Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis.

Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85-0.97. However, when multiclass classification, accuracy ranged from 0.75 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography.

Recently, deep learning-based segmentation models have been widely applied in the ophthalmic field. This study presents the complete process of constructing an orbital computed tomography (CT) segmentation model based on U-Net. For supervised learning, a labor-intensive and time-consuming process is required. The method of labeling with super-resolution to efficiently mask the ground truth on orbital CT images is introduced. Also, the volume of interest is cropped as part of the pre-processing of the dataset. Then, after extracting the volumes of interest of the orbital structures, the model for segmenting the key structures of the orbital CT is constructed using U-Net, with sequential 2D slices that are used as inputs and two bi-directional convolutional long-term short memories for conserving the inter-slice correlations. This study primarily focuses on the segmentation of the eyeball, optic nerve, and extraocular muscles. The evaluation of the segmentation reveals the potential application of segmentation to orbital CT images using deep learning methods.

Affinity prediction using deep learning based on SMILES input for D3R grand challenge 4.

Modern molecular docking comprises the prediction of pose and affinity. Prediction of docking poses is required for affinity prediction when three-dimensional coordinates of the ligand have not been provided. However, a large number of feature engineering is required for existing methods. In addition, there is a need for a robust model for the sequential combination of pose and affinity prediction due to the probabilistic deviation of the ligand position issue. We propose a pipeline using a bipartite graph neural network and transfer learning trained on a re-docking dataset. We evaluated our model on the released data from drug design data resource grand challenge 4 (D3R GC4). The two target protein data provided by the challenge have different patterns. The model outperformed the best participant by 9% on the BACE target protein from stage 2. Further, our model showed competitive performance on the CatS target protein.

COVID-19 through Adverse Outcome Pathways: Building networks to better understand the disease - 3rd CIAO AOP Design Workshop.

On April 28-29, 2021, 50 scientists from different fields of expertise met for the 3rd online CIAO workshop. The CIAO project "Modelling the Pathogenesis of COVID-19 using the Adverse Outcome Pathway (AOP) framework" aims at building a holistic assembly of the available scientific knowledge on COVID-19 using the AOP framework. An individual AOP depicts the disease progression from the initial contact with the SARS-CoV-2 virus through biological key events (KE) toward an adverse outcome such as respiratory distress, anosmia or multiorgan failure. Assembling the individual AOPs into a network highlights shared KEs as central biological nodes involved in multiple outcomes observed in COVID-19 patients. During the workshop, the KEs and AOPs established so far by the CIAO members were presented and posi­tioned on a timeline of the disease course. Modulating factors influencing the progression and severity of the disease were also addressed as well as factors beyond purely biological phenomena. CIAO relies on an interdisciplinary crowd­sourcing effort, therefore, approaches to expand the CIAO network by widening the crowd and reaching stakeholders were also discussed. To conclude the workshop, it was decided that the AOPs/KEs will be further consolidated, inte­grating virus variants and long COVID when relevant, while an outreach campaign will be launched to broaden the CIAO scientific crowd.

CEGAN: Classification Enhancement Generative Adversarial Networks for unraveling data imbalance problems.

The data imbalance problem in classification is a frequent but challenging task. In real-world datasets, numerous class distributions are imbalanced and the classification result under such condition reveals extreme bias in the majority data class. Recently, the potential of GAN as a data augmentation method on minority data has been studied. In this paper, we propose a classification enhancement generative adversarial networks (CEGAN) to enhance the quality of generated synthetic minority data and more importantly, to improve the prediction accuracy in data imbalanced condition. In addition, we propose an ambiguity reduction method using the generated synthetic minority data for the case of multiple similar classes that are degenerating the classification accuracy. The proposed method is demonstrated with five benchmark datasets. The results indicate that approximating the real data distribution using CEGAN improves the classification performance significantly in data imbalanced conditions compared with various standard data augmentation methods.

Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear.

Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.

The Effect of Resampling on Data-imbalanced Conditions for Prediction towards Nuclear Receptor Profiling Using Deep Learning.

