Mutations in the tail and rod domains of the neurofilament heavy-chain gene increase the risk of ALS.

OBJECTIVE: Neurofilament heavy-chain gene (NEFH) variants are associated with multiple neurodegenerative diseases, however, their relationship with ALS has not been robustly explored. Still, NEFH is commonly included in genetic screening panels worldwide. We therefore aimed to determine if NEFH variants modify ALS risk. METHODS: Genetic data of 11,130 people with ALS and 7,416 controls from the literature and Project MinE were analysed. We performed meta-analyses of published case-control studies reporting NEFH variants, and variant analysis of NEFH in Project MinE whole-genome sequencing data. RESULTS: Fixed-effects meta-analysis found that rare (MAF <1%) missense variants in the tail domain of NEFH increase ALS risk (OR 4.55, 95% CI 2.13-9.71, p < 0.0001). In Project MinE, ultrarare NEFH variants increased ALS risk (OR 1.37 95% CI 1.14-1.63, p = 0.0007), with rod domain variants (mostly intronic) appearing to drive the association (OR 1.45 95% CI 1.18-1.77, pMadsen-Browning = 0.0007, pSKAT-O = 0.003). While in the tail domain, ultrarare (MAF <0.1%) pathogenic missense variants were also associated with higher risk of ALS (OR 1.94, 95% CI 0.86-4.37, pMadsen-Browning = 0.039), supporting the meta-analysis results. Finally, several tail in-frame deletions were also found to affect disease risk, however, both protective and pathogenic deletions were found in this domain, highlighting an intricated architecture that requires further investigation. INTERPRETATION: We showed that NEFH tail missense and in-frame deletion variants, and intronic rod variants are risk factors for ALS. However, they are not variants of large effect, and their functional impact needs to be clarified in further studies. Therefore, their inclusion in routine genetic screening panels should be reconsidered.

Development of Predictive Models to Inform a Novel Risk Categorization Framework for Antibiotic Resistance in E. coli-Causing Uncomplicated Urinary Tract Infection.

BACKGROUND: In clinical practice, challenges in identifying patients with uncomplicated urinary tract infections (uUTIs) at risk of antibiotic non-susceptibility may lead to inappropriate prescribing and contribute to antibiotic resistance. We developed predictive models to quantify risk of non-susceptibility to four commonly prescribed antibiotic classes for uUTI, identify predictors of non-susceptibility to each class, and construct a corresponding risk categorization framework for non-susceptibility. METHODS: Eligible females aged ≥12 years with E. coli-caused uUTI were identified from Optum's de-identified Electronic Health Record dataset (10/1/2015‒2/29/2020). Four predictive models were developed to predict non-susceptibility to each antibiotic class and a risk categorization framework was developed to classify patients' isolates as low, moderate, and high risk of non-susceptibility to each antibiotic class. RESULTS: Predictive models were developed among 87487 patients. Key predictors of having a non-susceptible isolate to ≥3 antibiotic classes included number of previous UTI episodes, prior ß-lactam non-susceptibility, prior fluoroquinolone treatment, census bureau region, and race. The risk categorization framework classified 8.1%, 14.4%, 17.4%, and 6.3% of patients as having isolates at high risk of non-susceptibility to nitrofurantoin, trimethoprim-sulfamethoxazole, ß-lactams, and fluoroquinolones, respectively. Across classes, the proportion of patients categorized as having high-risk isolates was 3-12 folds higher among patients with non-susceptible isolates versus susceptible isolates. CONCLUSIONS: Our predictive models highlight factors that increase risk of non-susceptibility to antibiotics for uUTIs, while the risk categorization framework contextualizes risk of non-susceptibility to these treatments. Our findings provide valuable insight to clinicians treating uUTIs and may help inform empiric prescribing in this population.

Differences in femoral fracture localizations in men and women in Switzerland between 1998 and 2021-reversal of the secular trend?

