Interpretable Deep Learning System for Identifying Critical Patients Through the Prediction of Triage Level, Hospitalization, and Length of Stay: Prospective Study.

BACKGROUND: Triage is the process of accurately assessing patients' symptoms and providing them with proper clinical treatment in the emergency department (ED). While many countries have developed their triage process to stratify patients' clinical severity and thus distribute medical resources, there are still some limitations of the current triage process. Since the triage level is mainly identified by experienced nurses based on a mix of subjective and objective criteria, mis-triage often occurs in the ED. It can not only cause adverse effects on patients, but also impose an undue burden on the health care delivery system. OBJECTIVE: Our study aimed to design a prediction system based on triage information, including demographics, vital signs, and chief complaints. The proposed system can not only handle heterogeneous data, including tabular data and free-text data, but also provide interpretability for better acceptance by the ED staff in the hospital. METHODS: In this study, we proposed a system comprising 3 subsystems, with each of them handling a single task, including triage level prediction, hospitalization prediction, and length of stay prediction. We used a large amount of retrospective data to pretrain the model, and then, we fine-tuned the model on a prospective data set with a golden label. The proposed deep learning framework was built with TabNet and MacBERT (Chinese version of bidirectional encoder representations from transformers [BERT]). RESULTS: The performance of our proposed model was evaluated on data collected from the National Taiwan University Hospital (901 patients were included). The model achieved promising results on the collected data set, with accuracy values of 63%, 82%, and 71% for triage level prediction, hospitalization prediction, and length of stay prediction, respectively. CONCLUSIONS: Our system improved the prediction of 3 different medical outcomes when compared with other machine learning methods. With the pretrained vital sign encoder and repretrained mask language modeling MacBERT encoder, our multimodality model can provide a deeper insight into the characteristics of electronic health records. Additionally, by providing interpretability, we believe that the proposed system can assist nursing staff and physicians in taking appropriate medical decisions.

Interactive Healthcare Robot Using Attention-Based Question-Answer Retrieval and Medical Entity Extraction Models.

In healthcare facilities, answering the questions from the patients and their companions about the health problems is regarded as an essential task. With the current shortage of medical personnel resources and an increase in the patient-to-clinician ratio, staff in the medical field have consequently devoted less time to answering questions for each patient. However, studies have shown that correct healthcare information can positively improve patients' knowledge, attitudes, and behaviors. Therefore, delivering correct healthcare knowledge through a question-answering system is crucial. In this article, we develop an interactive healthcare question-answering system that uses attention-based models to answer healthcare-related questions. Attention-based transformer models are utilized to efficiently encode semantic meanings and extract the medical entities inside the user query individually. These two features are integrated through our designed fusion module to match against the pre-collected healthcare knowledge set, so that our system will finally give the most accurate response to the user in real-time. To improve the interactivity, we further introduce a recommendation module and an online web search module to provide potential questions and out-of-scope answers. Experimental results for question-answer retrieval show that the proposed method has the ability to retrieve the correct answer from the FAQ pairs in the healthcare domain. Thus, we believe that this application can bring more benefits to human beings.

Multimodal Assessment of Schizophrenia Symptom Severity From Linguistic, Acoustic and Visual Cues.

Assessing the condition of every schizophrenia patient correctly normally requires lengthy and frequent interviews with professionally trained doctors. To alleviate the time and manual burden on those mental health professionals, this paper proposes a multimodal assessment model that predicts the severity level of each symptom defined in Scale for the Assessment of Thought, Language, and Communication (TLC) and Positive and Negative Syndrome Scale (PANSS) based on the patient's linguistic, acoustic, and visual behavior. The proposed deep-learning model consists of a multimodal fusion framework and four unimodal transformer-based backbone networks. The second-stage pre-training is introduced to make each off-the-shelf pre-trained model learn the pattern of schizophrenia data more effectively. It learns to extract the desired features from the view of its modality. Next, the pre-trained parameters are frozen, and the light-weight trainable unimodal modules are inserted and fine-tuned to keep the number of parameters low while maintaining the superb performance simultaneously. Finally, the four adapted unimodal modules are fused into a final multimodal assessment model through the proposed multimodal fusion framework. For the purpose of validation, we train and evaluate the proposed model on schizophrenia patients recruited from National Taiwan University Hospital, whose performance achieves 0.534/0.685 in MAE/MSE, outperforming the related works in the literature. Through the experimental results and ablation studies, as well as the comparison with other related multimodal assessment works, our approach not only demonstrates the superiority of our performance but also the effectiveness of our approach to extract and integrate information from multiple modalities.

