Publications by authors named "Hogan W"

In this study, we examined a deep learning method for de-identification of clinical notes at UF Health under a cross-institute setting. We developed deep learning models using 2014 i2b2/UTHealth corpus and evaluated the performance using clinical notes collected from UF Health. We compared four pre-trained word embeddings, including two embeddings from the general domain and two embeddings from the clinical domain.

View Article and Find Full Text PDF

Background: The Drug Ontology (DrOn) is a modular, extensible ontology of drug products, their ingredients, and their biological activity created to enable comparative effectiveness and health services researchers to query National Drug Codes (NDCs) that represent products by ingredient, by molecular disposition, by therapeutic disposition, and by physiological effect (e.g., diuretic).

View Article and Find Full Text PDF

Background: Specific combinations of two drug classes are recommended in a variety of clinical situations in the management of hypertension. These preferred combinations are based on complimentary blood pressure (BP) lowering mechanisms or benefit for a concomitant disease.

Methods: Using electronic health records (EHRs) data from 27,579 ambulatory hypertensive patients, we investigated antihypertensive therapy prescribing patterns and associations of preferred two drug classes with BP control.

View Article and Find Full Text PDF

The Mount Sinai Acute GVHD International Consortium (MAGIC) algorithm probability (MAP), derived from 2 serum biomarkers, measures damage to crypts in the gastrointestinal tract during graft-versus-host disease (GVHD). We hypothesized that changes in MAP after treatment could validate it as a response biomarker. We prospectively collected serum samples and clinical stages of acute GVHD from 615 patients receiving hematopoietic cell transplantation in 20 centers at initiation of first-line systemic treatment and 4 weeks later.

View Article and Find Full Text PDF

Background: De-identification is a critical technology to facilitate the use of unstructured clinical text while protecting patient privacy and confidentiality. The clinical natural language processing (NLP) community has invested great efforts in developing methods and corpora for de-identification of clinical notes. These annotated corpora are valuable resources for developing automated systems to de-identify clinical text at local hospitals.

View Article and Find Full Text PDF

Tumour lysis syndrome (TLS) is a significant complication of haematologic malignancies and their management. The syndrome consists of laboratory abnormalities either alone (laboratory TLS) or with clinical sequelae including renal failure, seizures, and arrhythmias (clinical TLS). Clinical TLS is a predictor for worse overall morbidity and mortality in cancer patients, but can be prevented.

View Article and Find Full Text PDF

The D-index assesses neutropenia dynamics. Prolonged neutropenia is a major risk for invasive fungal infection (IFI); we hypothesized that D-index is predictive of IFI risk. We retrospectively reviewed 789 adults who underwent allogeneic hematopoietic transplant (HSCT) from 1/1/2005 to 9/30/2015.

View Article and Find Full Text PDF

Myelodysplastic syndrome unclassifiable (MDS-U) is a small subtype of myelodysplastic syndromes (MDS). However, rare literature exists in terms of natural progression and clinical outcome of patients with MDS-U. In the present study, we investigated the characteristics and the clinical outcomes of patients categorized as MDS-U based on 2008 World Health Organization criteria (WHO) in a single center comparing to other MDS groups.

View Article and Find Full Text PDF

Objective: To develop a natural language processing system that identifies relations of medications with adverse drug events from clinical narratives. This project is part of the 2018 n2c2 challenge.

Materials And Methods: We developed a novel clinical named entity recognition method based on an recurrent convolutional neural network and compared it to a recurrent neural network implemented using the long-short term memory architecture, explored methods to integrate medical knowledge as embedding layers in neural networks, and investigated 3 machine learning models, including support vector machines, random forests and gradient boosting for relation classification.

View Article and Find Full Text PDF

Objective: Cauda equina syndrome (CES) is a potentially devastating spinal condition requiring prompt diagnosis and intervention. This study examines the relationship between timing of surgery and patient outcomes such as mortality and total complications, and longitudinal trends in timing of operative treatment over the years 2000-2014.

Methods: This study considered patients in the Healthcare Cost and Utilization Project National Inpatient Sample Database between 2000 and 2014 who had both an International Classification of Disease, Ninth Edition, Clinical Modification code for CES (344.

View Article and Find Full Text PDF

Objective: To describe the multifactorial etiologies of extreme thrombocytosis (EXT) in different care settings and the frequency of finding an occult malignancy.

Patients And Methods: We conducted a retrospective chart review at Mayo Clinic from January 1, 2011, through December 31, 2016. Adult patients who had at least 2 readings of platelet counts greater than 1000×10/L within 30 days of each other were included.

View Article and Find Full Text PDF

Objective: To study the changes in overall outcome of patients with myelodysplastic syndromes (MDSs) after approval of several treatments.

Patients And Methods: We identified 54,953 MDS cases in the National Cancer Data Base diagnosed from January 1, 2004, through December 31, 2013, using International Classification of Diseases for Oncology, 3rd edition, codes 9980, 9982-9983, 9985-9987, 9989, 9991-9992. Overall survival and different subgroups were studied over 3 periods of diagnoses (2004-2006, 2007-2009, and 2010-2013).

