No abstract available.
Humans

OBJECTIVES: Human motion analysis can be applied to the diagnosis of musculoskeletal diseases, rehabilitation therapies, fall detection, and estimation of energy expenditure. To analyze human motion with micro-Doppler signatures measured by radar, a deep learning algorithm is one of the most effective approaches. Because deep learning requires a large data set, the high cost involved in measuring large amounts of human data is an intrinsic problem. The objective of this study is to augment human motion micro-Doppler data employing generative adversarial networks (GANs) to improve the accuracy of human motion classification. METHODS: To test data augmentation provided by GANs, authentic data for 7 human activities were collected using micro-Doppler radar. Each motion yielded 144 data samples. Software including GPU driver, CUDA library, cuDNN library, and Anaconda were installed to train the GANs. Keras-GPU, SciPy, Pillow, OpenCV, Matplotlib, and Git were used to create an Anaconda environment. The data produced by GANs were saved every 300 epochs, and the training was stopped at 3,000 epochs. The images generated from each epoch were evaluated, and the best images were selected. RESULTS: Each data set of the micro-Doppler signatures, consisting of 144 data samples, was augmented to produce 1,472 synthesized spectrograms of 64 × 64. Using the augmented spectrograms, the deep neural network was trained, increasing the accuracy of human motion classification. CONCLUSIONS: Data augmentation to increase the amount of training data was successfully conducted through the use of GANs. Thus, augmented micro-Doppler data can contribute to improving the accuracy of human motion recognition.
Boidae ; Classification ; Dataset ; Diagnosis ; Energy Metabolism ; Human Activities ; Humans ; Learning ; Motion Perception ; Musculoskeletal Diseases ; Rehabilitation ; Supervised Machine Learning

Background: and Purpose Parkinson’s disease (PD) is characterized by various prodromal symptoms, and these symptoms are mostly investigated retrospectively. While some symptoms such as rapid eye movement sleep behavior disorder are highly specific, others are common. This makes it challenging to predict those at risk of PD based solely on less-specific prodromal symptoms. The prediction accuracy when using only less-specific symptoms can be improved by analyzing the vast amount of information available using sophisticated deep-learning techniques. This study aimed to improve the performance of deep-learning-based screening in detecting prodromal PD using medical-claims data, including prescription information. Methods: We sampled 820 PD patients and 8,200 age- and sex-matched non-PD controls from Korean National Health Insurance cohort data. A deep-learning algorithm was developed using various combinations of diagnostic codes, medication codes, and prodromal periods. Results: During the prodromal period from year -3 to year 0, predicting PD using only diagnostic codes yielded a high accuracy of 0.937. Adding medication codes for the same period did not increase the accuracy (0.931–0.935). For the earlier prodromal period (year -6 to year -3), the accuracy of PD prediction decreased to 0.890 when using only diagnostic codes. The inclusion of all medication-codes data increased that accuracy markedly to 0.922. Conclusions A deep-learning algorithm using both prodromal diagnostic and medication codes was effective in screening PD. Developing a surveillance system with automatically collected medical-claims data for those at risk of developing PD could be cost-effective. This approach could streamline the process of developing disease-modifying drugs by focusing on the most-appropriate candidates for inclusion in accurate diagnostic tests.

Background: and Purpose Parkinson’s disease (PD) is characterized by various prodromal symptoms, and these symptoms are mostly investigated retrospectively. While some symptoms such as rapid eye movement sleep behavior disorder are highly specific, others are common. This makes it challenging to predict those at risk of PD based solely on less-specific prodromal symptoms. The prediction accuracy when using only less-specific symptoms can be improved by analyzing the vast amount of information available using sophisticated deep-learning techniques. This study aimed to improve the performance of deep-learning-based screening in detecting prodromal PD using medical-claims data, including prescription information. Methods: We sampled 820 PD patients and 8,200 age- and sex-matched non-PD controls from Korean National Health Insurance cohort data. A deep-learning algorithm was developed using various combinations of diagnostic codes, medication codes, and prodromal periods. Results: During the prodromal period from year -3 to year 0, predicting PD using only diagnostic codes yielded a high accuracy of 0.937. Adding medication codes for the same period did not increase the accuracy (0.931–0.935). For the earlier prodromal period (year -6 to year -3), the accuracy of PD prediction decreased to 0.890 when using only diagnostic codes. The inclusion of all medication-codes data increased that accuracy markedly to 0.922. Conclusions A deep-learning algorithm using both prodromal diagnostic and medication codes was effective in screening PD. Developing a surveillance system with automatically collected medical-claims data for those at risk of developing PD could be cost-effective. This approach could streamline the process of developing disease-modifying drugs by focusing on the most-appropriate candidates for inclusion in accurate diagnostic tests.

