scispace - formally typeset
Search or ask a question
Author

John Pestian

Bio: John Pestian is an academic researcher from Cincinnati Children's Hospital Medical Center. The author has contributed to research in topics: Suicidal ideation & Poison control. The author has an hindex of 29, co-authored 94 publications receiving 3184 citations. Previous affiliations of John Pestian include Hospital Research Foundation & Eastern Virginia Medical School.


Papers
More filters
Proceedings ArticleDOI
29 Jun 2007
TL;DR: A shared task involving the assignment of ICD-9-CM codes to radiology reports resulted in the first freely distributable corpus of fully anonymized clinical text, suggesting that human-like performance on this task is within the reach of currently available technologies.
Abstract: This paper reports on a shared task involving the assignment of ICD-9-CM codes to radiology reports. Two features distinguished this task from previous shared tasks in the biomedical domain. One is that it resulted in the first freely distributable corpus of fully anonymized clinical text. This resource is permanently available and will (we hope) facilitate future research. The other key feature of the task is that it required categorization with respect to a large and commercially significant set of labels. The number of participants was larger than in any previous biomedical challenge task. We describe the data production process and the evaluation measures, and give a preliminary analysis of the results. Many systems performed at levels approaching the inter-coder agreement, suggesting that human-like performance on this task is within the reach of currently available technologies.

385 citations

Journal ArticleDOI
TL;DR: Among children with a severe exacerbation of asthma, the addition of ipratropium bromide to albuterol and corticosteroid therapy significantly decreases the hospitalization rate.
Abstract: Background Anticholinergic medications such as ipratropium improve the pulmonary function of patients with acute exacerbations of asthma, but their effect on hospitalization rates is uncertain. Methods We conducted a randomized, double-blind, placebo-controlled study of 434 children (2 to 18 years old) who had acute exacerbations of moderate or severe asthma treated in the emergency department. All the children received a nebulized solution of albuterol (2.5 or 5 mg per dose, depending on body weight) every 20 minutes for three doses and then as needed. A corticosteroid (2 mg of prednisone or prednisolone per kilogram of body weight) was given orally with the second dose of albuterol. Children in the treatment group received 500 μg (2.5 ml) of ipratropium bromide with the second and third doses of albuterol; children in the control group received 2.5 ml of normal saline at these times. Results Overall, the rate of hospitalization was lower in the ipratropium group (59 of 215 children [27.4 percent]) than ...

264 citations

Journal ArticleDOI
30 Jan 2012
TL;DR: A shared task involving the assignment of emotions to suicide notes resulted in the corpus of fully anonymized clinical text and annotated suicide notes, suggesting that human-like performance on this task is within the reach of currently available technologies.
Abstract: This paper reports on a shared task involving the assignment of emotions to suicide notes. Two features distinguished this task from previous shared tasks in the biomedical domain. One is that it resulted in the corpus of fully anonymized clinical text and annotated suicide notes. This resource is permanently available and will (we hope) facilitate future research. The other key feature of the task is that it required categorization with respect to a large set of labels. The number of participants was larger than in any previous biomedical challenge task. We describe the data production process and the evaluation measures, and give a preliminary analysis of the results. Many systems performed at levels approaching the inter-coder agreement, suggesting that human-like performance on this task is within the reach of currently available technologies.

211 citations

Journal ArticleDOI
04 Aug 2010
TL;DR: An attempt to determine the role of computational algorithms in understanding a suicidal patient's thoughts, as represented by suicide notes is presented, and it is hypothesized that machine learning algorithms can categorize suicide notes as as mental health professionals and psychiatric physician trainees do.
Abstract: Suicide is the second leading cause of death among 25–34 year olds and the third leading cause of death among 15–25 year olds in the United States. In the Emergency Department, where suicidal patients often present, estimating the risk of repeated attempts is generally left to clinical judgment. This paper presents our second attempt to determine the role of computational algorithms in understanding a suicidal patient’s thoughts, as represented by suicide notes. We focus on developing methods of natural language processing that distinguish between genuine and elicited suicide notes. We hypothesize that machine learning algorithms can categorize suicide notes as well as mental health professionals and psychiatric physician trainees do. The data used are comprised of suicide notes from 33 suicide completers and matched to 33 elicited notes from healthy control group members. Eleven mental health professionals and 31 psychiatric trainees were asked to decide if a note was genuine or elicited. Their decisions were compared to nine different machine-learning algorithms. The results indicate that trainees accurately classified notes 49% of the time, mental health professionals accurately classified notes 63% of the time, and the best machine learning algorithm accurately classified the notes 78% of the time. This is an important step in developing an evidence-based predictor of repeated suicide attempts because it shows that natural language processing can aid in distinguishing between classes of suicidal notes.

199 citations

Journal ArticleDOI
TL;DR: It is shown that machine-learning and rule-based approaches worked best when augmented with external knowledge sources and coreference clues extracted from document structure and the systems performed better in coreference resolution when provided with ground truth mentions.

