A. Maxin, Do H Lim, Sophie Kush, Jack Carpenter, Rami Shaibani, Bernice G Gulek, Kimberly G. Harmon, A. Mariakakis, Lynn B McGrath, Michael R. Levitt
Quantitative pupillometry is used in mild traumatic brain injury (mTBI) with changes in pupil reactivity noted after blast injury, chronic mTBI, and sports-related concussion. We evaluated the diagnostic capabilities of a smartphone-based digital pupillometer to differentiate patients with mTBI in the emergency department from controls. Adult patients diagnosed with acute mTBI with normal neuroimaging were evaluated in an emergency department within 36 hours of injury (control group: healthy adults). The PupilScreen smartphone pupillometer was used to measure the pupillary light reflex (PLR), and quantitative curve morphological parameters of the PLR were compared between mTBI and healthy controls. To address the class imbalance in our sample, a synthetic minority oversampling technique was applied. All possible combinations of PLR parameters produced by the smartphone pupillometer were then applied as features to 4 binary classification machine learning algorithms: random forest, k-nearest neighbors, support vector machine, and logistic regression. A 10-fold cross-validation technique stratified by cohort was used to produce accuracy, sensitivity, specificity, area under the curve, and F1-score metrics for the classification of mTBI versus healthy participants. Of 12 patients with acute mTBI, 33% (4/12) were female (mean age 54.1, SD 22.2 years), and 58% (7/12) were White with a median Glasgow Coma Scale (GCS) of 15. Of the 132 healthy patients, 67% (88/132) were female, with a mean age of 36 (SD 10.2) years and 64% (84/132) were White with a median GCS of 15. Significant differences were observed in PLR recordings between healthy controls and patients with acute mTBI in the PLR parameters, that are (1) percent change (mean 34%, SD 8.3% vs mean 26%, SD 7.9%; P<.001), (2) minimum pupillary diameter (mean 34.8, SD 6.1 pixels vs mean 29.7, SD 6.1 pixels; P=.004), (3) maximum pupillary diameter (mean 53.6, SD 12.4 pixels vs mean 40.9, SD 11.9 pixels; P<.001), and (4) mean constriction velocity (mean 11.5, SD 5.0 pixels/second vs mean 6.8, SD 3.0 pixels/second; P<.001) between cohorts. After the synthetic minority oversampling technique, both cohorts had a sample size of 132 recordings. The best-performing binary classification model was a random forest model using the PLR parameters of latency, percent change, maximum diameter, minimum diameter, mean constriction velocity, and maximum constriction velocity as features. This model produced an overall accuracy of 93.5%, sensitivity of 96.2%, specificity of 90.9%, area under the curve of 0.936, and F1-score of 93.7% for differentiating between pupillary changes in mTBI and healthy participants. The absolute values are unable to be provided for the performance percentages reported here due to the mechanism of 10-fold cross validation that was used to obtain them. In this pilot study, quantitative smartphone pupillometry demonstrates the potential to be a useful tool in th
{"title":"Smartphone Pupillometry and Machine Learning for Detection of Acute Mild Traumatic Brain Injury: Cohort Study","authors":"A. Maxin, Do H Lim, Sophie Kush, Jack Carpenter, Rami Shaibani, Bernice G Gulek, Kimberly G. Harmon, A. Mariakakis, Lynn B McGrath, Michael R. Levitt","doi":"10.2196/58398","DOIUrl":"https://doi.org/10.2196/58398","url":null,"abstract":"\u0000 \u0000 Quantitative pupillometry is used in mild traumatic brain injury (mTBI) with changes in pupil reactivity noted after blast injury, chronic mTBI, and sports-related concussion.\u0000 \u0000 \u0000 \u0000 We evaluated the diagnostic capabilities of a smartphone-based digital pupillometer to differentiate patients with mTBI in the emergency department from controls.\u0000 \u0000 \u0000 \u0000 Adult patients diagnosed with acute mTBI with normal neuroimaging were evaluated in an emergency department within 36 hours of injury (control group: healthy adults). The PupilScreen smartphone pupillometer was used to measure the pupillary light reflex (PLR), and quantitative curve morphological parameters of the PLR were compared between mTBI and healthy controls. To address the class imbalance in our sample, a synthetic minority oversampling technique was applied. All possible combinations of PLR parameters produced by the smartphone pupillometer were then applied as features to 4 binary classification machine learning algorithms: random forest, k-nearest neighbors, support vector machine, and logistic regression. A 10-fold cross-validation technique stratified by cohort was used to produce accuracy, sensitivity, specificity, area under the curve, and F1-score metrics for the classification of mTBI versus healthy participants.\u0000 \u0000 \u0000 \u0000 Of 12 patients with acute mTBI, 33% (4/12) were female (mean age 54.1, SD 22.2 years), and 58% (7/12) were White with a median Glasgow Coma Scale (GCS) of 15. Of the 132 healthy patients, 67% (88/132) were female, with a mean age of 36 (SD 10.2) years and 64% (84/132) were White with a median GCS of 15. Significant differences were observed in PLR recordings between healthy controls and patients with acute mTBI in the PLR parameters, that are (1) percent change (mean 34%, SD 8.3% vs mean 26%, SD 7.9%; P<.001), (2) minimum pupillary diameter (mean 34.8, SD 6.1 pixels vs mean 29.7, SD 6.1 pixels; P=.004), (3) maximum pupillary diameter (mean 53.6, SD 12.4 pixels vs mean 40.9, SD 11.9 pixels; P<.001), and (4) mean constriction velocity (mean 11.5, SD 5.0 pixels/second vs mean 6.8, SD 3.0 pixels/second; P<.001) between cohorts. After the synthetic minority oversampling technique, both cohorts had a sample size of 132 recordings. The best-performing binary classification model was a random forest model using the PLR parameters of latency, percent change, maximum diameter, minimum diameter, mean constriction velocity, and maximum constriction velocity as features. This model produced an overall accuracy of 93.5%, sensitivity of 96.2%, specificity of 90.9%, area under the curve of 0.936, and F1-score of 93.7% for differentiating between pupillary changes in mTBI and healthy participants. The absolute values are unable to be provided for the performance percentages reported here due to the mechanism of 10-fold cross validation that was used to obtain them.\u0000 \u0000 \u0000 \u0000 In this pilot study, quantitative smartphone pupillometry demonstrates the potential to be a useful tool in th","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"48 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141347654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ilana Lefkovitz, Samantha Walsh, L. J. Blank, Nathalie Jetté, Benjamin R Kummer
