Investigation of daily patterns for smartphone keystroke dynamics based on loneliness and social isolation.

This study examined the relationship between loneliness levels and daily patterns of mobile keystroke dynamics in healthy individuals. Sixty-six young healthy Koreans participated in the experiment. Over five weeks, the participants used a custom Android keyboard. We divided the participants into four groups based on their level of loneliness (no loneliness, moderate loneliness, severe loneliness, and very severe loneliness). The very severe loneliness group demonstrated significantly higher typing counts during sleep time than the other three groups (one-way ANOVA, F = 3.75, p < 0.05). In addition, the average cosine similarity value of weekday and weekend typing patterns in the very severe loneliness group was higher than that in the no loneliness group (Welch's t-test, t = 2.27, p < 0.05). This meant that the no loneliness group's weekday and weekend typing patterns varied, whereas the very severe loneliness group's weekday and weekend typing patterns did not. Our results indicated that individuals with very high levels of loneliness tended to use mobile keyboards during late-night hours and did not significantly change their smartphone usage behavior between weekdays and weekends. These findings suggest that mobile keystroke dynamics have the potential to be used for the early detection of loneliness and the development of targeted interventions.

Deep learning-based optic disc classification is affected by optic-disc tilt.

We aimed to determine the effect of optic disc tilt on deep learning-based optic disc classification. A total of 2507 fundus photographs were acquired from 2236 eyes of 1809 subjects (mean age of 46 years; 53% men). Among all photographs, 1010 (40.3%) had tilted optic discs. Image annotation was performed to label pathologic changes of the optic disc (normal, glaucomatous optic disc changes, disc swelling, and disc pallor). Deep learning-based classification modeling was implemented to develop optic-disc appearance classification models with the photographs of all subjects and those with and without tilted optic discs. Regardless of deep learning algorithms, the classification models showed better overall performance when developed based on data from subjects with non-tilted discs (AUC, 0.988 ± 0.002, 0.991 ± 0.003, and 0.986 ± 0.003 for VGG16, VGG19, and DenseNet121, respectively) than when developed based on data with tilted discs (AUC, 0.924 ± 0.046, 0.928 ± 0.017, and 0.935 ± 0.008). In classification of each pathologic change, non-tilted disc models had better sensitivity and specificity than the tilted disc models. The optic disc appearance classification models developed based all-subject data demonstrated lower accuracy in patients with the appearance of tilted discs than in those with non-tilted discs. Our findings suggested the need to identify and adjust for the effect of optic disc tilt on the optic disc classification algorithm in future development.

Deep Learning-Based Early Warning Score for Predicting Clinical Deterioration in General Ward Cancer Patients.

BACKGROUND: Cancer patients who are admitted to hospitals are at high risk of short-term deterioration due to treatment-related or cancer-specific complications. A rapid response system (RRS) is initiated when patients who are deteriorating or at risk of deteriorating are identified. This study was conducted to develop a deep learning-based early warning score (EWS) for cancer patients (Can-EWS) using delta values in vital signs. METHODS: A retrospective cohort study was conducted on all oncology patients who were admitted to the general ward between 2016 and 2020. The data were divided into a training set (January 2016-December 2019) and a held-out test set (January 2020-December 2020). The primary outcome was clinical deterioration, defined as the composite of in-hospital cardiac arrest (IHCA) and unexpected intensive care unit (ICU) transfer. RESULTS: During the study period, 19,739 cancer patients were admitted to the general wards and eligible for this study. Clinical deterioration occurred in 894 cases. IHCA and unexpected ICU transfer prevalence was 1.77 per 1000 admissions and 43.45 per 1000 admissions, respectively. We developed two models: Can-EWS V1, which used input vectors of the original five input variables, and Can-EWS V2, which used input vectors of 10 variables (including an additional five delta variables). The cross-validation performance of the clinical deterioration for Can-EWS V2 (AUROC, 0.946; 95% confidence interval [CI], 0.943-0.948) was higher than that for MEWS of 5 (AUROC, 0.589; 95% CI, 0.587-0.560; p < 0.001) and Can-EWS V1 (AUROC, 0.927; 95% CI, 0.924-0.931). As a virtual prognostic study, additional validation was performed on held-out test data. The AUROC and 95% CI were 0.588 (95% CI, 0.588-0.589), 0.890 (95% CI, 0.888-0.891), and 0.898 (95% CI, 0.897-0.899), for MEWS of 5, Can-EWS V1, and the deployed model Can-EWS V2, respectively. Can-EWS V2 outperformed other approaches for specificities, positive predictive values, negative predictive values, and the number of false alarms per day at the same sensitivity level on the held-out test data. CONCLUSIONS: We have developed and validated a deep learning-based EWS for cancer patients using the original values and differences between consecutive measurements of basic vital signs. The Can-EWS has acceptable discriminatory power and sensitivity, with extremely decreased false alarms compared with MEWS.

