Serum Potassium Monitoring Using AI-Enabled Smartwatch Electrocardiograms.

BACKGROUND: Hyperkalemia, characterized by elevated serum potassium levels, heightens the risk of sudden cardiac death, particularly increasing risk for individuals with chronic kidney disease and end-stage renal disease (ESRD). Traditional laboratory test monitoring is resource-heavy, invasive, and unable to provide continuous tracking. Wearable technologies like smartwatches with electrocardiogram (ECG) capabilities are emerging as valuable tools for remote monitoring, potentially allowing for personalized monitoring with artificial intelligence (AI)-ECG interpretation. OBJECTIVES: The purpose of this study was to develop an AI-ECG algorithm to predict serum potassium level in ESRD patients with smartwatch-generated ECG waveforms. METHODS: A cohort of 152,508 patients with 293,557 ECGs paired serum potassium levels obtained within 1 hour at Cedars Sinai Medical Center was used to train an AI-ECG model ("Kardio-Net") to predict serum potassium level. The model was further fine-tuned on 4,337 ECGs from 1,463 patients with ESRD using inputs from 12- and single-lead ECGs. Kardio-Net was evaluated in held-out test cohorts from Cedars Sinai Medical Center and Stanford Healthcare (SHC) as well as a prospective international cohort of 40 ESRD patients with smartwatch ECGs at Chang Gung Memorial Hospital. RESULTS: The Kardio-Net, when applied to 12-lead ECGs, identified severe hyperkalemia (>6.5 mEq/L) with an AUC of 0.852 (95% CI: 0.745-0.956) and a mean absolute error (MAE) of 0.527 mEq/L. In external validation at SHC, the model achieved an AUC of 0.849 (95% CI: 0.823-0.875) and an MAE of 0.599 mEq/L. For single-lead ECGs, Kardio-Net detected severe hyperkalemia with an AUC of 0.876 (95% CI: 0.765-0.987) in the primary cohort and had an MAE of 0.575 mEq/L. In the external SHC validation, the AUC was 0.807 (95% CI: 0.778-0.835) with an MAE of 0.740 mEq/L. Using prospectively obtained smartwatch data, the AUC was 0.831 (95% CI: 0.693-0.975), with an MAE of 0.580 mEq/L. CONCLUSIONS: We validate a deep learning model to predict serum potassium levels from both 12-lead ECGs and single-lead smartwatch data, demonstrating its utility for remote monitoring of hyperkalemia.

Improvement in Adherance to Anesthesia Preoperative Appointment With Telemedicine: A Retrospective Analysis.

BACKGROUND: Amidst the coronavirus disease 2019 (COVID-19) pandemic, the sudden demand for virtual medical visits drove the expansion of telemedicine across all medical specialties. Current literature demonstrates limited knowledge of the impact of telehealth on appointment adherence, particularly in preoperative anesthesia evaluations. This study aims to describe the impact of telemedicine-based anesthesia evaluation and its effects on appointment completion.  Methods: This was a retrospective, non-randomized, cohort study of adult patients at the University of California, Los Angeles, United States, who received preoperative anesthesia evaluations by telemedicine or in-person in an academic medical center. From January to September 2021, we evaluated telemedicine and in-person appointment completion in patients scheduled for surgery. The primary outcome was the incidence of appointment completion. The secondary outcomes included appointment no-shows and cancellations.  Results: Of 1332 patients included in this study, 956 patients received telehealth visits while 376 patients received in-person preoperative anesthesia evaluations. Compared to the in-person group, the telemedicine group had more appointment completions (81.38% vs 76.60%), fewer cancellations (12.55% vs 19.41%), and no statistical difference in appointment no-shows (6.07% vs 3.99%). Compared to the in-person group, patients who received telemedicine evaluations were younger (55.81 ± 18.38 vs 65.97 ± 15.19), less likely Native American and Alaska Native (0.31% vs 1.60%), more likely of Hispanic or Latino ethnicity (16.63% vs 12.23%), required less interpreter services (4.18% vs 9.31%), had more private insurance coverage (53.45% vs 37.50%) and less Medicare coverage (37.03% vs 50.53%). CONCLUSIONS: This study demonstrates that telemedicine can improve preoperative anesthesia appointment completion and decrease appointment cancellations. We also demonstrate potential shortcomings of telemedicine in serving patients who are older, require interpreter services, or are non-privately insured. These inequities highlight potential avenues to increase equity and access to telemedicine.

