Dimensions of Electronic Health Record Data Quality Assessment: Enabling Reuse for Clinical Research, 20 J. AM. MED. INFORMATICS ASS’N 144, 147–48 (2013) (discussing terminology and dimensions of data quality).
    Google ScholarLocate open access versionFindings
  • 64 Interoperable systems can communicate with each other, exchange data, and operate seamlessly and in a coordinated fashion across organizations. BIOMEDICAL INFORMATICS: COMPUTER APPLICATIONS IN HEALTH CARE AND BIOMEDICINE 952 (Edward H. Shortliffe & James J. Cimino eds., 3d ed. 2006).
    Google ScholarFindings
  • 66 For a discussion of data de-identification, see Sharona Hoffman & Andy Podgurski, Balancing Privacy, Autonomy and Scientific Needs in Electronic Health Records Research, 65 SMU L. REV. 85, 104–05, 128–33 (2012).
    Google ScholarLocate open access versionFindings
  • 67 Daniel R. Verdon, ONC's DeSalvo Issues Next Health IT Challenge: Build Interoperable EHR Systems, MED. ECON. (Mar. 4, 2014), http://medicaleconomics.modernmedicine.com/medical-economics/news/oncs-desalvo-issues-next-health-itchallenge-build-interoperable-ehr-systems. The Office of the National Coordinator for Health Information Technology is part of the U.S. Department of Health and Human Services and is charged with promoting and facilitating the country’s transition to widespread use of health information technology.
    Locate open access versionFindings
  • 68 Hersh et al., supra note 57, at S33; Andrea L. Benin et al., Validity of Using an Electronic Medical Record for Assessing Quality of Care in an Outpatient Setting, 43 MED. CARE 691, 696 (2005).
    Google ScholarLocate open access versionFindings
  • 71 Dean F. Sittig & Hardeep Singh, Defining Health Information Technology– Related Errors: New Developments since To Err is Human, 171 ARCHIVES INTERNAL MED. 1281, 1283 (2011), available at http://archinte.jamanetwork.com/article.aspx?articleid=1105855.
    Locate open access versionFindings
  • 73 Rebecca Sanders & Diane Kelly, DEALING WITH RISK IN SCIENTIFIC SOFTWARE DEVELOPMENT, 25 IEEE SOFTWARE 21, 25, 27 (2008), available at http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4548404; Diane F. Kelly, A Software Chasm: Software Engineering and Scientific Computing, 24 IEEE SOFTWARE 120, 118 (2007), available at http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4375255; Les Hatton, The Chimera of Software Quality, 40 COMPUTER 104, 104 (2007), available at http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4292028.
    Locate open access versionFindings
  • 75 Stacy Singer, Electronic Medical Records May Cause Patient Care Errors, Florida Medical Board Says, PALM BEACH POST (June 5, 2010), http://www.palmbeachpost.com/news/news/electronic-medical-records-may-causepatient-care-/nL7Yc/.
    Locate open access versionFindings
  • 77 Stephany N. Duda et al., Measuring the Quality of Observational Study Data in an International HIV Research Network, 7 PLoS ONE 1, 1 (2012), available at http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0033908.
    Locate open access versionFindings
  • 78 Tammy Worth, Spike in Retrospective Audits: But Industry Insiders Dispute Any Abnormalities, HEALTHCARE FIN. NEWS (June 1, 2013), http://www.healthcare financenews.com/news/spike-retrospective-audits.
    Locate open access versionFindings
  • 80 Weiskopf & Weng, supra note 62, at 145. 81 45 C.F.R. §§ 164.524–.526 (2013).
    Google ScholarFindings
  • 85 Katie Hafner, A Busy Doctor’s Right Hand, Ever Ready to Type, N.Y. TIMES (Jan. 12, 2014), http://www.nytimes.com/2014/01/14/health/a-busy-doctorsright-hand-ever-ready-to-type.html?_r=0; Scott A. Shipman & Christine A. Sinsky, Expanding Primary Care Capacity by Reducing Waste and Improving the Efficiency of Care, 32 HEALTH AFF.1990, 1993 (2013).