View Article and Find Full Text PDF

The role of consolidation post autologous stem cell transplant in light chain amyloidosis is not well defined. We retrospectively identified patients who had light chain amyloidosis and underwent autologous stem cell transplant at the Mayo Clinic. Consolidation was defined as any treatment given after the day 100 evaluation post-transplant to maintain or deepen the response.

View Article and Find Full Text PDF

Objective: To demonstrate experience and feasibility of a precision medicine approach for patients with unexplained cytopenias, defined as low blood counts in one or more cell lineages, persistent for 6 months or longer, in the absence of known nutritional, autoimmune, infectious, toxic, and neoplastic (secondary) causes.

Patients And Methods: Patients were evaluated in our clinic between November 8, 2016, and January 12, 2018. After a thorough evaluation of known causes, family history, and appropriate clinical assays, genomic evaluation was performed in a stepwise manner, through Sanger, targeted, and/or whole-exome sequencing.

View Article and Find Full Text PDF

In appropriately selected patients with AL amyloidosis, autologous stem cell transplant (ASCT) is an established treatment modality with excellent outcomes and decreasing transplant related mortality (TRM) over time. We report on 15-year overall survival (OS) in 159 patients undergoing ASCT from 1996 to 2003, with median follow up of 17.1 years.

View Article and Find Full Text PDF

Purpose: To develop a prognostic model and cytogenetic risk classification for previously treated patients with chronic lymphocytic leukemia (CLL) undergoing reduced intensity conditioning (RIC) allogeneic hematopoietic cell transplantation (HCT).

Experimental Design: We performed a retrospective analysis of outcomes of 606 patients with CLL who underwent RIC allogeneic HCT between 2008 and 2014 reported to the Center for International Blood and Marrow Transplant Research.

Results: On the basis of multivariable models, disease status, comorbidity index, lymphocyte count, and white blood cell count at HCT were selected for the development of prognostic model.

View Article and Find Full Text PDF

Background: Recipients of hematopoietic stem cell transplantation (HSCT) are among the highest consumers of allogeneic red blood cell (RBC) and platelet (PLT) components. The impact of patient blood management (PBM) efforts on HSCT recipients is poorly understood.

Study Design And Methods: This observational study assessed changes in blood product use and patient-centered outcomes before and after implementing a multidisciplinary PBM program for patients undergoing HSCT at a large academic medical center.

View Article and Find Full Text PDF

Autologous stem cell transplantation (ASCT) is an integral component of the therapeutic arsenal in multiple myeloma. Given that overall survival (OS) is comparable between patients receiving up-front or delayed ASCT, some opt to collect stem cells and postpone transplant until the time of disease progression (i.e.

View Article and Find Full Text PDF

Autologous stem cell transplant (ASCT) for multiple myeloma (MM) is associated with diarrhea during the peri-transplant period. We aimed to appraise mechanisms of peri-ASCT diarrhea in a prospective, longitudinal study of patients with MM. We compared by repeated measures (RM)-ANOVA daily bowel movements (BMs) and consistency [7-point Bristol Stool Form Scale (BSFS)], fecal calprotectin (intestinal inflammation), C-mannitol excretion in urine 0-2 h (small intestinal permeability), fasting serum C4 (bile acid synthesis) and total and primary bile acid in stool samples during baseline, peri-transplant period (Days 5-7 after stem cell infusion), and after hematological recovery post-ASCT.

View Article and Find Full Text PDF

We sought to study whether survival after haploidentical transplantation is comparable to that after matched unrelated donor transplantation for 822 patients aged 50-75 years with acute myeloid leukemia in first or second complete remission. One hundred and ninety-two patients received grafts from haploidentical donors (sibling 25%; offspring 75%) and 631 patients from matched unrelated donors aged 18-40 years. Patients' and disease characteristics of the two groups were similar except that recipients of matched unrelated donor transplantation were more likely to have poor risk cytogenetics and more likely to receive myeloablative conditioning regimens.

View Article and Find Full Text PDF

Prior reports have suggested that 3 or more organs involved is a contraindication for autologous stem cell transplant (ASCT) in amyloid light chain (AL) amyloidosis. Therefore, most centers limit transplantation to patients who have no more than 2 organs significantly involved. We retrospectively reviewed all patients with AL amyloidosis with ≥3 involved organs and who had ASCT between 1996 and 2015 at Mayo Clinic, Rochester, Minnesota to assess transplant safety and outcomes.

View Article and Find Full Text PDF

We retrospectively reviewed the impact of impaired renal function (eGFR < 45 ml/min/SA) on post-transplant outcomes in patients receiving ASCT for AL amyloidosis. Patients were grouped into two cohorts, those with normal renal function (NRF) eGFR ≥ 45 ml/min (n = 568) and those with impaired renal function (IRF) eGFR < 45 ml/min (n = 87). Patients with IRF had higher renal stage (>Stage 1: 100% IRF vs 37% NRF, p < 0.

View Article and Find Full Text PDF