P-wave alternans rebound following pulmonary vein isolation predicts atrial arrhythmia recurrence.

INTRODUCTION: Numerous P-wave indices have been explored as biomarkers to assess atrial fibrillation (AF) risk and the impact of therapy with variable success. OBJECTIVE: We investigated the utility of P-wave alternans (PWA) to track the effects of pulmonary vein isolation (PVI) and to predict atrial arrhythmia recurrence. METHODS: This medical records study included patients who underwent PVI for AF ablation at our institution, along with 20 control subjects without AF or overt cardiovascular disease. PWA was assessed using novel artificial intelligence-enabled modified moving average (AI-MMA) algorithms. PWA was monitored from the 12-lead ECG at ~1 h before and ~16 h after PVI (n = 45) and at the 4- to 17-week clinically indicated follow-up visit (n = 30). The arrhythmia follow-up period was 955 ± 112 days. RESULTS: PVI acutely reduced PWA by 48%-63% (p < .05) to control ranges in leads II, III, aVF, the leads with the greatest sensitivity in monitoring PWA. Pre-ablation PWA was ~6 µV and decreased to ~3 µV following ablation. Patients who exhibited a rebound in PWA to pre-ablation levels at 4- to 17-week follow-up (p < .01) experienced recurrent atrial arrhythmias, whereas patients whose PWA remained reduced (p = .85) did not, resulting in a significant difference (p < .001) at follow-up. The AUC for PWA's prediction of first recurrence of atrial arrhythmia was 0.81 (p < .01) with 88% sensitivity and 82% specificity. Kaplan-Meier analysis estimated atrial arrhythmia-free survival (p < .01) with an adjusted hazard ratio of 3.4 (95% CI: 1.47-5.24, p < .02). CONCLUSION: A rebound in PWA to pre-ablation levels detected by AI-MMA in the 12-lead ECG at standard clinical follow-up predicts atrial arrhythmia recurrence.

A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction.

People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards independently. Previous assistive technologies for the visually impaired often struggle in real-world scenarios due to the need for constant training and lack of robustness, which limits their effectiveness, especially in dynamic and unfamiliar environments, where accurate and efficient perception is crucial. Therefore, we frame our research question in this paper as: How can we assist pBLV in recognizing scenes, identifying objects, and detecting potential tripping hazards in unfamiliar environments, where existing assistive technologies often falter due to their lack of robustness? We hypothesize that by leveraging large pretrained foundation models and prompt engineering, we can create a system that effectively addresses the challenges faced by pBLV in unfamiliar environments. Motivated by the prevalence of large pretrained foundation models, particularly in assistive robotics applications, due to their accurate perception and robust contextual understanding in real-world scenarios induced by extensive pretraining, we present a pioneering approach that leverages foundation models to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environment and providing warnings about potential risks. Specifically, our method begins by leveraging a large-image tagging model (i.e., Recognize Anything Model (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV, using prompt engineering. By combining the prompt and input image, a vision-language foundation model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing environmental objects and scenic landmarks, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method can recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.

Opting for conservative management over surgery for neonatal ovarian cysts.

OBJECTIVE: To explore the suitability of conservative management for neonatal ovarian cysts in newborns. METHODS: A retrospective cohort study was conducted, involving infants diagnosed with neonatal abdominal/pelvic cysts at two separate medical institutions from January 2015 through July 2021. Data collection included clinical characteristics, imaging results, pathological findings, and postnatal outcomes. Statistical analyses were performed using the Student's t-test, Mann-Whitney U-test, and receiver operating characteristic (ROC) curve. RESULTS: In total, 34 cases of neonatal abdominal/pelvic cystic masses were detected, with mean birth weight of 3401 ± 515 g. Of these, 22 patients underwent postnatal cystectomy/oophorectomy. Pathological assessments revealed 16 uncomplicated cysts, 5 complex cysts, and 1 ovarian cyst with torsion complications. Notably, the cysts' dimensions at the time of surgical intervention had significantly decreased from the initial measurements (p = 0.015). The ROC curve analysis presented an area under the curve of 0.642, indicating moderate accuracy in employing cyst size as a discriminative feature to differentiate complex from simple ovarian cysts. Additionally, a short-term follow-up of nonsurgical cases indicated a 100% resolution rate by 24 months of age (n = 9). CONCLUSION: Given their predominantly benign nature, the majority of neonatal ovarian cysts seem to be amenable to conservative management. This approach remains justified for larger cysts with minimal torsion risk, as well as considering the observed reduction in cyst size at birth, which further supports the case against surgical intervention.

