Search

Many Cyber-Physical Systems (CPS) have timing constraints that must be met by the cyber components (software and the network) to ensure safety. It is a tedious job to check if a CPS meets its timing requirement especially when it is distributed and the software and/or the underlying computing platforms are complex. Furthermore, the system design is brittle since a timing failure can still happen (e.g., network failure, soft error bit flip). In this article, we propose a new design methodology called Plan B where timing constraints of the CPS are monitored at runtime, and a proper backup routine is executed when a timing failure happens to ensure safety. We provide a model on how to express the desired timing behavior using a set of timing constructs in a C/C++ code and how to efficiently monitor them at the runtime. We showcase the effectiveness of our approach by conducting experiments on three case studies: (1) the full software stack for autonomous driving (Apollo), (2) a multi-agent system with 1/10th-scale model robots, and (3) a quadrotor for search and rescue application. We show that the system remains safe and stable even when intentional faults are injected to cause a timing failure. We also demonstrate that the system can achieve graceful degradation when a less extreme timing failure happens.

Normal-pressure hydrocephalus (NPH) is characterized by the clinical triad of dementia, gait instability, and urinary incontinence. The estimated annual incidence is 1.8 cases in 100,000 persons, making NPH a rare diagnosis and uncommon cause of dementia. NPH is a form of communicating hydrocephalus that can easily be missed in older adults with multiple comorbidities, so clinicians must exclude reversible causes of dementia before diagnosing irreversible causes such as Alzheimer disease.

BACKGROUND COVIDCare@Home (CC@H) is a multifaceted, interprofessional team-based remote monitoring program led by family medicine for patients diagnosed with COVID-19, based at Women’s College Hospital (WCH), an ambulatory academic center in Toronto, Canada. CC@H offers virtual visits (phone and video) to address the clinical needs and broader social determinants of the health of patients during the acute phase of COVID-19 infection, including finding a primary care provider (PCP) and support for food insecurity. OBJECTIVE The objective of this evaluation is to understand the implementation and quality outcomes of CC@H within the Quadruple Aim framework of patient experience, provider experience, cost, and population health. METHODS This multimethod cross-sectional evaluation follows the Quadruple Aim framework to focus on implementation and service quality outcomes, including feasibility, adoption, safety, effectiveness, equity, and patient centeredness. These measures were explored using clinical and service utilization data, patient experience data (an online survey and a postdischarge questionnaire), provider experience data (surveys, interviews, and focus groups), and stakeholder interviews. Descriptive analysis was conducted for surveys and utilization data. Deductive analysis was conducted for interviews and focus groups, mapping to implementation and quality domains. The Ontario Marginalization Index (ON-Marg) measured the proportion of underserved patients accessing CC@H. RESULTS In total, 3412 visits were conducted in the first 8 months of the program (April 8-December 8, 2020) for 616 discrete patients, including 2114 (62.0%) visits with family physician staff/residents and 149 (4.4%) visits with social workers/mental health professionals. There was a median of 5 (IQR 4) visits per patient, with a median follow-up of 7 days (IQR 27). The net promoter score was 77. In addition, 144 (23.3%) of the patients were in the most marginalized populations based on the residential postal code (as per ON-Marg). Interviews with providers and stakeholders indicated that the program continued to adapt to meet the needs of patients and the health care system. CONCLUSIONS Future remote monitoring should integrate support for addressing the social determinants of health and ensure patient-centered care through comprehensive care teams.