The Next-Generation Electronic Health Record in the ICU: A Focus on User-Technology Interface to Optimize Patient Safety and Quality.

As a knowledge-based field of medicine, critical care medicine has benefited from the use of the electronic health records (EHRs) in daily practice, as intensive care unit (ICU) patients generate thousands of pieces of clinical data each day.1 ICU teams must review, interpret, and take action on these data points when managing multiple patients in a time-constrained environment. The increasing number of available data facts to be processed by ICU clinicians for decision-making surpasses human cognitive capacity. ICU physicians described the current display and representation of patient data in the EHR as suboptimum. Performance dashboards are an information delivery system that display the most important information about performance objectives to ICU directors, allowing them to monitor and manage their ICU performance more effectively. The development of visualization dashboards that monitor ICU performance will still need to adhere to usability principles such as Jakob Nielsen's heuristics. The goal of improving EHR interfaces will directly enhance provider well-being, patient outcomes, and quality of care.

Evaluation of Telemedicine Use for Anesthesiology Pain Division: Retrospective, Observational Case Series Study.

BACKGROUND: An increasing number of patients require outpatient and interventional pain management. To help meet the rising demand for anesthesia pain subspecialty care in rural and metropolitan areas, health care providers have used telemedicine for pain management of both interventional patients and those with chronic pain. OBJECTIVE: In this study, we aimed to describe the implementation of a telemedicine program for pain management in an academic pain division in a large metropolitan area. We also aimed to estimate patient cost savings from telemedicine, before and after the California COVID-19 "Safer at Home" directive, and to estimate patient satisfaction with telemedicine for pain management care. METHODS: This was a retrospective, observational case series study of telemedicine use in a pain division at an urban academic medical center. From August 2019 to June 2020, we evaluated 1398 patients and conducted 2948 video visits for remote pain management care. We used the publicly available Internal Revenue Service's Statistics of Income data to estimate hourly earnings by zip code in order to estimate patient cost savings. We estimated median travel time and travel distance with Google Maps' Distance Matrix application programming interface, direct cost of travel with median value for regular fuel cost in California, and time-based opportunity savings from estimated hourly earnings and round-trip time. We reported patient satisfaction scores derived from a postvisit satisfaction survey containing questions with responses on a 5-point Likert scale. RESULTS: Patients who attended telemedicine visits avoided an estimated median round-trip driving distance of 26 miles and a median travel time of 69 minutes during afternoon traffic conditions. Within the sample, their median hourly earnings were US $28 (IQR US $21-$39) per hour. Patients saved a median of US $22 on gas and parking and a median total of US $52 (IQR US $36-$75) per telemedicine visit based on estimated hourly earnings and travel time. Patients who were evaluated serially with telemedicine for medication management saved a median of US $156 over a median of 3 visits. A total of 91.4% (286/313) of patients surveyed were satisfied with their telemedicine experience. CONCLUSIONS: Telemedicine use for pain management reduced travel distance, travel time, and travel and time-based opportunity costs for patients with pain. We achieved the successful implementation of telemedicine across a pain division in an urban academic medical center with high patient satisfaction and patient cost savings.

Advances in Mobile Health for Inflammatory Bowel Disease.

Mobile health has the potential to transform the management of chronic illnesses, expanding treatment from a purely clinic-based approach to a more patient-centered delivery of care. For patients with inflammatory bowel disease (IBD), a condition characterized by a relapsing and remitting course, adoption of mobile health strategies can promote improved quality of care delivery and clinical outcomes. Benefits of mobile health applications for IBD include tracking symptoms to guide disease management, coordinating data exchange across clinical care providers, increasing communication between patients and the care team, and providing educational materials to increase patient engagement and satisfaction. In this review, we present the current offerings for telemedicine systems and mobile applications designed for patients with IBD and discuss the potential advantages and limitations of utilizing mobile health in the care of these patients.

Implementation and Evaluation of a Neurology Telemedicine Initiative at a Major Academic Medical Center.

