Interpretable Deep-Learning Approaches for Osteoporosis Risk Screening and Individualized Feature Analysis Using Large Population-Based Data: Model Development and Performance Evaluation.

BACKGROUND: Osteoporosis is one of the diseases that requires early screening and detection for its management. Common clinical tools and machine-learning (ML) models for screening osteoporosis have been developed, but they show limitations such as low accuracy. Moreover, these methods are confined to limited risk factors and lack individualized explanation. OBJECTIVE: The aim of this study was to develop an interpretable deep-learning (DL) model for osteoporosis risk screening with clinical features. Clinical interpretation with individual explanations of feature contributions is provided using an explainable artificial intelligence (XAI) technique. METHODS: We used two separate data sets: the National Health and Nutrition Examination Survey data sets from the United States (NHANES) and South Korea (KNHANES) with 8274 and 8680 respondents, respectively. The study population was classified according to the T-score of bone mineral density at the femoral neck or total femur. A DL model for osteoporosis diagnosis was trained on the data sets and significant risk factors were investigated with local interpretable model-agnostic explanations (LIME). The performance of the DL model was compared with that of ML models and conventional clinical tools. Additionally, contribution ranking of risk factors and individualized explanation of feature contribution were examined. RESULTS: Our DL model showed area under the curve (AUC) values of 0.851 (95% CI 0.844-0.858) and 0.922 (95% CI 0.916-0.928) for the femoral neck and total femur bone mineral density, respectively, using the NHANES data set. The corresponding AUC values for the KNHANES data set were 0.827 (95% CI 0.821-0.833) and 0.912 (95% CI 0.898-0.927), respectively. Through the LIME method, significant features were induced, and each feature's integrated contribution and interpretation for individual risk were determined. CONCLUSIONS: The developed DL model significantly outperforms conventional ML models and clinical tools. Our XAI model produces high-ranked features along with the integrated contributions of each feature, which facilitates the interpretation of individual risk. In summary, our interpretable model for osteoporosis risk screening outperformed state-of-the-art methods.

Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks.

BACKGROUND: Despite the integral role of cephalometric analysis in orthodontics, there have been limitations regarding the reliability, accuracy, etc. of cephalometric landmarks tracing. Attempts on developing automatic plotting systems have continuously been made but they are insufficient for clinical applications due to low reliability of specific landmarks. In this study, we aimed to develop a novel framework for locating cephalometric landmarks with confidence regions using Bayesian Convolutional Neural Networks (BCNN). METHODS: We have trained our model with the dataset from the ISBI 2015 grand challenge in dental X-ray image analysis. The overall algorithm consisted of a region of interest (ROI) extraction of landmarks and landmarks estimation considering uncertainty. Prediction data produced from the Bayesian model has been dealt with post-processing methods with respect to pixel probabilities and uncertainties. RESULTS: Our framework showed a mean landmark error (LE) of 1.53 ± 1.74 mm and achieved a successful detection rate (SDR) of 82.11, 92.28 and 95.95%, respectively, in the 2, 3, and 4 mm range. Especially, the most erroneous point in preceding studies, Gonion, reduced nearly halves of its error compared to the others. Additionally, our results demonstrated significantly higher performance in identifying anatomical abnormalities. By providing confidence regions (95%) that consider uncertainty, our framework can provide clinical convenience and contribute to making better decisions. CONCLUSION: Our framework provides cephalometric landmarks and their confidence regions, which could be used as a computer-aided diagnosis tool and education.

Safety assessment of freeze-dried powdered Tenebrio molitor larvae (yellow mealworm) as novel food source: Evaluation of 90-day toxicity in Sprague-Dawley rats.

Worldwide demand for novel food source has grown and edible insects are a promising food sources for humans. Tenebrio molitor, as known as yellow mealworm, has advantages of being rich in protein, and easy to raise as a novel food source. The objective of this study was to evaluate subchronic toxicity, including potential hypersensitivity, of freeze-dried powdered T. molitor larvae (fdTML) in male and female Sprague-Dawley rats. The fdTML was administered orally once daily at dose levels of 0, 300, 1000 and 3000 mg/kg/day for 90 days. A toxicological assessment was performed, which included mortality, clinical signs, body and organ weights, food consumption, ophthalmology, urinalysis, hematology, serum chemistry, gross findings, histopathologic examination and allergic reaction. There were no fdTML- related findings in clinical signs, urinalysis, hematology and serum chemistry, gross examination, histopathologic examination or allergic reaction. In conclusion, the No Observed Adverse Effect Level (NOAEL) for fdTML was determined to be in excess of 3000 mg/kg/day in both sexes of rats under the experimental conditions of this study.

Multiplexed DNA-functionalized graphene sensor with artificial intelligence-based discrimination performance for analyzing chemical vapor compositions.

