Search

We examine how convolutional neural networks (CNNs) for cardiac rhythm device detection can exhibit failures in performance under suboptimal deployment scenarios and examine how medically adversarial image presentation can further impair neural network performance. We validated the publicly available Pacemaker-ID web server and mobile app on 43 local hospital emergency department (ED) cases of patients presenting with a cardiac rhythm device on anterior-posterior (AP) chest radiograph and assessed performance using Cohen's kappa coefficient for inter-rater reliability. To illustrate adversarial performance concerns, we then produced example CNN models using the 65,379 patient MIMIC-CXR chest radiograph retrospective database and evaluated performance with area under the receiver operating characteristic (AUROC). In retrospective review of 43 patients with cardiac rhythm devices on AP chest radiographs during our study period (January 1, 2020 to March 1, 2020), 74.4% (32/43) had device manufacturer information readily available within the electronic medical record. A total of 25.6% of patients (11/43) did not have this information documented in the patient chart and could ostensibly benefit from CNN-based identification of device manufacturer. For patients with known device manufacturer, the Pacemaker-ID prediction was accurate in 87.5% of cases (28/32). Mobile app accuracy varied from 62.5 to 93.75% depending on image capture settings and presentation. Cohen's kappa coefficient varied from 0.448 to 0.897 depending on mobile image capture conditions. For our additional analysis of medically adversarial performance failures with a DenseNet121 trained on MIMIC-CXR images, we showed that an AUROC of 0.9807 ± 0.0051 could be achieved on an example testing dataset while masking a 30% false positive rate in identification of cardiac rhythm devices versus clinically distinct entities such as vagal nerve stimulators. Despite the promise of CNN approaches for cardiac rhythm device analysis on chest radiographs, further study is warranted to assess potential for errors driven by user misuse when deploying these models to mobile devices as well as for cases when performance can be impaired by the presence of other support apparatuses. [ABSTRACT FROM AUTHOR]

Deep brain stimulators (DBSs), a widely used and comprehensively acknowledged restorative methodology, are a type of implantable medical device which uses electrical stimulation to treat neurological disorders. These devices are widely used to treat diseases such as Parkinson, movement disorder, epilepsy, and psychiatric disorders. Security in such devices plays a vital role since it can directly affect the mental, emotional, and physical state of human bodies. In worst-case situations, it can even lead to the patient's death. An adversary in such devices, for instance, can inhibit the normal functionality of the brain by introducing fake stimulation inside the human brain. Nonetheless, the adversary can impair the motor functions, alter impulse control, induce pain, or even modify the emotional pattern of the patient by giving fake stimulations through DBSs. This paper presents a deep learning methodology to predict different attack stimulations in DBSs. The proposed work uses long short-term memory, a type of recurrent network for forecasting and predicting rest tremor velocity. (A type of characteristic observed to evaluate the intensity of the neurological diseases) The prediction helps in diagnosing fake versus genuine stimulations. The effect of deep brain stimulation was tested on Parkinson tremor patients. The proposed methodology was able to detect different types of emulated attack patterns efficiently and thereby notifying the patient about the possible attack.

Deep Brain Stimulation (DBS) is an implantable medical device used for electrical stimulation to treat neurological disorders. Traditional DBS devices provide fixed frequency pulses, but personalized adjustment of stimulation parameters is crucial for optimal treatment. This paper introduces a Basal Ganglia inspired Reinforcement Learning (BGRL) approach, incorporating a closed-loop feedback mechanism to suppress neural synchrony during neurological fluctuations. The BGRL approach leverages the resemblance between the Basal Ganglia region of brain by incorporating the actor–critic architecture of reinforcement learning (RL). Simulation results demonstrate that BGRL significantly reduces synchronous electrical pulses compared to other standard RL algorithms. BGRL algorithm outperforms existing RL methods in terms of suppression capability and energy consumption, validated through comparisons using ensemble oscillators. Results shown in the paper demonstrate BGRL suppressed the synchronous electrical pulses across three signaling regimes namely regular, chaotic and bursting by 40%, 146% and 40% respectively as compared to soft actor–critic model. BGRL shows promise in effectively suppressing neural synchrony in DBS therapy, providing an efficient alternative to open-loop methodologies. • Stabilize the synchronization and convergence points allowing for more accurate estimation. • Avoid overestimated bias to generalize the model well. • Adds noise to the target action to exploit the Q-function errors by smoothing out Q-values. • Ran simulations which capture the characteristics of closed loop DBS. [ABSTRACT FROM AUTHOR]