The Effects of Social Presence and Familiarity on Children-Robot Interactions.

In children-robot interactions, an impression of a robot's "social presence" (i.e., an interactive agent that feels like a person) links positively to an improved relationship with the robot. However, building relationships takes many exposures, and there is an intellectual gap in how social presence and familiarity collaborate in modulating children-robot relationships. We investigated whether social presence altered over time, how repeated exposure and social presence affected rapport, and how social presence would modulate children's attitudes toward the robot. Fourteen children (four female, age = 10.79 ± 1.12) interacted with a companion robot for four days in spontaneous interactions. The findings revealed that children who perceived the robot as having a higher social presence developed a stronger rapport than those who perceived a lower social presence. However, repeated encounters did not change the children's perceptions of the robot's social presence. Children rated higher rapport after repeated interactions regardless of social presence levels. This suggests that while a higher social presence initially elevated the positive relationship between children and the robot, it was the repeated interactions that continued solidifying the rapport. Additionally, children who perceived a higher social presence from the robot felt less relational uneasiness about their relationship with robots. These findings highlight the importance of robots' social presence and familiarity in promoting positive relationships in children-robot interaction.

Lower-than-normal glycemic levels to achieve optimal reduction of diabetes risk among individuals with prediabetes: A prospective cohort study.

AIMS/HYPOTHESIS: To determine whether lower than currently accepted glycemic levels could lead to optimal risk reduction of incident diabetes among individuals with prediabetes. METHODS: We enrolled 9903 individuals with prediabetes and 16,902 individuals with normoglycemia from a prospective cohort participating health check-ups between 2006 and 2017. While classifying fasting glucose into <5.0, 5.0-5.5, and 5.6-6.9 mmol/L and postprandial glucose into <6.7, 6.7-7.7, and 7.8-11.0 mmol/L, we grouped fasting/postprandial glucose into five categories (<5.0/<6.7, <5.0/6.7-7.7, 5.0-5.5/<6.7, 5.0-5.5/6.7-7.7 mmol/L, 5.6-6.9/7.8-11.0 mmol/L). The primary outcome was incident diabetes. RESULTS: In individuals with prediabetes, the presence of a baseline fasting glucose <5.0 mmol/L or a postprandial glucose <6.7 mmol/L led to a greater risk reduction of incident diabetes with hazard ratios of 0.34 (95% confidence interval, 0.27-0.42) and 0.47 (0.41-0.54), respectively, relative to a fasting glucose 5.6-6.9 mmol/L and a postprandial glucose 7.8-11.0 mmol/L. For individuals with prediabetes having fasting/postprandial glucose <5.0/<6.7 mmol/L, the incidence of 6.4 (4.7-8.8) per 1000 person-years corresponded to that of 5.8 (4.2-8.0) per 1000 person-years for individuals with normoglycemia having 5.0-5.5/6.7-7.7 mmol/L. CONCLUSIONS/INTERPRETATION: Given that lower-than-normal glycemic levels were plausible for optimal risk reduction of diabetes, stringent glycemic management could be beneficial for diabetes prevention among individuals with prediabetes.

Three-Dimensional Maneuver Control of Multiagent Systems With Constrained Input.