Number and age-standardized incidences of femoral fractures by sex and localization were determined annually between 1998 and 2021 in subjects aged 45 years or older living in Switzerland. The number and incidences of femoral neck, pertrochanteric, subtrochanteric, and femoral shaft fractures followed distinct unexpected trend patterns. INTRODUCTION: Long-term incidence trends for femoral fractures by individual localizations are unknown. METHODS: Annual absolute number of hospitalizations and median age at hospital admission between 1998 and 2021 were extracted from the medical database of the Swiss Federal Office of Statistics by sex and 10-year age groups for the following 10th International Classification of Diseases (ICD-10) codes: femoral neck (ICD-10 S72.0), pertrochanteric (S72.1), subtrochanteric (S72.2), and femoral shaft fractures (S72.3). Age-standardized incidence rates (ASI) and corresponding trends were calculated. RESULTS: Over 24 years, the number of femoral neck fractures increased in men (+ 45%) but decreased in women (- 7%) with ASI significantly decreasing by 20% and 37% (p < 0.001 for trend for both), respectively. By contrast, the number of pertrochanteric fractures increased by 67% and 45% in men and women, respectively, corresponding to a horizontal ASI-trend in men (n.s.) and a modest significant decreasing ASI-trend in women (p < 0.001). The number of subtrochanteric fractures increased in both sexes with corresponding modest significant reductions in ASI-trends (p = 0.015 and 0.002, respectively). Femoral shaft fractures almost doubled in men (+ 71%) and doubled in women (+ 100%) with corresponding significant increases in ASI-trends (p = 0.001 and p < 0.001, respectively). Age at admission increased for all fracture localizations, more so in men than in women and more so for subtrochanteric and shaft fractures than for "typical" hip fractures. CONCLUSION: Incidence changes of pertrochanteric fractures and femoral shaft fractures deserve increased attention, especially in men. Pooling diagnostic codes for defining hip fractures may hide differing patterns by localization and sex.

Unsupervised machine learning identifies distinct ALS molecular subtypes in post-mortem motor cortex and blood expression data.

Amyotrophic lateral sclerosis (ALS) displays considerable clinical and genetic heterogeneity. Machine learning approaches have previously been utilised for patient stratification in ALS as they can disentangle complex disease landscapes. However, lack of independent validation in different populations and tissue samples have greatly limited their use in clinical and research settings. We overcame these issues by performing hierarchical clustering on the 5000 most variably expressed autosomal genes from motor cortex expression data of people with sporadic ALS from the KCL BrainBank (N = 112). Three molecular phenotypes linked to ALS pathogenesis were identified: synaptic and neuropeptide signalling, oxidative stress and apoptosis, and neuroinflammation. Cluster validation was achieved by applying linear discriminant analysis models to cases from TargetALS US motor cortex (N = 93), as well as Italian (N = 15) and Dutch (N = 397) blood expression datasets, for which there was a high assignment probability (80-90%) for each molecular subtype. The ALS and motor cortex specificity of the expression signatures were tested by mapping KCL BrainBank controls (N = 59), and occipital cortex (N = 45) and cerebellum (N = 123) samples from TargetALS to each cluster, before constructing case-control and motor cortex-region logistic regression classifiers. We found that the signatures were not only able to distinguish people with ALS from controls (AUC 0.88 ± 0.10), but also reflect the motor cortex-based disease process, as there was perfect discrimination between motor cortex and the other brain regions. Cell types known to be involved in the biological processes of each molecular phenotype were found in higher proportions, reinforcing their biological interpretation. Phenotype analysis revealed distinct cluster-related outcomes in both motor cortex datasets, relating to disease onset and progression-related measures. Our results support the hypothesis that different mechanisms underpin ALS pathogenesis in subgroups of patients and demonstrate potential for the development of personalised treatment approaches. Our method is available for the scientific and clinical community at https://alsgeclustering.er.kcl.ac.uk .

Addressing the unresolved challenge of quantifying skiing exposure-A proof of concept using smartphone sensors.

In epidemiological studies related to winter sports, especially alpine skiing, an unresolved methodological challenge is the quantification of actual on-snow activity exposure. Such information would be relevant for reporting meaningful measures of injury incidence, which refers to the number of new injuries that occur in a given population and time period. Accordingly, accurate determination of the denominator, i.e., actual "activity exposure time", is critical for injury surveillance and reporting. In this perspective article, we explore the question of whether wearable sensors in combination with mHealth applications are suitable tools to accurately quantify the periods in a ski day when the skier is physically skiing and not resting or using a mechanical means of transport. As a first proof of concept, we present exemplary data from a youth competitive alpine skier who wore his smartphone with embedded sensors on his body on several ski days during one winter season. We compared these data to self-reported estimates of ski exposure, as used in athletes' training diaries. In summary, quantifying on-snow activity exposure in alpine skiing using sensor data from smartphones is technically feasible. For example, the sensors could be used to track ski training sessions, estimate the actual time spent skiing, and even quantify the number of runs and turns made as long as the smartphone is worn. Such data could be very useful in determining actual exposure time in the context of injury surveillance and could prove valuable for effective stress management and injury prevention in athletes.