Natural language processing (NLP), a branch of artificial intelligence that analyzes unstructured language, is being increasingly used in health care. However, the extent to which NLP has been formally studied in neurological disorders remains unclear. We sought to characterize studies that applied NLP to the diagnosis, prediction, or treatment of common neurological disorders. This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) standards. The search was conducted using MEDLINE and Embase on May 11, 2022. Studies of NLP use in migraine, Parkinson disease, Alzheimer disease, stroke and transient ischemic attack, epilepsy, or multiple sclerosis were included. We excluded conference abstracts, review papers, as well as studies involving heterogeneous clinical populations or indirect clinical uses of NLP. Study characteristics were extracted and analyzed using descriptive statistics. We did not aggregate measurements of performance in our review due to the high variability in study outcomes, which is the main limitation of the study. In total, 916 studies were identified, of which 41 (4.5%) met all eligibility criteria and were included in the final review. Of the 41 included studies, the most frequently represented disorders were stroke and transient ischemic attack (n=20, 49%), followed by epilepsy (n=10, 24%), Alzheimer disease (n=6, 15%), and multiple sclerosis (n=5, 12%). We found no studies of NLP use in migraine or Parkinson disease that met our eligibility criteria. The main objective of NLP was diagnosis (n=20, 49%), followed by disease phenotyping (n=17, 41%), prognostication (n=9, 22%), and treatment (n=4, 10%). In total, 18 (44%) studies used only machine learning approaches, 6 (15%) used only rule-based methods, and 17 (41%) used both. We found that NLP was most commonly applied for diagnosis, implying a potential role for NLP in augmenting diagnostic accuracy in settings with limited access to neurological expertise. We also found several gaps in neurological NLP research, with few to no studies addressing certain disorders, which may suggest additional areas of inquiry. Prospective Register of Systematic Reviews (PROSPERO) CRD42021228703; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=228703
{"title":"Direct Clinical Applications of Natural Language Processing in Common Neurological Disorders: Scoping Review","authors":"Ilana Lefkovitz, Samantha Walsh, L. J. Blank, Nathalie Jetté, Benjamin R Kummer","doi":"10.2196/51822","DOIUrl":"https://doi.org/10.2196/51822","url":null,"abstract":"\u0000 \u0000 Natural language processing (NLP), a branch of artificial intelligence that analyzes unstructured language, is being increasingly used in health care. However, the extent to which NLP has been formally studied in neurological disorders remains unclear.\u0000 \u0000 \u0000 \u0000 We sought to characterize studies that applied NLP to the diagnosis, prediction, or treatment of common neurological disorders.\u0000 \u0000 \u0000 \u0000 This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) standards. The search was conducted using MEDLINE and Embase on May 11, 2022. Studies of NLP use in migraine, Parkinson disease, Alzheimer disease, stroke and transient ischemic attack, epilepsy, or multiple sclerosis were included. We excluded conference abstracts, review papers, as well as studies involving heterogeneous clinical populations or indirect clinical uses of NLP. Study characteristics were extracted and analyzed using descriptive statistics. We did not aggregate measurements of performance in our review due to the high variability in study outcomes, which is the main limitation of the study.\u0000 \u0000 \u0000 \u0000 In total, 916 studies were identified, of which 41 (4.5%) met all eligibility criteria and were included in the final review. Of the 41 included studies, the most frequently represented disorders were stroke and transient ischemic attack (n=20, 49%), followed by epilepsy (n=10, 24%), Alzheimer disease (n=6, 15%), and multiple sclerosis (n=5, 12%). We found no studies of NLP use in migraine or Parkinson disease that met our eligibility criteria. The main objective of NLP was diagnosis (n=20, 49%), followed by disease phenotyping (n=17, 41%), prognostication (n=9, 22%), and treatment (n=4, 10%). In total, 18 (44%) studies used only machine learning approaches, 6 (15%) used only rule-based methods, and 17 (41%) used both.\u0000 \u0000 \u0000 \u0000 We found that NLP was most commonly applied for diagnosis, implying a potential role for NLP in augmenting diagnostic accuracy in settings with limited access to neurological expertise. We also found several gaps in neurological NLP research, with few to no studies addressing certain disorders, which may suggest additional areas of inquiry.\u0000 \u0000 \u0000 \u0000 Prospective Register of Systematic Reviews (PROSPERO) CRD42021228703; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=228703\u0000","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"54 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141112826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alba Prats-Bisbe, Jaume López-Carballo, A. García-Molina, David Leno-Colorado, A. García-Rudolph, E. Opisso, Raimon Jané