This study presents a new technology that can detect and discriminate individual chemical vapors to determine the chemical vapor composition of mixed chemical composition in situ based on a multiplexed DNA-functionalized graphene (MDFG) nanoelectrode without the need to condense the original vapor or target dilution. To the best of our knowledge, our artificial intelligence (AI)-operated arrayed electrodes were capable of identifying the compositions of mixed chemical gases with a mixed ratio in the early stage. This innovative technology comprised an optimized combination of nanodeposited arrayed electrodes and artificial intelligence techniques with advanced sensing capabilities that could operate within biological limits, resulting in the verification of mixed vapor chemical components. Highly selective sensors that are tolerant to high humidity levels provide a target for "breath chemovapor fingerprinting" for the early diagnosis of diseases. The feature selection analysis achieved recognition rates of 99% and above under low-humidity conditions and 98% and above under humid conditions for mixed chemical compositions. The 1D convolutional neural network analysis performed better, discriminating the compositional state of chemical vapor under low- and high-humidity conditions almost perfectly. This study provides a basis for the use of a multiplexed DNA-functionalized graphene gas sensor array and artificial intelligence-based discrimination of chemical vapor compositions in breath analysis applications.

Diagnosis of obstructive sleep apnea with prediction of flow characteristics according to airway morphology automatically extracted from medical images: Computational fluid dynamics and artificial intelligence approach.

BACKGROUND: Obstructive sleep apnea syndrome (OSAS) is being observed in an increasing number of cases. It can be diagnosed using several methods such as polysomnography. OBJECTIVES: To overcome the challenges of time and cost faced by conventional diagnostic methods, this paper proposes computational fluid dynamics (CFD) and machine-learning approaches that are derived from the upper-airway morphology with automatic segmentation using deep learning. METHOD: We adopted a 3D UNet deep-learning model to perform medical image segmentation. 3D UNet prevents the feature-extraction loss that may occur by concatenating layers and extracts the anteroposterior coordination and width of the airway morphology. To create flow characteristics of the upper airway training data, we analyzed the changes in flow characteristics according to the upper-airway morphology using CFD. A multivariate Gaussian process regression (MVGPR) model was used to train the flow characteristic values. The trained MVGPR enables the prompt prediction of the aerodynamic features of the upper airway without simulation. Unlike conventional regression methods, MVGPR can be trained by considering the correlation between the flow characteristics. As a diagnostic step, a support vector machine (SVM) with predicted aerodynamic and biometric features was used in this study to classify patients as healthy or suffering from moderate OSAS. SVM is beneficial as it is easy to learn even with a small dataset, and it can diagnose various flow characteristics as factors while enhancing the feature via the kernel function. As the patient dataset is small, the Monte Carlo cross-validation was used to validate the trained model. Furthermore, to overcome the imbalanced data problem, the oversampling method was applied. RESULT: The segmented upper-airway results of the high-resolution and low-resolution models present overall average dice coefficients of 0.76±0.041 and 0.74±0.052, respectively. Furthermore, the classification accuracy, sensitivity, specificity, and F1-score of the diagnosis algorithm were 81.5%, 89.3%, 86.2%, and 87.6%, respectively. CONCLUSION: The convenience and accuracy of sleep apnea diagnosis are improved using deep learning and machine learning. Further, the proposed method can aid clinicians in making appropriate decisions to evaluate the possible applications of OSAS.

Coronary artery decision algorithm trained by two-step machine learning algorithm.

A two-step machine learning (ML) algorithm for estimating both fractional flow reserve (FFR) and decision (DEC) for the coronary artery is introduced in this study. The primary purpose of this model is to suggest the possibility of ML-based FFR to be more accurate than the FFR calculation technique based on a computational fluid dynamics (CFD) method. For this purpose, a two-step ML algorithm that considers the flow characteristics and biometric features as input features of the ML model is designed. The first step of the algorithm is based on the Gaussian progress regression model and is trained by a synthetic model using CFD analysis. The second step of the algorithm is based on a support vector machine with patient data, including flow characteristics and biometric features. Consequently, the accuracy of the FFR estimated from the first step of the algorithm was similar to that of the CFD-based method, while the accuracy of DEC in the second step was improved. This improvement in accuracy was analyzed using flow characteristics and biometric features.

LC50 Determination of tert-Butyl Acetate using a Nose Only Inhalation Exposure in Rats.

tert-Butyl acetate (TBAc) is an organic solvent, which is commonly used in architectural coatings and industrial solvents. It has recently been exempted from the definition of a volatile organic compound (VOC) by the Air Resources Board (ARB) . Since the use of TBAc as a substitute for other VOCs has increased, thus its potential risk in humans has also increased. However, its inhalation toxicity data in the literature are very limited. Hence, inhalation exposure to TBAc was carried out to investigate its toxic effects in this study. Adult male rats were exposed to TBAc for 4 h for 1 day by using a nose-only inhalation exposure chamber (low dose, 2370 mg/m(3) (500 ppm) ; high dose, 9482 mg/m(3) (2000 ppm) ) . Shamtreated control rats were exposed to clean air in the inhalation chamber for the same period. The animals were killed at 2, 7, and 15 days after exposure. At each time point, body weight measurement, bronchoalveolar lavage fluid (BALF) analysis, histopathological examination, and biochemical assay were performed. No treatment-related abnormal effects were observed in any group according to time course. Based on those findings, the median lethal concentration (LC50) of TBAc was over 9482 mg/m(3) in this study. According to the MSDS, the 4 h LC50 for TBAc for rats is over 2230 mg/m(3). We suggested that this value is changed and these findings may be applied in the risk assessment of TBAc which could be beneficial in a sub-acute study.