Reset
Showing 20 of 610 academic articles

TRANSFER LEARNING: INCEPTION-V3 BASED CUSTOM CLASSIFICATION APPROACH FOR FOOD IMAGES

Vishwanath C Burkapalli, Priyadarshini C Patil • ICTACT Journal on Image and Video Processing (2020)

Deep-learning approach has become more popular in the field of image processing. When it is concerned with health issues, there are lots of improvements in the applications of food image classification by deep learning methods. Transfer lea...

DOAJ Open Access (DOAJ) DOI: 10.21917/ijivp.2020.0321

The Comparability of Men Who Have Sex With Men Recruited From Venue-Time-Space Sampling and Facebook: A Cohort Study

Hernandez-Romieu, Alfonso C, Sullivan, Patrick S, Sanchez, Travis H, Kelley, Colleen F et al. • JMIR Research Protocols (2014)

BackgroundRecruiting valid samples of men who have sex with men (MSM) is a key component of the US human immunodeficiency virus (HIV) surveillance and of research studies seeking to improve HIV prevention for MSM. Social media, such as Face...

DOAJ Open Access (DOAJ) DOI: 10.2196/resprot.3342

Artificial neural network–based model for sleep quality prediction for frontline medical staff during major medical assistance

Qingquan Chen, Zeshun Chen, Xi Zhu, Jiajing Zhuang et al. • Digital Health (2024)

Background: The sleep quality of medical staff was severely affected during COVID-19, but the factors influencing the sleep quality of frontline staff involved in medical assistance remained unclear, and screening tools for their sleep qual...

DOAJ Open Access (DOAJ) DOI: 10.1177/20552076241287363

Machine learning framework for early identification of high-spending Crohn’s disease patients using administrative claims

Jamieson D Gray, Lukasz S Wylezinski, Charles F Spurlock • BMJ Health & Care Informatics (2026)

Objectives To develop and evaluate a machine learning (ML) model that predicts Crohn’s disease (CD) patients responsible for the top quartile of healthcare spending.Methods De-identified commercial claims (2016–2018) from ~267 000 continuou...

DOAJ Open Access (DOAJ) DOI: 10.1136/bmjhci-2025-101761

ACHENY: A standard Chenopodiaceae image dataset for deep learning models

Ahmad Heidary-Sharifabad, Mohsen Sardari Zarchi, Sima Emadi, Gholamreza Zarei • Data in Brief (2021)

This paper contains datasets related to the “Efficient Deep Learning Models for Categorizing Chenopodiaceae in the wild” (Heidary-Sharifabad et al., 2021). There are about 1500 species of Chenopodiaceae that are spread worldwide and often a...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.dib.2021.107478

A pairwise residue contact area-based mean force potential for discrimination of native protein structure

Pezeshk Hamid, Eslahchi Changiz, Sadeghi Mehdi, Arab Shahriar et al. • BMC Bioinformatics (2010)

Abstract Background Considering energy function to detect a correct protein fold from incorrect ones is very important for protein structure prediction and protein folding. Knowledge-based mean force potentials are certainly the most popula...

DOAJ Open Access (DOAJ) DOI: 10.1186/1471-2105-11-16

A Virtual Reading Center Model Using Crowdsourcing to Grade Photographs for Trachoma: Validation Study

Christopher J Brady, R Chase Cockrell, Lindsay R Aldrich, Meraf A Wolle et al. • Journal of Medical Internet Research (2023)

BackgroundAs trachoma is eliminated, skilled field graders become less adept at correctly identifying active disease (trachomatous inflammation—follicular [TF]). Deciding if trachoma has been eliminated from a district or if treatment strat...

DOAJ Open Access (DOAJ) DOI: 10.2196/41233

Comparative assessment of patient education content generated by five large language models on post-stroke complications: A cross-sectional study of safety, accuracy, reliability, readability, and empathy

Long-Xian Liu, Huan-Huan Wang, Shuang Lu, Guo Yu et al. • Digital Health (2026)

Objective To compare the safety, accuracy, reliability, readability, and empathy of patient education content generated by five large language models (LLMs) for post-stroke complications. Methods This CHART-guided cross-sectional comparativ...