Low Muscle and High Fat Percentages Are Associated with Low Natural Killer Cell Activity: A Cross-Sectional Study.

This study aimed to investigate whether body fat and muscle percentages are associated with natural killer cell activity (NKA). This was a cross-sectional study, conducted on 8058 subjects in a medical center in Korea. The association between the muscle and fat percentage tertiles and a low NKA, defined as an interferon-gamma level lower than 500 pg/mL, was assessed. In both men and women, the muscle mass and muscle percentage were significantly low in participants with a low NKA, whereas the fat percentage, white blood cell count, and C-reactive protein (CRP) level were significantly high in those with a low NKA. Compared with the lowest muscle percentage tertile as a reference, the fully adjusted odd ratios (ORs) (95% confidence intervals (CIs)) for a low NKA were significantly lower in T2 (OR: 0.69; 95% CI: 0.55-0.86) and T3 (OR: 0.74; 95% CI: 0.57-0.95) of men, and T3 (OR: 0.76; 95% CI: 0.59-0.99) of women. Compared with the lowest fat percentage tertile as a reference, the fully adjusted OR was significantly higher in T3 of men (OR: 1.31; 95% CI: 1.01-1.69). A high muscle percentage was significantly inversely associated with a low NKA in men and women, whereas a high fat percentage was significantly associated with a low NKA in men.

Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers.

Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model's performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (N = 778), data were augmented to split the training dataset (N = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset.

Exploring Autonomic Alterations during Seizures in Temporal Lobe Epilepsy: Insights from a Heart-Rate Variability Analysis.

Epilepsy's impact on cardiovascular function and autonomic regulation, including heart-rate variability, is complex and may contribute to sudden unexpected death in epilepsy (SUDEP). Lateralization of autonomic control in the brain remains the subject of debate; nevertheless, ultra-short-term heart-rate variability (HRV) analysis is a useful tool for understanding the pathophysiology of autonomic dysfunction in epilepsy patients. A retrospective study reviewed medical records of patients with temporal lobe epilepsy who underwent presurgical evaluations. Data from 75 patients were analyzed and HRV indices were extracted from electrocardiogram recordings of preictal, ictal, and postictal intervals. Various HRV indices were calculated, including time domain, frequency domain, and nonlinear indices, to assess autonomic function during different seizure intervals. The study found significant differences in HRV indices based on hemispheric laterality, language dominancy, hippocampal atrophy, amygdala enlargement, sustained theta activity, and seizure frequency. HRV indices such as the root mean square of successive differences between heartbeats, pNN50, normalized low-frequency, normalized high-frequency, and the low-frequency/high-frequency ratio exhibited significant differences during the ictal period. Language dominancy, hippocampal atrophy, amygdala enlargement, and sustained theta activity were also found to affect HRV. Seizure frequency was correlated with HRV indices, suggesting a potential relationship with the risk of SUDEP.

Feasibility of a deep learning-based diagnostic platform to evaluate lower urinary tract disorders in men using simple uroflowmetry.

