Automated Detection and Segmentation of Bone Metastases on Spine MRI Using U-Net: A Multicenter Study.

OBJECTIVE: To develop and evaluate a deep learning model for automated segmentation and detection of bone metastasis on spinal MRI. MATERIALS AND METHODS: We included whole spine MRI scans of adult patients with bone metastasis: 662 MRI series from 302 patients (63.5 ± 11.5 years; male:female, 151:151) from three study centers obtained between January 2015 and August 2021 for training and internal testing (random split into 536 and 126 series, respectively) and 49 MRI series from 20 patients (65.9 ± 11.5 years; male:female, 11:9) from another center obtained between January 2018 and August 2020 for external testing. Three sagittal MRI sequences, including non-contrast T1-weighted image (T1), contrast-enhanced T1-weighted Dixon fat-only image (FO), and contrast-enhanced fat-suppressed T1-weighted image (CE), were used. Seven models trained using the 2D and 3D U-Nets were developed with different combinations (T1, FO, CE, T1 + FO, T1 + CE, FO + CE, and T1 + FO + CE). The segmentation performance was evaluated using Dice coefficient, pixel-wise recall, and pixel-wise precision. The detection performance was analyzed using per-lesion sensitivity and a free-response receiver operating characteristic curve. The performance of the model was compared with that of five radiologists using the external test set. RESULTS: The 2D U-Net T1 + CE model exhibited superior segmentation performance in the external test compared to the other models, with a Dice coefficient of 0.699 and pixel-wise recall of 0.653. The T1 + CE model achieved per-lesion sensitivities of 0.828 (497/600) and 0.857 (150/175) for metastases in the internal and external tests, respectively. The radiologists demonstrated a mean per-lesion sensitivity of 0.746 and a mean per-lesion positive predictive value of 0.701 in the external test. CONCLUSION: The deep learning models proposed for automated segmentation and detection of bone metastases on spinal MRI demonstrated high diagnostic performance.

Developing a deep learning model for sleep stage prediction in obstructive sleep apnea cohort using 60 GHz frequency-modulated continuous-wave radar.

Given the significant impact of sleep on overall health, radar technology offers a promising, non-invasive, and cost-effective avenue for the early detection of sleep disorders, even prior to relying on polysomnography (PSG)-based classification. In this study, we employed an attention-based bidirectional long short-term memory (Attention Bi-LSTM) model to accurately predict sleep stages using 60 GHz frequency-modulated continuous-wave (FMCW) radar. Our dataset comprised 78 participants from an ongoing obstructive sleep apnea (OSA) cohort, recruited between July 2021 and November 2022, who underwent overnight polysomnography alongside radar sensor monitoring. The dataset encompasses comprehensive polysomnography recordings, spanning both sleep and wakefulness states. The predictions achieved a Cohen's kappa coefficient of 0.746 and an overall accuracy of 85.2% in classifying wakefulness, rapid-eye-movement (REM) sleep, and non-REM (NREM) sleep (N1 + N2 + N3). The results demonstrated that the models incorporating both Radar 1 and Radar 2 data consistently outperformed those using only Radar 1 data, indicating the potential benefits of utilising multiple radars for sleep stage classification. Although the performance of the models tended to decline with increasing OSA severity, the addition of Radar 2 data notably improved the classification accuracy. These findings demonstrate the potential of radar technology as a valuable screening tool for sleep stage classification.

Predicting short-term outcomes in atrial-fibrillation-related stroke using machine learning.