Background Multiplex polymerase chain reaction (PCR) panels allow for rapid detection or exclusion of pathogens causing meningitis and encephalitis (ME). The clinical impact of rapid multiplex PCR ME panel results on the duration of empiric antibiotic therapy is not well characterized. Methods We performed a retrospective prepost study at our institution that evaluated the clinical impact of a multiplex PCR ME panel among adults with suspected bacterial meningitis who received empiric antibiotic therapy and underwent lumbar puncture in the emergency department. The primary outcome was the duration of empiric antibiotic therapy. Results The positive pathogen detection rates were similar between pre- and post-multiplex PCR ME panel periods (17.5%, 24 of 137 vs 20.3%, 14 of 69, respectively). The median duration of empiric antibiotic therapy was significantly reduced in the post-multiplex PCR ME panel period compared with the pre-multiplex PCR ME panel period (34.7 vs 12.3 hours, P = .01). At any point in time, 46% more patients in the post-multiplex PCR ME panel period had empiric antibiotic therapy discontinued or de-escalated compared with the pre-multiplex PCR ME panel period (sex- and immunosuppressant use-adjusted hazard ratio 1.46, P = .01). The median hospital length of stay was shorter in the post-multiplex PCR ME panel period (3 vs 4 days, P = .03). Conclusions The implementation of the multiplex PCR ME panel for bacterial meningitis reduced the duration of empiric antibiotic therapy and possibly hospital length of stay compared with traditional microbiological testing methods., In this pre-post study, implementation of a multiplex polymerase chain reaction panel testing for agents of meningitis significantly reduced the duration of empiric antibiotic therapy, time to targeted therapy, and hospital length of stay compared with traditional microbiological testing methods.

We report a deep learning-based framework which can be used to screen thin blood smears for sickle-cell-disease using images captured by a smartphone-based microscope. This framework first uses a deep neural network to enhance and standardize the smartphone images to the quality of a diagnostic level benchtop microscope, and a second deep neural network performs cell segmentation. We experimentally demonstrated that this technique can achieve 98% accuracy with an area-under-the-curve (AUC) of 0.998 on a blindly tested dataset made up of thin blood smears coming from 96 patients, of which 32 had been diagnosed with sickle cell disease.

Analyzing electrolytes in urine, such as sodium, potassium, calcium, chloride, and nitrite, has significant diagnostic value in detecting various conditions, such as kidney disorder, urinary stone disease, urinary tract infection, and cystic fibrosis. Ideally, by regularly monitoring these ions with the convenience of dipsticks and portable tools, such as cellphones, informed decision making is possible to control the consumption of these ions. Here, we report a paper-based sensor for measuring the concentration of sodium, potassium, calcium, chloride, and nitrite in urine, accurately quantified using a smartphone-enabled platform. By testing the device with both Tris buffer and artificial urine containing a wide range of electrolyte concentrations, we demonstrate that the proposed device can be used for detecting potassium, calcium, chloride, and nitrite within the whole physiological range of concentrations, and for binary quantification of sodium concentration.

BACKGROUND Health systems are increasingly looking toward the private sector to provide digital solutions to address health care demands. Innovation in digital health is largely driven by small- and medium-sized enterprises (SMEs), yet these companies experience significant barriers to entry, especially in public health systems. Complex and fragmented care models, alongside a myriad of relevant stakeholders (eg, purchasers, providers, and producers of health care products), make developing value propositions for digital solutions highly challenging. OBJECTIVE This study aims to identify areas for health system improvement to promote the integration of innovative digital health technologies developed by SMEs. METHODS This paper qualitatively analyzes a series of case studies to identify health system barriers faced by SMEs developing digital health technologies in Canada and proposed solutions to encourage a more innovative ecosystem. The Women’s College Hospital Institute for Health System Solutions and Virtual Care established a consultation program for SMEs to help them increase their innovation capacity and take their ideas to market. The consultation involved the SME filling out an onboarding form and review of this information by an expert advisory committee using guided considerations, leading to a recommendation report provided to the SME. This paper reports on the characteristics of 25 SMEs who completed the program and qualitatively analyzed their recommendation reports to identify common barriers to digital health innovation. RESULTS A total of 2 central themes were identified, each with 3 subthemes. First, a common barrier to system integration was the lack of formal evaluation, with SMEs having limited resources and opportunities to conduct such an evaluation. Second, the health system’s current structure does not create incentives for clinicians to use digital technologies, which threatens the sustainability of SMEs’ business models. SMEs faced significant challenges in engaging users and payers from the public system due to perverse economic incentives. Physicians are compensated by in-person visits, which actively works against the goals of many digital health solutions of keeping patients out of clinics and hospitals. CONCLUSIONS There is a significant disconnect between the economic incentives that drive clinical behaviors and the use of digital technologies that would benefit patients’ well-being. To encourage the use of digital health technologies, publicly funded health systems need to dedicate funding for the evaluation of digital solutions and streamlined pathways for clinical integration.