In this article, we propose a new 3-D maneuver controller for a class of nonlinear multiagent systems (MASs) with nonholonomic constraint and saturated control. The system is designed under a distributed communication topology and the controller is more flexible and efficient for general formation maneuver tasks. The saturation design generates control inputs within pregiven bounds, which makes the system more applicable in practice. Moreover, based on the nonholonomic model, the proposed control also considers the heading angles of the agents. Thus, the maneuver controller can achieve a more natural tracking movement where the heading of the formation will align to the direction of the reference trajectory during the tracking motion. Several simulation examples are given to validate our results and demonstrate the competence for various maneuver tasks of MASs.

Pain Assessment in the Emergency Department: A Prospective Videotaped Study.

INTRODUCTION: Research suggests that pain assessment involves a complex interaction between patients and clinicians. We sought to assess the agreement between pain scores reported by the patients themselves and the clinician's perception of a patient's pain in the emergency department (ED). In addition, we attempted to identify patient and physician factors that lead to greater discrepancies in pain assessment. METHODS: We conducted a prospective observational study in the ED of a tertiary academic medical center. Using a standard protocol, trained research personnel prospectively enrolled adult patients who presented to the ED. The entire triage process was recorded, and triage data were collected. Pain scores were obtained from patients on a numeric rating scale of 0 to 10. Five physician raters provided their perception of pain ratings after reviewing videos. RESULTS: A total of 279 patients were enrolled. The mean age was 53 years. There were 141 (50.5%) female patients. The median self-reported pain score was 4 (interquartile range 0-6). There was a moderately positive correlation between self-reported pain scores and physician ratings of pain (correlation coefficient, 0.46; P <0.001), with a weighted kappa coefficient of 0.39. Some discrepancies were noted: 102 (37%) patients were rated at a much lower pain score, whereas 52 (19%) patients were given a much higher pain score from physician review. The distributions of chief complaints were different between the two groups. Physician raters tended to provide lower pain scores to younger (P = 0.02) and less ill patients (P = 0.008). Additionally, attending-level physician raters were more likely to provide a higher pain score than resident-level raters (P <0.001). CONCLUSION: Patients' self-reported pain scores correlate positively with the pain score provided by physicians, with only a moderate agreement between the two. Under- and over-estimations of pain in ED patients occur in different clinical scenarios. Pain assessment in the ED should consider both patient and physician factors.

Mental Status Detection for Schizophrenia Patients via Deep Visual Perception.

Schizophrenia is a mental disorder that will progressively change a person's mental state and cause serious social problems. Symptoms of schizophrenia are highly correlated to emotional status, especially depression. We are thus motivated to design a mental status detection system for schizophrenia patients in order to provide an assessment tool for mental health professionals. Our system consists of two phases, including model learning and status detection. For the learning phase, we propose a multi-task learning framework to infer the patient's mental state, including emotion and depression severity. Unlike previous studies inferring emotional status mainly by facial analysis, in the learning phase, we adopted a Cross-Modality Graph Convolutional Network (CMGCN) to effectively integrate visual features from different modalities, including the face and context. We also designed task-aware objective functions to realize better model convergence for multi-task learning, i.e., emotion recognition and depression estimation. Further, we followed the correlation between depression and emotion to design the Emotion Passer module, to transfer the prior knowledge on emotion to the depression model. For the detection phase, we drew on characteristics of schizophrenia to detect the mental status. In the experiments, we performed a series of experiments on several benchmark datasets, and the results show that the proposed learning framework boosts state-of-the-art (SOTA) methods significantly. In addition, we take a trial on schizophrenia patients, and our system can achieve 69.52 in mAP in a real situation.

Physician gestalt for emergency department triage: A prospective videotaped study.