Acquired brain injury (ABI) is a prominent cause of disability globally, with virtual reality (VR) emerging as a promising aid in neurorehabilitation. Nonetheless, the diversity among VR interventions can result in inconsistent outcomes and pose challenges in determining efficacy. Recent reviews offer best practice recommendations for designing and implementing therapeutic VR interventions to evaluate the acceptance of fully immersive VR interventions. This study aims to evaluate the usability and feasibility of a co-designed VR-based neurorehabilitation support tool by conducting multiple proof-of-concept trials in a sample of patients with ABI within a hospital setting. A single session deploying custom immersive serious games to train cognitive functions using a new-generation head-mounted display was conducted among a sample of inpatients with ABI. Structured questionnaires were administered at the end of the session to evaluate the usability of the system and the intervention, participants’ familiarity with the technology, and any adverse effects related to cybersickness. Additionally, the training duration while wearing the headset and the demographic characteristics of the participants were considered. A total of 20 patients with ABI participated in a 1-hour proof-of-concept trial. The mean usability score was 37 (SD 2.6) out of 40, the technology familiarity level was 9.2 (SD 2.9) out of 12, and the Simulator Sickness Questionnaire total score was 1.3 (SD 2). On average, participants wore the headset for approximately 25.6 (SD 4.7) minutes during the intervention. There were no substantial differences in usability and technology familiarity levels based on patients’ etiology or age, with no notable symptoms of cybersickness reported. Significantly strong correlations were noted between cybersickness symptoms and various usability categories, including exposure, motivation, interactivity, task specificity, and immersion aspects. Further, there was a significant association between the intervention time and the number of tasks performed (P<.001). Furthermore, patients who derived enjoyment from VR sessions expressed a heightened interest in incorporating VR into their daily neurorehabilitation practice (P<.001). Moreover, oculomotor issues were found to be highly sensitive to the onset of disorientation sickness symptoms (P<.001). Through a collaborative approach, this study showcases the usability and feasibility of a VR-based support tool for cognitive rehabilitation among inpatients with ABI. Key components of such interventions encompass a multidisciplinary array of immersive experiences integrating neurorehabilitation principles and serious games techniques.
{"title":"Virtual Reality–Based Neurorehabilitation Support Tool for People With Cognitive Impairments Resulting From an Acquired Brain Injury: Usability and Feasibility Study","authors":"Alba Prats-Bisbe, Jaume López-Carballo, A. García-Molina, David Leno-Colorado, A. García-Rudolph, E. Opisso, Raimon Jané","doi":"10.2196/50538","DOIUrl":"https://doi.org/10.2196/50538","url":null,"abstract":"\u0000 \u0000 Acquired brain injury (ABI) is a prominent cause of disability globally, with virtual reality (VR) emerging as a promising aid in neurorehabilitation. Nonetheless, the diversity among VR interventions can result in inconsistent outcomes and pose challenges in determining efficacy. Recent reviews offer best practice recommendations for designing and implementing therapeutic VR interventions to evaluate the acceptance of fully immersive VR interventions.\u0000 \u0000 \u0000 \u0000 This study aims to evaluate the usability and feasibility of a co-designed VR-based neurorehabilitation support tool by conducting multiple proof-of-concept trials in a sample of patients with ABI within a hospital setting.\u0000 \u0000 \u0000 \u0000 A single session deploying custom immersive serious games to train cognitive functions using a new-generation head-mounted display was conducted among a sample of inpatients with ABI. Structured questionnaires were administered at the end of the session to evaluate the usability of the system and the intervention, participants’ familiarity with the technology, and any adverse effects related to cybersickness. Additionally, the training duration while wearing the headset and the demographic characteristics of the participants were considered.\u0000 \u0000 \u0000 \u0000 A total of 20 patients with ABI participated in a 1-hour proof-of-concept trial. The mean usability score was 37 (SD 2.6) out of 40, the technology familiarity level was 9.2 (SD 2.9) out of 12, and the Simulator Sickness Questionnaire total score was 1.3 (SD 2). On average, participants wore the headset for approximately 25.6 (SD 4.7) minutes during the intervention. There were no substantial differences in usability and technology familiarity levels based on patients’ etiology or age, with no notable symptoms of cybersickness reported. Significantly strong correlations were noted between cybersickness symptoms and various usability categories, including exposure, motivation, interactivity, task specificity, and immersion aspects. Further, there was a significant association between the intervention time and the number of tasks performed (P<.001). Furthermore, patients who derived enjoyment from VR sessions expressed a heightened interest in incorporating VR into their daily neurorehabilitation practice (P<.001). Moreover, oculomotor issues were found to be highly sensitive to the onset of disorientation sickness symptoms (P<.001).\u0000 \u0000 \u0000 \u0000 Through a collaborative approach, this study showcases the usability and feasibility of a VR-based support tool for cognitive rehabilitation among inpatients with ABI. Key components of such interventions encompass a multidisciplinary array of immersive experiences integrating neurorehabilitation principles and serious games techniques.\u0000","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"38 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140234481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Joaquín Amigó-Vega, Maarten C Ottenhoff, Maxime Verwoert, Pieter Kubben, Christian Herff
