Search

Abstract Background Primary sclerosing cholangitis (PSC) patients have a risk of developing cholangiocarcinoma (CCA). Establishing predictive models for CCA in PSC is important. Methods In a large cohort of 1,459 PSC patients seen at Mayo Clinic (1993–2020), we quantified the impact of clinical/laboratory variables on CCA development using univariate and multivariate Cox models and predicted CCA using statistical and artificial intelligence (AI) approaches. We explored plasma bile acid (BA) levels’ predictive power of CCA (subset of 300 patients, BA cohort). Results Eight significant risk factors (false discovery rate: 20%) were identified with univariate analysis; prolonged inflammatory bowel disease (IBD) was the most important one. IBD duration, PSC duration, and total bilirubin remained significant (p

Abstract Background Cellular senescence is a cell fate in response to diverse forms of age-related damage and stress that has been implicated in the pathogenesis of idiopathic pulmonary fibrosis (IPF). The associations between circulating levels of candidate senescence biomarkers and disease outcomes have not been specifically studied in IPF. In this study we assessed the circulating levels of candidate senescence biomarkers in individuals affected by IPF and controls and evaluated their ability to predict disease outcomes. Methods We measured the plasma concentrations of 32 proteins associated with senescence in Lung Tissue Research Consortium participants and studied their relationship with the diagnosis of IPF, parameters of pulmonary and physical function, health-related quality of life, mortality, and lung tissue expression of P16, a prototypical marker of cellular senescence. A machine learning approach was used to evaluate the ability of combinatorial biomarker signatures to predict disease outcomes. Results The circulating levels of several senescence biomarkers were significantly elevated in persons affected by IPF compared to controls. A subset of biomarkers accurately classified participants as having or not having the disease and was significantly correlated with measures of pulmonary function, health-related quality of life and, to an extent, physical function. An exploratory analysis revealed senescence biomarkers were also associated with mortality in IPF participants. Finally, the plasma concentrations of several biomarkers were associated with their expression levels in lung tissue as well as the expression of P16. Conclusions Our results suggest that circulating levels of candidate senescence biomarkers are informative of disease status, pulmonary and physical function, and health-related quality of life. Additional studies are needed to validate the combinatorial biomarkers signatures that emerged using a machine learning approach.

Abstract Background Methotrexate is the preferred initial disease-modifying antirheumatic drug (DMARD) for rheumatoid arthritis (RA). However, clinically useful tools for individualized prediction of response to methotrexate treatment in patients with RA are lacking. We aimed to identify clinical predictors of response to methotrexate in patients with rheumatoid arthritis (RA) using machine learning methods. Methods Randomized clinical trials (RCT) of patients with RA who were DMARD-naïve and randomized to placebo plus methotrexate were identified and accessed through the Clinical Study Data Request Consortium and Vivli Center for Global Clinical Research Data. Studies with available Disease Activity Score with 28-joint count and erythrocyte sedimentation rate (DAS28-ESR) at baseline and 12 and 24 weeks were included. Latent class modeling of methotrexate response was performed. The least absolute shrinkage and selection operator (LASSO) and random forests methods were used to identify predictors of response. Results A total of 775 patients from 4 RCTs were included (mean age 50 years, 80% female). Two distinct classes of patients were identified based on DAS28-ESR change over 24 weeks: “good responders” and “poor responders.” Baseline DAS28-ESR, anti-citrullinated protein antibody (ACPA), and Health Assessment Questionnaire (HAQ) score were the top predictors of good response using LASSO (area under the curve [AUC] 0.79) and random forests (AUC 0.68) in the external validation set. DAS28-ESR ≤ 7.4, ACPA positive, and HAQ ≤ 2 provided the highest likelihood of response. Among patients with 12-week DAS28-ESR > 3.2, ≥ 1 point improvement in DAS28-ESR baseline-to-12-week was predictive of achieving DAS28-ESR ≤ 3.2 at 24 weeks. Conclusions We have developed and externally validated a prediction model for response to methotrexate within 24 weeks in DMARD-naïve patients with RA, providing variably weighted clinical features and defined cutoffs for clinical decision-making.

