-
Translational Vision Science &... Jun 2024This study investigated the distribution of fundus tessellation density (FTD) in a Chinese pediatric population and its potential in reflecting early myopic maculopathy...
PURPOSE
This study investigated the distribution of fundus tessellation density (FTD) in a Chinese pediatric population and its potential in reflecting early myopic maculopathy (tessellated fundus).
METHODS
Participants were enrolled from kindergartens, primary schools, and middle schools, with cluster sampling in Shanghai, China. A series of ophthalmic examinations was conducted. Based on fundus photograph, FTD was quantitatively assessed using an artificial intelligence algorithm, and tessellated fundus was diagnosed by well-trained ophthalmologists.
RESULTS
A total of 14,234 participants aged four to 18 years were included, with 7421 boys (52.1%). Tessellated fundus was observed in 2200 (15.5%) participants. The median of FTD was 0.86% (range 0.0-42.1%). FTD increased with age and axial length. In the logistics regression, larger FTD was independently associated with tessellated fundus (P < 0.001). The area under curves of receiver operating characteristic curve for categorizing tessellated fundus using FTD was 0.774, and the cutoff point of FTD was 2.22%.
CONCLUSIONS
The density of fundus tessellation was consistent with the severity of myopia. FTD could help diagnose the early stage of myopic maculopathy, tessellated fundus, providing a new pattern for myopia screening and detection of early myopic fundus changes.
TRANSLATIONAL RELEVANCE
Quantification of fundus tessellation with artificial intelligence could help detect early myopic maculopathy.
Topics: Humans; Male; Adolescent; Child; Female; Fundus Oculi; Child, Preschool; China; ROC Curve; Myopia, Degenerative; Macular Degeneration; Artificial Intelligence; Photography
PubMed: 38922627
DOI: 10.1167/tvst.13.6.22 -
Journal of Cancer Education : the... Jun 2024
PubMed: 38922554
DOI: 10.1007/s13187-024-02471-4 -
Magma (New York, N.Y.) Jun 2024To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning,... (Review)
Review
OBJECT
To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning, sequence design, and correction of acquisition artifacts.
MATERIALS AND METHODS
A comprehensive analysis was conducted on recent AI-based methods in neuro MRI acquisition. The study focused on key technological advances, their impact on clinical practice, and potential risks associated with these methods.
RESULTS
The findings indicate that AI-based algorithms have a substantial positive impact on the MRI acquisition process, improving both efficiency and throughput. Specific algorithms were identified as particularly effective in optimizing acquisition steps, with reported improvements in workflow efficiency.
DISCUSSION
The review highlights the transformative potential of AI in neuro MRI acquisition, emphasizing the technological advances and clinical benefits. However, it also discusses potential risks and challenges, suggesting areas for future research to mitigate these concerns and further enhance AI integration in MRI acquisition.
PubMed: 38922525
DOI: 10.1007/s10334-024-01182-7 -
Simulation in Healthcare : Journal of... Jun 2024
PubMed: 38922444
DOI: 10.1097/SIH.0000000000000803 -
Neuroinformatics Jun 2024Morphometry is fundamental for studying and correlating neuronal morphology with brain functions. With increasing computational power, it is possible to extract... (Review)
Review
Morphometry is fundamental for studying and correlating neuronal morphology with brain functions. With increasing computational power, it is possible to extract morphometric characteristics automatically, including features such as length, volume, and number of neuron branches. However, to the best of our knowledge, there is no mapping of morphometric tools yet. In this context, we conducted a systematic search and review to identify and analyze tools within the scope of neuron analysis. Thus, the work followed a well-defined protocol and sought to answer the following research questions: What open-source tools are available for neuronal morphometric analysis? What morphometric characteristics are extracted by these tools? For this, aiming for greater robustness and coverage, the study was based on the paper analysis as well as the study of documentation and tests with the tools available in repositories. We analyzed 1,586 papers and mapped 23 tools, where NeuroM, L-Measure, and NeuroMorphoVis extract the most features. Furthermore, we contribute to the body of knowledge with the unprecedented presentation of 150 unique morphometric features whose terminologies were categorized and standardized. Overall, the study contributes to advancing the understanding of the complex mechanisms underlying the brain.
PubMed: 38922389
DOI: 10.1007/s12021-024-09674-6 -
International Journal of Colorectal... Jun 2024The 8th AJCC TNM staging for non-metastatic lymph node-positive colon adenocarcinoma patients(NMLP-CA) stages solely by lymph node status, irrespective of the positivity...