PURPOSE: To diagnose lower urinary tract symptoms (LUTS) in a noninvasive manner, we created a prediction model for bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using simple uroflowmetry. In this study, we used deep learning to analyze simple uroflowmetry. MATERIALS AND METHODS: We performed a retrospective review of 4,835 male patients aged ≥40 years who underwent a urodynamic study at a single center. We excluded patients with a disease or a history of surgery that could affect LUTS. A total of 1,792 patients were included in the study. We extracted a simple uroflowmetry graph automatically using the ABBYY Flexicapture® image capture program (ABBYY, Moscow, Russia). We applied a convolutional neural network (CNN), a deep learning method to predict DUA and BOO. A 5-fold cross-validation average value of the area under the receiver operating characteristic (AUROC) curve was chosen as an evaluation metric. When it comes to binary classification, this metric provides a richer measure of classification performance. Additionally, we provided the corresponding average precision-recall (PR) curves. RESULTS: Among the 1,792 patients, 482 (26.90%) had BOO, and 893 (49.83%) had DUA. The average AUROC scores of DUA and BOO, which were measured using 5-fold cross-validation, were 73.30% (mean average precision [mAP]=0.70) and 72.23% (mAP=0.45), respectively. CONCLUSIONS: Our study suggests that it is possible to differentiate DUA from non-DUA and BOO from non-BOO using a simple uroflowmetry graph with a fine-tuned VGG16, which is a well-known CNN model.

Selective Prediction With Long Short-term Memory Using Unit-Wise Batch Standardization for Time Series Health Data Sets: Algorithm Development and Validation.

BACKGROUND: In any health care system, both the classification of data and the confidence level of such classifications are important. Therefore, a selective prediction model is required to classify time series health data according to confidence levels of prediction. OBJECTIVE: This study aims to develop a method using long short-term memory (LSTM) models with a reject option for time series health data classification. METHODS: An existing selective prediction method was adopted to implement an option for rejecting a classification output in LSTM models. However, a conventional selection function approach to LSTM does not achieve acceptable performance during learning stages. To tackle this problem, we proposed a unit-wise batch standardization that attempts to normalize each hidden unit in LSTM to apply the structural characteristics of LSTM models that concern the selection function. RESULTS: The ability of our method to approximate the target confidence level was compared by coverage violations for 2 time series of health data sets consisting of human activity and arrhythmia. For both data sets, our approach yielded lower average coverage violations (0.98% and 1.79% for each data set) than those of the conventional approach. In addition, the classification performance when using the reject option was compared with that of other normalization methods. Our method demonstrated superior performance for selective risk (12.63% and 17.82% for each data set), false-positive rates (2.09% and 5.8% for each data set), and false-negative rates (10.58% and 17.24% for each data set). CONCLUSIONS: Our normalization approach can help make selective predictions for time series health data. We expect this technique to enhance the confidence of users in classification systems and improve collaborative efforts between humans and artificial intelligence in the medical field through the use of classification that considers confidence.

Automatic Prediction of Conductive Hearing Loss Using Video Pneumatic Otoscopy and Deep Learning Algorithm.