In toxicity evaluation based on the nuclear receptor signalling pathway, in silico prediction tools are used for the detection of the early stages of long-term toxicities, the prioritization of newly synthesized chemicals and the acquisition of the selectivity and sensitivity. Computational prediction model is one of the promising tools for the toxicity screening of the chemical-protein interaction as deep learning has been improved the prediction accuracies. However, the challenge is that data-imbalanced conditions, where the volume of toxic chemical compound dataset is much smaller than the nontoxic dataset, result in low prediction accuracy of the toxic dataset providing valid information to toxicity hazard. In this paper, we have examined the effect of data imbalance in the toxicity assessment data of AR (LBD), ER (LBD), AhR, and PPAR as nuclear receptors, and identified the severe imbalance between the prediction of the toxic and nontoxic datasets. As the acquisition of the balanced selectivity and sensitivity is required for the assessment of toxicity hazards, data resampling methods have been investigated in order to improve the bias problem in binary classification for toxicity hazard profiling of nuclear receptor. The experimental results achieved a sensitivity of 0.714 and a specificity of 0.787, with an overall accuracy of 0.829 and a ROC-AUC of 0.822 by the simple resampling methods.

Influence of Ginkgo biloba extract on the pharmacodynamic effects and pharmacokinetic properties of ticlopidine: an open-label, randomized, two-period, two-treatment, two-sequence, single-dose crossover study in healthy Korean male volunteers.

BACKGROUND: Ginkgo biloba extract is an herbal medicine used in the treatment of vascular disorders that may be coadministered with antiplatelet agents such as ticlopidine. Regulatory authorities requested evaluation of the pharmacodynamic and pharmacokinetic interactions between these entities, according to the drug-development guidance for fixed-dose combination formulations in Korea. OBJECTIVE: This study was performed to evaluate the potential pharmacodynamic and pharmacokinetic interactions between ticlopidine and Ginkgo biloba extract. METHODS: An open-label, randomized, 2-period, 2-treatment, 2-sequence, single-dose crossover study was conducted in healthy Korean male volunteers. All volunteers were randomly assigned to a sequence group for the 2 treatments, which consisted of ticlopidine 250 mg alone and ticlopidine 250 mg with Ginkgo biloba extract 80 mg, separated by a 1-week washout period between the treatments. Bleeding time was determined just before dosing and at 5, 12, and 48 hours after dosing. Platelet aggregation was evaluated before dosing and at 4, 8, 26, and 48 hours after dosing. Blood samples (8 mL) from each of the volunteers were collected from an indwelling intravenous cannula inserted into a forearm vein before dosing and at 0.5, 1, 1.5, 2, 2.5, 3, 4, 6, 8, 12, 24, and 48 hours after dosing. Ticlopidine concentrations were determined by a validated method using HPLC and ultraviolet detection. Adverse events were identified using general health-related questions, vital signs, physical examinations, ECGs, and laboratory tests. RESULTS: A total of 24 healthy men participated in the study (mean [SD] age, 24.1 [4.3] years; weight, 66.6 [7.4] kg; height, 174.7 [5.0] cm). The baseline corrected bleeding times were not significantly different between the ticlopidine-alone and ticlopidine/ Ginkgo biloba groups, and changes in platelet aggregation were not significantly different between the groups. Likewise, the pharmacokinetic parameters of ticlopidine were not significantly different between the groups; the geometric mean ratios of the ticlopidine/ Ginkgo biloba group to the ticlopidine-alone group were 1.03 (90% CI, 0.92-1.16) for C(max), 1.08 (90% CI, 0.98-1.19) for AUC(0-last), and 1.10 (90% CI, 1.00-1.20) for AUC(0-infinity). A total of 28 adverse events were reported: 11 in the ticlopidine-alone group and 17 in the ticlopidine/Ginkgo biloba group. The adverse events judged to be possibly related to ticlopidine in the ticlopidine-alone group were epigastric discomfort (2 cases), diarrhea (1), skin eruption (1), and a feeling of being cold (1) or hot (1). The adverse events judged to be related to ticlopidine or Ginkgo biloba in the ticlopidine/Ginkgo biloba group were epigastric discomfort (2), diarrhea (2), nausea (2), and headache (1). CONCLUSIONS: In this small group of healthy Korean men, the addition of a single dose of Ginkgo biloba extract did not prolong the bleeding time and was not associated with additional antiplatelet effects compared with the administration of ticlopidine alone. The coadministration of Ginkgo biloba extract with ticlopidine was not associated with any significant changes in the pharmacokinetic profile of ticlopidine compared with ticlopidine administered alone.

