Thomas M. Gudewicz

The feasibility of using natural language processing to extract clinical information from breast pathology reports.

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.

Cutaneous and mammary apocrine carcinomas have different immunoprofiles

Often the distinction of cutaneous apocrine carcinoma from metastatic mammary apocrine carcinoma to the skin can be a diagnostic dilemma because both tumors share similar histologic features and have overlapping immunohistochemical profile. We compared the expression of adipophilin, cytokeratin 5/6, p63, GATA3, mammaglobin, androgen receptor, estrogen receptor, progesterone receptor, and HER2 by immunohistochemistry in 14 cutaneous apocrine carcinomas (11 primary tumors, 3 metastases) and 26 primary apocrine carcinomas of the breast. Whereas focal adipophilin staining was seen in 36% (5/14) of cutaneous apocrine carcinoma, strong and diffuse adipophilin staining was seen in 88% (22/25) of mammary apocrine carcinoma (P = .0013). Differences in estrogen receptor and progesterone receptor expression were also statistically significant (P = .018 and .043). Androgen receptor was strongly positive in all cutaneous and mammary cases. Although there was no significant difference in the frequency of expression of cytokeratin 5/6, p63, HER2, GATA3, and mammaglobin in cutaneous apocrine carcinoma versus mammary apocrine carcinoma, strong and diffuse cytokeratin 5/6 and/or mammaglobin expression were seen only in cutaneous apocrine carcinoma. In conclusion, cutaneous apocrine carcinoma is likely adipophilin- ER+ PR+/- HER2- and can exhibit strong and diffuse cytokeratin 5/6 and/or mammaglobin expression. On the contrary, a mammary apocrine carcinoma is likely adipophilin+ ER- PR- and often exhibit 3+ HER2 with corresponding HER2 gene amplification. A panel of adipophilin, ER, PR, HER2, cytokeratin 5/6, and mammaglobin may be helpful in distinguishing cutaneous apocrine carcinoma from mammary apocrine carcinoma.

Spinal cord glioblastoma: 25years of experience from a single institution.

Accounting for less than 0.2% of all glioblastomas, high grade gliomas of the spinal cord are very rare. Here, we discuss our approach to managing patients with high grade spinal cord glioma and review the literature on the subject. Six patients with high grade spinal cord gliomas who presented to our institution between 1990 and 2015 were reviewed. Each patient underwent subtotal surgical resection, with a subset receiving adjuvant chemotherapy and radiation. Our primary outcomes of interest were pre-operative and post-operative functional status. One year survival rate was 100%. All patients had stable or improved American Spine Injury Association score immediately after surgery, which was maintained at 3months in 83.3% of patients. Karnofsky Performance Status (KPS) was stable at 3month follow up in 50% of patients, but all had decreased KPS 1year after surgery. A subset of patients received post-operative radiation and chemotherapy with 0% tumor recurrence rate at 3months. We assessed the molecular profiles of tumors from two patients in our series and found that each had mutations in TP53, but had wildtype BRAF, IDH-1, and MGMT. Taken together, our data show that patients with high grade spinal cord gliomas have an excellent survival at 1year, but with some decline in functional status within this period. Further studies are needed to elucidate the natural history of the disease and to explore the role of adjuvant targeted molecular therapies.

Host Genetics Predict Clinical Deterioration in HCV-Related Cirrhosis

Single nucleotide polymorphisms (SNPs) in the epidermal growth factor (EGF, rs4444903), patatin-like phospholipase domain-containing protein 3 (PNPLA3, rs738409) genes, and near the interleukin-28B (IL28B, rs12979860) gene are linked to treatment response, fibrosis, and hepatocellular carcinoma (HCC) in chronic hepatitis C. Whether these SNPs independently or in combination predict clinical deterioration in hepatitis C virus (HCV)-related cirrhosis is unknown. We genotyped SNPs in EGF, PNPLA3, and IL28B from liver tissue from 169 patients with biopsy-proven HCV cirrhosis. We estimated risk of clinical deterioration, defined as development of ascites, encephalopathy, variceal hemorrhage, HCC, or liver-related death using Cox proportional hazards modeling. During a median follow-up of 6.6 years, 66 of 169 patients experienced clinical deterioration. EGF non-AA, PNPLA3 non-CC, and IL28B non-CC genotypes were each associated with increased risk of clinical deterioration in age, sex, and race-adjusted analysis. Only EGF non-AA genotype was independently associated with increased risk of clinical deterioration (hazard ratio [HR] 2.87; 95% confidence interval [CI] 1.31–6.25) after additionally adjusting for bilirubin, albumin, and platelets. Compared to subjects who had 0–1 unfavorable genotypes, the HR for clinical deterioration was 1.79 (95%CI 0.96–3.35) for 2 unfavorable genotypes and 4.03 (95%CI 2.13–7.62) for unfavorable genotypes for all three loci (Ptrend<0.0001). In conclusion, among HCV cirrhotics, EGF non-AA genotype is independently associated with increased risk for clinical deterioration. Specific PNPLA3 and IL28B genotypes also appear to be associated with clinical deterioration. These SNPs have potential to identify patients with HCV-related cirrhosis who require more intensive monitoring for decompensation or future therapies preventing disease progression.