169 citations


Cited by
More filters
01 Jan 2009
TL;DR: Physicians should consider modification of immunosuppressive regimens to decrease the risk of PTD in high-risk transplant recipients and Randomized trials are needed to evaluate the use of oral glucose-lowering agents in transplant recipients.
Abstract: OBJECTIVE — To systematically review the incidence of posttransplantation diabetes (PTD), risk factors for its development, prognostic implications, and optimal management. RESEARCH DESIGN AND METHODS — We searched databases (MEDLINE, EMBASE, the Cochrane Library, and others) from inception to September 2000, reviewed bibliographies in reports retrieved, contacted transplantation experts, and reviewed specialty journals. Two reviewers independently determined report inclusion (original studies, in all languages, of PTD in adults with no history of diabetes before transplantation), assessed study methods, and extracted data using a standardized form. Meta-regression was used to explain between-study differences in incidence. RESULTS — Nineteen studies with 3,611 patients were included. The 12-month cumulative incidence of PTD is lower (10% in most studies) than it was 3 decades ago. The type of immunosuppression explained 74% of the variability in incidence (P 0.0004). Risk factors were patient age, nonwhite ethnicity, glucocorticoid treatment for rejection, and immunosuppression with high-dose cyclosporine and tacrolimus. PTD was associated with decreased graft and patient survival in earlier studies; later studies showed improved outcomes. Randomized trials of treatment regimens have not been conducted. CONCLUSIONS — Physicians should consider modification of immunosuppressive regimens to decrease the risk of PTD in high-risk transplant recipients. Randomized trials are needed to evaluate the use of oral glucose-lowering agents in transplant recipients, paying particular attention to interactions with immunosuppressive drugs. Diabetes Care 25:583–592, 2002

3,716 citations

Journal ArticleDOI
TL;DR: The global situation of antibiotic resistance, its major causes and consequences, and key areas in which action is urgently needed are described and identified.
Abstract: The causes of antibiotic resistance are complex and include human behaviour at many levels of society; the consequences affect everybody in the world. Similarities with climate change are evident. Many efforts have been made to describe the many different facets of antibiotic resistance and the interventions needed to meet the challenge. However, coordinated action is largely absent, especially at the political level, both nationally and internationally. Antibiotics paved the way for unprecedented medical and societal developments, and are today indispensible in all health systems. Achievements in modern medicine, such as major surgery, organ transplantation, treatment of preterm babies, and cancer chemotherapy, which we today take for granted, would not be possible without access to effective treatment for bacterial infections. Within just a few years, we might be faced with dire setbacks, medically, socially, and economically, unless real and unprecedented global coordinated actions are immediately taken. Here, we describe the global situation of antibiotic resistance, its major causes and consequences, and identify key areas in which action is urgently needed.

3,181 citations

Patent
30 Oct 2007
TL;DR: An analyte monitor includes a sensor, a sensor control unit, and a display unit as discussed by the authors, which is used to display an indication of a level of an analyte, based on the data obtained using the sensor.
Abstract: An analyte monitor includes a sensor, a sensor control unit, and a display unit. The sensor has, for example, a substrate, a recessed channel formed in the substrate, and conductive material disposed in the recessed channel to form a working electrode. The sensor control unit typically has a housing adapted for placement on skin and is adapted to receive a portion of an electrochemical sensor. The sensor control unit also includes two or more conductive contacts disposed on the housing and configured for coupling to two or more contact pads on the sensor. A transmitter is disposed in the housing and coupled to the plurality of conductive contacts for transmitting data obtained using the sensor. The display unit has a receiver for receiving data transmitted by the transmitter of the sensor control unit and a display coupled to the receiver for displaying an indication of a level of an analyte. The analyte monitor may also be part of a drug delivery system to alter the level of the analyte based on the data obtained using the sensor.

1,856 citations

Journal ArticleDOI
01 Aug 2013
TL;DR: It is shown how the combined strength and wisdom of the crowds can be used to generate a large, high‐quality, word–emotion and word–polarity association lexicon quickly and inexpensively.
Abstract: Even though considerable attention has been given to the polarity of words (positive and negative) and the creation of large polarity lexicons, research in emotion analysis has had to rely on limited and small emotion lexicons. In this paper, we show how the combined strength and wisdom of the crowds can be used to generate a large, high-quality, word–emotion and word–polarity association lexicon quickly and inexpensively. We enumerate the challenges in emotion annotation in a crowdsourcing scenario and propose solutions to address them. Most notably, in addition to questions about emotions associated with terms, we show how the inclusion of a word choice question can discourage malicious data entry, help to identify instances where the annotator may not be familiar with the target term (allowing us to reject such annotations), and help to obtain annotations at sense level (rather than at word level). We conducted experiments on how to formulate the emotion-annotation questions, and show that asking if a term is associated with an emotion leads to markedly higher interannotator agreement than that obtained by asking if a term evokes an emotion.

1,719 citations