Introduction: The COVID-19 pandemic forced rapid adoption of telemedicine for care of neurology patients. This study contributes to this literature by describing the structure and implementation of telemedicine-based outpatient neurology clinics at the UCLA Medical Center and estimates patient cost savings, before and after the California COVID-19 "Safer at Home" directive, and patient satisfaction. Methods: This was a retrospective, nonrandomized, case series study of telemedicine-based neurological management in an urban academic medical center from October 2018 to June 2020. We estimated roundtrip travel time, roundtrip travel distance, total savings, and surveyed patient and provider satisfaction with telemedicine care. We supported these findings through evaluation of 7,194 patients by telemedicine and conducted 9,189 video visits for neurological care. Results: The median telemedicine patient avoided a roundtrip driving distance of 33 miles and roundtrip travel time of 75 min. Within sample, median hourly earnings were $27/h. The median patient saved $18 on fuel and parking and $36 of time-based opportunity savings, for total savings of $54 per video visit. Eighty-six percent of patients surveyed were satisfied with their video visit experience. Conclusions: Telemedicine reduced travel time and also reduced costs for neurology patients. Patients and providers both reported high levels of satisfaction with telemedicine.

The Age of Artificial Intelligence: Use of Digital Technology in Clinical Nutrition.

PURPOSE OF REVIEW: Computing advances over the decades have catalyzed the pervasive integration of digital technology in the medical industry, now followed by similar applications for clinical nutrition. This review discusses the implementation of such technologies for nutrition, ranging from the use of mobile apps and wearable technologies to the development of decision support tools for parenteral nutrition and use of telehealth for remote assessment of nutrition. RECENT FINDINGS: Mobile applications and wearable technologies have provided opportunities for real-time collection of granular nutrition-related data. Machine learning has allowed for more complex analyses of the increasing volume of data collected. The combination of these tools has also translated into practical clinical applications, such as decision support tools, risk prediction, and diet optimization. SUMMARY: The state of digital technology for clinical nutrition is still young, although there is much promise for growth and disruption in the future.

Development, Implementation, and Evaluation of a Telemedicine Preoperative Evaluation Initiative at a Major Academic Medical Center.

BACKGROUND: With health care practice consolidation, the increasing geographic scope of health care systems, and the advancement of mobile telecommunications, there is increasing interest in telemedicine-based health care consultations. Anesthesiology has had experience with telemedicine consultation for preoperative evaluation since 2004, but the majority of studies have been conducted in rural settings. There is a paucity of literature of use in metropolitan areas. In this article, we describe the implementation of a telemedicine-based anesthesia preoperative evaluation and report the program's patient satisfaction, clinical case cancellation rate outcomes, and cost savings in a large metropolitan area (Los Angeles, CA). METHODS: This is a descriptive study of a telemedicine-based preoperative anesthesia evaluation process in an academic medical center within a large metropolitan area. In a 2-year period, we evaluated 419 patients scheduled for surgery by telemedicine and 1785 patients who were evaluated in-person. RESULTS: Day-of-surgery case cancellations were 2.95% and 3.23% in the telemedicine and the in-person cohort, respectively. Telemedicine patients avoided a median round trip driving distance of 63 miles (Q1 24; Q3 119) and a median time saved of 137 (Q1 95; Q3 195) and 130 (Q1 91; Q3 237) minutes during morning and afternoon traffic conditions, respectively. Patients experienced time-based savings, particularly from traveling across a metropolitan area, which amounted to $67 of direct and opportunity cost savings. From patient satisfaction surveys, 98% (129 patients out of 131 completed surveys) of patients who were consulted via telemedicine were satisfied with their experience. CONCLUSIONS: This study demonstrates the implementation of a telemedicine-based preoperative anesthesia evaluation from an academic medical center in a metropolitan area with high patient satisfaction, cost savings, and without increase in day-of-procedure case cancellations.

Intraoperative Treatment of Fetal Asystole After Endovascular Repair of Aortic Coarctation in a Pregnant Woman with Mitral Stenosis.

A G1P0 woman with aortic coarctation and mitral valve stenosis underwent endovascular aortic repair with continuous fetal monitoring during the 20th week of pregnancy. On tracheal extubation, an episode of fetal asystole followed by fetal bradycardia was identified. Ephedrine, nitroglycerin, and terbutaline were administered for intrauterine fetal resuscitation. Subsequently, the patient developed hypertension and pulmonary edema, which were treated with furosemide and noninvasive positive pressure ventilation. The fetal heart rate normalized. We conclude that intraoperative monitoring of a previable fetus may aid in optimizing maternal hemodynamics. Before performing interventional procedures in pregnant women, a multidisciplinary team should discuss the goals of neonatal care should adverse fetal events be detected.