Using machine learning to parse breast pathology reports

Purpose Extracting information from electronic medical record is a time-consuming and expensive process when done manually. Rule-based and machine learning techniques are two approaches to solving this problem. In this study, we trained a machine learning model on pathology reports to extract pertinent tumor characteristics, which enabled us to create a large database of attribute searchable pathology reports. This database can be used to identify cohorts of patients with characteristics of interest.Methods We collected a total of 91,505 breast pathology reports from three Partners hospitals: Massachusetts General Hospital, Brigham and Women’s Hospital, and Newton-Wellesley Hospital, covering the period from 1978 to 2016. We trained our system with annotations from two datasets, consisting of 6295 and 10,841 manually annotated reports. The system extracts 20 separate categories of information, including atypia types and various tumor characteristics such as receptors. We also report a learning curve analysis to show how much annotation our model needs to perform reasonably.Results The model accuracy was tested on 500 reports that did not overlap with the training set. The model achieved accuracy of 90% for correctly parsing all carcinoma and atypia categories for a given patient. The average accuracy for individual categories was 97%. Using this classifier, we created a database of 91,505 parsed pathology reports.ConclusionsOur learning curve analysis shows that the model can achieve reasonable results even when trained on a few annotations. We developed a user-friendly interface to the database that allows physicians to easily identify patients with target characteristics and export the matching cohort. This model has the potential to reduce the effort required for analyzing large amounts of data from medical records, and to minimize the cost and time required to glean scientific insight from these data.

Case 30-2016

Dr. Daniel J. Daunis (Psychiatry): A 63-year-old woman with bipolar disorder, worsening depression, and multiple other medical conditions, including lung cancer and breast cancer, was admitted to the inpatient psychiatry service of this hospital for electroconvulsive therapy (ECT). The patient had a long-standing history of bipolar disorder, including depressive episodes, which were characterized by low motivation, low energy, a feeling of hopelessness, agoraphobia, and suicidal ideation without suicide attempts, and brief episodes, each lasting for 2 to 3 weeks, of hypomania and mania with irritable or elevated mood, labile affect, pressured speech, and a decreased need for sleep. Twelve years before this admission, she had received a diagnosis of stage IIA estrogen-receptor–positive and progesterone-receptor–positive, HER2/neu-negative invasive ductal carcinoma of the left breast, with lymphatic-vessel invasion and isolated tumor cells in 2 of 2 lymph nodes. The patient underwent lumpectomy and adjuvant wholebreast radiation therapy. Follow-up therapy included four cycles of doxorubicin and cyclophosphamide chemotherapy and a 5-year course of tamoxifen. She had also been hospitalized three times for mania with psychotic features, including paranoia and visual hallucinations; her most recent hospitalization for mania occurred during her treatment for breast cancer, 11 years before this admission for ECT. She also had attention deficit–hyperactivity disorder (ADHD). Over the years, she had been treated with lithium, stimulants, atypical antipsychotic agents, and multiple classes of antidepressants. Six years before this admission, the patient discontinued primary care follow-up, and shortly thereafter she discontinued psychiatric care. Two years before this admission, a diagnosis of stage II non–small-cell carcinoma of the right lung was made. At the time of the diagnosis, she was referred to a psychiatrist at the cancer center of this hospital. Her medications were adjusted, and her depression abated. She underwent a right upper lobectomy and received adjuvant chemotherapy. From the Departments of Psychiatry (K.E.I., O.F.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.) and the Division of Medical Oncology (J.P.), Massachusetts General Hospital, and the Departments of Psychiatry (K.E.I., O.F.), Medicine (J.P.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.), Harvard Medical School — both in Boston.

