In this age, we aspire to practice evidence-based medicine , which has been described as an approach that applies “the best available   evidence gained from the scientific method to medical decision   making.” (Sackett DL, Rosenberg WM, Gray JA et al) Instead, we   are more likely to practice     memory-based medicine  meaning that “Current medical practice relies heavily on the unaided mind to recall   a great amount of detailed knowledge.”(Crane RM)   Our failure to practice evidence based medicine is endemic   throughout medical care, as documented by McGlynn et. al. who   found that barely 55% of patients get recommended care, and that   this could be seen in the management of multiple conditions (Figures   1 & 2). Furthermore, the average time from the discovery of   medicine to reach patients is 17 years – because of the slow   adoption of practice changes.(Balas EA, Boren SA)  ….

To download full manuscript, click:

HughesDrohanDecision_Analysis_In_Cancer_Management

Abstract: Family history of cancer is critical for identifying and managing patients at risk for cancer. However, the quality of family history data is dependent on the accuracy of patient self reporting. Therefore, the validity of family history reporting is crucial to the quality of clinical care. A retrospective review of family history data collected at a community hospital between 2005 and 2009 was performed in 43,257 women presenting for screening mammography. Reported numbers of breast, colon, prostate, lung, and ovarian cancer were compared in maternal relatives vs. paternal relatives and in first vs. second degree relatives. Significant reporting differences were found between maternal and paternal family history of cancer, in addition to degree of relative. The number of paternal family histories of cancer was significantly lower than that of maternal family histories of cancer. Similarly, the percentage of grandparents’ family histories of cancer was significantly lower than the percentage of parents’ family histories of cancer. This trend was found in all cancers except prostate cancer. Self-reported family history in the community setting is often influenced by both bloodline of the cancer history and the degree of relative affected. This is evident by the underreporting of paternal family histories of cancer, and also, though to a lesser extent, by degree. These discrepancies in reporting family history of cancer imply we need to take more care in collecting accurate family histories and also in the clinical management of individuals in relation to hereditary risk.

Click to download PDF

OzanneHughes2012JGenCounsBiasInReportingMaternalPaternalFamilyHistory

Julliette M. Buckley, Suzanne B. Coopey, John Sharko, Fernanda Polubriaginof, Brian Drohan, Ahmet K. Belli, Elizabeth M. H. Kim, Judy E. Garber1, Barbara L. Smith, Michele A. Gadd, Michelle C. Specht, Constance A. Roche, Thomas M. Gudewicz2, Kevin S. Hughes

Departments of Surgical Oncology and 2Surgical Pathology, Massachusetts General Hospital, 1Department of Surgical Oncology, Dana Farber Cancer Institute, Boston, Massachusetts, USA E-mail: *Kevin S. Hughes – kshughes@partners.org *Corresponding author

Received: 20 December 11 Accepted: 22 May 12 Published: 30 June 12

This article may be cited as: Buckley JM, Coopey SB, Sharko J, Polubriaginof F, Drohan B, Belli AK, et al. The feasibility of using natural language processing to extract clinical information from breast pathology reports. J Pathol Inform 2012;3:23.

Abstract Objective: The opportunity to integrate clinical decision support systems into clinical practice is limited due to the lack of structured, machine readable data in the current format of the electronic health record. Natural language processing has been designed to convert free text into machine readable data. The aim of the current study was to ascertain the feasibility of using natural language processing to extract clinical information from >76,000 breast pathology reports. Approach and Procedure: Breast pathology reports from three institutions were analyzed using natural language processing software (Clearforest, Waltham, MA) to extract information on a variety of pathologic diagnoses of interest. Data tables were created from the extracted information according to date of surgery, side of surgery, and medical record number. The variety of ways in which each diagnosis could be represented was recorded, as a means of demonstrating the complexity of machine interpretation of free text. Results: There was widespread variation in how pathologists reported common pathologic diagnoses. We report, for example, 124 ways of saying invasive ductal carcinoma and 95 ways of saying invasive lobular carcinoma. There were >4000 ways of saying invasive ductal carcinoma was not present. Natural language processor sensitivity and specificity were 99.1% and 96.5% when compared to expert human coders. Conclusion: We have demonstrated how a large body of free text medical information such as seen in breast pathology reports, can be converted to a machine readable format using natural language processing, and described the inherent complexities of the task.