OBJECTIVE: Appropriate triage in patients presenting to the emergency department (ED) is often challenging. Little is known about the role of physician gestalt in ED triage. We aimed to compare the accuracy of emergency physician gestalt against the currently used computerized triage process. METHODS: We conducted a prospective observational study in the ED at an academic medical center. Adult patients aged ≥20 years were included and underwent a standard triage protocol. The patients underwent system-based triage using the computerized software the Taiwan Triage and Acuity Scale. The entire triage process was recorded, and triage data were collected. Five physician raters provided triage levels (physician-based) according to their perceived urgency after reviewing videos. The primary outcome was hospital admission. The secondary outcomes were ED length of stay (EDLOS) and charges. RESULTS: In total, 656 patients were recruited (mean age 52 years, 50% male). The median system-based triage level was 3. By contrast, the median physician-based triage level was 4. The physician raters tended to provide lower triage levels than the system, with an average difference of 1. There was modest concordance between the two triage methods (correlation coefficient 0.30), with a weighted kappa coefficient of 0.18. The area under the receiver operating curve for the system- and physician-based triage in predicting hospital admission were similar (0.635 vs. 0.631, p = 0.896). Attending physicians appeared to have better performance than residents in predicting admission. The variation explained (R2 ) in EDLOS and charges were similar between the two triage methods (R2  = 3% for EDLOS, 7%-9% for charges). CONCLUSIONS: Emergency physician gestalt for triage showed similar performance to a computerized system; however, physicians redistributed patients to lower triage levels. Physician gestalt has advantages for identifying low-risk patients. This approach may avoid undue time pressure for health care providers and promote rapid discharge.

A Digital Screening System for Alzheimer Disease Based on a Neuropsychological Test and a Convolutional Neural Network: System Development and Validation.

BACKGROUND: Alzheimer disease (AD) and other types of dementia are now considered one of the world's most pressing health problems for aging people worldwide. It was the seventh-leading cause of death, globally, in 2019. With a growing number of patients with dementia and increasing costs for treatment and care, early detection of the disease at the stage of mild cognitive impairment (MCI) will prevent the rapid progression of dementia. In addition to reducing the physical and psychological stress of patients' caregivers in the long term, it will also improve the everyday quality of life of patients. OBJECTIVE: The aim of this study was to design a digital screening system to discriminate between patients with MCI and AD and healthy controls (HCs), based on the Rey-Osterrieth Complex Figure (ROCF) neuropsychological test. METHODS: The study took place at National Taiwan University between 2018 and 2019. In order to develop the system, pretraining was performed using, and features were extracted from, an open sketch data set using a data-driven deep learning approach through a convolutional neural network. Later, the learned features were transferred to our collected data set to further train the classifier. The first data set was collected using pen and paper for the traditional method. The second data set used a tablet and smart pen for data collection. The system's performance was then evaluated using the data sets. RESULTS: The performance of the designed system when using the data set that was collected using the traditional pen and paper method resulted in a mean area under the receiver operating characteristic curve (AUROC) of 0.913 (SD 0.004) when distinguishing between patients with MCI and HCs. On the other hand, when discriminating between patients with AD and HCs, the mean AUROC was 0.950 (SD 0.003) when using the data set that was collected using the digitalized method. CONCLUSIONS: The automatic ROCF test scoring system that we designed showed satisfying results for differentiating between patients with AD and MCI and HCs. Comparatively, our proposed network architecture provided better performance than our previous work, which did not include data augmentation and dropout techniques. In addition, it also performed better than other existing network architectures, such as AlexNet and Sketch-a-Net, with transfer learning techniques. The proposed system can be incorporated with other tests to assist clinicians in the early diagnosis of AD and to reduce the physical and mental burden on patients' family and friends.

Assessing Schizophrenia Patients Through Linguistic and Acoustic Features Using Deep Learning Techniques.

Thought, language, and communication disorders are among the salient characteristics of schizophrenia. Such impairments are often exhibited in patients' conversations. Researches have shown that assessments of thought disorder are crucial for tracking the clinical patients' conditions and early detection of clinical high-risks. Detecting such symptoms require a trained clinician's expertise, which is prohibitive due to cost and the high patient-to-clinician ratio. In this paper, we propose a machine learning method using Transformer-based model to help automate the assessment of the severity of the thought disorder of schizophrenia. The proposed model uses both textual and acoustic speech between occupational therapists or psychiatric nurses and schizophrenia patients to predict the level of their thought disorder. Experimental results show that the proposed model has the ability to closely predict the results of assessments for Schizophrenia patients base on the extracted semantic, syntactic and acoustic features. Thus, we believe our model can be a helpful tool to doctors when they are assessing schizophrenia patients.