Background Recording time in invasive neuroscientific research is limited and must be used as efficiently as possible. Time is often lost due to a long setup time and errors by the researcher, driven by the number of manually performed steps. Currently, recording solutions that automate experimental overhead are either custom-made by researchers or provided as a submodule in comprehensive neuroscientific toolboxes, and there are no platforms focused explicitly on recording. Objective Minimizing the number of manual actions may reduce error rates and experimental overhead. However, automation should avoid reducing the flexibility of the system. Therefore, we developed a software package named T-REX (Standalone Recorder of Experiments) that specifically simplifies the recording of experiments while focusing on retaining flexibility. Methods The proposed solution is a standalone webpage that the researcher can provide without an active internet connection. It is built using Bootstrap5 for the frontend and the Python package Flask for the backend. Only Python 3.7+ and a few dependencies are required to start the different experiments. Data synchronization is implemented using Lab Streaming Layer, an open-source networked synchronization ecosystem, enabling all major programming languages and toolboxes to be used for developing and executing the experiments. Additionally, T-REX runs on Windows, Linux, and macOS. Results The system reduces experimental overhead during recordings to a minimum. Multiple experiments are centralized in a simple local web interface that reduces an experiment’s setup, start, and stop to a single button press. In principle, any type of experiment, regardless of the scientific field (eg, behavioral or cognitive sciences, and electrophysiology), can be executed with the platform. T-REX includes an easy-to-use interface that can be adjusted to specific recording modalities, amplifiers, and participants. Because of the automated setup, easy recording, and easy-to-use interface, participants may even start and stop experiments by themselves, thus potentially providing data without the researcher’s presence. Conclusions We developed a new recording platform that is operating system independent, user friendly, and robust. We provide researchers with a solution that can greatly increase the time spent on recording instead of setting up (with its possible errors).
背景:在侵入性神经科学研究中，记录时间是有限的，必须尽可能有效地利用。由于手动执行步骤的数量，研究人员的设置时间和错误经常导致时间损失。目前，自动化实验开销的记录解决方案要么是由研究人员定制的，要么是作为综合神经科学工具箱中的子模块提供的，而且没有明确专注于记录的平台。目的尽量减少人工操作的次数，降低错误率和实验开销。但是，自动化应该避免降低系统的灵活性。因此，我们开发了一个名为T-REX (Standalone Recorder of Experiments)的软件包，专门简化实验记录，同时注重保持灵活性。提出的解决方案是一个独立的网页，研究人员可以提供没有一个活跃的互联网连接。它使用Bootstrap5作为前端，使用Python包Flask作为后端。启动不同的实验只需要Python 3.7+和一些依赖项。数据同步使用Lab Streaming Layer实现，这是一个开源的网络同步生态系统，可以使用所有主要的编程语言和工具箱来开发和执行实验。此外，T-REX可以在Windows、Linux和macOS上运行。结果该系统将记录过程中的实验开销降至最低。多个实验集中在一个简单的本地web界面，减少了实验的设置，开始和停止到一个单一的按钮按下。原则上，任何类型的实验，无论科学领域(例如，行为或认知科学，以及电生理学)，都可以在平台上执行。T-REX包括一个易于使用的界面，可以调整到特定的记录模式，放大器和参与者。由于自动设置，易于记录和易于使用的界面，参与者甚至可以自己开始和停止实验，从而有可能在没有研究人员在场的情况下提供数据。结论我们开发了一种新的录音平台，该平台与操作系统无关，用户友好，功能强大。我们为研究人员提供了一种解决方案，可以大大增加花费在记录上的时间，而不是设置(可能存在错误)。
{"title":"The Easy and Versatile Neural Recording Platform (T-REX): Design and Development Study","authors":"Joaquín Amigó-Vega, Maarten C Ottenhoff, Maxime Verwoert, Pieter Kubben, Christian Herff","doi":"10.2196/47881","DOIUrl":"https://doi.org/10.2196/47881","url":null,"abstract":"Background Recording time in invasive neuroscientific research is limited and must be used as efficiently as possible. Time is often lost due to a long setup time and errors by the researcher, driven by the number of manually performed steps. Currently, recording solutions that automate experimental overhead are either custom-made by researchers or provided as a submodule in comprehensive neuroscientific toolboxes, and there are no platforms focused explicitly on recording. Objective Minimizing the number of manual actions may reduce error rates and experimental overhead. However, automation should avoid reducing the flexibility of the system. Therefore, we developed a software package named T-REX (Standalone Recorder of Experiments) that specifically simplifies the recording of experiments while focusing on retaining flexibility. Methods The proposed solution is a standalone webpage that the researcher can provide without an active internet connection. It is built using Bootstrap5 for the frontend and the Python package Flask for the backend. Only Python 3.7+ and a few dependencies are required to start the different experiments. Data synchronization is implemented using Lab Streaming Layer, an open-source networked synchronization ecosystem, enabling all major programming languages and toolboxes to be used for developing and executing the experiments. Additionally, T-REX runs on Windows, Linux, and macOS. Results The system reduces experimental overhead during recordings to a minimum. Multiple experiments are centralized in a simple local web interface that reduces an experiment’s setup, start, and stop to a single button press. In principle, any type of experiment, regardless of the scientific field (eg, behavioral or cognitive sciences, and electrophysiology), can be executed with the platform. T-REX includes an easy-to-use interface that can be adjusted to specific recording modalities, amplifiers, and participants. Because of the automated setup, easy recording, and easy-to-use interface, participants may even start and stop experiments by themselves, thus potentially providing data without the researcher’s presence. Conclusions We developed a new recording platform that is operating system independent, user friendly, and robust. We provide researchers with a solution that can greatly increase the time spent on recording instead of setting up (with its possible errors).","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135317337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background One of the bottlenecks of visualization research is the lack of volunteers for studies that evaluate new methods and paradigms. The increased availability of web-based marketplaces, combined with the possibility of implementing volume rendering, a computationally expensive method, on mobile devices, has opened the door for using gamification in the context of medical image visualization studies. Objective We aimed to describe a gamified study that we conducted with the goal of comparing several cerebrovascular visualization techniques and to evaluate whether gamification is a valid paradigm for conducting user studies in the domain of medical imaging. Methods The study was implemented in the form of a mobile game, Connect Brain, which was developed and distributed on both Android (Google LLC) and iOS (Apple Inc) platforms. Connect Brain features 2 minigames: one asks the player to make decisions about the depth of different vessels, and the other asks the player to determine whether 2 vessels are connected. Results The gamification paradigm, which allowed us to collect many data samples (5267 and 1810 for the depth comparison and vessel connectivity tasks, respectively) from many participants (N=111), yielded similar results regarding the effectiveness of visualization techniques to those of smaller in-laboratory studies. Conclusions The results of our study suggest that the gamification paradigm not only is a viable alternative to traditional in-laboratory user studies but could also present some advantages.