Click to download PDF

JPatholInform_2012_3_1_23_97788

Brian Drohan, MS,* Elissa M. Ozanne, PhD,and Kevin S. Hughes, MD

*Department of Computer Science, University of Massachusetts Lowell, Massachusetts; Institute for Technology Assessment, Massachusetts General Hospital, Harvard Medical School, Massachusetts; and Avon Breast Evaluation Center, Massachusetts General Hospital, Newton-Wellesley Hospital, Harvard Medical School, Massachusetts

Abstract: Currently, management strategies exist that can decrease the morbidity and mortality associated with having a BRCA1 or BRCA2 mutation. Unfortunately, the task of identifying these patients at high risk is a daunting challenge. This problem is intensified because Electronic Health Records (EHRs) today lack the functionality needed to identify these women and to manage those women once they have been identified. Numerous niche software programs have been developed to fill this gap. Unfortunately, these extremely valuable niche programs are prevented from being interoperable with the EHRs, on the premise that each EHR vendor will build their own programs. Effectively, in our efforts to adopt EHRs, we have lost sight of the fact that they can only have a major impact on quality of care if they contain structured data and if they interact with robust Clinical Decision Support (CDS) tools. We are at a cross roads in the development of the health care Information Technology infrastructure. We can choose a path where each EHR vendor develops each CDS module independently. Alternatively, we can choose a path where experts in each field develop external niche software modules that are interoperable with any EHR vendor. We believe that the modular approach to development of niche software programs that are interoperable with current EHRs will markedly increase the speed at which useful and functional EHRs that improve quality of care become a reality. Thus, in order to realize the benefits of CDS, we suggest vendors develop means to become interoperable with external modular niche programs.

Get PDF here:

Drohan_BreastJ_2009ModularEHR

To see our approach to the Modular EHR, go to:

http://thebreastcancersurgeon.org/hughesriskappsriskmodule/

      

Co-Director

Avon Comprehensive Breast Evaluation Center

Massachusetts General Hospital

Boston, Massachusetts

Breast Cancer 

Surgical Director

Breast/Ovarian Cancer Risk Assessment Program

Massachusetts General Hospital

Boston, Massachusetts

 Breast Cancer

Associate Professor of Surgery

Harvard Medical School

Boston, Massachusetts

Breast Cancer 

Medical Director

Bermuda Cancer Genetics Risk Assessment Clinic

Hamilton, Bermuda

Dr. Hughes is a Breast Surgeon and a member of the Department of Surgical Oncology at the Massachusetts General Hospital in Boston, Massachusetts. 

He is actively involved in patient care with an emphasis on:

• The screening and diagnosis of breast diseases, such as the management of breast lumps, nipple discharge or abnormal mammogram findings
• The diagnosis and treatment of breast cancer
• The identification and management of women at high risk of breast cancer due to a strong family history
• The identification and management of women at high risk of breast cancer due to a biopsy diagnosis of atypical ductal hyperplasia, atypical lobular hyperplasia, lobular carcinoma in situ ro borderline DCIS
• The management of breast cancer

He is a graduate of Dartmouth College and Dartmouth Medical School, and trained at the Mercy Hospital of Pittsburgh for general surgery, followed by a fellowship in surgical oncology at the National Cancer Institute. 

Dr. Hughes was formerly on the faculty of Tufts University, the University of California, Davis and Brown University.  Dr. Hughes is actively involved in research regarding the

• Genetics and Risk factors for Breast Cancer
• Screening for breast cancer
• Diagnostic approaches to Breast Disease and Breast Cancer
• Treatment of breast cancer

Dr. Hughes is actively involved in the development of Electronic Health Records that improve the quality of patient care and decrease clinician workload.  He co-authored the HL7, ANSI approved standard for transmitting family health history between Electronic Health Records.

Http://www.HughesRiskApps.com

*The Massachusetts General Hospital Avon Foundation Comprehensive Breast Evaluation Center, Boston, MA, offers women the most advanced breast imaging, surgical screening, diagnosis and management, and pathology services available.

http://www.TheBreastCancerSurgeon.org