BACKGROUND Chronic obstructive pulmonary disease (COPD) is a leading cause of mortality and leads to frequent hospital admissions and emergency department (ED) visits. COPD exacerbations are an important patient outcome, and reducing their frequency would result in significant cost savings. Remote monitoring and self-monitoring could both help patients manage their symptoms and reduce the frequency of exacerbations, but they have different resource implications and have not been directly compared. OBJECTIVE This study aims to compare the effectiveness of implementing a technology-enabled self-monitoring program versus a technology-enabled remote monitoring program in patients with COPD compared with a standard care group. METHODS We conducted a 3-arm randomized controlled trial evaluating the effectiveness of a remote monitoring and a self-monitoring program relative to standard care. Patients with COPD were recruited from outpatient clinics and a pulmonary rehabilitation program. Patients in both interventions used a Bluetooth-enabled device kit to monitor oxygen saturation, blood pressure, temperature, weight, and symptoms, but only patients in the remote monitoring group were monitored by a respiratory therapist. All patients were assessed at baseline and at 3 and 6 months after program initiation. Outcomes included self-management skills, as measured by the Partners in Health (PIH) Scale; patient symptoms measured with the St George’s Respiratory Questionnaire (SGRQ); and the Bristol COPD Knowledge Questionnaire (BCKQ). Patients were also asked to self-report on health system use, and data on health use were collected from the hospital. RESULTS A total of 122 patients participated in the study: 40 in the standard care, 41 in the self-monitoring, and 41 in the remote monitoring groups. Although all 3 groups improved in PIH scores, BCKQ scores, and SGRQ impact scores, there were no significant differences among any of the groups. No effects were observed on the SGRQ activity or symptom scores or on hospitalizations, ED visits, or clinic visits. CONCLUSIONS Despite regular use of the technology, patients with COPD assigned to remote monitoring or self-monitoring did not have any improvement in patient outcomes such as self-management skills, knowledge, or symptoms, or in health care use compared with each other or with a standard care group. This may be owing to low health care use at baseline, the lack of structured educational components in the intervention groups, and the lack of integration of the action plan with the technology. CLINICALTRIAL ClinicalTrials.gov NCT03741855; https://clinicaltrials.gov/ct2/show/ NCT03741855

BACKGROUND Chronic obstructive pulmonary disease (COPD) is the third leading cause of mortality worldwide. Reducing the number of COPD exacerbations is an important patient outcome and a major cost-saving approach. Both technology-enabled self-monitoring (SM) and remote monitoring (RM) programs have the potential to reduce exacerbations, but they have not been directly compared with each other. As RM is a more resource-intensive strategy, it is important to understand whether it is more effective than SM. OBJECTIVE The objective of this study is to evaluate the impact of SM and RM on self-management behaviors, COPD disease knowledge, and respiratory status relative to standard care (SC). METHODS This was a 3-arm open-label randomized controlled trial comparing SM, RM, and SC completed in an outpatient COPD clinic in a community hospital. Patients in the SM and RM groups recorded their vital signs (oxygen, blood pressure, temperature, and weight) and symptoms with the Cloud DX platform every day and were provided with a COPD action plan. Patients in the RM group also received access to a respiratory therapist (RT). The RT monitored their vital signs intermittently and contacted them when their vitals varied outside of predetermined thresholds. The RT also contacted patients once a week irrespective of their vital signs or symptoms. All patients were randomized to 1 of the 3 groups and assessed at baseline and 3 and 6 months after program initiation. The primary outcome was the Partners in Health scale, which measures self-management skills. Secondary outcomes included the St. George's Respiratory Questionnaire, Bristol COPD Knowledge Questionnaire, COPD Assessment Test, and modified-Medical Research Council Breathlessness Scale. Patients were also asked to self-report on health system usage. RESULTS A total of 122 patients participated in the study, 40 in the SC, 41 in the SM, and 41 in the RM groups. Out of those patients, 7 in the SC, 5 in the SM, and 6 in the RM groups did not complete the study. There were no significant differences in the rates of study completion among the groups (P=.80). CONCLUSIONS Both SM and RM have shown promise in reducing acute care utilization and exacerbation frequencies. As far as we are aware, no studies to date have directly compared technology-enabled self-management with RM programs in COPD patients. We believe that this study will be an important contribution to the literature. CLINICALTRIAL ClinicalTrials.gov NCT03741855; https://clinicaltrials.gov/ct2/show/NCT03741855 INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/13920

