scholarly journals Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature (Preprint)

2017 ◽  
Author(s):  
Jette Henderson ◽  
Junyuan Ke ◽  
Joyce C Ho ◽  
Joydeep Ghosh ◽  
Byron C Wallace
Keyword(s):  
Patient Characteristics ◽  
Classification Model ◽  
Journal Articles ◽  
Evaluation Tool ◽  
Web Based ◽  
Nosql Databases ◽  
Multiple Classification ◽  
Essential Properties ◽  
Order Of Magnitude

BACKGROUND Researchers are developing methods to automatically extract clinically relevant and useful patient characteristics from raw healthcare datasets. These characteristics, often capturing essential properties of patients with common medical conditions, are called computational phenotypes. Being generated by automated or semiautomated, data-driven methods, such potential phenotypes need to be validated as clinically meaningful (or not) before they are acceptable for use in decision making. OBJECTIVE The objective of this study was to present Phenotype Instance Verification and Evaluation Tool (PIVET), a framework that uses co-occurrence analysis on an online corpus of publically available medical journal articles to build clinical relevance evidence sets for user-supplied phenotypes. PIVET adopts a conceptual framework similar to the pioneering prototype tool PheKnow-Cloud that was developed for the phenotype validation task. PIVET completely refactors each part of the PheKnow-Cloud pipeline to deliver vast improvements in speed without sacrificing the quality of the insights PheKnow-Cloud achieved. METHODS PIVET leverages indexing in NoSQL databases to efficiently generate evidence sets. Specifically, PIVET uses a succinct representation of the phenotypes that corresponds to the index on the corpus database and an optimized co-occurrence algorithm inspired by the Aho-Corasick algorithm. We compare PIVET’s phenotype representation with PheKnow-Cloud’s by using PheKnow-Cloud’s experimental setup. In PIVET’s framework, we also introduce a statistical model trained on domain expert–verified phenotypes to automatically classify phenotypes as clinically relevant or not. Additionally, we show how the classification model can be used to examine user-supplied phenotypes in an online, rather than batch, manner. RESULTS PIVET maintains the discriminative power of PheKnow-Cloud in terms of identifying clinically relevant phenotypes for the same corpus with which PheKnow-Cloud was originally developed, but PIVET’s analysis is an order of magnitude faster than that of PheKnow-Cloud. Not only is PIVET much faster, it can be scaled to a larger corpus and still retain speed. We evaluated multiple classification models on top of the PIVET framework and found ridge regression to perform best, realizing an average F1 score of 0.91 when predicting clinically relevant phenotypes. CONCLUSIONS Our study shows that PIVET improves on the most notable existing computational tool for phenotype validation in terms of speed and automation and is comparable in terms of accuracy.

scholarly journals Samplinghelper a web-based tool to assess the reliability of sampling strategies in sewers and receiving waters

2011 ◽  
Vol 63 (12) ◽  
pp. 2975-2982 ◽  
Author(s):  
L. Rossi ◽  
L. Rumley ◽  
C. Ort ◽  
P. Minkkinen ◽  
D. A. Barry ◽  
...  
Keyword(s):  
Chemical Compounds ◽  
Sampling Strategies ◽  
Sampling Errors ◽  
Sampling Step ◽  
Web Based ◽  
Order Of Magnitude ◽  
Theory Of Sampling ◽  
Receiving Waters ◽  
Use Of The Internet

Sampling is a key step in the analysis of chemical compounds. It is particularly important in the environmental field, for example for wastewater effluents, wet-weather discharges or streams in which the flows and concentrations vary greatly over time. In contrast to the improvements that have occurred in analytical measurement, developments in the field of sampling are less active. However, sampling errors may exceed by an order of magnitude those related to analytical processes. We proposed an Internet-based application based on a sampling theory to identify and quantify the errors in the process of taking samples. This general theory of sampling, already applied to different areas, helps to answer questions related to the number of samples, their volume, their representativeness, etc. The use of the internet to host this application facilitates use of theoretical tools and raise awareness of the uncertainties related to sampling. An example is presented, which highlights the importance of the sampling step in the quality of analytical results.