Case 30-2016: A 63-Year-Old Woman with Bipolar Disorder, Cancer, and Worsening Depression

Dr. Daniel J. Daunis (Psychiatry): A 63-year-old woman with bipolar disorder, worsening depression, and multiple other medical conditions, including lung cancer and breast cancer, was admitted to the inpatient psychiatry service of this hospital for electroconvulsive therapy (ECT). The patient had a long-standing history of bipolar disorder, including depressive episodes, which were characterized by low motivation, low energy, a feeling of hopelessness, agoraphobia, and suicidal ideation without suicide attempts, and brief episodes, each lasting for 2 to 3 weeks, of hypomania and mania with irritable or elevated mood, labile affect, pressured speech, and a decreased need for sleep. Twelve years before this admission, she had received a diagnosis of stage IIA estrogen-receptor–positive and progesterone-receptor–positive, HER2/neu-negative invasive ductal carcinoma of the left breast, with lymphatic-vessel invasion and isolated tumor cells in 2 of 2 lymph nodes. The patient underwent lumpectomy and adjuvant wholebreast radiation therapy. Follow-up therapy included four cycles of doxorubicin and cyclophosphamide chemotherapy and a 5-year course of tamoxifen. She had also been hospitalized three times for mania with psychotic features, including paranoia and visual hallucinations; her most recent hospitalization for mania occurred during her treatment for breast cancer, 11 years before this admission for ECT. She also had attention deficit–hyperactivity disorder (ADHD). Over the years, she had been treated with lithium, stimulants, atypical antipsychotic agents, and multiple classes of antidepressants. Six years before this admission, the patient discontinued primary care follow-up, and shortly thereafter she discontinued psychiatric care. Two years before this admission, a diagnosis of stage II non–small-cell carcinoma of the right lung was made. At the time of the diagnosis, she was referred to a psychiatrist at the cancer center of this hospital. Her medications were adjusted, and her depression abated. She underwent a right upper lobectomy and received adjuvant chemotherapy. From the Departments of Psychiatry (K.E.I., O.F.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.) and the Division of Medical Oncology (J.P.), Massachusetts General Hospital, and the Departments of Psychiatry (K.E.I., O.F.), Medicine (J.P.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.), Harvard Medical School — both in Boston.

CASE RECORDS of the MASSACHUSETTS GENERAL HOSPITAL. Case 30-2016. A 63-Year-Old Woman with Bipolar Disorder, Cancer, and Worsening Depression.

Dr. Daniel J. Daunis (Psychiatry): A 63-year-old woman with bipolar disorder, worsening depression, and multiple other medical conditions, including lung cancer and breast cancer, was admitted to the inpatient psychiatry service of this hospital for electroconvulsive therapy (ECT). The patient had a long-standing history of bipolar disorder, including depressive episodes, which were characterized by low motivation, low energy, a feeling of hopelessness, agoraphobia, and suicidal ideation without suicide attempts, and brief episodes, each lasting for 2 to 3 weeks, of hypomania and mania with irritable or elevated mood, labile affect, pressured speech, and a decreased need for sleep. Twelve years before this admission, she had received a diagnosis of stage IIA estrogen-receptor–positive and progesterone-receptor–positive, HER2/neu-negative invasive ductal carcinoma of the left breast, with lymphatic-vessel invasion and isolated tumor cells in 2 of 2 lymph nodes. The patient underwent lumpectomy and adjuvant wholebreast radiation therapy. Follow-up therapy included four cycles of doxorubicin and cyclophosphamide chemotherapy and a 5-year course of tamoxifen. She had also been hospitalized three times for mania with psychotic features, including paranoia and visual hallucinations; her most recent hospitalization for mania occurred during her treatment for breast cancer, 11 years before this admission for ECT. She also had attention deficit–hyperactivity disorder (ADHD). Over the years, she had been treated with lithium, stimulants, atypical antipsychotic agents, and multiple classes of antidepressants. Six years before this admission, the patient discontinued primary care follow-up, and shortly thereafter she discontinued psychiatric care. Two years before this admission, a diagnosis of stage II non–small-cell carcinoma of the right lung was made. At the time of the diagnosis, she was referred to a psychiatrist at the cancer center of this hospital. Her medications were adjusted, and her depression abated. She underwent a right upper lobectomy and received adjuvant chemotherapy. From the Departments of Psychiatry (K.E.I., O.F.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.) and the Division of Medical Oncology (J.P.), Massachusetts General Hospital, and the Departments of Psychiatry (K.E.I., O.F.), Medicine (J.P.), Radiation Oncology (A.G.T.), Radiology (P.E.F.), and Pathology (T.M.G.), Harvard Medical School — both in Boston.

