Purpose It has been hypothesized that wide excision alone with margins ≥ 1 cm may be adequate treatment for small, grade 1 or 2 ductal carcinoma in situ (DCIS). To test this hypothesis, we conducted a prospective, single-arm trial. Methods Entry criteria included DCIS of predominant grade 1 or 2 with a mammographic extent of ≤ 2.5 cm treated with wide excision with final margins of ≥ 1 cm or a re-excision without residual DCIS. Tamoxifen was not permitted. The accrual goal was 200 patients. Results In July 2002, the study closed to accrual at 158 patients because the number of local recurrences met the predetermined stopping rules. The median age was 51 and the median follow-up time was 40 months. Thirteen patients developed local recurrence as the first site of treatment failure 7 to 63 months after study entry. The rate of ipsilateral local recurrence as first site of treatment failure was 2.4% per patient-year, corresponding to a 5-year rate of 12%. Nine patients (69%) experienced recurrence of DCIS and four (31%) experienced recurrence with invasive disease. Twelve recurrences were detected mammographically and one was palpable. Ten were in the same quadrant as the initial DCIS and three were elsewhere within the ipsilateral breast. No patient had positive axillary nodes at recurrence or subsequent metastatic disease. Conclusion Despite margins of ≥ 1 cm, the local recurrence rate is substantial when patients with small, grade 1 or 2 DCIS are treated with wide excision alone. This risk should be considered in assessing the possible use of radiation therapy with or without tamoxifen in these patients.
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.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.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.
