Explore highly relevant questions in the Baumann skin type questionnaire through the digital skin analyzer: A retrospective single-center study in South Korea.

BACKGROUND: Baumann skin type questionnaire (BSTQ) has been widely used for evaluating skin types in dermatology. However, it requires excessive assessment time and lacks sufficient clinical validation for the Asian population. AIMS: We aimed to establish optimized BSTQ based on dermatological assessment of the Asian population. METHODS: This was a single-center retrospective study, where the patient completed a modified BSTQ and a digital photography examination. The answers to four question groups for evaluating skin properties, including oily versus dry (O-D), sensitive versus resistant (S-R), pigmented versus non-pigmented (P-N), and wrinkled versus tight (W-T) were compared with the measurements. Highly relevant questions are selected using two different strategies and used to determine the threshold level, which was compared with skin-type measurement. RESULTS: In O-D, S-R, P-N, and W-T, 3-5 out of 6, 2-6 out of 9, 3-6 out of 7, and 4-9 out of 11 questions were selected, respectively. As a result, skin type scores from two strategies and measurements showed similar Pearson correlation coefficient values compared to modified BSTQ (for O-D and sebum, 0.236/0.266 vs. 0.232; for O-D and porphyrin, 0.230/0.267 vs. 0.230; for S-R and redness, 0.157/0.175 vs. 0.095; for S-R and porphyrin, 0.061 vs. 0.051; for P-N and melanin pigmentation, 0.156/0.208 vs. 0.150; for W-T and wrinkle, 0.265/0.269 vs. 0.217). CONCLUSION: Two strategies for optimizing BSTQ are proposed and validated for Asian patients. Compared to the BSTQ, our methods show comparable performance with a significantly reduced number of questions.

High-Resolution Motor State Detection in Parkinson's Disease Using Convolutional Neural Networks.

Patients with advanced Parkinson's disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.

A Multi-Layer Gaussian Process for Motor Symptom Estimation in People With Parkinson's Disease.

The assessment of Parkinson's disease (PD) poses a significant challenge, as it is influenced by various factors that lead to a complex and fluctuating symptom manifestation. Thus, a frequent and objective PD assessment is highly valuable for effective health management of people with Parkinson's disease (PwP). Here, we propose a method for monitoring PwP by stochastically modeling the relationships between wrist movements during unscripted daily activities and corresponding annotations about clinical displays of movement abnormalities. We approach the estimation of PD motor signs by independently modeling and hierarchically stacking Gaussian process models for three classes of commonly observed movement abnormalities in PwP including tremor, (non-tremulous) bradykinesia, and (non-tremulous) dyskinesia. We use clinically adopted severity measures as annotations for training the models, thus allowing our multi-layer Gaussian process prediction models to estimate not only their presence but also their severities. The experimental validation of our approach demonstrates strong agreement of the model predictions with these PD annotations. Our results show that the proposed method produces promising results in objective monitoring of movement abnormalities of PD in the presence of arbitrary and unknown voluntary motions, and makes an important step toward continuous monitoring of PD in the home environment.

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

An unsupervised approach to detecting and isolating athletic movements.

To enable automatic analysis of athletic movement, the first task is to recognize the athletic movements to be analyzed from a continuous motion data stream. Automated detection of athletic movement and the isolation of the recruited body parts would enable the analysis of sporting movements for improving sports performance and preventing possible injuries. In this paper, an unsupervised method for detecting and isolating athletic movements is proposed. Given motion capture data, the method automatically identifies when athletic movements are being performed and the body parts involved using the concepts of the manipulability and kinematic dimensionality reduction. Experiments demonstrate the ability of the proposed approach to detect and isolate athletic movements from a variety of motion data.