    Findings
  • 87 See PhysAssist Scribes, http://www.iamscribe.com/index.php (last visited Oct.15, 2014); ScribeAmerica, https://www.scribeamerica.com/ (last visited Oct.15, 2014).
    Findings
  • 90 Robert Hoyt & Ann Yoshihashi, Lessons Learned from Implementation of Voice Recognition for Documentation in the Military Electronic Health Record System, 7 PERSP. HEALTH INFO. MGMT. 1, 1 (2010), available at http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2805557/.91 Krystl Haerian et al., Use of Clinical Alerting to Improve the Collection of Clinical Research Data, 2009 AMIA SYMP. PROC.218, 219–20, available at http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2815392/pdf/amia-f2009-218.pdf.
    Locate open access versionFindings
  • 95 David A. Hanauer, EMERSE: The Electronic Medical Record Search Engine, 2006 AMIA ANNU. SYMP. PROC., 941, 941, available at http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1839699/pdf/AMIA2006_0941.pdf.
    Locate open access versionFindings
  • 98 Abigail McWilliams et al., Guest Editors’ Introduction Corporate Social Responsibility: Strategic Implications, 43 J. MGMT. STUD. 1, 9 (2006) (defining “externality” as “the impact of an economic agent’s actions on the well-being of a bystander” and citing innovation as an example of a positive externality because of its general social benefits).
    Google ScholarLocate open access versionFindings
  • 100 Sharona Hoffman & Andy Podgurski, Meaningful Use and Certification of Health Information Technology: What about Safety?, 39 J. L. MED. & ETHICS 77, 78 (2011); 42 C.F.R. §§ 495.2–495.370 (2013).
    Google ScholarLocate open access versionFindings
  • 101 Hoffman & Podgurski, supra note 100, at 78. President Obama’s stimulus legislation, the American Recovery and Reinvestment Act of 2009, “provides for payments of up to $44,000 per clinician under the Medicare incentive program and $63,750 per clinician under the Medicaid program.” Id. at 77.
    Google ScholarLocate open access versionFindings
  • 103 See 45 C.F.R. §§ 170.314(b), (f) (2014) (addressing care coordination and public health).
    Google ScholarFindings
  • 104 Robert Tagalicod & Jacob Reider, Progress on Adoption of Electronic Health Records, CTR. FOR MEDICARE & MEDICAID SERV. (Dec. 13, 2013, 12:41 PM), http://www.cms.gov/eHealth/ListServ_Stage3Implementation.html.
    Findings
  • 105 Anthony Brino, Senators Press for EHR Interoperability, HEALTHCARE IT NEWS (Jan. 6, 2014), http://www.healthcareitnews.com/news/senators-press-ehrinteroperability (reporting that House and Senate bills call upon the Department of Health and Human Services “to adopt a common interoperability standard by 2017, as part of the rules for meaningful use Stage 3”); Verdon, supra note 67 (reporting that Dr. Karen DeSalvo, National Coordinator for Health Information Technology, has declared that interoperability will be a national priority).
    Locate open access versionFindings
  • 110 Audit Program Protocol, U.S. DEPARTMENT OF HEALTH & HUM. SERVICES, http://www.hhs.gov/ocr/privacy/hipaa/enforcement/audit/protocol.html (last visited Oct.6, 2014); Patrick Ouellette, OCR Readies Pre-Audit Survey for HIPAA Covered Entities, BAs, HEALTHITSECURITY.COM (Feb.25, 2014), should be among OCR’s areas of focus during audits, and the agency should require covered entities to demonstrate that they have implemented measures to verify and improve data quality.
    Locate open access versionFindings
  • 111 Enforcement Highlights, U.S. DEPARTMENT OF HEALTH & HUM. SERVICES (Mar. 31, 2014), http://www.hhs.gov/ocr/privacy/hipaa/enforcement/highlights/. The report covers the period of April 2003 (the HIPAA Privacy Rule’s effective date)through March 2014. Id.
    Findings
  • 116 See generally Acad. of Physicians in Clinical Research, About APCR, APCRNET.ORG, http://www.apcrnet.org/FunctionalMenuCategory/AboutAPCR.aspx (last visited Oct.6, 2014).
    Locate open access versionFindings
Author
sharona hoffman
sharona hoffman
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科