Case 29-2016

Dr. Alyssa R. Letourneau: A 53-year-old woman with systemic lupus erythematosus with associated nephritis and chronic renal insufficiency was seen in the gynecology clinic of this hospital because of pain and a lump in the left breast. The patient had been in her usual health until 4 months before this presentation, when she noted a small, tender lump in the left breast on self-examination. Evaluation by her primary care physician revealed a firm, slightly mobile mass (measuring 5 mm in greatest dimension) in the upper inner quadrant of the left breast. The skin overlying the mass appeared normal, and there was no nipple discharge or axillary lymphadenopathy. The right breast and the remainder of the physical examination were normal. Three days earlier, routine laboratory tests had been performed by her nephrologist; the test results are shown in Table 1. Dr. Pragya A. Dang: Three days later, combined digital mammography and tomosynthesis of the left breast was negative, with no suspicious masses, areas of architectural distortion, or microcalcifications (Fig. 1). Ultrasonography targeted to the 10 o’clock position in the left breast revealed a superficial, hyperechoic, oval mass (measuring 6 mm in greatest dimension) with circumscribed margins that was located 5 cm from the nipple, in the dermis. The radiologic differential diagnosis included a sebaceous cyst, and the mass was thought to be probably benign. A plan was made to perform follow-up imaging in 6 months. Dr. Letourneau: Two months later, the patient was seen for routine follow-up in the nephrology and rheumatology clinics of this hospital. She reported fatigue, nausea, and epigastric pain. Mild epigastric tenderness was present; the remainder of the physical examination was normal. Laboratory test results are shown in Table 1. One month later, computed tomography of the abdomen and pelvis, performed without the administration of contrast material, revealed no evidence of pancreatitis; there was a new, indeterminate, hyperdense lesion (measuring 1.9 cm in greatest dimension) in the upper pole of the left kidney. Four months after the patient’s initial presentation, she was seen in the gynecology clinic of this hospital for a routine annual examination. She reported that pain in the left breast had developed 5 days earlier and that she had noted a lump in the upper outer quadrant. The pain had been persistent, was present throughout the breast, was worst near the nipple, and was unaffected by movement or change in position. From the Departments of Medicine (K.T.J., A.R.L.), Radiology (P.A.D.), Surgi‐ cal Oncology (M.C.S.), and Pathology (T.M.G.), Massachusetts General Hospi‐ tal, and the Departments of Medicine (K.T.J., A.R.L.), Radiology (P.A.D.), Sur‐ gery (M.C.S.), and Pathology (T.M.G.), Harvard Medical School — both in Boston.

Case 29-2016: A 53-Year-Old Woman with Pain and a Mass in the Breast

Dr. Alyssa R. Letourneau: A 53-year-old woman with systemic lupus erythematosus with associated nephritis and chronic renal insufficiency was seen in the gynecology clinic of this hospital because of pain and a lump in the left breast. The patient had been in her usual health until 4 months before this presentation, when she noted a small, tender lump in the left breast on self-examination. Evaluation by her primary care physician revealed a firm, slightly mobile mass (measuring 5 mm in greatest dimension) in the upper inner quadrant of the left breast. The skin overlying the mass appeared normal, and there was no nipple discharge or axillary lymphadenopathy. The right breast and the remainder of the physical examination were normal. Three days earlier, routine laboratory tests had been performed by her nephrologist; the test results are shown in Table 1. Dr. Pragya A. Dang: Three days later, combined digital mammography and tomosynthesis of the left breast was negative, with no suspicious masses, areas of architectural distortion, or microcalcifications (Fig. 1). Ultrasonography targeted to the 10 o’clock position in the left breast revealed a superficial, hyperechoic, oval mass (measuring 6 mm in greatest dimension) with circumscribed margins that was located 5 cm from the nipple, in the dermis. The radiologic differential diagnosis included a sebaceous cyst, and the mass was thought to be probably benign. A plan was made to perform follow-up imaging in 6 months. Dr. Letourneau: Two months later, the patient was seen for routine follow-up in the nephrology and rheumatology clinics of this hospital. She reported fatigue, nausea, and epigastric pain. Mild epigastric tenderness was present; the remainder of the physical examination was normal. Laboratory test results are shown in Table 1. One month later, computed tomography of the abdomen and pelvis, performed without the administration of contrast material, revealed no evidence of pancreatitis; there was a new, indeterminate, hyperdense lesion (measuring 1.9 cm in greatest dimension) in the upper pole of the left kidney. Four months after the patient’s initial presentation, she was seen in the gynecology clinic of this hospital for a routine annual examination. She reported that pain in the left breast had developed 5 days earlier and that she had noted a lump in the upper outer quadrant. The pain had been persistent, was present throughout the breast, was worst near the nipple, and was unaffected by movement or change in position. From the Departments of Medicine (K.T.J., A.R.L.), Radiology (P.A.D.), Surgi‐ cal Oncology (M.C.S.), and Pathology (T.M.G.), Massachusetts General Hospi‐ tal, and the Departments of Medicine (K.T.J., A.R.L.), Radiology (P.A.D.), Sur‐ gery (M.C.S.), and Pathology (T.M.G.), Harvard Medical School — both in Boston.