Faktor-Faktor yang Berpengaruh dalam Mendapatkan Pekerjaan bagi Lulusan Statistika IPB dengan Menggunakan Metode CHAID

2019 ◽  
Vol 8 (1) ◽  
Author(s):  
Aulia Dwi Oktavia ◽  
Aam Alamudi ◽  
Budi Susetyo
Keyword(s):  
College Graduates ◽  
Influential Factors ◽  
Classification Model ◽  
Statistical Software ◽  
Waiting Period ◽  
Level Of Education ◽  
Economic Problems ◽  
Factors Influencing

Unemployment is one of the economic problems in Indonesia. Judging from the level of education that was completed there were unemployment from the level of college graduates. This encourages the level of competition in getting jobs to be more stringent, so that college graduates (bachelor of Statistics in IPB) must have the preparation of various factors to maintain the quality of their graduates. The quality of college graduates can be seen from the length of time waiting to get a job. This study aims to determine the influential factors in getting a job for graduates of the IPB Statistics degree, so that the CHAID method can be used in this study. The results of CHAID's analysis in this study in the form of tree diagrams using α = 10% explained that the factors influencing the waiting period variables were sex, internship, and the ability to master statistical software, where the accuracy value generated by the classification model was 79.3 %.

Telehealth During COVID-19 for Remote Vision Rehabilitation of a Patient with mTBI

2020 ◽  
pp. 191-198
Keyword(s):  
Veterans Health ◽  
Health Administration ◽  
Web Based ◽  
Home Setting ◽  
Therapeutic Goals ◽  
Vision Rehabilitation ◽  
Novel Coronavirus ◽  
Performance Challenges ◽  
Perception Of Performance

Background: Binocular and accommodative vision problems are common after mild traumatic brain injury (mTBI). Traditionally, the management of visual dysfunctions following mTBI included in-office vision rehabilitation with a trained eye care provider. The concept of providing telehealth for remote vision rehabilitation in mTBI patients is a relatively novel practice that has not been widely utilized until the recent outbreak of the 2019 novel coronavirus (COVID-19) pandemic. Case Report: We describe the implementation of telehealth for remote vision rehabilitation during COVID-19 within the Veterans’ Health Administration (VHA) system in an adult patient with multiple confirmed histories of mTBI. Conclusion: Our telehealth remote vision rehabilitation was successfully implemented utilizing established VHA’s web-based videoconferencing tools. Therapeutic goals identified prior to COVID 19 were addressed without any challenges. The delivery of vision rehabilitation intervention via telehealth allowed for the continuance of services within the home setting that led to improvements in functional vision, decreased perception of performance challenges, and improved quality of life.

An Analysis of Pronouns Used in Selected International Journal Articles: Exploring Authors’ Flexibility and Consistency

2019 ◽  
Vol 1 (3) ◽  
pp. 73-78
Author(s):  
Rumintang Harianja ◽  
Ratih Saltri Yudar ◽  
Susy Deliani ◽  
Mutia Sari Nursafira ◽  
Budianto Hamuddin
Keyword(s):  
Current Issue ◽  
Journal Article ◽  
Scientific Article ◽  
Journal Articles ◽  
The Impact

This study aims at identifying the pronouns used in journal articles in terms of numbers and familiarity. The data taken from three different journals from three various fields, i.e., Education, Medics and Engineering. It consists of  21 articles taken from the current issue 2018, where this study started. It is selected conveniently due to its unique and fame as a discipline and reputable sources. In collecting the data, the researcher accessed the journals published by science direct (Q1 Scopus indexed). The analysis showed that the writer in these three international journals commonly used several pronouns interchangeably. However, some articles in journal from Medical and Engineering consistently used only one chosen pronoun, which was recorded found at different sections in the journal article. The data then coded and transcribed to ease the analysis in this researcher. As a result of the study, it was found out that the data showed 19 kinds of pronouns in total were used in these three different fields. These results showed us that the pronoun usage in a scientific article from these three various fields varies with options of different pronouns.  The pronoun seems used to help the impact of imposition and showing politeness or quality of the articles. 