Recent declines in honey bee colonies in the United States have put increased strain on agricultural pollination. Nosema ceranae and Nosema apis, are microsporidian parasites that are highly pathogenic to honey bees and have been implicated as a factor in honey bee losses. While traditional methods for quantifying Nosema infection have high sensitivity and specificity, there is no field-portable device for field measurements by beekeepers. Here we present a field-portable and cost-effective smartphone-based platform for detection and quantification of chitin-positive Nosema spores in honey bees. The handheld platform, weighing only 374 g, consists of a smartphone-based fluorescence microscope, a custom-developed smartphone application, and an easy to perform sample preparation protocol. We tested the performance of the platform using samples at different parasite concentrations and compared the method with manual microscopic counts and qPCR quantification. We demonstrated that this device provides results that are comparable with other methods, having a limit of detection of 0.5 × 106 spores per bee. Thus, the assay can easily identify infected colonies and provide accurate quantification of infection levels requiring treatment of infection, suggesting that this method is potentially adaptable for diagnosis of Nosema infection in the field by beekeepers. Coupled with treatment recommendations, this protocol and smartphone-based optical platform could improve the diagnosis and treatment of nosemosis in bees and provide a powerful proof-of-principle for the use of such mobile diagnostics as useful analytical tools for beekeepers in resource-limited settings.

Background Health systems are increasingly looking toward the private sector to provide digital solutions to address health care demands. Innovation in digital health is largely driven by small- and medium-sized enterprises (SMEs), yet these companies experience significant barriers to entry, especially in public health systems. Complex and fragmented care models, alongside a myriad of relevant stakeholders (eg, purchasers, providers, and producers of health care products), make developing value propositions for digital solutions highly challenging. Objective This study aims to identify areas for health system improvement to promote the integration of innovative digital health technologies developed by SMEs. Methods This paper qualitatively analyzes a series of case studies to identify health system barriers faced by SMEs developing digital health technologies in Canada and proposed solutions to encourage a more innovative ecosystem. The Women’s College Hospital Institute for Health System Solutions and Virtual Care established a consultation program for SMEs to help them increase their innovation capacity and take their ideas to market. The consultation involved the SME filling out an onboarding form and review of this information by an expert advisory committee using guided considerations, leading to a recommendation report provided to the SME. This paper reports on the characteristics of 25 SMEs who completed the program and qualitatively analyzed their recommendation reports to identify common barriers to digital health innovation. Results A total of 2 central themes were identified, each with 3 subthemes. First, a common barrier to system integration was the lack of formal evaluation, with SMEs having limited resources and opportunities to conduct such an evaluation. Second, the health system’s current structure does not create incentives for clinicians to use digital technologies, which threatens the sustainability of SMEs’ business models. SMEs faced significant challenges in engaging users and payers from the public system due to perverse economic incentives. Physicians are compensated by in-person visits, which actively works against the goals of many digital health solutions of keeping patients out of clinics and hospitals. Conclusions There is a significant disconnect between the economic incentives that drive clinical behaviors and the use of digital technologies that would benefit patients’ well-being. To encourage the use of digital health technologies, publicly funded health systems need to dedicate funding for the evaluation of digital solutions and streamlined pathways for clinical integration.

We introduce a deep learning based approach that uses a neural network to enhance the image resolution and color accuracy of a smartphone microscope, mitigating the gap between low cost mobile imaging devices and high end benchtop microscopes.

Giardia lamblia causes a disease known as giardiasis, which results in diarrhea, abdominal cramps, and bloating. Although conventional pathogen detection methods used in water analysis laboratories offer high sensitivity and specificity, they are time consuming, and need experts to operate bulky equipment and analyze the samples. Here we present a field-portable and cost-effective smartphone-based waterborne pathogen detection platform that can automatically classify Giardia cysts using machine learning. Our platform enables the detection and quantification of Giardia cysts in one hour, including sample collection, labeling, filtration, and automated counting steps. We evaluated the performance of three prototypes using Giardia-spiked water samples from different sources (e.g., reagent-grade, tap, non-potable, and pond water samples). We populated a training database with >30,000 cysts and estimated our detection sensitivity and specificity using 20 different classifier models, including decision trees, nearest neighbor classifiers, support vector machines (SVMs), and ensemble classifiers, and compared their speed of training and classification, as well as predicted accuracies. Among them, cubic SVM, medium Gaussian SVM, and bagged-trees were the most promising classifier types with accuracies of ~ 94.1%, 94.2%, and 95%, respectively; we selected the latter as our preferred classifier for the detection and enumeration of Giardia cysts that are imaged using our mobile-phone fluorescence microscope. Without the need for any experts or microbiologists, this field-portable pathogen detection platform can present a useful tool for water quality monitoring in resource-limited-settings.