Background: Prognostic prediction and the identification of prognostic factors are critical during the early period of atrial-fibrillation (AF)-related strokes as AF is associated with poor outcomes in stroke patients. Methods: Two independent datasets, namely, the Korean Atrial Fibrillation Evaluation Registry in Ischemic Stroke Patients (K-ATTENTION) and the Korea University Stroke Registry (KUSR), were used for internal and external validation, respectively. These datasets include common variables such as demographic, laboratory, and imaging findings during early hospitalization. Outcomes were unfavorable functional status with modified Rankin scores of 3 or higher and mortality at 3 months. We developed two machine learning models, namely, a tree-based model and a multi-layer perceptron (MLP), along with a baseline logistic regression model. The area under the receiver operating characteristic curve (AUROC) was used as the outcome metric. The Shapley additive explanation (SHAP) method was used to evaluate the contributions of variables. Results: Machine learning models outperformed logistic regression in predicting both outcomes. For 3-month unfavorable outcomes, MLP exhibited significantly higher AUROC values of 0.890 and 0.859 in internal and external validation sets, respectively, than those of logistic regression. For 3-month mortality, both machine learning models exhibited significantly higher AUROC values than the logistic regression for internal validation but not for external validation. The most significant predictor for both outcomes was the initial National Institute of Health and Stroke Scale. Conclusion: The explainable machine learning model can reliably predict short-term outcomes and identify high-risk patients with AF-related strokes.

Prediction of Hearing Prognosis After Intact Canal Wall Mastoidectomy With Tympanoplasty Using Artificial Intelligence.

OBJECTIVE: To evaluate the performance of a machine learning model and the effects of major prognostic factors on hearing outcomes following intact canal wall (ICW) mastoidectomy with tympanoplasty. STUDY DESIGN: Retrospective cross-sectional study. SETTING: Tertiary hospital. METHODS: A total of 484 patients with chronic otitis media who underwent ICW tympanomastoidectomy between January 2007 and December 2020 were included in this study. Successful hearing outcomes were defined by a postoperative air-bone gap (ABG) of ≤20 dB and preoperative air conduction (AC)-postoperative AC value of ≥15 dB according to the Korean Otological Society guidelines for outcome reporting after chronic otitis media surgery. The light gradient boosting machine (LightGBM) and multilayer perceptron (MLP) models were tested as artificial intelligence models and compared using logistic regression. The main outcome assessed was the successful hearing outcome after surgery, measured using the area under the receiver operating characteristic curve (AUROC). RESULTS: In the analysis using the postoperative ABG criterion, the LightGBM exhibited a significantly higher AUROC compared to those of the baseline model (mean, 0.811). According to the difference between preoperative and postoperative AC, the MLP showed a significantly higher AUROC than those of the baseline model (mean, 0.795). CONCLUSION: This study analyzed multiple factors that could affect the hearing outcome using different artificial intelligence models and found that preoperative hearing status was the most important factor. Our findings provide additional information regarding postoperative hearing for clinicians.

Machine learning-based prediction of in-ICU mortality in pneumonia patients.

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO2/FiO2 ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Prediction of Mortality Among Patients With Isolated Traumatic Brain Injury Using Machine Learning Models in Asian Countries: An International Multi-Center Cohort Study.

Abstract Traumatic brain injury (TBI) is a significant healthcare concern in several countries, accounting for a major burden of morbidity, mortality, disability, and socioeconomic losses. Although conventional prognostic models for patients with TBI have been validated, their performance has been limited. Therefore, we aimed to construct machine learning (ML) models to predict the clinical outcomes in adult patients with isolated TBI in Asian countries. The Pan-Asian Trauma Outcome Study registry was used in this study, and the data were prospectively collected from January 1, 2015, to December 31, 2020. Among a total of 6540 patients (≥ 15 years) with isolated moderate and severe TBI, 3276 (50.1%) patients were randomly included with stratification by outcomes and subgrouping variables for model evaluation, and 3264 (49.9%) patients were included for model training and validation. Logistic regression was considered as a baseline, and ML models were constructed and evaluated using the area under the precision-recall curve (AUPRC) as the primary outcome metric, area under the receiver operating characteristic curve (AUROC), and precision at fixed levels of recall. The contribution of the variables to the model prediction was measured using the SHapley Additive exPlanations (SHAP) method. The ML models outperformed logistic regression in predicting the in-hospital mortality. Among the tested models, the gradient-boosted decision tree showed the best performance (AUPRC, 0.746 [0.700-0.789]; AUROC, 0.940 [0.929-0.952]). The most powerful contributors to model prediction were the Glasgow Coma Scale, O2 saturation, transfusion, systolic and diastolic blood pressure, body temperature, and age. Our study suggests that ML techniques might perform better than conventional multi-variate models in predicting the outcomes among adult patients with isolated moderate and severe TBI.