Comparison of the pharmacokinetics of ticlopidine between administration of a combined fixed-dose tablet formulation of ticlopidine 250 mg/ginkgo extract 80 mg, and concomitant administration of ticlopidine 250-mg and ginkgo extract 80-mg tablets: an open-label, two-treatment, single-dose, randomized-sequence crossover study in healthy Korean male volunteers.

BACKGROUND: Ticlopidine is an antiplatelet agent used for the prevention of vascular accidents. In clinical practice in Korea, ginkgo extract may be administered along with ticlopidine to enhance the inhibition of platelet aggregation. OBJECTIVE: To meet the requirements for marketing a combined fixed-dose formulation in Korea, the investigators compared the pharmacokinetic characteristics of ticlopidine in a combined fixed-dose tablet of ticlopidine/ginkgo extract with the concomitant administration of ticlopidine and ginkgo extract tablets. METHODS: An open-label, 2-period, 2-treatment, single-dose, randomized-sequence crossover study was conducted in healthy Korean male volunteers. Subjects were randomly allocated to 2 sequence groups. In one period, a combined ticlopidine 250 mg/ ginkgo extract 80-mg fixed-dose tablet was administered and, in the other period, ticlopidine 250-mg and ginkgo extract 80-mg tablets were concomitantly administered. A 7-day washout separated the 2 periods. For analysis of pharmacokinetic properties, including C(max), T(max), t((1/2)), AUC(0-infinity), and AUC(0-last), serial blood sampling was performed up to 48 hours after study drug administration during each period. Ticlopidine concentrations in plasma were determined by a validated method using LC-MS/MS. In order for the 2 treatments to be considered bioequivalent, the 90% CI of the geometric means ratios for C(max) and AUC needed to be between 80% and 125%. Bleeding time was determined before dosing (0 hour) and at 5 and 24 hours after dosing. Adverse events (AEs) were identified through patient interview, recording of blood pressure, heart rate, and body temperature, physical examination, 12-lead ECG, and laboratory assessments. RESULTS: Twenty-four healthy Korean male subjects (mean [range] age, 23.9 [22-38] years; height, 174.0 [162-184] cm; weight, 67.4 [56-80] kg) completed the study. Median (range) T(max) of ticlopidine was 1.5 (0.5-2.0) hours in both groups. The mean (SD) t((1/2)) of ticlopidine in the combined fixed-dose formulation and the concomitant administration groups was 19.5 (3.4) and 19.0 (3.3) hours after study drug administration, respectively. The geometric means ratios of ticlopidine AUC(0-last), AUC(0-infinity), and C(max) between the combined fixed-dose formulation and concomitant administration were 1.04 (90% CI, 0.96-1.13), 1.04 (90% CI, 0.96-1.13), and 1.09 (90% CI, 0.96-1.23), respectively. The mean (SD) bleeding time at predose (0), and 5 and 24 hours after dose administration was 4.5 (1.6) to 5.4 (1.7) minutes in the combined fixed-dose formulation group and 4.4 (1.6) to 5.1 (1.1) minutes in the concomitant administration group. Five subjects (3 in the combined fixed-dose formulation group and 2 in the concomitant administration group) had bleeding times >8 minutes, but this was not considered to be clinically significant. A total of 24 AEs were reported in 13 of 24 subjects: nausea (3 cases), diarrhea (3), dizziness (3), epigastric discomfort (2), headache (2), rhinorrhea (2), purulent sputum (2), dyspepsia (1), upper abdominal pain (1), cough (1), pharyngolaryngeal pain (1), oropharyngeal swelling (1), dysphonia (1), and dysphagia (1). All were considered mild or moderate in nature. There was no statistically significant difference between the 2 treatments in the number of AEs or in the number of subjects who reported an AE. CONCLUSION: Administration of a single dose of a combined fixed-dose formulation of ticlopidine 250 mg/ ginkgo extract 80-mg tablets and concomitant administration of ticlopidine and ginkgo extract tablets did not result in statistically significant differences in the pharmacokinetics of ticlopidine in these healthy Korean male volunteers.