We present a field portable and cost-effective smartphone based microscopy platform for rapid and sensitive detection and automated counting of waterborne pathogens, i.e., Giardia lamblia cysts, in large volume water samples using machine learning.

Background Chronic obstructive pulmonary disease (COPD) is the third leading cause of mortality worldwide. Reducing the number of COPD exacerbations is an important patient outcome and a major cost-saving approach. Both technology-enabled self-monitoring (SM) and remote monitoring (RM) programs have the potential to reduce exacerbations, but they have not been directly compared with each other. As RM is a more resource-intensive strategy, it is important to understand whether it is more effective than SM. Objective The objective of this study is to evaluate the impact of SM and RM on self-management behaviors, COPD disease knowledge, and respiratory status relative to standard care (SC). Methods This was a 3-arm open-label randomized controlled trial comparing SM, RM, and SC completed in an outpatient COPD clinic in a community hospital. Patients in the SM and RM groups recorded their vital signs (oxygen, blood pressure, temperature, and weight) and symptoms with the Cloud DX platform every day and were provided with a COPD action plan. Patients in the RM group also received access to a respiratory therapist (RT). The RT monitored their vital signs intermittently and contacted them when their vitals varied outside of predetermined thresholds. The RT also contacted patients once a week irrespective of their vital signs or symptoms. All patients were randomized to 1 of the 3 groups and assessed at baseline and 3 and 6 months after program initiation. The primary outcome was the Partners in Health scale, which measures self-management skills. Secondary outcomes included the St. George's Respiratory Questionnaire, Bristol COPD Knowledge Questionnaire, COPD Assessment Test, and modified-Medical Research Council Breathlessness Scale. Patients were also asked to self-report on health system usage. Results A total of 122 patients participated in the study, 40 in the SC, 41 in the SM, and 41 in the RM groups. Out of those patients, 7 in the SC, 5 in the SM, and 6 in the RM groups did not complete the study. There were no significant differences in the rates of study completion among the groups (P=.80). Conclusions Both SM and RM have shown promise in reducing acute care utilization and exacerbation frequencies. As far as we are aware, no studies to date have directly compared technology-enabled self-management with RM programs in COPD patients. We believe that this study will be an important contribution to the literature. Trial Registration ClinicalTrials.gov NCT03741855; https://clinicaltrials.gov/ct2/show/NCT03741855 International Registered Report Identifier (IRRID) DERR1-10.2196/13920

Sickle cell disease (SCD) is a major public health priority throughout much of the world, affecting millions of people. In many regions, particularly those in resource-limited settings, SCD is not consistently diagnosed. In Africa, where the majority of SCD patients reside, more than 50% of the 0.2-0.3 million children born with SCD each year will die from it; many of these deaths are in fact preventable with correct diagnosis and treatment. Here we present a deep learning framework which can perform automatic screening of sickle cells in blood smears using a smartphone microscope. This framework uses two distinct, complementary deep neural networks. The first neural network enhances and standardizes the blood smear images captured by the smartphone microscope, spatially and spectrally matching the image quality of a laboratory-grade benchtop microscope. The second network acts on the output of the first image enhancement neural network and is used to perform the semantic segmentation between healthy and sickle cells within a blood smear. These segmented images are then used to rapidly determine the SCD diagnosis per patient. We blindly tested this mobile sickle cell detection method using blood smears from 96 unique patients (including 32 SCD patients) that were imaged by our smartphone microscope, and achieved ~98% accuracy, with an area-under-the-curve (AUC) of 0.998. With its high accuracy, this mobile and cost-effective method has the potential to be used as a screening tool for SCD and other blood cell disorders in resource-limited settings., Comment: 30 pages, 5 figures