Identifying Mild Cognitive Impairment by Using Human-Robot Interactions.

BACKGROUND: Mild cognitive impairment (MCI), which is common in older adults, is a risk factor for dementia. Rapidly growing health care demand associated with global population aging has spurred the development of new digital tools for the assessment of cognitive performance in older adults. OBJECTIVE: To overcome methodological drawbacks of previous studies (e.g., use of potentially imprecise screening tools that fail to include patients with MCI), this study investigated the feasibility of assessing multiple cognitive functions in older adults with and without MCI by using a social robot. METHODS: This study included 33 older adults with or without MCI and 33 healthy young adults. We examined the utility of five robotic cognitive tests focused on language, episodic memory, prospective memory, and aspects of executive function to classify age-associated cognitive changes versus MCI. Standardized neuropsychological tests were collected to validate robotic test performance. RESULTS: The assessment was well received by all participants. Robotic tests assessing delayed episodic memory, prospective memory, and aspects of executive function were optimal for differentiating between older adults with and without MCI, whereas the global cognitive test (i.e., Mini-Mental State Examination) failed to capture such subtle cognitive differences among older adults. Furthermore, robot-administered tests demonstrated sound ability to predict the results of standardized cognitive tests, even after adjustment for demographic variables and global cognitive status. CONCLUSION: Overall, our results suggest the human-robot interaction approach is feasible for MCI identification. Incorporating additional cognitive test measures might improve the stability and reliability of such robot-assisted MCI diagnoses.

Development and Validation of an Integrated Healthy Workplace Management Model in Taiwan

Background@#Impacts of exposure are generally monitored and recorded after injuries or illness occur. Yet, absence of conventional after-the-effect impacts (i.e., lagging indicators), tend to focus on physical health and injuries, and fail to inform if workers are not exposed to safety and health hazards. In contrast to lagging indicators, leading indicators are proactive, preventive, and predictive indexes that offer insights how effective safety and health. The present study is to validate an extended Voluntary Protection Programs (VPP) that consists of six leading indicators. @*Methods@#Questionnaires were distributed to 13 organizations (response rate = 93.1%, 1,439 responses) in Taiwan. Cronbach α, multiple linear regression and canonical correlation were used to test the reliability of the extended Voluntary Protection Programs (VPP) which consists of six leading indicators (safe climate, transformational leadership, organizational justice, organizational support, hazard prevention and control, and training). Criteria-related validation strategy was applied to examine relationships of six leading indicators with six criteria (perceived health, burnout, depression, job satisfaction, job performance, and life satisfaction). @*Results@#The results showed that the Cronbach's α of six leading indicators ranged from 0.87 to 0.92. The canonical correlation analysis indicated a positive correlation between the six leading indicators and criteria (1st canonical function: correlation = 0.647, square correlation = 0.419, p < 0.001). @*Conclusions@#The present study validates the extended VPP framework that focuses on promoting safety and physical and mental health. Results further provides applications of the extended VPP framework to promote workers' safety and health.

A Novel Deep Learning-Based System for Triage in the Emergency Department Using Electronic Medical Records: Retrospective Cohort Study.