OBJECTIVES: Diseases of the middle ear can interfere with normal sound transmission, which results in conductive hearing loss. Since video pneumatic otoscopy (VPO) findings reveal not only the presence of middle ear effusions but also dynamic movements of the tympanic membrane and part of the ossicles, analyzing VPO images was expected to be useful in predicting the presence of middle ear transmission problems. Using a convolutional neural network (CNN), a deep neural network implementing computer vision, this preliminary study aimed to create a deep learning model that detects the presence of an air-bone gap, conductive component of hearing loss, by analyzing VPO findings. DESIGN: The medical records of adult patients who underwent VPO tests and pure-tone audiometry (PTA) on the same day were reviewed for enrollment. Conductive hearing loss was defined as an average air-bone gap of more than 10 dB at 0.5, 1, 2, and 4 kHz on PTA. Two significant images from the original VPO videos, at the most medial position on positive pressure and the most laterally displaced position on negative pressure, were used for the analysis. Applying multi-column CNN architectures with individual backbones of pretrained CNN versions, the performance of each model was evaluated and compared for Inception-v3, VGG-16 or ResNet-50. The diagnostic accuracy predicting the presence of conductive component of hearing loss of the selected deep learning algorithm used was compared with experienced otologists. RESULTS: The conductive hearing loss group consisted of 57 cases (mean air-bone gap = 25 ± 8 dB): 21 ears with effusion, 14 ears with malleus-incus fixation, 15 ears with stapes fixation including otosclerosis, one ear with a loose incus-stapes joint, 3 cases with adhesive otitis media, and 3 ears with middle ear masses including congenital cholesteatoma. The control group consisted of 76 cases with normal hearing thresholds without air-bone gaps. A total of 1130 original images including repeated measurements were obtained for the analysis. Of the various network architectures designed, the best was to feed each of the images into the individual backbones of Inception-v3 (three-column architecture) and concatenate the feature maps after the last convolutional layer from each column. In the selected model, the average performance of 10-fold cross-validation in predicting conductive hearing loss was 0.972 mean areas under the curve (mAUC), 91.6% sensitivity, 96.0% specificity, 94.4% positive predictive value, 93.9% negative predictive value, and 94.1% accuracy, which was superior to that of experienced otologists, whose performance had 0.773 mAUC and 79.0% accuracy on average. The algorithm detected over 85% of cases with stapes fixations or ossicular chain problems other than malleus-incus fixations. Visualization of the region of interest in the deep learning model revealed that the algorithm made decisions generally based on findings in the malleus and nearby tympanic membrane. CONCLUSIONS: In this preliminary study, the deep learning algorithm created to analyze VPO images successfully detected the presence of conductive hearing losses caused by middle ear effusion, ossicular fixation, otosclerosis, and adhesive otitis media. Interpretation of VPO using the deep learning algorithm showed promise as a diagnostic tool to differentiate conductive hearing loss from sensorineural hearing loss, which would be especially useful for patients with poor cooperation.

Artificial intelligence-based classification of bone tumors in the proximal femur on plain radiographs: System development and validation.

PURPOSE: Early detection and classification of bone tumors in the proximal femur is crucial for their successful treatment. This study aimed to develop an artificial intelligence (AI) model to classify bone tumors in the proximal femur on plain radiographs. METHODS: Standard anteroposterior hip radiographs were obtained from a single tertiary referral center. A total of 538 femoral images were set for the AI model training, including 94 with malignant, 120 with benign, and 324 without tumors. The image data were pre-processed to be optimized for training of the deep learning model. The state-of-the-art convolutional neural network (CNN) algorithms were applied to pre-processed images to perform three-label classification (benign, malignant, or no tumor) on each femur. The performance of the CNN model was verified using fivefold cross-validation and was compared against that of four human doctors. RESULTS: The area under the receiver operating characteristic (AUROC) of the best performing CNN model for the three-label classification was 0.953 (95% confidence interval, 0.926-0.980). The diagnostic accuracy of the model (0.853) was significantly higher than that of the four doctors (0.794) (P = 0.001) and also that of each doctor individually (0.811, 0.796, 0.757, and 0.814, respectively) (P<0.05). The mean sensitivity, specificity, precision, and F1 score of the CNN models were 0.822, 0.912, 0.829, and 0.822, respectively, whereas the mean values of four doctors were 0.751, 0.889, 0.762, and 0.797, respectively. CONCLUSIONS: The AI-based model demonstrated high performance in classifying the presence of bone tumors in the proximal femur on plain radiographs. Our findings suggest that AI-based technology can potentially reduce the misdiagnosis of doctors who are not specialists in musculoskeletal oncology.

Deep learning models for screening of high myopia using optical coherence tomography.