Accuracy and Usability of Smartphone-Based Distance Estimation Approaches for Visual Assistive Technology Development.

Goal: Distance information is highly requested in assistive smartphone Apps by people who are blind or low vision (PBLV). However, current techniques have not been evaluated systematically for accuracy and usability. Methods: We tested five smartphone-based distance-estimation approaches in the image center and periphery at 1-3 meters, including machine learning (CoreML), infrared grid distortion (IR_self), light detection and ranging (LiDAR_back), and augmented reality room-tracking on the front (ARKit_self) and back-facing cameras (ARKit_back). Results: For accuracy in the image center, all approaches had <±2.5 cm average error, except CoreML which had ±5.2-6.2 cm average error at 2-3 meters. In the periphery, all approaches were more inaccurate, with CoreML and IR_self having the highest average errors at ±41 cm and ±32 cm respectively. For usability, CoreML fared favorably with the lowest central processing unit usage, second lowest battery usage, highest field-of-view, and no specialized sensor requirements. Conclusions: We provide key information that helps design reliable smartphone-based visual assistive technologies to enhance the functionality of PBLV.

Evidence-based practice education in physical medicine and rehabilitation residency programs: A Canadian national survey.

OBJECTIVE: The current extent and quality of evidence based practice (EBP) training for physiatrists is unclear at this time. Training of EBP is also available to residents in Canada. The extent, quality and impact of the training was explored. DESIGN: Cohort study Results: about half of the Canadian programs reported a formal EBP curriculum. The most frequently reported method of providing EBP education were resident participation in journal club. CONCLUSIONS: Despite the increasing integration of EBP into residency program education, there remains a critical lack of knowledge and skills for implementation of EBP into clinical practice among Canadian PM&R residency programs.

Neuroimaging features of accidental fentanyl overdose in a toddler.

The opioid epidemic has become a significant public health crisis worldwide. With the rise in popularity of fentanyl, opioid overdoses continue to rise at unprecedented rates. Unfortunately, young children have become collateral damage in the face of the opioid epidemic. Accidental exposures and ingestions are the leading cause of opioid overdose in this age group and can result in significant acute complications, long-term sequelae and even death. We present the case of a toddler with accidental fentanyl ingestion who experienced seizures and required intubation for respiratory distress. He was found to have notable diffusion restriction cerebellar changes on MRI and ultimately discharged with normal neurological function. Our case adds to the growing literature of the clinical presentation and neuroimaging features associated with opioid toxicity in young children.

Wearables for persons with blindness and low vision: form factor matters.

Based on statistics from the WHO and the International Agency for the Prevention of Blindness, an estimated 43.3 million people have blindness and 295 million have moderate and severe vision impairment globally as of 2020, statistics expected to increase to 61 million and 474 million respectively by 2050, staggering numbers. Blindness and low vision (BLV) stultify many activities of daily living, as sight is beneficial to most functional tasks. Assistive technologies for persons with blindness and low vision (pBLV) consist of a wide range of aids that work in some way to enhance one's functioning and support independence. Although handheld and head-mounted approaches have been primary foci when building new platforms or devices to support function and mobility, this perspective reviews potential shortcomings of these form factors or embodiments and posits that a body-centered approach may overcome many of these limitations.

Training AI to Recognize Objects of Interest to the Blind and Low Vision Community.