Background: and Purpose Parkinson’s disease (PD) is characterized by various prodromal symptoms, and these symptoms are mostly investigated retrospectively. While some symptoms such as rapid eye movement sleep behavior disorder are highly specific, others are common. This makes it challenging to predict those at risk of PD based solely on less-specific prodromal symptoms. The prediction accuracy when using only less-specific symptoms can be improved by analyzing the vast amount of information available using sophisticated deep-learning techniques. This study aimed to improve the performance of deep-learning-based screening in detecting prodromal PD using medical-claims data, including prescription information. Methods: We sampled 820 PD patients and 8,200 age- and sex-matched non-PD controls from Korean National Health Insurance cohort data. A deep-learning algorithm was developed using various combinations of diagnostic codes, medication codes, and prodromal periods. Results: During the prodromal period from year -3 to year 0, predicting PD using only diagnostic codes yielded a high accuracy of 0.937. Adding medication codes for the same period did not increase the accuracy (0.931–0.935). For the earlier prodromal period (year -6 to year -3), the accuracy of PD prediction decreased to 0.890 when using only diagnostic codes. The inclusion of all medication-codes data increased that accuracy markedly to 0.922. Conclusions A deep-learning algorithm using both prodromal diagnostic and medication codes was effective in screening PD. Developing a surveillance system with automatically collected medical-claims data for those at risk of developing PD could be cost-effective. This approach could streamline the process of developing disease-modifying drugs by focusing on the most-appropriate candidates for inclusion in accurate diagnostic tests.

A 40-year-old female visited our clinic for visual disturbance of the right eye, in which a few creamy-yellow retinal lesions and visual field constrictions were noted. She had been treated for primary CNS lymphoma and was in complete remission. After failure to follow-up for three months, she lost vision in the right eye, at which time active panuveitis was seen. Decreased vision and field constriction was observed in the left eye. Her left eye showed a granular pattern and dye leakage from the vessels and disc on fluorescein angiography and small RPE humps were seen in optical coherence tomography (OCT). Diffuse large malignant B-cells with strong immunoreactivities with CD20 immunostaining were seen in the epiretinal membrane biopsy specimen. Intravitreal injections of methotrexate (MTX) (800 microgram/0.1 ml in the right eye, 400 microgram/0.05 ml in the left eye) were performed twice weekly for one month, once weekly for the following month, once every two weeks for the next month, followed by nine monthly injections. Both eyes were free from malignant cells on vitreous biopsy six months later. There was no leakage seen by angiography, but the granular pattern persisted. Visual field constriction was slightly improved, and the small RPE humpsdetachments seen in OCT disappeared. EOG Arden ratio was decreased in both eyes, and b wave amplitude of scotopic ERG was decreased in the left eye. She was free from recurrence until six months later. No ocular complications except minimal opacity of the crystalline lenses were noted in both eyes.
Adult ; Antimetabolites, Antineoplastic/*administration & dosage ; Drug Administration Schedule ; Eye Neoplasms/*drug therapy ; Female ; Humans ; Injections ; Lymphoma/*drug therapy ; Methotrexate/*administration & dosage ; Treatment Outcome ; Vitreous Body

No abstract available.
Diffusion Magnetic Resonance Imaging ; Diffusion ; Optic Nerve Diseases ; Optic Nerve ; Optic Neuritis

Delayed anoxic encephalopathy after carbon monoxide (CO) poisoning is characterized by neurological deterioration that occurs after recovery from acute CO intoxication. There has been no established therapy. We report a patient recovered from acute CO intoxication developed various neurological symptoms. After the administration of high dose prednisolone and anticholinesterase inhibitor, the therapeutic effect was remarkable and confirmed by quantitative analysis of diffusion-tensor imaging (DTI). DTI could be used to evaluate the therapeutic effect for delayed anoxic encephalopathy after CO poisoning.
Carbon Monoxide Poisoning ; Carbon Monoxide ; Carbon ; Diffusion Tensor Imaging ; Humans ; Hypoxia, Brain ; Leukoencephalopathies ; Magnetic Resonance Imaging ; Poisoning ; Prednisolone

No abstract available.
Blepharoptosis ; Headache ; Sinusitis

Sarcoidosis is an idiopathic multisystemic granulomatous disorder that most commonly affects young adults. It most frequently presents with bilateral hilar lesions, lymphadenopathy, pulmonary infiltration and cutaneous or ocular lesions. Cutaneous sarcoidosis occurs in 20% to 35% of the case of systemic sarcoidosis, but it can occur without systemic disease, as in the patient whose case is described herein. We present a patient with cutaneous sarcoidosis and who developed specific sarcoidosis lesions in the mucous membrane of the lower lip. To the best of our knowledge, the lip is the rare site for the occurance of sarcoidosis, as reported in the Korean literature. Herein, we report on a 53-year-old woman who had an asymptomatic mass on the lip and this was diagnosed as sarcoidosis.
Female ; Humans ; Lip ; Lymphatic Diseases ; Membranes ; Middle Aged ; Mucous Membrane ; Sarcoidosis ; Young Adult