Assessment of the impact of EHR heterogeneity for clinical research through a case study of silent brain infarction.

BACKGROUND: The rapid adoption of electronic health records (EHRs) holds great promise for advancing medicine through practice-based knowledge discovery. However, the validity of EHR-based clinical research is questionable due to poor research reproducibility caused by the heterogeneity and complexity of healthcare institutions and EHR systems, the cross-disciplinary nature of the research team, and the lack of standard processes and best practices for conducting EHR-based clinical research. METHOD: We developed a data abstraction framework to standardize the process for multi-site EHR-based clinical studies aiming to enhance research reproducibility. The framework was implemented for a multi-site EHR-based research project, the ESPRESSO project, with the goal to identify individuals with silent brain infarctions (SBI) at Tufts Medical Center (TMC) and Mayo Clinic. The heterogeneity of healthcare institutions, EHR systems, documentation, and process variation in case identification was assessed quantitatively and qualitatively. RESULT: We discovered a significant variation in the patient populations, neuroimaging reporting, EHR systems, and abstraction processes across the two sites. The prevalence of SBI for patients over age 50 for TMC and Mayo is 7.4 and 12.5% respectively. There is a variation regarding neuroimaging reporting where TMC are lengthy, standardized and descriptive while Mayo's reports are short and definitive with more textual variations. Furthermore, differences in the EHR system, technology infrastructure, and data collection process were identified. CONCLUSION: The implementation of the framework identified the institutional and process variations and the heterogeneity of EHRs across the sites participating in the case study. The experiment demonstrates the necessity to have a standardized process for data abstraction when conducting EHR-based clinical studies.

Guiding peripheral arterial disease management with magnetic resonance imaging.

Peripheral arterial disease (PAD) management is exceptionally challenging. Despite advances in diagnostic and therapeutic technologies, long-term vessel patency and limb salvage rates are limited. Patients with PAD frequently require extensive workup with noninvasive tests and imaging to delineate their disease and help guide appropriate management. Ultrasound and computed tomography are commonly ordered in the workup of PAD. Magnetic resonance imaging (MRI), on the other hand, is less often acknowledged as a useful tool in this disease. Nevertheless, MRI is an important test that can effectively characterize atherosclerotic plaque, assess vessel patency in highly calcified disease, and measure lower extremity perfusion.

Natural Language Processing for the Identification of Silent Brain Infarcts From Neuroimaging Reports.

BACKGROUND: Silent brain infarction (SBI) is defined as the presence of 1 or more brain lesions, presumed to be because of vascular occlusion, found by neuroimaging (magnetic resonance imaging or computed tomography) in patients without clinical manifestations of stroke. It is more common than stroke and can be detected in 20% of healthy elderly people. Early detection of SBI may mitigate the risk of stroke by offering preventative treatment plans. Natural language processing (NLP) techniques offer an opportunity to systematically identify SBI cases from electronic health records (EHRs) by extracting, normalizing, and classifying SBI-related incidental findings interpreted by radiologists from neuroimaging reports. OBJECTIVE: This study aimed to develop NLP systems to determine individuals with incidentally discovered SBIs from neuroimaging reports at 2 sites: Mayo Clinic and Tufts Medical Center. METHODS: Both rule-based and machine learning approaches were adopted in developing the NLP system. The rule-based system was implemented using the open source NLP pipeline MedTagger, developed by Mayo Clinic. Features for rule-based systems, including significant words and patterns related to SBI, were generated using pointwise mutual information. The machine learning models adopted convolutional neural network (CNN), random forest, support vector machine, and logistic regression. The performance of the NLP algorithm was compared with a manually created gold standard. The gold standard dataset includes 1000 radiology reports randomly retrieved from the 2 study sites (Mayo and Tufts) corresponding to patients with no prior or current diagnosis of stroke or dementia. 400 out of the 1000 reports were randomly sampled and double read to determine interannotator agreements. The gold standard dataset was equally split to 3 subsets for training, developing, and testing. RESULTS: Among the 400 reports selected to determine interannotator agreement, 5 reports were removed due to invalid scan types. The interannotator agreements across Mayo and Tufts neuroimaging reports were 0.87 and 0.91, respectively. The rule-based system yielded the best performance of predicting SBI with an accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.991, 0.925, 1.000, 1.000, and 0.990, respectively. The CNN achieved the best score on predicting white matter disease (WMD) with an accuracy, sensitivity, specificity, PPV, and NPV of 0.994, 0.994, 0.994, 0.994, and 0.994, respectively. CONCLUSIONS: We adopted a standardized data abstraction and modeling process to developed NLP techniques (rule-based and machine learning) to detect incidental SBIs and WMDs from annotated neuroimaging reports. Validation statistics suggested a high feasibility of detecting SBIs and WMDs from EHRs using NLP.