This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divided into three groups based on axial length: a "normal group," a "high myopia group," and an "other retinal disease" group. The researchers trained and validated three DL models to classify the three groups based on horizontal and vertical OCT images of the 600 eyes. For evaluation, OCT images of 90 eyes were used. Diagnostic agreements of human doctors and DL models were analyzed. The area under the receiver operating characteristic curve of the three DL models was evaluated. Absolute agreement of retina specialists was 99.11% (range: 97.78-100%). Absolute agreement of the DL models with multiple-column model was 100.0% (ResNet 50), 90.0% (Inception V3), and 72.22% (VGG 16). Areas under the receiver operating characteristic curves of the DL models with multiple-column model were 0.99 (ResNet 50), 0.97 (Inception V3), and 0.86 (VGG 16). The DL model based on ResNet 50 showed comparable diagnostic performance with retinal specialists. The DL model using OCT images demonstrated reliable diagnostic performance to identify high myopia.

A Fully Automated Analytic System for Measuring Endolymphatic Hydrops Ratios in Patients With Ménière Disease via Magnetic Resonance Imaging: Deep Learning Model Development Study.

BACKGROUND: Recently, the analysis of endolymphatic hydropses (EHs) via inner ear magnetic resonance imaging (MRI) for patients with Ménière disease has been attempted in various studies. In addition, artificial intelligence has rapidly been incorporated into the medical field. In our previous studies, an automated algorithm for EH analysis was developed by using a convolutional neural network. However, several limitations existed, and further studies were conducted to compensate for these limitations. OBJECTIVE: The aim of this study is to develop a fully automated analytic system for measuring EH ratios that enhances EH analysis accuracy and clinical usability when studying Ménière disease via MRI. METHODS: We proposed the 3into3Inception and 3intoUNet networks. Their network architectures were based on those of the Inception-v3 and U-Net networks, respectively. The developed networks were trained for inner ear segmentation by using the magnetic resonance images of 124 people and were embedded in a new, automated EH analysis system-inner-ear hydrops estimation via artificial intelligence (INHEARIT)-version 2 (INHEARIT-v2). After fivefold cross-validation, an additional test was performed by using 60 new, unseen magnetic resonance images to evaluate the performance of our system. The INHEARIT-v2 system has a new function that automatically selects representative images from a full MRI stack. RESULTS: The average segmentation performance of the fivefold cross-validation was measured via the intersection of union method, resulting in performance values of 0.743 (SD 0.030) for the 3into3Inception network and 0.811 (SD 0.032) for the 3intoUNet network. The representative magnetic resonance slices (ie, from a data set of unseen magnetic resonance images) that were automatically selected by the INHEARIT-v2 system only differed from a maximum of 2 expert-selected slices. After comparing the ratios calculated by experienced physicians and those calculated by the INHEARIT-v2 system, we found that the average intraclass correlation coefficient for all cases was 0.941; the average intraclass correlation coefficient of the vestibules was 0.968, and that of the cochleae was 0.914. The time required for the fully automated system to accurately analyze EH ratios based on a patient's MRI stack was approximately 3.5 seconds. CONCLUSIONS: In this study, a fully automated full-stack magnetic resonance analysis system for measuring EH ratios was developed (named INHEARIT-v2), and the results showed that there was a high correlation between the expert-calculated EH ratio values and those calculated by the INHEARIT-v2 system. The system is an upgraded version of the INHEARIT system; it has higher segmentation performance and automatically selects representative images from an MRI stack. The new model can help clinicians by providing objective analysis results and reducing the workload for interpreting magnetic resonance images.

Deep-learning framework and computer assisted fatty infiltration analysis for the supraspinatus muscle in MRI.