BACKGROUND
The 8th AJCC TNM staging for non-metastatic lymph node-positive colon adenocarcinoma patients(NMLP-CA) stages solely by lymph node status, irrespective of the positivity of tumor deposits (TD). This study uses machine learning and Cox regression to predict the prognostic value of tumor deposits in NMLP-CA.
METHODS
Patient data from the SEER registry (2010-2019) was used to develop CSS nomograms based on prognostic factors identified via multivariate Cox regression. Model performance was evaluated by c-index, dynamic calibration, and Schmid score. Shapley additive explanations (SHAP) were used to explain the selected models.
RESULTS
The study included 16,548 NMLP-CA patients, randomized 7:3 into training (n = 11,584) and test (n = 4964) sets. Multivariate Cox analysis identified TD, age, marital status, primary site, grade, pT stage, and pN stage as prognostic for cancer-specific survival (CSS). In the test set, the gradient boosting machine (GBM) model achieved the best C-index (0.733) for CSS prediction, while the Cox model and GAMBoost model optimized dynamic calibration(6.473) and Schmid score (0.285), respectively. TD ranked among the top 3 most important features in the models, with increasing predictive significance over time.
CONCLUSIONS
Positive tumor deposit status confers worse prognosis in NMLP-CA patients. Tumor deposits may confer higher TNM staging. Furthermore, TD could play a more significant role in the staging system.
Topics: Humans; Colonic Neoplasms; Machine Learning; Male; Adenocarcinoma; Female; Prognosis; Proportional Hazards Models; Middle Aged; Lymph Nodes; Aged; Lymphatic Metastasis; Neoplasm Staging; Nomograms; SEER Program
PubMed: 38922361
DOI: 10.1007/s00384-024-04671-2 -
Anais Da Academia Brasileira de Ciencias 2024The need for the identification of risk factors associated to COVID-19 disease severity remains urgent. Patients' care and resource allocation can be potentially...
The need for the identification of risk factors associated to COVID-19 disease severity remains urgent. Patients' care and resource allocation can be potentially different and are defined based on the current classification of disease severity. This classification is based on the analysis of clinical parameters and routine blood tests, which are not standardized across the globe. Some laboratory test alterations have been associated to COVID-19 severity, although these data are conflicting partly due to the different methodologies used across different studies. This study aimed to construct and validate a disease severity prediction model using machine learning (ML). Seventy-two patients admitted to a Brazilian hospital and diagnosed with COVID-19 through RT-PCR and/or ELISA, and with varying degrees of disease severity, were included in the study. Their electronic medical records and the results from daily blood tests were used to develop a ML model to predict disease severity. Using the above data set, a combination of five laboratorial biomarkers was identified as accurate predictors of COVID-19 severe disease with a ROC-AUC of 0.80 ± 0.13. Those biomarkers included prothrombin activity, ferritin, serum iron, ATTP and monocytes. The application of the devised ML model may help rationalize clinical decision and care.
Topics: Humans; COVID-19; Machine Learning; Severity of Illness Index; Female; Male; Biomarkers; Middle Aged; Prognosis; SARS-CoV-2; Adult; Ferritins; Aged; Brazil; Hematologic Tests; ROC Curve; Risk Factors
PubMed: 38922277
DOI: 10.1590/0001-376520242023089 -
Toxins Jun 2024Mycotoxins, toxic secondary metabolites produced by certain fungi, pose significant threats to global food safety and public health. These compounds can contaminate a... (Review)
Review
Mycotoxins, toxic secondary metabolites produced by certain fungi, pose significant threats to global food safety and public health. These compounds can contaminate a variety of crops, leading to economic losses and health risks to both humans and animals. Traditional lab analysis methods for mycotoxin detection can be time-consuming and may not always be suitable for large-scale screenings. However, in recent years, machine learning (ML) methods have gained popularity for use in the detection of mycotoxins and in the food safety industry in general due to their accurate and timely predictions. We provide a systematic review on some of the recent ML applications for detecting/predicting the presence of mycotoxin on a variety of food ingredients, highlighting their advantages, challenges, and potential for future advancements. We address the need for reproducibility and transparency in ML research through open access to data and code. An observation from our findings is the frequent lack of detailed reporting on hyperparameters in many studies and a lack of open source code, which raises concerns about the reproducibility and optimisation of the ML models used. The findings reveal that while the majority of studies predominantly utilised neural networks for mycotoxin detection, there was a notable diversity in the types of neural network architectures employed, with convolutional neural networks being the most popular.