The osteoporosis treatment gap in Switzerland between 1998 and 2018.

The annual number of patients treated for osteoporosis between 1998 and 2018 in Switzerland increased until 2008 and steadily decreased thereafter. With a continuously growing population at fracture risk exceeding an intervention threshold, the treatment gap has increased and the incidence of hip fractures has stopped declining in the past decade. INTRODUCTION: The existence of an osteoporosis treatment gap, defined as the percentage of patients at risk for osteoporotic fractures exceeding an intervention threshold but remaining untreated, is widely acknowledged. Between 1998 and 2018, new bone active substances (BAS) indicated for the treatment of osteoporosis became available. Whether and if so to what extent these new introductions have altered the treatment gap is unknown. METHODS: The annual number of patients treated with a BAS was calculated starting from single-drug unit sales. The number of patients theoretically eligible for treatment with a BAS was estimated based on four scenarios corresponding to different intervention thresholds (one based solely on a bone mineral density T score threshold and three FRAX-based thresholds) and the resulting annual treatment gaps were calculated. RESULTS: In Switzerland, the estimated number of patients on treatment with a BAS increased from 35,901 in year 1998 to 233,381 in year 2018. However, this number grew regularly since 1998, peaked in 2008, and steadily decreased thereafter, in timely coincidence with the launch of intravenous bisphosphonates and the RANKL inhibitor denosumab. When expressed in numbers of untreated persons at risk for osteoporotic fractures exceeding a given intervention threshold, the treatment gaps were of similar magnitude in 1998 (when the first BSAs just had become available) and 2018. There was a strong association, which does not imply causation, between the proportion of patients treated and hip fracture incidence. CONCLUSION: In Switzerland, the osteoporosis treatment gap has increased over the past decade. The availability of new BAS has not contributed to its decrease.

Hospitalizations for major osteoporotic fractures in Switzerland: a long-term trend analysis between 1998 and 2018.

Between 1998 and 2018, the number of hospitalizations for major osteoporotic fractures increased. After standardization for age, these numerical increases translated into a reduced incidence of hospitalizations for hip fractures and an increased incidence of hospitalizations for spine, proximal humerus, and distal radius fractures in both sexes. INTRODUCTION: The longterm epidemiological trends of hospitalizations for major osteoporotic fractures (MOF) between 1998 and 2018 in Switzerland are unknown. METHODS: The absolute number of acute hospitalizations for MOF (hip fractures and fractures of the spine, proximal humerus, and distal radius) and related length of acute hospital stay were extracted from the medical database of the Swiss Federal Office of Statistics. Age-standardized incidence rates were calculated using 1998 as the reference year. RESULTS: Hospitalizations for MOF increased from 4483 to 7542 (+ 68.2%) in men and from 13,242 to 19,362 (+ 46.2%) in women. The age-standardized incidence of hospitalizations for MOF increased by 5.7% in men (p = 0.002) and by 5.1% in women (p = 0.018). The age-standardized incidence of hip fractures decreased by 15.3% in men (p < 0.001) and by 21.5% in women (p < 0.001). In parallel, the age-standardized incidence of MOF other than hip fractures increased by 31.8% in men (p < 0.001) and by 40.1% in women (p < 0.001). The mean length of acute hospital stays for MOF decreased from 16.3 to 8.5 days in men and from 16.9 to 8.1 days in women. CONCLUSION: Between 1998 and 2018, the number of hospitalizations for MOF increased significantly by a larger extent than expected based on the ageing of the Swiss population alone. This increase was solely driven by an increased incidence of MOF other than hip fractures as incident hip fractures decreased over time in both sexes, more so in women than in men.

Conditional generation of medical time series for extrapolation to underrepresented populations.