Occupation ratio and fatty infiltration are important parameters for evaluating patients with rotator cuff tears. We analyzed the occupation ratio using a deep-learning framework and studied the fatty infiltration of the supraspinatus muscle using an automated region-based Otsu thresholding technique. To calculate the amount of fatty infiltration of the supraspinatus muscle using an automated region-based Otsu thresholding technique. The mean Dice similarity coefficient, accuracy, sensitivity, specificity, and relative area difference for the segmented lesion, measuring the similarity of clinician assessment and that of a deep neural network, were 0.97, 99.84, 96.89, 99.92, and 0.07, respectively, for the supraspinatus fossa and 0.94, 99.89, 93.34, 99.95, and 2.03, respectively, for the supraspinatus muscle. The fatty infiltration measure using the Otsu thresholding method significantly differed among the Goutallier grades (Grade 0; 0.06, Grade 1; 4.68, Grade 2; 20.10, Grade 3; 42.86, Grade 4; 55.79, p < 0.0001). The occupation ratio and fatty infiltration using Otsu thresholding demonstrated a moderate negative correlation (ρ = - 0.75, p < 0.0001). This study included 240 randomly selected patients who underwent shoulder magnetic resonance imaging (MRI) from January 2015 to December 2016. We used a fully convolutional deep-learning algorithm to quantitatively detect the fossa and muscle regions by measuring the occupation ratio of the supraspinatus muscle. Fatty infiltration was objectively evaluated using the Otsu thresholding method. The proposed convolutional neural network exhibited fast and accurate segmentation of the supraspinatus muscle and fossa from shoulder MRI, allowing automatic calculation of the occupation ratio. Quantitative evaluation using a modified Otsu thresholding method can be used to calculate the proportion of fatty infiltration in the supraspinatus muscle. We expect that this will improve the efficiency and objectivity of diagnoses by quantifying the index used for shoulder MRI.

Comparing Ictal Cardiac Autonomic Changes in Patients with Frontal Lobe Epilepsy and Temporal Lobe Epilepsy by Ultra-Short-Term Heart Rate Variability Analysis.

Background and Objectives: Abnormal epileptic discharges in the brain can affect the central brain regions that regulate autonomic activity and produce cardiac symptoms, either at onset or during propagation of a seizure. These autonomic alterations are related to cardiorespiratory disturbances, such as sudden unexpected death in epilepsy. This study aims to investigate the differences in cardiac autonomic function between patients with temporal lobe epilepsy (TLE) and frontal lobe epilepsy (FLE) using ultra-short-term heart rate variability (HRV) analysis around seizures. Materials and Methods: We analyzed electrocardiogram (ECG) data recorded during 309 seizures in 58 patients with epilepsy. Twelve patients with FLE and 46 patients with TLE were included in this study. We extracted the HRV parameters from the ECG signal before, during and after the ictal interval with ultra-short-term HRV analysis. We statistically compared the HRV parameters using an independent t-test in each interval to compare the differences between groups, and repeated measures analysis of variance was used to test the group differences in longitudinal changes in the HRV parameters. We performed the Tukey-Kramer multiple comparisons procedure as the post hoc test. Results: Among the HRV parameters, the mean interval between heartbeats (RRi), normalized low-frequency band power (LF) and LF/HF ratio were statistically different between the interval and epilepsy types in the t-test. Repeated measures ANOVA showed that the mean RRi and RMSSD were significantly different by epilepsy type, and the normalized LF and LF/HF ratio significantly interacted with the epilepsy type and interval. Conclusions: During the pre-ictal interval, TLE patients showed an elevation in sympathetic activity, while the FLE patients showed an apparent increase and decrease in sympathetic activity when entering and ending the ictal period, respectively. The TLE patients showed a maintained elevation of sympathetic and vagal activity in the pos-ictal interval. These differences in autonomic cardiac characteristics between FLE and TLE might be relevant to the ictal symptoms which eventually result in SUDEP.

Prediction of risk factors for pharyngo-cutaneous fistula after total laryngectomy using artificial intelligence.

OBJECTIVES: Pharyngocutaneous fistula (PCF) is one of the major complications following total laryngectomy (TL). Previous studies about PCF risk factors showed inconsistent results, and artificial intelligence (AI) has not been used. We identified the clinical risk factors for PCF using multiple AI models. MATERIALS & METHODS: Patients who received TL in the authors' institution during the last 20 years were enrolled (N = 313) in this study. They consisted of no PCF (n = 247) and PCF groups (n = 66). We compared 29 clinical variables between the two groups and performed logistic regression and AI analysis including random forest, gradient boosting, and neural network to predict PCF after TL. RESULTS: The best prediction performance for AI was achieved when age, smoking, body mass index, hypertension, chronic kidney disease, hemoglobin level, operation time, transfusion, nodal staging, surgical margin, extent of neck dissection, type of flap reconstruction, hematoma after TL, and concurrent chemoradiation were included in the analysis. Among logistic regression and AI models, the neural network showed the highest area under the curve (0.667 ± 0.332). CONCLUSION: Diverse clinical factors were identified as PCF risk factors using AI models and the neural network demonstrated highest predictive power. This first study about prediction of PCF using AI could be used to select high risk patients for PCF when performing TL.