{"title":"Connect Brain, a Mobile App for Studying Depth Perception in Angiography Visualization: Gamification Study","authors":"Andrey Titov, Simon Drouin, Marta Kersten-Oertel","doi":"10.2196/45828","DOIUrl":"https://doi.org/10.2196/45828","url":null,"abstract":"Background One of the bottlenecks of visualization research is the lack of volunteers for studies that evaluate new methods and paradigms. The increased availability of web-based marketplaces, combined with the possibility of implementing volume rendering, a computationally expensive method, on mobile devices, has opened the door for using gamification in the context of medical image visualization studies. Objective We aimed to describe a gamified study that we conducted with the goal of comparing several cerebrovascular visualization techniques and to evaluate whether gamification is a valid paradigm for conducting user studies in the domain of medical imaging. Methods The study was implemented in the form of a mobile game, Connect Brain, which was developed and distributed on both Android (Google LLC) and iOS (Apple Inc) platforms. Connect Brain features 2 minigames: one asks the player to make decisions about the depth of different vessels, and the other asks the player to determine whether 2 vessels are connected. Results The gamification paradigm, which allowed us to collect many data samples (5267 and 1810 for the depth comparison and vessel connectivity tasks, respectively) from many participants (N=111), yielded similar results regarding the effectiveness of visualization techniques to those of smaller in-laboratory studies. Conclusions The results of our study suggest that the gamification paradigm not only is a viable alternative to traditional in-laboratory user studies but could also present some advantages.","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Natarajan Sriraam, S. Raghu, Erik D Gommer, Danny M W Hilkman, Yasin Temel, Shyam Vasudeva Rao, AS Hegde, Pieter Kubben
{"title":"Application of Low-cost Mobile Health for Remote Monitoring of Epilepsy Patients (Preprint)","authors":"Natarajan Sriraam, S. Raghu, Erik D Gommer, Danny M W Hilkman, Yasin Temel, Shyam Vasudeva Rao, AS Hegde, Pieter Kubben","doi":"10.2196/50660","DOIUrl":"https://doi.org/10.2196/50660","url":null,"abstract":"","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"2012 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139361423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Andrews, M. Craven, B. Guo, J. Weyer, Simon Lees, S. Zormpas, S. Thorpe, Julie Devonshire, V. San Antonio‐Arce, W. Whitehouse, J. Julie, Sam Malins, A. Hammers, A. Reif, H. Ruhé, F. Durbano, S. Barlati, Arjune Sen, J. Frederiksen, Alessandra Martinelli, A. Callén, J. Torras-Borrell, N. Berrocal-Izquierdo, A. Zabalza, R. Morriss, C. Hollis
Multiple sclerosis (MS), epilepsy, and depression are chronic central nervous system conditions in which remote measurement technology (RMT) may offer benefits compared with usual assessment. We previously worked with clinicians, patients, and researchers to develop 13 use cases for RMT: 5 in epilepsy (seizure alert, seizure counting, risk scoring, triage support, and trend analysis), 3 in MS (detecting silent progression, detecting depression in MS, and donating data to a biobank), and 5 in depression (detecting trends, reviewing treatment, self-management, comorbid monitoring, and carer alert). In this study, we aimed to evaluate the use cases and related implementation issues with an expert panel of clinicians external to our project consortium. We used a Delphi exercise to validate the use cases and suggest a prioritization among them and to ascertain the importance of a variety of implementation issues related to RMT. The expert panel included clinicians from across Europe who were external to the project consortium. The study had 2 survey rounds (n=23 and n=17) and a follow-up interview round (n=9). Data were analyzed for consensus between participants and for stability between survey rounds. The interviews explored the reasons for answers given in the survey. The findings showed high stability between rounds on questions related to specific use cases but lower stability on questions relating to wider issues around the implementation of RMT. Overall, questions on wider issues also had less consensus. All 5 use cases for epilepsy (seizure alert, seizure counting, risk scoring, triage support, and trend analysis) were considered beneficial, with consensus among participants above the a priori threshold for most questions, although use case 3 (risk scoring) was considered less likely to facilitate or catalyze care. There was very little consensus on the benefits of the use cases in MS, although this may have resulted from a higher dropout rate of MS clinicians (50%). Participants agreed that there would be benefits for all 5 of the depression use cases, although fewer questions on use case 4 (triage support) reached consensus agreement than for depression use cases 1 (detecting trends), 2 (reviewing treatment), 3 (self-management), and 5 (carer alert). The qualitative analysis revealed further insights into each use case and generated 8 themes on practical issues related to implementation. Overall, these findings inform the prioritization of use cases for RMT that could be developed in future work, which may include clinical trials, cost-effectiveness studies, and the commercial development of RMT products and services. Priorities for further development include the use of RMT to provide more accurate records of symptoms and treatment response than is currently possible and to provide data that could help inform patient triage and generate timely alerts for patients and carers.