Deep-Learning-Based Stroke Screening Using Skeleton Data from Neurological Examination Videos.

According to the Korea Institute for Health and Social Affairs, in 2017, the elderly, aged 65 or older, had an average of 2.7 chronic diseases per person. The concern for the medical welfare of the elderly is increasing due to a low birth rate, an aging population, and the lack of medical personnel. The demand for services that take user age, cognitive capacity, and difficulty into account is rising. As a result, there is an increased demand for smart healthcare systems that can lower hospital admissions and offer patients individualized care. This has motivated us to develop an AI system that can easily screen and manage neurological diseases through videos. As neurological diseases can be diagnosed by visual analysis to some extent, in this study, we set out to estimate the possibility of a person having a neurological disease from videos. Among neurological diseases, we focus on stroke because it is a common condition in the elderly population and results in high mortality and morbidity worldwide. The proposed method consists of three steps: (1) transforming neurological examination videos into landmark data, (2) converting the landmark data into recurrence plots, and (3) estimating the possibility of a stroke using deep neural networks. Major features, such as the hand, face, pupil, and body movements of a person are extracted from test videos taken under several neurological examination protocols using deep-learning-based landmark extractors. Sequences of these landmark data are then converted into recurrence plots, which can be interpreted as images. These images can be fed into convolutional neural networks to classify stroke using feature-fusion techniques. A case study of the application of a disease screening test to assess the capability of the proposed method is presented.

Prediction of hearing recovery in unilateral sudden sensorineural hearing loss using artificial intelligence.

Despite the significance of predicting the prognosis of idiopathic sudden sensorineural hearing loss (ISSNHL), no predictive models have been established. This study used artificial intelligence to develop prognosis models to predict recovery from ISSNHL. We retrospectively reviewed the medical data of 453 patients with ISSNHL (men, 220; women, 233; mean age, 50.3 years) who underwent treatment at a tertiary hospital between January 2021 and December 2019 and were followed up after 1 month. According to Siegel's criteria, 203 patients recovered in 1 month. Demographic characteristics, clinical and laboratory data, and pure-tone audiometry were analyzed. Logistic regression (baseline), a support vector machine, extreme gradient boosting, a light gradient boosting machine, and multilayer perceptron were used. The outcomes were the area under the receiver operating characteristic curve (AUROC) primarily, area under the precision-recall curve, Brier score, balanced accuracy, and F1 score. The light gradient boosting machine model had the best AUROC and balanced accuracy. Together with multilayer perceptron, it was also significantly superior to logistic regression in terms of AUROC. Using the SHapley Additive exPlanation method, we found that the initial audiogram shape is the most important prognostic factor. Machine/deep learning methods were successfully established to predict the prognosis of ISSNHL.

Interpretable machine learning for early neurological deterioration prediction in atrial fibrillation-related stroke.

We aimed to develop a novel prediction model for early neurological deterioration (END) based on an interpretable machine learning (ML) algorithm for atrial fibrillation (AF)-related stroke and to evaluate the prediction accuracy and feature importance of ML models. Data from multicenter prospective stroke registries in South Korea were collected. After stepwise data preprocessing, we utilized logistic regression, support vector machine, extreme gradient boosting, light gradient boosting machine (LightGBM), and multilayer perceptron models. We used the Shapley additive explanation (SHAP) method to evaluate feature importance. Of the 3,213 stroke patients, the 2,363 who had arrived at the hospital within 24 h of symptom onset and had available information regarding END were included. Of these, 318 (13.5%) had END. The LightGBM model showed the highest area under the receiver operating characteristic curve (0.772; 95% confidence interval, 0.715-0.829). The feature importance analysis revealed that fasting glucose level and the National Institute of Health Stroke Scale score were the most influential factors. Among ML algorithms, the LightGBM model was particularly useful for predicting END, as it revealed new and diverse predictors. Additionally, the effects of the features on the predictive power of the model were individualized using the SHAP method.

Real-world oral anticoagulants for Asian patients with non-valvular atrial fibrillation: A PRISMA-compliant article.