The widespread adoption of electronic health records (EHRs) and subsequent increased availability of longitudinal healthcare data has led to significant advances in our understanding of health and disease with direct and immediate impact on the development of new diagnostics and therapeutic treatment options. However, access to EHRs is often restricted due to their perceived sensitive nature and associated legal concerns, and the cohorts therein typically are those seen at a specific hospital or network of hospitals and therefore not representative of the wider population of patients. Here, we present HealthGen, a new approach for the conditional generation of synthetic EHRs that maintains an accurate representation of real patient characteristics, temporal information and missingness patterns. We demonstrate experimentally that HealthGen generates synthetic cohorts that are significantly more faithful to real patient EHRs than the current state-of-the-art, and that augmenting real data sets with conditionally generated cohorts of underrepresented subpopulations of patients can significantly enhance the generalisability of models derived from these data sets to different patient populations. Synthetic conditionally generated EHRs could help increase the accessibility of longitudinal healthcare data sets and improve the generalisability of inferences made from these data sets to underrepresented populations.

Global healthcare fairness: We should be sharing more, not less, data.

The availability of large, deidentified health datasets has enabled significant innovation in using machine learning (ML) to better understand patients and their diseases. However, questions remain regarding the true privacy of this data, patient control over their data, and how we regulate data sharing in a way that that does not encumber progress or further potentiate biases for underrepresented populations. After reviewing the literature on potential reidentifications of patients in publicly available datasets, we argue that the cost-measured in terms of access to future medical innovations and clinical software-of slowing ML progress is too great to limit sharing data through large publicly available databases for concerns of imperfect data anonymization. This cost is especially great for developing countries where the barriers preventing inclusion in such databases will continue to rise, further excluding these populations and increasing existing biases that favor high-income countries. Preventing artificial intelligence's progress towards precision medicine and sliding back to clinical practice dogma may pose a larger threat than concerns of potential patient reidentification within publicly available datasets. While the risk to patient privacy should be minimized, we believe this risk will never be zero, and society has to determine an acceptable risk threshold below which data sharing can occur-for the benefit of a global medical knowledge system.

Forecasting the COVID-19 Pandemic: Lessons learned and future directions.

I.The Coronavirus Disease 2019 (COVID-19) has demonstrated that accurate forecasts of infection and mortality rates are essential for informing healthcare resource allocation, designing countermeasures, implementing public health policies, and increasing public awareness. However, there exist a multitude of modeling methodologies, and their relative performances in accurately forecasting pandemic dynamics are not currently comprehensively understood. In this paper, we introduce the non-mechanistic MIT-LCP forecasting model, and assess and compare its performance to various mechanistic and non-mechanistic models that have been proposed for forecasting COVID-19 dynamics. We performed a comprehensive experimental evaluation which covered the time period of November 2020 to April 2021, in order to determine the relative performances of MIT-LCP and seven other forecasting models from the United States' Centers for Disease Control and Prevention (CDC) Forecast Hub. Our results show that there exist forecasting scenarios well-suited to both mechanistic and non-mechanistic models, with mechanistic models being particularly performant for forecasts that are further in the future when recent data may not be as informative, and non-mechanistic models being more effective with shorter prediction horizons when recent representative data is available. Improving our understanding of which forecasting approaches are more reliable, and in which forecasting scenarios, can assist effective pandemic preparation and management.

Detection of diabetes from whole-body MRI using deep learning.

Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be further, hitherto unknown, features of body fat distribution that could additionally contribute to the disease. We used machine learning with dense convolutional neural networks to detect diabetes-related variables from 2371 T1-weighted whole-body MRI data sets. MRI was performed in participants undergoing metabolic screening with oral glucose tolerance tests. Models were trained for sex, age, BMI, insulin sensitivity, HbA1c, and prediabetes or incident diabetes. The results were compared with those of conventional models. The area under the receiver operating characteristic curve was 87% for the type 2 diabetes discrimination and 68% for prediabetes, both superior to conventional models. Mean absolute regression errors were comparable to those of conventional models. Heatmaps showed that lower visceral abdominal regions were critical in diabetes classification. Subphenotyping revealed a group with high future diabetes and microalbuminuria risk.Our results show that diabetes is detectable from whole-body MRI without additional data. Our technique of heatmap visualization identifies plausible anatomical regions and highlights the leading role of fat accumulation in the lower abdomen in diabetes pathogenesis.

Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation.

Privacy concerns around sharing personally identifiable information are a major barrier to data sharing in medical research. In many cases, researchers have no interest in a particular individual's information but rather aim to derive insights at the level of cohorts. Here, we utilise generative adversarial networks (GANs) to create medical imaging datasets consisting entirely of synthetic patient data. The synthetic images ideally have, in aggregate, similar statistical properties to those of a source dataset but do not contain sensitive personal information. We assess the quality of synthetic data generated by two GAN models for chest radiographs with 14 radiology findings and brain computed tomography (CT) scans with six types of intracranial haemorrhages. We measure the synthetic image quality by the performance difference of predictive models trained on either the synthetic or the real dataset. We find that synthetic data performance disproportionately benefits from a reduced number of classes. Our benchmark also indicates that at low numbers of samples per class, label overfitting effects start to dominate GAN training. We conducted a reader study in which trained radiologists discriminate between synthetic and real images. In accordance with our benchmark results, the classification accuracy of radiologists improves with an increasing resolution. Our study offers valuable guidelines and outlines practical conditions under which insights derived from synthetic images are similar to those that would have been derived from real data. Our results indicate that synthetic data sharing may be an attractive alternative to sharing real patient-level data in the right setting.

Diurnal variations in multi-sensor wearable-derived sleep characteristics in morning- and evening-type shift workers under naturalistic conditions.

Consumer-grade, multi-sensor, rest-activity trackers may be powerful tools, to help optimize rest-activity management in shiftwork populations undergoing circadian misalignment. Nevertheless, performance testing of such devices under field conditions is scarce. We previously validated Fitbit Charge 2TM against home polysomnography and now evaluated the potential of this device to document differences in rest-activity behavior, including sleep macrostructure, in first-responder shift workers in an operational setting. We continuously monitored 89 individuals (54% females; mean age: 33.9 ± 7.7 years) for 32.5 ± 9.3 days and collected 2,974 individual sleep episodes scattered around the clock. We stratified the study participants according to their self-reported circadian preference on the reduced Horne-Östberg Morningness-Evening Questionnaire (rMEQ; the scores from 4 participants were missing). Fitbit estimates of sleep duration, wakefulness after sleep onset (WASO), REM sleep percentage in the first NREM-REM sleep cycle, and REM sleep latency formed approximately sinusoidal oscillations across 24 hours. Generalized additive mixed model analyses revealed that the phase position of sleep duration minimum was delayed by 2.8 h in evening types (ET; rMEQ ≤ 11; n = 20) and by 2.6 h in intermediate types (IT; 11 < rMEQ < 18; n = 45) when compared to morning types (MT; rMEQ ≥ 18; n = 20). Similarly, the phase position of WASO was delayed by 2.7 h in ET compared to MT. While nocturnal sleep duration did not differ among the three groups, sleep episodes during the biological day decreased in duration from ET to IT to MT. Together, the findings support the notion that a consumer-grade, rest-activity tracker allows estimation of behavioral sleep/wake cycles and sleep macrostructure in shift workers under naturalistic conditions that are consistent with their self-reported chronotype.

Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge.

Consumer wearables and sensors are a rich source of data about patients' daily disease and symptom burden, particularly in the case of movement disorders like Parkinson's disease (PD). However, interpreting these complex data into so-called digital biomarkers requires complicated analytical approaches, and validating these biomarkers requires sufficient data and unbiased evaluation methods. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of PD and severity of three PD symptoms: tremor, dyskinesia, and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC = 0.87), as well as tremor- (best AUPR = 0.75), dyskinesia- (best AUPR = 0.48) and bradykinesia-severity (best AUPR = 0.95).

Real-time prediction of COVID-19 related mortality using electronic health records.

Coronavirus disease 2019 (COVID-19) is a respiratory disease with rapid human-to-human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to the exponential growth of infections, identifying patients with the highest mortality risk early is critical to enable effective intervention and prioritisation of care. Here, we present the COVID-19 early warning system (CovEWS), a risk scoring system for assessing COVID-19 related mortality risk that we developed using data amounting to a total of over 2863 years of observation time from a cohort of 66 430 patients seen at over 69 healthcare institutions. On an external cohort of 5005 patients, CovEWS predicts mortality from 78.8% (95% confidence interval [CI]: 76.0, 84.7%) to 69.4% (95% CI: 57.6, 75.2%) specificity at sensitivities greater than 95% between, respectively, 1 and 192 h prior to mortality events. CovEWS could enable earlier intervention, and may therefore help in preventing or mitigating COVID-19 related mortality.