{"title":"Clinical Perspectives on Using Remote Measurement Technology in Assessing Epilepsy, Multiple Sclerosis, and Depression: Delphi Study","authors":"J. Andrews, M. Craven, B. Guo, J. Weyer, Simon Lees, S. Zormpas, S. Thorpe, Julie Devonshire, V. San Antonio‐Arce, W. Whitehouse, J. Julie, Sam Malins, A. Hammers, A. Reif, H. Ruhé, F. Durbano, S. Barlati, Arjune Sen, J. Frederiksen, Alessandra Martinelli, A. Callén, J. Torras-Borrell, N. Berrocal-Izquierdo, A. Zabalza, R. Morriss, C. Hollis","doi":"10.2196/41439","DOIUrl":"https://doi.org/10.2196/41439","url":null,"abstract":"\u0000 \u0000 Multiple sclerosis (MS), epilepsy, and depression are chronic central nervous system conditions in which remote measurement technology (RMT) may offer benefits compared with usual assessment. We previously worked with clinicians, patients, and researchers to develop 13 use cases for RMT: 5 in epilepsy (seizure alert, seizure counting, risk scoring, triage support, and trend analysis), 3 in MS (detecting silent progression, detecting depression in MS, and donating data to a biobank), and 5 in depression (detecting trends, reviewing treatment, self-management, comorbid monitoring, and carer alert).\u0000 \u0000 \u0000 \u0000 In this study, we aimed to evaluate the use cases and related implementation issues with an expert panel of clinicians external to our project consortium.\u0000 \u0000 \u0000 \u0000 We used a Delphi exercise to validate the use cases and suggest a prioritization among them and to ascertain the importance of a variety of implementation issues related to RMT. The expert panel included clinicians from across Europe who were external to the project consortium. The study had 2 survey rounds (n=23 and n=17) and a follow-up interview round (n=9). Data were analyzed for consensus between participants and for stability between survey rounds. The interviews explored the reasons for answers given in the survey.\u0000 \u0000 \u0000 \u0000 The findings showed high stability between rounds on questions related to specific use cases but lower stability on questions relating to wider issues around the implementation of RMT. Overall, questions on wider issues also had less consensus. All 5 use cases for epilepsy (seizure alert, seizure counting, risk scoring, triage support, and trend analysis) were considered beneficial, with consensus among participants above the a priori threshold for most questions, although use case 3 (risk scoring) was considered less likely to facilitate or catalyze care. There was very little consensus on the benefits of the use cases in MS, although this may have resulted from a higher dropout rate of MS clinicians (50%). Participants agreed that there would be benefits for all 5 of the depression use cases, although fewer questions on use case 4 (triage support) reached consensus agreement than for depression use cases 1 (detecting trends), 2 (reviewing treatment), 3 (self-management), and 5 (carer alert). The qualitative analysis revealed further insights into each use case and generated 8 themes on practical issues related to implementation.\u0000 \u0000 \u0000 \u0000 Overall, these findings inform the prioritization of use cases for RMT that could be developed in future work, which may include clinical trials, cost-effectiveness studies, and the commercial development of RMT products and services. Priorities for further development include the use of RMT to provide more accurate records of symptoms and treatment response than is currently possible and to provide data that could help inform patient triage and generate timely alerts for patients and carers.\u0000","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84903234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tom Hähnel, Tim Feige, Julia Kunze, Andrea Epler, Anika Frank, J. Bendig, N. Schnalke, M. Wolz, P. Themann, B. Falkenburger
{"title":"Automatic Cluster Analysis using a Semantic Relatedness Model for the Phonematic and Semantic Verbal Fluency Task in Parkinson's Disease: Results from a Prospective Multicenter Study (Preprint)","authors":"Tom Hähnel, Tim Feige, Julia Kunze, Andrea Epler, Anika Frank, J. Bendig, N. Schnalke, M. Wolz, P. Themann, B. Falkenburger","doi":"10.2196/46021","DOIUrl":"https://doi.org/10.2196/46021","url":null,"abstract":"","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"78 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85525362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marc Garbey, Guillaume Joerger, Quentin Lesport, Helen Girma, Sienna McNett, Mohammad Abu-Rub, Henry Kaminski
Background: Telemedicine practice for neurological diseases has grown significantly during the COVID-19 pandemic.Telemedicine offers an opportunity to assess digitalization of examinations and enhances access to modern computer vision and artificial intelligence processing to annotate and quantify examinations in a consistent and reproducible manner. The Myasthenia Gravis Core Examination (MG-CE) has been recommended for the telemedicine evaluation of patients with myasthenia gravis.