BACKGROUND AND PURPOSE: This study aimed to evaluate the comparative efficacy and safety of 4 non-vitamin K antagonist oral anticoagulants (NOACs) and warfarin in Asians with non-valvular atrial fibrillation in real-world practice through a network meta-analysis of observational studies. METHODS: We searched multiple comprehensive databases (PubMed, Embase, and Cochrane library) for studies published until August 2020. Hazard ratios and 95% confidence intervals were used for the pooled estimates. Efficacy outcomes included ischemic stroke (IS), stroke/systemic embolism (SSE), myocardial infarction (MI), and all-cause mortality, and safety outcomes included major bleeding, gastrointestinal (GI) bleeding, and intracerebral hemorrhage (ICH). The P score was calculated for ranking probabilities. Subgroup analyses were separately performed in accordance with the dosage range of NOACs ("standard-" and "low-dose"). RESULTS: A total of 11, 6, and 8 studies were allocated to the total population, standard-dose group, and low-dose group, respectively. In the total study population, edoxaban ranked the best in terms of IS and ICH prevention and apixaban ranked the best for SSE, major bleeding, and GI bleeding. In the standard-dose regimen, apixaban ranked the best in terms of IS and SSE prevention. For major bleeding, GI bleeding, and ICH, edoxaban ranked the best. In the low-dose regimen, edoxaban ranked the best for IS, SSE, GI bleeding, and ICH prevention. For major bleeding prevention, apixaban ranked best. CONCLUSIONS: All 4 NOACs had different efficacy and safety outcomes according to their type and dosage. Apixaban and edoxaban might be relatively better and more well-balanced treatment for Asian patients with non-valvular atrial fibrillation.

Reperfusion Therapy in Acute Ischemic Stroke with Active Cancer: A Meta-Analysis Aided by Machine Learning.

OBJECTIVES: While the prevalence of active cancer patients experiencing acute stroke is increasing, the effects of active cancer on reperfusion therapy outcomes are inconclusive. Thus, we aimed to compare the safety and outcomes of reperfusion therapy in acute stroke patients with and without active cancer. MATERIALS AND METHODS: A comprehensive literature search was conducted for studies comparing the effects of intravenous thrombolysis (IVT) or endovascular treatment (EVT) in ischemic stroke patients with and without active cancer. The literature was screened using both a manual and machine learning algorithm approach. The outcomes evaluated were symptomatic intracerebral hemorrhage (sICH), all-type intracerebral hemorrhage (aICH), successful recanalization, favorable outcomes (modified Rankin Scale, 0-2), and mortality. We calculated the pooled odds ratio (OR) and 95% confidence interval (CI) using the random-effects model from the included studies. RESULTS: Seven studies were analyzed in this meta-analysis. IVT (n = 1012) was associated with an increased risk of sICH (OR, 9.80; 95% CI, 3.19-30.13) in the active cancer group. However, no significant differences in aICH, favorable outcomes, and mortality were found between groups. Although sICH and successful recanalization in the EVT group (n = 2496) were similar, we observed fewer favorable outcomes (OR, 0.55; 95% CI, 0.33-0.93) and a high prevalence of mortality (OR, 2.91; 95% CI, 1.89-4.47) in the active cancer group. CONCLUSIONS: Reperfusion therapy may benefit selected patients with acute ischemic stroke with active cancer, considering the comparable clinical outcomes of IVT and procedure-related outcomes of EVT. These results should be cautiously interpreted and confirmed in future well-designed large-scale studies.

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm.

According to recent studies, patients with COVID-19 have different feature characteristics on chest X-ray (CXR) than those with other lung diseases. This study aimed at evaluating the layer depths and degree of fine-tuning on transfer learning with a deep convolutional neural network (CNN)-based COVID-19 screening in CXR to identify efficient transfer learning strategies. The CXR images used in this study were collected from publicly available repositories, and the collected images were classified into three classes: COVID-19, pneumonia, and normal. To evaluate the effect of layer depths of the same CNN architecture, CNNs called VGG-16 and VGG-19 were used as backbone networks. Then, each backbone network was trained with different degrees of fine-tuning and comparatively evaluated. The experimental results showed the highest AUC value to be 0.950 concerning COVID-19 classification in the experimental group of a fine-tuned with only 2/5 blocks of the VGG16 backbone network. In conclusion, in the classification of medical images with a limited number of data, a deeper layer depth may not guarantee better results. In addition, even if the same pre-trained CNN architecture is used, an appropriate degree of fine-tuning can help to build an efficient deep learning model.