Label-Free SERS Analysis of Urine Using a 3D-Stacked AgNW-Glass Fiber Filter Sensor for the Diagnosis of Pancreatic Cancer and Prostate Cancer.

Metabolomics shows tremendous potential for the early diagnosis and screening of cancer. For clinical application as an effective diagnostic tool, however, improved analytical methods for complex biological fluids are required. Here, we developed a reliable rapid urine analysis system based on surface-enhanced Raman spectroscopy (SERS) using 3D-stacked silver nanowires (AgNWs) on a glass fiber filter (GFF) sensor and applied it to the diagnosis of pancreatic cancer and prostate cancer. Urine samples were pretreated with centrifugation to remove large debris and with calcium ion addition to improve the binding of metabolites to AgNWs. The label-free urine-SERS detection using the AgNW-GFF SERS sensor showed different spectral patterns and distinguishable specific peaks in three groups: normal control (n = 30), pancreatic cancer (n = 22), and prostate cancer (n = 22). Multivariate analyses of SERS spectra using unsupervised principal component analysis and supervised orthogonal partial least-squares discriminant analysis showed excellent discrimination between the pancreatic cancer group and the prostate cancer group as well as between the normal control group and the combined cancer groups. The results demonstrate the great potential of the urine-SERS analysis system using the AgNW-GFF SERS sensor for the noninvasive diagnosis and screening of cancers.

Automatic stenosis recognition from coronary angiography using convolutional neural networks.

BACKGROUND AND OBJECTIVE: Coronary artery disease, which is mostly caused by atherosclerotic narrowing of the coronary artery lumen, is a leading cause of death. Coronary angiography is the standard method to estimate the severity of coronary artery stenosis, but is frequently limited by intra- and inter-observer variations. We propose a deep-learning algorithm that automatically recognizes stenosis in coronary angiographic images. METHODS: The proposed method consists of key frame detection, deep learning model training for classification of stenosis on each key frame, and visualization of the possible location of the stenosis. Firstly, we propose an algorithm that automatically extracts key frames essential for diagnosis from 452 right coronary artery angiography movie clips. Our deep learning model is then trained with image-level annotations to classify the areas narrowed by over 50 %. To make the model focus on the salient features, we apply a self-attention mechanism. The stenotic locations are visualized using the activated area of feature maps with gradient-weighted class activation mapping. RESULTS: The automatically detected key frame was very close to the manually selected key frame (average distance (1.70 ± 0.12) frame per clip). The model was trained with key frames on internal datasets, and validated with internal and external datasets. Our training method achieved high frame-wise area-under-the-curve of 0.971, frame-wise accuracy of 0.934, and clip-wise accuracy of 0.965 in the average values of cross-validation evaluations. The external validation results showed high performances with the mean frame-wise area-under-the-curve of (0.925 and 0.956) in the single and ensemble model, respectively. Heat map visualization shows the location for different types of stenosis in both internal and external data sets. With the self-attention mechanism, the stenosis could be precisely localized, which helps to accurately classify the stenosis by type. CONCLUSIONS: Our automated classification algorithm could recognize and localize coronary artery stenosis highly accurately. Our approach might provide the basis for a screening and assistant tool for the interpretation of coronary angiography.

Highly sensitive and repeatable DNA-SERS detection system using silver nanowires-glass fiber filter substrate.