Objective: We aimed to assess the ability to take accurate and robust measurements during the examination, which would allow improvement in workflow efficiency by making the data acquisition and analytics fully automatic and thereby limit the potential for observation bias.
Methods: We used Zoom (Zoom Video Communications) videos of patients with myasthenia gravis undergoing the MG-CE. The core examination tests required 2 broad categories of processing. First, computer vision algorithms were used to analyze videos with a focus on eye or body motions. Second, for the assessment of examinations involving vocalization, a different category of signal processing methods was required. In this way, we provide an algorithm toolbox to assist clinicians with the MG-CE. We used a data set of 6 patients recorded during 2 sessions.
Results: Digitalization and control of quality of the core examination are advantageous and let the medical examiner concentrate on the patient instead of managing the logistics of the test. This approach showed the possibility of standardized data acquisition during telehealth sessions and provided real-time feedback on the quality of the metrics the medical doctor is assessing. Overall, our new telehealth platform showed submillimeter accuracy for ptosis and eye motion. In addition, the method showed good results in monitoring muscle weakness, demonstrating that continuous analysis is likely superior to pre-exercise and post-exercise subjective assessment.
Conclusions: We demonstrated the ability to objectively quantitate the MG-CE. Our results indicate that the MG-CE should be revisited to consider some of the new metrics that our algorithm identified. We provide a proof of concept involving the MG-CE, but the method and tools developed can be applied to many neurological disorders and have great potential to improve clinical care.
背景:在2019冠状病毒病大流行期间，神经系统疾病的远程医疗实践显著增加。远程医疗提供了评估数字化检查的机会，并增强了对现代计算机视觉和人工智能处理的访问，以一致和可重复的方式注释和量化检查。重症肌无力核心检查(MG-CE)已被推荐用于重症肌无力患者的远程医疗评估。目的:我们旨在评估在检查过程中进行准确和稳健测量的能力，这将通过使数据采集和分析完全自动化来提高工作流程效率，从而限制观察偏差的可能性。方法:采用Zoom (Zoom Video Communications)视频对重症肌无力患者进行MG-CE检查。核心考试要求处理两大类问题。首先，使用计算机视觉算法来分析重点关注眼睛或身体运动的视频。其次，对于涉及发声的考试的评估，需要一种不同类型的信号处理方法。通过这种方式，我们提供了一个算法工具箱来帮助临床医生进行MG-CE。我们使用了在两个疗程中记录的6名患者的数据集。结果:核心检查的数字化和质量控制是有利的，可以让法医专注于患者，而不是管理检验的后勤工作。这种方法显示了在远程保健会议期间进行标准化数据采集的可能性，并提供了关于医生正在评估的指标质量的实时反馈。总的来说，我们的新远程医疗平台在上睑下垂和眼动方面显示了亚毫米级的精度。此外，该方法在监测肌无力方面效果良好，表明连续分析可能优于运动前和运动后的主观评价。结论:我们证明了客观定量MG-CE的能力。我们的结果表明，应该重新审视MG-CE，以考虑我们的算法确定的一些新指标。我们提供了一个涉及MG-CE的概念证明，但所开发的方法和工具可以应用于许多神经系统疾病，并具有改善临床护理的巨大潜力。
{"title":"A Digital Telehealth System to Compute the Myasthenia Gravis Core Examination Metrics.","authors":"Marc Garbey, Guillaume Joerger, Quentin Lesport, Helen Girma, Sienna McNett, Mohammad Abu-Rub, Henry Kaminski","doi":"10.2196/43387","DOIUrl":"https://doi.org/10.2196/43387","url":null,"abstract":"<p><strong>Background: </strong>Telemedicine practice for neurological diseases has grown significantly during the COVID-19 pandemic.Telemedicine offers an opportunity to assess digitalization of examinations and enhances access to modern computer vision and artificial intelligence processing to annotate and quantify examinations in a consistent and reproducible manner. The Myasthenia Gravis Core Examination (MG-CE) has been recommended for the telemedicine evaluation of patients with myasthenia gravis.</p><p><strong>Objective: </strong>We aimed to assess the ability to take accurate and robust measurements during the examination, which would allow improvement in workflow efficiency by making the data acquisition and analytics fully automatic and thereby limit the potential for observation bias.</p><p><strong>Methods: </strong>We used Zoom (Zoom Video Communications) videos of patients with myasthenia gravis undergoing the MG-CE. The core examination tests required 2 broad categories of processing. First, computer vision algorithms were used to analyze videos with a focus on eye or body motions. Second, for the assessment of examinations involving vocalization, a different category of signal processing methods was required. In this way, we provide an algorithm toolbox to assist clinicians with the MG-CE. We used a data set of 6 patients recorded during 2 sessions.</p><p><strong>Results: </strong>Digitalization and control of quality of the core examination are advantageous and let the medical examiner concentrate on the patient instead of managing the logistics of the test. This approach showed the possibility of standardized data acquisition during telehealth sessions and provided real-time feedback on the quality of the metrics the medical doctor is assessing. Overall, our new telehealth platform showed submillimeter accuracy for ptosis and eye motion. In addition, the method showed good results in monitoring muscle weakness, demonstrating that continuous analysis is likely superior to pre-exercise and post-exercise subjective assessment.</p><p><strong>Conclusions: </strong>We demonstrated the ability to objectively quantitate the MG-CE. Our results indicate that the MG-CE should be revisited to consider some of the new metrics that our algorithm identified. We provide a proof of concept involving the MG-CE, but the method and tools developed can be applied to many neurological disorders and have great potential to improve clinical care.</p>","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"2 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10334459/pdf/nihms-1900815.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9815795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jennifer S Pigott, Megan Armstrong, Elizabeth Chesterman, J. Read, D. Nimmons, K. Walters, N. Davies, A. Schrag