Association of Diffusion and Anatomic Imaging Parameters with Survival for Patients with Newly Diagnosed Glioblastoma Participating in Two Different Clinical Trials.

PURPOSE: To evaluate the time course and association with survival of anatomic lesion volumes and diffusion imaging parameters for patients with newly diagnosed glioblastoma who were treated with radiation and concurrently with either temozolomide and enzastaurin (TMZ+enza cohort) or temozolomide, erlotonib, and bevaciumab (TMZ+erl+bev cohort). MATERIALS AND METHODS: Regions of interest corresponding to the contrast-enhancing and hyperintense lesions on T2-weighted images were generated. Diffusion-weighted images were processed to provide maps of apparent diffusion coefficient, fractional anisotropy, and longitudinal and radial eigenvalues. Histograms of diffusion values were generated and summary statistics calculated. Cox proportional hazards models were employed to assess the association of representative imaging parameters with survival with adjustments for age, Karnofsky performance status, and extent of resection. RESULTS: Although progression-free survival was significantly longer for the TMZ+erl+bev cohort (12.8 vs 7.3 months), there was no significant difference in overall survival between the two populations (17.0 vs 17.8 months). The median contrast-enhancing lesion volumes decreased from 6.3 to 1.9 cm(3) from baseline to the postradiotherapy scan for patients in the TMZ+enza cohort and from 2.8 to 0.9cm(3) for the TMZ+erl+bev cohort. Changes in the T2 lesion volumes were only significant for the latter cohort (26.5 to 11.9 cm(3)). The median apparent diffusion coefficient and related diffusion parameters were significantly increased for the TMZ+enza cohort (1054 to 1225 µm(2)/s). More of the anatomic parameters were associated with survival for the TMZ+enza cohort, whereas more diffusion parameters were associated with survival for the TMZ+erl+bev cohort. CONCLUSION: The early changes in anatomic and diffusion imaging parameters and their association with survival reflected differences in the mechanisms of action of the treatments that were being given. This suggests that integrating diffusion metrics and anatomic lesion volumes into the Response Assessment in Neuro-Oncology criteria would assist in interpreting treatment-induced changes and predicting outcome in patients with newly diagnosed glioblastoma who are receiving such combination treatments.

Comparison of ADC metrics and their association with outcome for patients with newly diagnosed glioblastoma being treated with radiation therapy, temozolomide, erlotinib and bevacizumab.

To evaluate metrics that describe changes in apparent diffusion coefficient (ADC) and to examine their association with clinical outcome for patients with newly diagnosed GBM who were participating in a Phase II clinical trial of treatment with radiation (RT), temozolomide, erlatonib and bevacizumab. Thirty six patients were imaged after surgery but prior to therapy and at regular follow-up time points. The following ADC metrics were evaluated: (1) histogram percentiles within the T2-hyperintense lesion (T2L) at serial follow-ups; (2) parameters obtained by fitting a two-mixture normal distribution to the histogram within the contrast-enhancing lesion (CEL) at baseline; (3) parameters obtained using both traditional and graded functional diffusion maps within the CEL and T2L. Cox Proportional Hazards models were employed to assess the association of the ADC parameters with overall survival (OS) and progression-free survival (PFS). A lower ADC percentile value within the T2L at early follow-up time points was associated with worse outcome. Of particular interest is that, even when adjusting for clinical prognostic factors, the ADC10% within the T2L at 2 months was strongly associated with OS (p < 0.001) and PFS (p < 0.007). fDM metrics showed an association with OS and PFS within the CEL when considered by univariate analysis, but not in the T2L. Our study emphasizes the value of ADC metrics obtained from the T2L at the post-RT time point as non-invasive biomarkers for assessing residual tumor in patients with newly diagnosed GBM being treated with combination therapy that includes the anti-angiogenic agent bevacizumab.

Outcomes after anterior or complete corpus callosotomy in children.