Evaluating Qualitative Research

2017 ◽  
Author(s):  
Jeasik Cho
Keyword(s):  
Qualitative Research ◽  
Large Scale ◽  
Academic Research ◽  
Research Community ◽  
Assessment Tools ◽  
Journal Articles ◽  
Journal Editors ◽  
The Past ◽  
Grant Proposals

This book provides the qualitative research community with some insight on how to evaluate the quality of qualitative research. This topic has gained little attention during the past few decades. We, qualitative researchers, read journal articles, serve on masters’ and doctoral committees, and also make decisions on whether conference proposals, manuscripts, or large-scale grant proposals should be accepted or rejected. It is assumed that various perspectives or criteria, depending on various paradigms, theories, or fields of discipline, have been used in assessing the quality of qualitative research. Nonetheless, until now, no textbook has been specifically devoted to exploring theories, practices, and reflections associated with the evaluation of qualitative research. This book constructs a typology of evaluating qualitative research, examines actual information from websites and qualitative journal editors, and reflects on some challenges that are currently encountered by the qualitative research community. Many different kinds of journals’ review guidelines and available assessment tools are collected and analyzed. Consequently, core criteria that stand out among these evaluation tools are presented. Readers are invited to join the author to confidently proclaim: “Fortunately, there are commonly agreed, bold standards for evaluating the goodness of qualitative research in the academic research community. These standards are a part of what is generally called ‘scientific research.’ ”

scholarly journals Web-based Medical Education During COVID-19 Lockdown: A Step Back or a Leap to the Future?

2021 ◽  
pp. 153473462110118
Author(s):  
Anna Eleftheriou ◽  
Aikaterini Rokou ◽  
Christos Argyriou ◽  
Nikolaos Papanas ◽  
George S. Georgiadis
Keyword(s):  
Medical Education ◽  
Clinical Training ◽  
Medical Training ◽  
Medical Schools ◽  
Web Based ◽  
Clinical Exposure ◽  
Virtual Teaching ◽  
Based Medicine ◽  
The Impact

The impact of coronavirus infectious disease (COVID-19) on medical education has been substantial. Medical students require considerable clinical exposure. However, due to the risk of COVID-19, the majority of medical schools globally have discontinued their normal activities. The strengths of virtual teaching now include a variety of web-based resources. New interactive forms of virtual teaching are being developed to enable students to interact with patients from their homes. Conversely, students have received decreased clinical training in certain medical and surgical specialities, which may, in turn, reduce their performance, confidence, and abilities as future physicians. We sought to analyze the effect of telemedicine on the quality of medical education in this new emerging era and highlight the benefits and drawbacks of web-based medical training in building up future physicians. The COVID-19 pandemic has posed an unparalleled challenge to medical schools, which are aiming to deliver quality education to students virtually, balancing between evidence-based and experience-based medicine.

scholarly journals Association between sleep habits and symptoms of oral disease in adolescents: the 2017 Korea Youth Risk Behavior Web-based Survey

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Eun-Sil Choi ◽  
Hyun-Sun Jeon ◽  
So-Jung Mun
Keyword(s):  
Risk Behavior ◽  
Sleep Duration ◽  
Oral Disease ◽  
Type B ◽  
Quality Of Sleep ◽  
Sleep Habits ◽  
Web Based ◽  
Disease Symptoms ◽  
Youth Risk Behavior

Abstract Background This cross-sectional study aimed to examine the relationship between sleep habits and oral disease symptoms in adolescents. Methods Among 62,276 adolescents who participated in the 13th Korea Youth Risk Behavior Web-based Survey (2017), we selected a total of 54,766 adolescents (age, 12–18 years; male, 49.9%) for the final analysis, after excluding those who did not report their sleep duration. The 13th Korea Youth Risk Behavior Web-based Survey data were obtained from a stratified, multistage, clustered sample. Independent variables included general characteristics, oral health behavior, sleep types, sleep duration, and sleep quality; dependent variables comprised oral disease symptoms. Sleep was categorized according to bedtime astype A (bedtime < 1 a.m.) and type B (bedtime ≥ 1 a.m.). Data were analyzed using logistic regression analysis. Statistical significance was set at p < 0.05. Results After adjusting for all covariates, adolescents with type A sleep had a higher risk of toothache on chewing (OR = 1.08, 95% CI 1.02–1.15) than adolescents with type B. Adolescents who slept for 6 h or less each night had a higher risk of pain in the tongue and buccal mucosa (OR = 1.35, 95% CI 1.18–1.54), gingival pain, and bleeding (OR = 1.31, 95% CI 1.19–1.45) than those who slept for more than 8 h. Adolescents with low quality of sleep had a higher risk of toothache or throbbing (OR = 1.70, 95% CI 1.60–1.81), toothache on chewing (OR = 1.73, 95% CI 1.65–1.82), and halitosis (OR = 1.51, 95% CI 1.41–1.59) than those with high quality of sleep. Conclusions Our findings indicate that some oral symptoms are related to sleep duration and quality. It is essential to inculcate good sleeping habits in adolescents by emphasizing the effects of inadequate sleep duration and quality.