A Novel Method for Gait Analysis on Center of Pressure Excursion Based on a Pressure-Sensitive Mat.

Center of pressure (COP) during gait is a useful measure for assessing gait ability and has been investigated using platform or insole systems. However, these systems have inherent restrictions in repeated measure design or in obtaining true vertical force. This study proposes a novel method based on a pressure-sensitive mat system for COP measurement and presents normal reference values for the system. To explore repeatability, this work also investigated relative and absolute intra-rater reliabilities and determined the number of footfalls required to obtain a reliable measurement. Ninety healthy young adults participated and performed barefoot walking on a force-sensitive mat at a comfortable and fast pace. The time points and subphase duration of the stance phase, displacement ranges, and mean locations of COP and velocity of COP excursion were parameterized. The results showed acceptable and consistent variabilities of the parameters. Seven footfalls were determined as the threshold for most parameters to show a good to reasonable level of reliability. In conclusion, the presented method can be used as a reliable measurement for COP excursion, and it is recommended that more than seven footfalls be collected to ensure a high level of reliability.

Effects of therapeutic exercise on sea sand on pain, fatigue, and balance in patients with chronic ankle instability: a feasibility study.

BACKGROUND: Chronic ankle instability (CAI) is a common disease following ankle sprain and appears balance and gait problems, pain, and fatigue. This study aimed to examine the effect of therapeutic exercise performed on sea sand on pain, fatigue, and balance ability in patients with CAI. METHODS: This study was designed as a randomized controlled trial. Subjects with a Cumberland Ankle Instability Tool (CAIT) score of less than 27 were selected. 22 subjects were randomly assigned to the sea sand (SS) group (N.=11) or the self-management (SM) group (N.=11). The SS group performed the therapeutic exercise on sea sand and the SM group conducted the exercises on a firm surface at home 5 times over the course of a week. To measure static balance, center of pressure (COP) of one-leg standing on the force plate was assessed. Visual Analog Scale (VAS) was used to measure pain and fatigue. RESULTS: The SS group showed statistically significant improvements in all static balance outcomes (COP-area, COP-average velocity, minor-axis, major-axis) after the intervention (P<0.05), while the SM group did not show a significant change in all static balance parameters (P>0.05). Also, the SS group showed statistically significant improvements in pain and fatigue (P<0.05). All outcomes except major axis showed statistically significant differences between SS group and SM group at change value (P<0.05). CONCLUSIONS: Therapeutic exercise on sea sand effectively improved balance and decreased pain and fatigue. Thus, it can be considered a rehabilitation method for CAI patients.

The effects of spinal support device on pain and extensibility of the hamstrings in patients with non-specific low back pain.

[Purpose] The objective of this study was to investigate the effects of spinal support device (SSD) on pain and hamstring extensibility in patients with non-specific low back pain (NSLBP). [Subjects and Methods] 20 patients with NSLBP were recruited and randomly assigned to either the SSD group or the control group. In the SSD group, SSD was applied; in the control group, bed rest in supine position was performed. Both groups underwent treatment 20 min/day, 3 times a week, for a duration of 4 weeks. To assess the hamstring extensibility, sit and reach test (SRT) was performed. To assess pain pressure threshold (PPT) of the sacroiliac joint, a pressure algometer was used. Visual analog scale (VAS) was used to quantify pain. [Results] The SSD group showed a significant improvement in sacroiliac joint pain with increased VAS, and the control group showed a significantly increased VAS after intervention. In the SSD group, VAS was significantly increased, but SRT was not changed compared with the control group. [Conclusion] These results demonstrated that an application of SSD effectively attenuates low back pain. Therefore, SSD may be a suitable intervention for pain control in patients with NSLBP.