Topics: Mycotoxins; Machine Learning; Food Contamination; Animals; Humans; Neural Networks, Computer
PubMed: 38922162
DOI: 10.3390/toxins16060268 -
Toxins May 2024Patulin, a toxic mycotoxin, can contaminate apple-derived products. The FDA has established an action level of 50 ppb (ng/g) for patulin in apple juice and apple juice...
Patulin, a toxic mycotoxin, can contaminate apple-derived products. The FDA has established an action level of 50 ppb (ng/g) for patulin in apple juice and apple juice products. To effectively monitor this mycotoxin, there is a need for adequate analytical methods that can reliably and efficiently determine patulin levels. In this work, we developed an automated sample preparation workflow followed by liquid chromatography-atmospheric pressure chemical ionization tandem mass spectrometry (LC-APCI-MS/MS) detection to identify and quantify patulin in a single method, further expanding testing capabilities for monitoring patulin in foods compared to traditional optical methods. Using a robotic sample preparation system, apple juice, apple cider, apple puree, apple-based baby food, applesauce, fruit rolls, and fruit jam were fortified with C-patulin and extracted using dichloromethane (DCM) without human intervention, followed by an LC-APCI-MS/MS analysis in negative ionization mode. The method achieved a limit of quantification of 4.0 ng/g and linearity ranging from 2 to 1000 ng/mL (r > 0.99). Quantitation was performed with isotope dilution using C-patulin as an internal standard and solvent calibration standards. Average recoveries (relative standard deviations, RSD%) in seven spike matrices were 95% (9%) at 10 ng/g, 110% (5%) at 50 ng/g, 101% (7%) at 200 ng/g, and 104% (4%) at 1000 ng/g ( = 28). The ranges of within-matrix and between-matrix variability (RSD) were 3-8% and 4-9%, respectively. In incurred samples, the identity of patulin was further confirmed with a comparison of the information-dependent acquisition-enhanced product ion (IDA-EPI) MS/MS spectra to a reference standard. The metrological traceability of the patulin measurements in an incurred apple cider (21.1 ± 8.0 µg/g) and apple juice concentrate (56.6 ± 15.6 µg/g) was established using a certified reference material and calibration data to demonstrate data confidence intervals (k = 2, 95% confidence interval).
Topics: Patulin; Malus; Tandem Mass Spectrometry; Fruit and Vegetable Juices; Chromatography, Liquid; Robotics; Food Contamination; Fruit
PubMed: 38922133
DOI: 10.3390/toxins16060238 -
Toxics May 2024Ischemic stroke (IS), chronic obstructive pulmonary disease (COPD) and diabetes mellitus (DM) account for a large burden of premature deaths. However, few studies have...
Ischemic stroke (IS), chronic obstructive pulmonary disease (COPD) and diabetes mellitus (DM) account for a large burden of premature deaths. However, few studies have investigated the associations between fine particular matter (PM) components and mortality of IS, COPD and DM. We aimed to examine these associations in Beijing, China. Data on daily mortality, air pollutants and meteorological factors from 2008 to 2011 in Beijing were collected. Daily concentrations of five PM components, namely, sulfate ion (SO), ammonium ion (NH), nitrate ion (NO), organic matter (OM) and black carbon (BC), were obtained from the Tracking Air Pollution (TAP) database in China. The association between PM components and daily deaths was explored using a quasi-Poisson regression with the distributed lag nonlinear model (DLNM). The average daily concentrations of SO, NH, NO, OM and BC were 11.24, 8.37, 12.00, 17.34 and 3.32 μg/m, respectively. After adjusting for temperature, relative humidity, pressure, particulate matter less than 10 μm in aerodynamic diameter (PM), nitrogen dioxide (NO) and sulfur dioxide (SO), an IQR increase in OM at lag day 2 and lag day 6 was associated with an increased DM mortality risk (RR 1.038; 95% CI: 1.005-1.071) and COPD mortality risk (RR 1.013; 95% CI: 1.001-1.026). An IQR increase in BC at lag day 0 and lag day 6 was associated with increased COPD mortality risk (RR 1.228; 95% CI: 1.017-1.48, RR 1.059; 95% CI: 1.001-1.121). Cumulative exposure to SO and NH was associated with an increased mortality risk for IS, with the highest effect found for lag of 0-7 days (RR 1.085; 95% CI: 1.010-1.167, RR 1.083; 95% CI: 1.003-1.169). These effects varied by sex and age group. This study demonstrated associations of short-term exposure to PM components with increased risk of IS, COPD and DM mortality in the general population. Our study also highlighted susceptible subgroups.
PubMed: 38922061
DOI: 10.3390/toxics12060381