Recent object detection models show promising advances in their architecture and performance, expanding potential applications for the benefit of persons with blindness or low vision (pBLV). However, object detection models are usually trained on generic data rather than datasets that focus on the needs of pBLV. Hence, for applications that locate objects of interest to pBLV, object detection models need to be trained specifically for this purpose. Informed by prior interviews, questionnaires, and Microsoft's ORBIT research, we identified thirty-five objects pertinent to pBLV. We employed this user-centric feedback to gather images of these objects from the Google Open Images V6 dataset. We subsequently trained a YOLOv5x model with this dataset to recognize these objects of interest. We demonstrate that the model can identify objects that previous generic models could not, such as those related to tasks of daily functioning - e.g., coffee mug, knife, fork, and glass. Crucially, we show that careful pruning of a dataset with severe class imbalances leads to a rapid, noticeable improvement in the overall performance of the model by two-fold, as measured using the mean average precision at the intersection over union thresholds from 0.5 to 0.95 (mAP50-95). Specifically, mAP50-95 improved from 0.14 to 0.36 on the seven least prevalent classes in the training dataset. Overall, we show that careful curation of training data can improve training speed and object detection outcomes. We show clear directions on effectively customizing training data to create models that focus on the desires and needs of pBLV.Clinical Relevance- This work demonstrated the benefits of developing assistive AI technology customized to individual users or the wider BLV community.

Commute Booster: A Mobile Application for First/Last Mile and Middle Mile Navigation Support for People With Blindness and Low Vision.

OBJECTIVE: People with blindness and low vision face substantial challenges when navigating both indoor and outdoor environments. While various solutions are available to facilitate travel to and from public transit hubs, there is a notable absence of solutions for navigating within transit hubs, often referred to as the "middle mile". Although research pilots have explored the middle mile journey, no solutions exist at scale, leaving a critical gap for commuters with disabilities. In this paper, we proposed a novel mobile application, Commute Booster, that offers full trip planning and real-time guidance inside the station. METHODS AND PROCEDURES: Our system consists of two key components: the general transit feed specification (GTFS) and optical character recognition (OCR). The GTFS dataset generates a comprehensive list of wayfinding signage within subway stations that users will encounter during their intended journey. The OCR functionality enables users to identify relevant navigation signs in their immediate surroundings. By seamlessly integrating these two components, Commute Booster provides real-time feedback to users regarding the presence or absence of relevant navigation signs within the field of view of their phone camera during their journey. RESULTS: As part of our technical validation process, we conducted tests at three subway stations in New York City. The sign detection achieved an impressive overall accuracy rate of 0.97. Additionally, the system exhibited a maximum detection range of 11 meters and supported an oblique angle of approximately 110 degrees for field of view detection. CONCLUSION: The Commute Booster mobile application relies on computer vision technology and does not require additional sensors or infrastructure. It holds tremendous promise in assisting individuals with blindness and low vision during their daily commutes. Clinical and Translational Impact Statement: Commute Booster translates the combination of OCR and GTFS into an assistive tool, which holds great promise for assisting people with blindness and low vision in their daily commute.

Implementing Remote Patient Monitoring of Physical Activity in Clinical Practice.

PURPOSE: Remote patient monitoring (RPM) is a tool for patients to share data collected outside of office visits. RPM uses technology and the digital transmission of data to inform clinician decision-making in patient care. Using RPM to track routine physical activity is feasible to operationalize, given contemporary consumer-grade devices that can sync to the electronic health record. Objective monitoring through RPM can be more reliable than patient self-reporting for physical activity. DESIGN AND METHODS: This article reports on four pilot studies that highlight the utility and practicality of RPM for physical activity monitoring in outpatient clinical care. Settings include endocrinology, cardiology, neurology, and pulmonology settings. RESULTS: The four pilot use cases discussed demonstrate how RPM is utilized to monitor physical activity, a shift that has broad implications for prediction, prevention, diagnosis, and management of chronic disease and rehabilitation progress. CLINICAL RELEVANCE: If RPM for physical activity is to be expanded, it will be important to consider that certain populations may face challenges when accessing digital health services. CONCLUSION: RPM technology provides an opportunity for clinicians to obtain objective feedback for monitoring progress of patients in rehabilitation settings. Nurses working in rehabilitation settings may need to provide additional patient education and support to improve uptake.

Speech-induced atrial tachycardia: A narrative review of putative mechanisms implicating the autonomic nervous system.

Despite being uncommon, speech-induced atrial tachycardias carry significant morbidity and affect predominantly healthy individuals. Little is known about their mechanism, treatment, and prognosis. In this review, we seek to identify the underlying connections and pathophysiology between speech and arrhythmias while providing an informed approach to evaluation and management.