Nosocomial meningitis can occur in association with central nervous system (CNS) devices such as cerebrospinal shunts or drains, intrathecal pumps, and deep brain stimulators and carry substantial morbidity and mortality. Diagnosing and treating these infections may be challenging to physicians as cerebrospinal fluid cultures may be negative due to previous antibiotic therapy and cerebrospinal abnormalities may be secondary to the primary neurosurgical issue that prompted the placement of the CNS device (e.g., 'chemical meningitis' due to intracranial hemorrhage). Besides antibiotic therapy given intravenously and sometimes intrathecally, removal of the device with repeat cultures prior to re-implantation is key in achieving successful outcomes. [ABSTRACT FROM AUTHOR]

Background: The microTargeting™ platform (MTP) stereotaxy system (FHC Inc., Bowdoin, Me., USA) was FDA approved in 2001 utilizing rapid-prototyping technology to create custom platforms for human stereotaxy procedures. It has also been called the STarFix (surgical targeting fixture) system since it is based on the concept of a patient- and procedure-specific surgical fixture. This is an alternative stereotactic method by which planned trajectories are incorporated into custom-built, miniature stereotactic platforms mounted onto bone fiducial markers. Our goal is to report the clinical experience with this system over a 6-year period. Methods: We present the largest reported series of patients who underwent deep brain stimulation (DBS) implantations using customized rapidly prototyped stereotactic frames (MTP). Clinical experience and technical features for the use of this stereotactic system are described. Final lead location analysis using postoperative CT was performed to measure the clinical accuracy of the stereotactic system. Results: Our series included 263 patients who underwent 284 DBS implantation surgeries at one institution over a 6-year period. The clinical targeting error without accounting for brain shift in this series was found to be 1.99 mm (SD 0.9). Operating room time was reduced through earlier incision time by 2 h per case. Conclusion: Customized, miniature stereotactic frames, namely STarFix platforms, are an acceptable and efficient alternative method for DBS implantation. Its clinical accuracy and outcome are comparable to those associated with traditional stereotactic frame systems. Copyright © 2010 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

Abstract: Reductions in MRI-induced heating at 1.5 T resulting from a simple design change to coiled wires were investigated. MRI-induced heating was assessed for two different coiled wire forms (length, 26 cm): (1) multi-filar coiled wire form and (2) multi-filar coiled wire form having a different coiled pitch, providing an air gap spacing between adjacent five-filar coil loops. Each wire had an electrode and was insulated to create a lead, similar to that which would be used for a medical implant. The wire forms were placed in a gelled-saline-filled head/torso phantom and imaged at 1.5 T [whole-body average specific absorption rate (SAR), 1.79 W/kg]. Fluoroptic thermometry probes were used to measure temperatures at the distal ends of the wires. The experiments demonstrated a substantial reduction in MRI-induced heating for the modified wire compared to the unmodified wire (i.e., 10.5°C difference observed in one experiment and 26°C difference in another). These findings have important implications for MRI-induced heating of leads used for medical implants. [Copyright &y& Elsevier]

Purpose: To discover oculofacial plastic surgeon practice patterns for cautery selection in the setting of implantable electronic devices and present guidelines based on a review of current literature., Methods: A 10-Question web-based survey was sent to the email list serve of the American Society of Ophthalmic Plastic and Reconstructive Surgery to determine surgeon cautery preference in the setting of various implantable electronic devices and comfort level with the guidelines for cautery selection in their practice or institution. The relationship between survey questions was assessed for statistical significance using Pearson's Chi-square tests., Results: Two hundred ninety-three (41% response rate) surveys were completed and included for analysis. Greater than half of respondents either had no policy (36%) or were unaware of a policy (19%) in their practice or institution regarding cautery selection in patients with a cardiac implantable electronic device. Bipolar cautery was favored for use in patients with a cardiac implantable electronic device (79%-80%) and this number dropped in patients with implantable neurostimulators (30%). Overall, one-third of respondents did not feel comfortable with their practice/institution policy., Conclusion: Choices and comfort level among oculofacial plastic surgeons for cautery selection in patients with implantable electronic devices vary considerably, and some choices may increase the risk for interference-related complications. Practice patterns vary significantly in the setting of a neurostimulator or cochlear implant, where interference can cause thermal injury to the brain and implant damage, respectively. Guidelines are proposed for cautery selection in patients with implantable electronic devices undergoing oculofacial plastic surgery.