This paper describes a new simple DNA detection method based on surface-enhanced Raman scattering (SERS) technology using a silver nanowire stacked-glass fiber filter substrate. In this system, DNA-intercalating dye (EVAGreen) and reference dye (ROX) are used together to improve the repeatability and reliability of the SERS signals. We found that the SERS signal of EVAGreen was reduced by intercalation into DNA amplicons of a polymerase chain reaction on the silver nanowire stacked-glass fiber filter substrate, whereas that of ROX stayed constant. The DNA amplicons could be quantified by correcting the EVAGreen-specific SERS signal intensity with the ROX-specific SERS signal intensity. Multivariate analysis by partial least square methods was also successfully performed. And we further applied it to loop-mediated isothermal amplification with potential use for on-site diagnostics. The sensitivities of the DNA-SERS detection showed about 100 times higher than those of conventional fluorescence-based detection methods. The DNA-SERS detection method can be applied to various isothermal amplification methods, which is expected to realize on-site molecular diagnostics with high sensitivity, repeatability, simplicity, affordability, and convenience.

The long-lasting post-stimulation inhibitory effects of bladder activity induced by posterior tibial nerve stimulation in unanesthetized rats.

Tibial nerve stimulation (TNS) is one of the neuromodulation methods used to treat an overactive bladder (OAB). However, the treatment mechanism is not accurately understood owing to significant differences in the results obtained from animal and clinical studies. Thus, this study was aimed to confirm the response of bladder activity to the different stimulation frequencies and to observe the duration of prolonged post-stimulation inhibitory effects following TNS. This study used unanesthetized rats to provide a closer approximation of the clinical setting and evaluated the changes in bladder activity in response to 30 min of TNS at different frequencies. Moreover, we observed the long-term changes of post-stimulation inhibitory effects. Our results showed that bladder response was immediately inhibited after 30 min of 10 Hz TNS, whereas it was excited at 50 Hz TNS. We also used the implantable stimulator to observe a change in duration of the prolonged post-stimulation inhibitory effects of the TNS and found large discrepancies in the time that the inhibitory effect lasted after stimulation between individual animals. This study provides important evidence that can be used to understand the neurophysiological mechanisms underlying the bladder inhibitory response induced by TNS as well as the long-lasting prolonged post-stimulation effect.

Computer-aided recognition of myopic tilted optic disc using deep learning algorithms in fundus photography.

BACKGROUND: It is necessary to consider myopic optic disc tilt as it seriously impacts normal ocular parameters. However, ophthalmologic measurements are within inter-observer variability and time-consuming to get. This study aimed to develop and evaluate deep learning models that automatically recognize a myopic tilted optic disc in fundus photography. METHODS: This study used 937 fundus photographs of patients with normal or myopic tilted disc, collected from Samsung Medical Center between April 2016 and December 2018. We developed an automated computer-aided recognition system for optic disc tilt on color fundus photographs via a deep learning algorithm. We preprocessed all images with two image resizing techniques. GoogleNet Inception-v3 architecture was implemented. The performances of the models were compared with the human examiner's results. Activation map visualization was qualitatively analyzed using the generalized visualization technique based on gradient-weighted class activation mapping (Grad-CAM++). RESULTS: Nine hundred thirty-seven fundus images were collected and annotated from 509 subjects. In total, 397 images from eyes with tilted optic discs and 540 images from eyes with non-tilted optic discs were analyzed. We included both eye data of most included patients and analyzed them separately in this study. For comparison, we conducted training using two aspect ratios: the simple resized dataset and the original aspect ratio (AR) preserving dataset, and the impacts of the augmentations for both datasets were evaluated. The constructed deep learning models for myopic optic disc tilt achieved the best results when simple image-resizing and augmentation were used. The results were associated with an area under the receiver operating characteristic curve (AUC) of 0.978 ± 0.008, an accuracy of 0.960 ± 0.010, sensitivity of 0.937 ± 0.023, and specificity of 0.963 ± 0.015. The heatmaps revealed that the model could effectively identify the locations of the optic discs, the superior retinal vascular arcades, and the retinal maculae. CONCLUSIONS: We developed an automated deep learning-based system to detect optic disc tilt. The model demonstrated excellent agreement with the previous clinical criteria, and the results are promising for developing future programs to adjust and identify the effect of optic disc tilt on ophthalmic measurements.