scholarly journals Access to care and worsening eating disorder symptomatology in youth during the COVID-19 pandemic

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Rebecca Spigel ◽  
Jessica A. Lin ◽  
Carly E. Milliren ◽  
Melissa Freizinger ◽  
Julia A. Vitagliano ◽  
...  
Keyword(s):  
Quality Of Care ◽  
Eating Disorder ◽  
Access To Care ◽  
Treatment Quality ◽  
Related Factors ◽  
Web Based ◽  
Face To Face ◽  
Recovery Study ◽  
And Behaviors

Abstract Background Shelter-in-place orders and social distancing guidelines, in response to the COVID-19 pandemic, have limited traditional face-to-face interactions and led to many clinical providers transitioning to the use of videoconferencing platforms. The present study aims to assess how the COVID-19 pandemic has impacted adolescents’/young adults’ (AYA) eating disorder (ED)-related care, and how access to, changes in, perceived disruptions to, and quality of care are associated with ED thoughts and behaviors. Methods AYA enrolled in the RECOVERY study, a pre-existing web-based longitudinal study, and completed a COVID-19-specific survey (n = 89). We examined bivariate associations of four markers of care: i) access to care, ii) changes in care, iii) perceived disruption to care, and iv) quality of care. Using multiple logistic regression, we examined the associations of pandemic-related markers of care with changes in ED thoughts and behaviors. We excluded those not engaged in treatment pre-pandemic (n = 16). Results In the remaining 73 participants, reported access to care was high, with 92% of respondents continuing care with at least one ED provider during the pandemic; however, 47% stopped some treatment during the pandemic. Nearly one-third (32%) perceived a disruption in treatment. Quality of care remained high with 67% reporting care to be better than or as good as pre-pandemic. Respondents acknowledged heightened symptomatology: 81% reported increased ED thoughts and 81% reported increased ED behaviors due to COVID-19-related factors. However, none of the markers of care described were significantly associated with ED thoughts or behaviors in regression analyses adjusting for demographic variables and baseline characteristics, except our quality of care measure which was approaching significance (p = 0.07). Conclusions Our findings show the majority of AYA who had care prior to the pandemic continued receiving some element of their multi-disciplinary ED treatment and perceived their care as high quality. None of the markers of care described were statistically associated with increased ED thoughts and behaviors.

scholarly journals AI-based localization and classification of skin disease with erythema

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ha Min Son ◽  
Wooho Jeon ◽  
Jinhyun Kim ◽  
Chan Yeong Heo ◽  
Hye Jin Yoon ◽  
...  
Keyword(s):  
Neural Network ◽  
Skin Diseases ◽  
Classification Model ◽  
Screening Tests ◽  
Sensitivity Score ◽  
Common Skin ◽  
Novel Method ◽  
Improved Performance ◽  
High Level

AbstractAlthough computer-aided diagnosis (CAD) is used to improve the quality of diagnosis in various medical fields such as mammography and colonography, it is not used in dermatology, where noninvasive screening tests are performed only with the naked eye, and avoidable inaccuracies may exist. This study shows that CAD may also be a viable option in dermatology by presenting a novel method to sequentially combine accurate segmentation and classification models. Given an image of the skin, we decompose the image to normalize and extract high-level features. Using a neural network-based segmentation model to create a segmented map of the image, we then cluster sections of abnormal skin and pass this information to a classification model. We classify each cluster into different common skin diseases using another neural network model. Our segmentation model achieves better performance compared to previous studies, and also achieves a near-perfect sensitivity score in unfavorable conditions. Our classification model is more accurate than a baseline model trained without segmentation, while also being able to classify multiple diseases within a single image. This improved performance may be sufficient to use CAD in the field of dermatology.

Sign in / Sign up

Export Citation Format

Share Document