DOAJ Open Access (DOAJ) DOI: 10.1177/20552076261493266

Effects of chronic taurine administration on healthy pregnant rats and the consequences on the offspring: Datasets for motor tests and oxidative stress

Viridiana Vargas-Castro, Ricardo Gomez-Diaz, Victor M. Blanco-Alvarez, Constantino Tomas-Sanchez et al. • Data in Brief (2022)

We present the data for taurine (2-aminoethanesulfonic acid) treatment to healthy pregnant Sprague Dawley rats (SD). At embryonic day 15 (E15), healthy pregnant SD rats were given taurine treatment (50 mg/L drinking water) and then to their...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.dib.2022.108015

Injury death certificates without specification of the circumstances leading to the fatal injury – the Norwegian Cause of Death Registry 2005–2014

Christian Lycke Ellingsen, Marta Ebbing, G. Cecilie Alfsen, Stein Emil Vollset • Population Health Metrics (2018)

Abstract Background For injury deaths, the underlying cause of death is defined as the circumstances leading to the injury. When this information is missing, the ICD-10 code X59 (Exposure to unspecified factor) is used. Lack of knowledge of...

DOAJ Open Access (DOAJ) DOI: 10.1186/s12963-018-0176-2

Electronic Cigarette Use Is Not Associated with COVID-19 Diagnosis

Thulasee Jose, Ivana T. Croghan, J. Taylor Hays, Darrell R. Schroeder et al. • Journal of Primary Care & Community Health (2021)

This analysis tested the hypothesis that current e-cigarette use was associated with an increased risk of SARS-CoV-2 infection in patients seeking medical care. E-cigarette and conventional cigarette use were ascertained using a novel elect...

DOAJ Open Access (DOAJ) DOI: 10.1177/21501327211024391

Understanding tinnitus symptom dynamics and clinical improvement through intensive longitudinal data

Milena Engelke, Jorge Piano Simões, Laura Basso, Nina Wunder et al. • npj Digital Medicine (2025)

Abstract Intensive longitudinal sampling enhances subjective data collection by capturing real-time, dynamic inputs in natural settings, complementing traditional methods. This study evaluates the feasibility of using daily self-reported ap...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41746-024-01425-w

Association of androgen receptor and tumour-infiltrating lymphocytes with bone recurrence in triple-negative breast cancer

Petra Ilenič, Ajda Herman, Erik Langerholc, Barbara Gazić et al. • Journal of Bone Oncology (2024)

Background: As compared to endocrine responsive breast cancer bone is less frequent site of distant recurrence in triple-negative breast cancer (TNBC). A biomarker which predicts bone recurrence would allow a more personalized treatment app...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.jbo.2023.100518

Deep learning prediction of pathological complete response in breast cancer using Mamba architecture

Wenchuan Zhang, Shuwan Zhang, Fengling Li, Yuanyuan Zhao et al. • npj Digital Medicine (2026)

Abstract Deep learning is capable of efficiently predicting the therapeutic efficacy of neoadjuvant chemotherapy (NAC) in breast cancer. However, current methods predominantly rely on convolutional neural networks or transformer architectur...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41746-026-02849-2

Development and validation of an interpretable machine learning model for predicting the risk of coronary heart disease risk in diabetes mellitus patients: a dual-center retrospective study

Ye Kuang, Yan Yu, Jing Li, Chuanmei Peng et al. • BMC Medical Informatics and Decision Making (2026)

Abstract Background Diabetes mellitus (DM) combined with coronary heart disease (CHD) significantly increases the risk of cardiovascular events with a greater mortality rate. Therefore, establishing a predictive model can help DM patients r...

DOAJ Open Access (DOAJ) DOI: 10.1186/s12911-026-03461-w

Exploring feature selection and classification methods for predicting heart disease

Robinson Spencer, Fadi Thabtah, Neda Abdelhamid, Michael Thompson • Digital Health (2020)

Machine learning has been used successfully to improve the accuracy of computer-aided diagnosis systems. This paper experimentally assesses the performance of models derived by machine learning techniques by using relevant features chosen b...

DOAJ Open Access (DOAJ) DOI: 10.1177/2055207620914777

Accelerated maximum likelihood parameter estimation for stochastic biochemical systems

Daigle Bernie J, Roh Min K, Petzold Linda R, Niemi Jarad • BMC Bioinformatics (2012)

Abstract Background A prerequisite for the mechanistic simulation of a biochemical system is detailed knowledge of its kinetic parameters. Despite recent experimental advances, the estimation of unknown parameter values from observed data i...

DOAJ Open Access (DOAJ) DOI: 10.1186/1471-2105-13-68

Estimation of the probability of daily fluctuations of incidence of COVID-19 according to official data

Andrey Gerasimov, Elena Galkina, Elena Danilova, Irina Ikonnikova et al. • PeerJ (2021)

When studying the dynamics of morbidity and mortality, one should not limit ourselves to analyzing general trends. Interesting information can be obtained from the analysis of deviations in morbidity and mortality from the general dynamics....

DOAJ Open Access (DOAJ) DOI: 10.7717/peerj.11049