Abstract Background Primary sclerosing cholangitis (PSC) is a rare, chronic cholestatic liver disease that often progresses to end-stage liver disease and/or the development of hepatobiliary neoplasia. Lack of prognostic tools and treatment options for PSC is driven in part by our poor understanding of its pathogenesis, which is thought to be complex, the interaction of genetic variants, environmental influences and biological response throughout the course of disease. The PSC Scientific Community Resource (PSC-SCR) seeks to overcome previous shortcomings by facilitating novel research in PSC with the ultimate goals of individualizing patient care and improving patient outcomes. Methods PSC patients who receive their health care at Mayo Clinic or a collaborating site are identified by chart review and invited in person or by mail to participate. Non-Mayo patients are offered enrollment if they provide sufficient access to their medical records to evaluate inclusion/exclusion criteria. Controls without liver disease are identified with assistance of the Mayo Clinic Biobank. Participant consent is obtained at the beginning of the recruitment process by mail-in, electronic or face-to-face protocols. Clinical data is extracted from the medical record by qualified physicians and entered in a custom designed database. Participants fill out a custom-designed, comprehensive questionnaire, which collects scientifically relevant demographic and clinical information. Biospecimens are collected using mail-in kits thar are returned via overnight carrier service and processed by the biospecimen accessioning and processing facility at Mayo Clinic, which coordinates sample transfers and provides required sample preparation services. The resource is currently being utilized to perform omics-scale projects investigating the exposome, metabolome, methylome, immunome and microbiome in PSC. Datasets and residual biospecimens will be shared with researchers proposing scientifically sound PSC-focused research with approval of the appropriate review boards. Discussion Patient-based studies leveraging the latest technologies for targeted and wide-scale interrogation of multiple omics layers offer promise to accelerate PSC research through discovery of unappreciated aspects of disease pathogenesis. However, the rarity of PSC severely limits such studies. Here we describe our effort to overcome this limitation, the PSC-SCR, a repository of patient biospecimens coupled with clinical and omics data for use by the broader PSC research community.

Abstract Background Osteoporosis has become an important public health issue. Most of the population, particularly elderly people, are at some degree of risk of osteoporosis-related fractures. Accurate identification and surveillance of patient populations with fractures has a significant impact on reduction of cost of care by preventing future fractures and its corresponding complications. Methods In this study, we developed a rule-based natural language processing (NLP) algorithm for identification of twenty skeletal site-specific fractures from radiology reports. The rule-based NLP algorithm was based on regular expressions developed using MedTagger, an NLP tool of the Apache Unstructured Information Management Architecture (UIMA) pipeline to facilitate information extraction from clinical narratives. Radiology notes were retrieved from the Mayo Clinic electronic health records data warehouse. We developed rules for identifying each fracture type according to physicians’ knowledge and experience, and refined these rules via verification with physicians. This study was approved by the institutional review board (IRB) for human subject research. Results We validated the NLP algorithm using the radiology reports of a community-based cohort at Mayo Clinic with the gold standard constructed by medical experts. The micro-averaged results of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.930, 1.0, 1.0, 0.941, 0.961, respectively. The F1-score is 1.0 for 8 fractures, and above 0.9 for a total of 17 out of 20 fractures (85%). Conclusions The results verified the effectiveness of the proposed rule-based NLP algorithm in automatic identification of osteoporosis-related skeletal site-specific fractures from radiology reports. The NLP algorithm could be utilized to accurately identify the patients with fractures and those who are also at high risk of future fractures due to osteoporosis. Appropriate care interventions to those patients, not only the most at-risk patients but also those with emerging risk, would significantly reduce future fractures.

Abstract Background Automatic clinical text classification is a natural language processing (NLP) technology that unlocks information embedded in clinical narratives. Machine learning approaches have been shown to be effective for clinical text classification tasks. However, a successful machine learning model usually requires extensive human efforts to create labeled training data and conduct feature engineering. In this study, we propose a clinical text classification paradigm using weak supervision and deep representation to reduce these human efforts. Methods We develop a rule-based NLP algorithm to automatically generate labels for the training data, and then use the pre-trained word embeddings as deep representation features for training machine learning models. Since machine learning is trained on labels generated by the automatic NLP algorithm, this training process is called weak supervision. We evaluat the paradigm effectiveness on two institutional case studies at Mayo Clinic: smoking status classification and proximal femur (hip) fracture classification, and one case study using a public dataset: the i2b2 2006 smoking status classification shared task. We test four widely used machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron Neural Networks (MLPNN), and Convolutional Neural Networks (CNN), using this paradigm. Precision, recall, and F1 score are used as metrics to evaluate performance. Results CNN achieves the best performance in both institutional tasks (F1 score: 0.92 for Mayo Clinic smoking status classification and 0.97 for fracture classification). We show that word embeddings significantly outperform tf-idf and topic modeling features in the paradigm, and that CNN captures additional patterns from the weak supervision compared to the rule-based NLP algorithms. We also observe two drawbacks of the proposed paradigm that CNN is more sensitive to the size of training data, and that the proposed paradigm might not be effective for complex multiclass classification tasks. Conclusion The proposed clinical text classification paradigm could reduce human efforts of labeled training data creation and feature engineering for applying machine learning to clinical text classification by leveraging weak supervision and deep representation. The experimental experiments have validated the effectiveness of paradigm by two institutional and one shared clinical text classification tasks.