BACKGROUND: Emergency department (ED) crowding has resulted in delayed patient treatment and has become a universal health care problem. Although a triage system, such as the 5-level emergency severity index, somewhat improves the process of ED treatment, it still heavily relies on the nurse's subjective judgment and triages too many patients to emergency severity index level 3 in current practice. Hence, a system that can help clinicians accurately triage a patient's condition is imperative. OBJECTIVE: This study aims to develop a deep learning-based triage system using patients' ED electronic medical records to predict clinical outcomes after ED treatments. METHODS: We conducted a retrospective study using data from an open data set from the National Hospital Ambulatory Medical Care Survey from 2012 to 2016 and data from a local data set from the National Taiwan University Hospital from 2009 to 2015. In this study, we transformed structured data into text form and used convolutional neural networks combined with recurrent neural networks and attention mechanisms to accomplish the classification task. We evaluated our performance using area under the receiver operating characteristic curve (AUROC). RESULTS: A total of 118,602 patients from the National Hospital Ambulatory Medical Care Survey were included in this study for predicting hospitalization, and the accuracy and AUROC were 0.83 and 0.87, respectively. On the other hand, an external experiment was to use our own data set from the National Taiwan University Hospital that included 745,441 patients, where the accuracy and AUROC were similar, that is, 0.83 and 0.88, respectively. Moreover, to effectively evaluate the prediction quality of our proposed system, we also applied the model to other clinical outcomes, including mortality and admission to the intensive care unit, and the results showed that our proposed method was approximately 3% to 5% higher in accuracy than other conventional methods. CONCLUSIONS: Our proposed method achieved better performance than the traditional method, and its implementation is relatively easy, it includes commonly used variables, and it is better suited for real-world clinical settings. It is our future work to validate our novel deep learning-based triage algorithm with prospective clinical trials, and we hope to use it to guide resource allocation in a busy ED once the validation succeeds.

Social Robots for Evaluating Attention State in Older Adults.

Sustained attention is essential for older adults to maintain an active lifestyle, and the deficiency of this function is often associated with health-related risks such as falling and frailty. The present study examined whether the well-established age-effect on reducing mind-wandering, the drift to internal thoughts that are seen to be detrimental to attentional control, could be replicated by using a robotic experimenter for older adults who are not as familiar with online technologies. A total of 28 younger and 22 older adults performed a Sustained Attention to Response Task (SART) by answering thought probes regarding their attention states and providing confidence ratings for their own task performances. The indices from the modified SART suggested a well-documented conservative response strategy endorsed by older adults, which were represented by slower responses and increased omission errors. Moreover, the slower responses and increased omissions were found to be associated with less self-reported mind-wandering, thus showing consistency with their higher subjective ratings of attentional control. Overall, this study demonstrates the potential of constructing age-related cognitive profiles with attention evaluation instruction based on a social companion robot for older adults at home.

An efficient context-aware screening system for Alzheimer's disease based on neuropsychology test.

Alzheimer's disease (AD) and other dementias have become the fifth leading cause of death worldwide. Accurate early detection of the disease and its precursor, Mild Cognitive Impairment (MCI), is crucial to alleviate the burden on the healthcare system. While most of the existing work in the literature applied neural networks directly together with several data pre-processing techniques, we proposed in this paper a screening system that is to perform classification based on automatic processing of the transcripts of speeches from the subjects undertaking a neuropsychological test. Our system is also shown applicable to different datasets and languages, suggesting that our system holds a high potential to be deployed widely in hospitals across regions. We conducted comprehensive experiments on two different languages datasets, the Pitt dataset and the NTUHV dataset, to validate our study. The results showed that our proposed system significantly outperformed the previous works on both datasets, with the score of the area under the receiver operating characteristic curve (AUROC) of classifying AD and healthy control (HC) being as high as 0.92 on the Pitt dataset and 0.97 on the NTUHV dataset. The performance on classifying MCI and HC remained promising, with the AUROC being 0.83 on the Pitt dataset and 0.88 on the NTUHV dataset.

Online Gait Detection with an Automatic Mobile Trainer Inspired by Neuro-Developmental Treatment.