Whole-Gland Prostate Cancer Cryoablation with Magnetic Resonance Imaging Guidance: One-Year Follow-Up.

PURPOSE: Patients who develop prostate cancer after prior abdominal perineal resection are poor surgical candidates, and have limited treatment options. Therefore, our goal is to present results from a single institutional experience of four patients who underwent whole gland MRI-guided cryoablation with a history complicated by prior abdominoperineal resection. MATERIALS AND METHODS: Four MRI-guided cryoablative treatments (mean age 64, range 59-69 years) for primary and locally recurrent prostate adenocarcinoma were retrospectively reviewed in patients with prior abdominal perineal resection for colorectal cancer (3) and juvenile polyposis (1). Average prostate volume prior to ablation was 23 cc, with an average PSA of 5.6 ng/mL. For each gland, 7-10 cryoprobes were placed approximately 0.5 cm apart in the prostate gland under MRI guidance by a transperineal approach with 3-4 freeze-thaw cycles performed. Each patient had follow up imaging and PSA measurements out to 12 months post ablation. RESULTS: All four patient's PSA dropped below 0.1 ng/mL at 3-6 month post-ablation and remained at these levels at 12 months. Three of the 4 patients had PSA measurements to 33 months post-ablation, with no evidence of recurrence. No patient developed urinary incontinence due to the whole gland cryoablation. CONCLUSION: With all four patients in our study having undetectable PSAs 12 months post ablation, and with no patient developing urinary incontinence due to the cryoablation, MRI-guided cryoablation appears to be a promising treatment option in patients who are poor surgical candidates due to prior pelvic surgery and/or radiation.

Thermal ablation of intrahepatic cholangiocarcinoma: Safety, efficacy, and factors affecting local tumor progression.

PURPOSE: To evaluate the safety and oncologic efficacy of percutaneous thermal ablation of intrahepatic cholangiocarcinoma (ICC) and identify risk factors for local tumor progression (LTP). MATERIALS AND METHODS: Retrospective review of an institutional tumor ablation registry demonstrated that 20 patients (9 males, 11 females; mean age 62.5 ± 15.8 years) with 50 ICCs (mean size 1.8 ± 1.3 cm) were treated with percutaneous radiofrequency ablation (RFA) or microwave ablation (MWA) between 2006 and 2015. Thirty-eight of the treated ICCs (76%) were metastases that developed after surgical resection of the primary tumor. Patient demographics, procedure technical parameters, and clinical outcomes were reviewed. A Cox proportional hazards model was used to examine the risk of LTP by ablation modality. Survival analyses were performed using the Kaplan-Meier method. RESULTS: Mean imaging follow-up time was 41.5 ± 42.7 months. Forty-four (88%) ICCs were treated with RFA, and 6 (12%) with MWA. Eleven (22%) cases of LTP developed in 5 (25%) patients. The median time to LTP among these 11 tumors was 7.1 months (range, 2.3-22.9 months). Risk of LTP was not significantly different for ICCs treated with MWA compared to RFA (HR 2.72; 95% CI 0.58-12.84; p = 03.21). Median disease-free survival was 8.2 months (1.1-70.4 months), and median overall survival was 23.6 months (7.4-122.5 months). No major complication occurred. CONCLUSIONS: Percutaneous thermal ablation is a safe and effective treatment for patients with ICCs and may be particularly valuable in unresectable patients, or those who have already undergone hepatic surgery. Tumor size and ablation modality were not associated with LTP, whereas primary tumors and superficially located tumors were more likely to subsequently recur.