A Deep Learning Approach to Diagnosing Multiple Sclerosis from Smartphone Data.

Multiple sclerosis (MS) affects the central nervous system with a wide range of symptoms. MS can, for example, cause pain, changes in mood and fatigue, and may impair a person's movement, speech and visual functions. Diagnosis of MS typically involves a combination of complex clinical assessments and tests to rule out other diseases with similar symptoms. New technologies, such as smartphone monitoring in free-living conditions, could potentially aid in objectively assessing the symptoms of MS by quantifying symptom presence and intensity over long periods of time. Here, we present a deep-learning approach to diagnosing MS from smartphone-derived digital biomarkers that uses a novel combination of a multilayer perceptron with neural soft attention to improve learning of patterns in long-term smartphone monitoring data. Using data from a cohort of 774 participants, we demonstrate that our deep-learning models are able to distinguish between people with and without MS with an area under the receiver operating characteristic curve of 0.88 (95% CI: 0.70, 0.88). Our experimental results indicate that digital biomarkers derived from smartphone data could in the future be used as additional diagnostic criteria for MS.

Clinical Predictive Models for COVID-19: Systematic Study.

BACKGROUND: COVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU. OBJECTIVE: The aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care. METHODS: Using a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations. RESULTS: Our experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00). CONCLUSIONS: Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources.

Automated False Alarm Reduction in a Real-Life Intensive Care Setting Using Motion Detection.

BACKGROUND: Contemporary monitoring systems are sensitive to motion artifacts and cause an excess of false alarms. This results in alarm fatigue and hazardous alarm desensitization. To reduce the number of false alarms, we developed and validated a novel algorithm to classify alarms, based on automatic motion detection in videos. METHODS: We considered alarms generated by the following continuously measured parameters: arterial oxygen saturation, systolic blood pressure, mean blood pressure, heart rate, and mean intracranial pressure. The movements of the patient and in his/her surroundings were monitored by a camera situated at the ceiling. Using the algorithm, alarms were classified into RED (true), ORANGE (possibly false), and GREEN alarms (false, i.e., artifact). Alarms were reclassified by blinded clinicians. The performance was evaluated using confusion matrices. RESULTS: A total of 2349 alarms from 45 patients were reclassified. For RED alarms, sensitivity was high (87.0%) and specificity was low (29.6%) for all parameters. As the sensitivities and specificities for RED and GREEN alarms are interrelated, the opposite was observed for GREEN alarms, i.e., low sensitivity (30.2%) and high specificity (87.2%). As RED alarms should not be missed, even at the expense of false positives, the performance was acceptable. The low sensitivity for GREEN alarms is acceptable, as it is not harmful to tag a GREEN alarm as RED/ORANGE. It still contributes to alarm reduction. However, a 12.8% false-positive rate for GREEN alarms is critical. CONCLUSIONS: The proposed system is a step forward toward alarm reduction; however, implementation of additional layers, such as signal curve analysis, multiple parameter correlation analysis and/or more sophisticated video-based analytics are needed for improvement.

Oxide mediated spectral shifting in aluminum resonant optical antennas.

As a key feature among metals showing good plasmonic behavior, aluminum extends the spectrum of achievable plasmon resonances of optical antennas into the deep ultraviolet. Due to degradation, a native oxide layer gives rise to a metal-core/oxide-shell nanoparticle and influences the spectral resonance peak position. In this work, we examine the role of the underlying processes by applying numerical nanoantenna models that are experimentally not feasible. Finite-difference time-domain simulations are carried out for a large variety of elongated single-arm and two-arm gap nanoantennas. In a detailed analysis, which takes into account the varying surface-to-volume ratio, we show that the overall spectral shift toward longer wavelengths is mainly driven by the higher index surrounding material rather than by the decrease of the initial aluminum volume. In addition, we demonstrate experimentally that this shifting can be minimized by an all-inert fabrication and subsequent proof-of-concept encapsulation.