This paper demonstrates the development of an automatic mobile trainer employing inertial movement units (IMUs). The device is inspired by Neuro-Developmental Treatment (NDT), which is an effective rehabilitation method for stroke patients that promotes the relearning of motor skills by repeated training. However, traditional NDT training is very labor intensive and time consuming for therapists, thus, stroke patients usually cannot receive sufficient rehabilitation training. Therefore, we developed a mobile assisted device that can automatically repeat the therapists' intervention and help increase patient training time. The proposed mobile trainer, which allows the users to move at their preferred speeds, consists of three systems: the gait detection system, the motor control system, and the movable mechanism. The gait detection system applies IMUs to detect the user's gait events and triggers the motor control system accordingly. The motor control system receives the triggering signals and imitates the therapist's intervention patterns by robust control. The movable mechanism integrates these first two systems to form a mobile gait-training device. Finally, we conducted preliminary tests and defined two performance indexes to evaluate the effectiveness of the proposed trainer. Based on the results, the mobile trainer is deemed successful at improving the testing subjects' walking ability.

The effect of electroacupuncture merged with rehabilitation for frozen shoulder syndrome: A single-blind randomized sham-acupuncture controlled study.

PURPOSE: Frozen shoulder syndrome (FSS) causes pain and reduces the range of motion in the shoulder joint. To investigate the short and medium-term effects of electroacupuncture in people with FSS, we evaluated the therapeutic effects of true and sham electroacupuncture on pain relief and improvement of shoulder function. METHODS: In this randomized, single-blind controlled clinical trial, 21 subjects with FSS were randomly assigned to two groups: a true electroacupuncture group (TEAG) and a sham electroacupuncture group (SEAG). The two groups underwent 18 sessions of treatment over approximately 6-9 weeks and were then followed up at 1, 3, and 6 months. Their effectiveness for alleviating the intensity of shoulder pain was evaluated with a visual analog scale (VAS), while improved shoulder mobility was evaluated by the active range of motion (AROM) and passive range of motion (PROM), and shoulder functional ability was evaluated using the Shoulder Pain and Disability Index (SPADI). RESULTS: It demonstrated that the TEAG or SEAG showed lasting effects at 1, 3, and 6 months, although with no significant difference between these two groups in the shoulder functional ability outcomes. However, the decline in the VAS occurred earlier in the TEAG than the SEAG. Also, there was much more improvement in AROM for flexion and abduction in the TEAG than the SEAG. An increase in the abduction angle after electroacupuncture and manual rehabilitation was also apparent. CONCLUSION: These results suggest that electroacupuncture plus rehabilitation may provide earlier pain relief for patients with FSS and could be applied clinically.

An Automatic Assessment System for Alzheimer's Disease Based on Speech Using Feature Sequence Generator and Recurrent Neural Network.

Alzheimer disease and other dementias have become the 7th cause of death worldwide. Still lacking a cure, an early detection of the disease in order to provide the best intervention is crucial. To develop an assessment system for the general public, speech analysis is the optimal solution since it reflects the speaker's cognitive skills abundantly and data collection is relatively inexpensive compared with brain imaging, blood testing, etc. While most of the existing literature extracted statistics-based features and relied on a feature selection process, we have proposed a novel Feature Sequence representation and utilized a data-driven approach, namely, the recurrent neural network to perform classification in this study. The system is also shown to be fully-automated, which implies the system can be deployed widely to all places easily. To validate our study, a series of experiments have been conducted with 120 speech samples, and the score in terms of the area under the receiver operating characteristic curve is as high as 0.838.

Assistive Control System for Upper Limb Rehabilitation Robot.

This paper presents an assistive control system with a special kinematic structure of an upper limb rehabilitation robot embedded with force/torque sensors. A dynamic human model integrated with sensing torque is used to simulate human interaction under three rehabilitation modes: active mode, assistive mode, and passive mode. The hereby proposed rehabilitation robot, called NTUH-ARM, provides 7 degree-of- freedom (DOF) motion and runs subject to an inherent mapping between the 7 DOFs of the robot arm and the 4 DOFs of the human arm. The Lyapunov theory is used to analyze the stability of the proposed controller design. Clinical trials have been conducted with six patients, one of which acts as a control. The results of these experiments are positive and STREAM assessment by physical therapists also reveals promising results.