BACKGROUND: Corpus callosotomy (CC) is a valuable palliative surgical option for children with medically refractory epilepsy due to generalized or multifocal cortical seizure onset. OBJECTIVE: To investigate the extent of CC resulting in optimal seizure control in a pediatric patient population and to evaluate the modification of seizure profile after various CC approaches. METHODS: The records of 58 children (3-22 years of age at the time of surgery) with medically refractory epilepsy who underwent CC between 1995 and 2011 were retrospectively reviewed. RESULTS: Anterior two thirds callosotomy resulted in resolution of absence (P = .03) and astatic (P = .03) seizures, whereas anterior two thirds callosotomy followed by second-stage completion resulted in resolution of generalized tonic-clonic (GTC) (P = .03), astatic (P = .005), and myoclonic (P = .03) seizures in addition to a trend toward resolution of absence seizures (P = .08). Single-stage upfront complete callosotomy resulted in resolution of absence (P = .002), astatic (P < .0001), myoclonic (P = .007), and complex partial (P = .008) seizures in addition to a trend toward resolution of GTC (P = .06). In comparing a composite of subjects who underwent anterior two thirds callosotomy alone or 2-stage complete callosotomy before the second stage to complete the callosotomy with subjects who underwent upfront complete CC, a more favorable outcome was found in those with the upfront complete CC (P = .02). CONCLUSION: Single-stage upfront complete callosotomy is effective in relieving a broader spectrum of seizure types than anterior two thirds callosotomy or 2-stage complete callosotomy in children. The advantages of single-stage complete callosotomy must be weighed against the potentially higher risk of neurological and operative complications.

Complete versus anterior two-thirds corpus callosotomy in children: analysis of outcome.

OBJECT: The goal of this study was to evaluate the efficacy of anterior versus complete sectioning of the corpus callosum in children suffering from medically refractory epilepsy. The authors report seizure outcome in patients who underwent anterior two-thirds or complete corpus callosotomy (CC) during the period 1995-2008 at St. Louis Children's Hospital. METHODS: The medical records of 27 children and adolescents with a minimum follow-up of 6 months were retrospectively evaluated with respect to seizure status, anticonvulsant outcomes, and subjective results. Preoperatively, patients suffered from a variety of seizure types that occurred daily, weekly, or episodically. The male/female ratio was 19:8, and patients ranged in age between 3 and 19 years (mean 9.93 years). Seizure outcome, parental assessment of daily function, and changes in the number of prescribed antiepileptic drugs were all assessed. RESULTS: Fifteen patients underwent an initial anterior two-thirds CC, and 12 underwent a complete CC. Of the 15 patients who underwent an anterior CC, 7 went on to receive a posterior CC. Seizure control was superior in children undergoing a complete CC (91%, Class I-III) versus an anterior two-thirds CC (75%, Class I-III). Seizure types most affected by CC included atonic, myoclonic, and absence. The number of postoperative antiepileptic drugs did not significantly change following CC in either the anterior only or complete groups. One patient experienced a transient disconnection syndrome that resolved within 4 weeks, and 4 patients experienced mild hemiparesis and speech delays that resolved with therapy. Three patients experienced surgical complications requiring a second operation. The overall daily function and attentiveness of the patients improved. CONCLUSIONS: A complete CC should be considered as the initial procedure in lower-functioning children afflicted by absence, atonic, or myoclonic seizures. Severely affected higher-functioning children may also benefit from a complete CC, without clinically significant disconnection syndromes. A completion posterior CC may benefit patients in whom a prior anterior CC has failed.

Piezoelectric control of needle-free transdermal drug delivery.

Transdermal drug delivery occurs primarily through hypodermic needle injections, which cause pain, require a trained administrator, and may contribute to the spread of disease. With the growing number of pharmaceutical therapies requiring transdermal delivery, an effective, safe, and simple needle-free alternative is needed. We present and characterize a needle-free jet injector that employs a piezoelectric actuator to accelerate a micron-scale stream of fluid (40-130 microm diameter) to velocities sufficient for skin penetration and drug delivery (50-160 m/s). Existing jet injectors, powered by compressed springs and gases, are not widely used due to painful injections and poor reliability in skin penetration depth and dose. In contrast, our device offers electronic control of the actuator expansion rate, resulting in direct control of jet velocity and thus the potential for more precise injections. We apply a simple fluid-dynamic model to predict the device response to actuator expansion. Further, we demonstrate that injection parameters including expelled volume, jet pressure, and penetration depth in soft materials vary with actuator expansion rate, but are highly coupled. Finally, we discuss how electronically-controlled jet injectors may enable the decoupling of injection parameters such as penetration depth and dose, improving the reliability of needle-free transdermal drug delivery.