The COVID-19 pandemic led to many consultations being conducted remotely. Cognitive impairment is recognized as a potential barrier to remote health care interactions and is common and heterogeneous in Parkinson disease. Studies have shown remote consultations in Parkinson disease to be feasible, but little is known about real-life experience, especially for those with cognitive impairment. We explored the experiences and perceptions of remote consultations for people with Parkinson disease and cognitive impairment. This study aimed to explore the experiences of remote consultations for people with Parkinson disease and cognitive impairment from the perspective of service users and professionals and investigate considerations for future service delivery. Semistructured interviews were conducted remotely with 11 people with Parkinson disease and cognitive impairment, 10 family caregivers, and 24 health care professionals (HCPs) between 2020 and 2021. Purposive sampling was used. Interviews were audio-recorded, transcribed, and analyzed using reflexive thematic analysis. Overall, four themes were identified: “the nature of remote interactions,” “challenges exacerbated by being remote,” “expectation versus reality,” and “optimizing for the future.” Remote consultations were considered as “transactional” and less personal, with difficulties in building rapport, and considered to play a different role from that of in-person consultations. The loss of nonverbal communication and ability of HCPs to sense led to remote consultations being perceived as riskier by all groups. Issues arising from communication and cognitive impairment, balancing the voices of the person with Parkinson disease and the caregiver, and discussions of the future affect this population specifically. Remote consultations were reported to have been more successful than anticipated in all 3 groups. Obstacles were not always as expected; for example, age was less of a barrier than predicted. Video consultations were perceived as being preferable to telephone consultations by many participants, but not accessible to all people with Parkinson disease. With widespread expectation of ongoing remote consultations, potential improvements for these 3 groups and health care services were identified, including practice, preparation, increased awareness of issues, expectation management by HCPs, and more time and flexibility for consultations. Advantages and challenges of remote consultations for this population are identified. Consultations could be improved with increased support, practice, preparation, awareness of issues, and more time and flexibility within services.
{"title":"Remote Consultations for People With Parkinson Disease and Cognitive Impairment: Interview Study With Patients, Caregivers, and Health Care Professionals","authors":"Jennifer S Pigott, Megan Armstrong, Elizabeth Chesterman, J. Read, D. Nimmons, K. Walters, N. Davies, A. Schrag","doi":"10.2196/39974","DOIUrl":"https://doi.org/10.2196/39974","url":null,"abstract":"\u0000 \u0000 The COVID-19 pandemic led to many consultations being conducted remotely. Cognitive impairment is recognized as a potential barrier to remote health care interactions and is common and heterogeneous in Parkinson disease. Studies have shown remote consultations in Parkinson disease to be feasible, but little is known about real-life experience, especially for those with cognitive impairment. We explored the experiences and perceptions of remote consultations for people with Parkinson disease and cognitive impairment.\u0000 \u0000 \u0000 \u0000 This study aimed to explore the experiences of remote consultations for people with Parkinson disease and cognitive impairment from the perspective of service users and professionals and investigate considerations for future service delivery.\u0000 \u0000 \u0000 \u0000 Semistructured interviews were conducted remotely with 11 people with Parkinson disease and cognitive impairment, 10 family caregivers, and 24 health care professionals (HCPs) between 2020 and 2021. Purposive sampling was used. Interviews were audio-recorded, transcribed, and analyzed using reflexive thematic analysis.\u0000 \u0000 \u0000 \u0000 Overall, four themes were identified: “the nature of remote interactions,” “challenges exacerbated by being remote,” “expectation versus reality,” and “optimizing for the future.” Remote consultations were considered as “transactional” and less personal, with difficulties in building rapport, and considered to play a different role from that of in-person consultations. The loss of nonverbal communication and ability of HCPs to sense led to remote consultations being perceived as riskier by all groups. Issues arising from communication and cognitive impairment, balancing the voices of the person with Parkinson disease and the caregiver, and discussions of the future affect this population specifically. Remote consultations were reported to have been more successful than anticipated in all 3 groups. Obstacles were not always as expected; for example, age was less of a barrier than predicted. Video consultations were perceived as being preferable to telephone consultations by many participants, but not accessible to all people with Parkinson disease. With widespread expectation of ongoing remote consultations, potential improvements for these 3 groups and health care services were identified, including practice, preparation, increased awareness of issues, expectation management by HCPs, and more time and flexibility for consultations.\u0000 \u0000 \u0000 \u0000 Advantages and challenges of remote consultations for this population are identified. Consultations could be improved with increased support, practice, preparation, awareness of issues, and more time and flexibility within services.\u0000","PeriodicalId":73555,"journal":{"name":"JMIR neurotechnology","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91127508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：