Search

AbstractBackground Diabetic retinopathy (DR) is a common complication of diabetes and may lead to irreversible visual loss. Efficient screening and improved treatment of both diabetes and DR have amended visual prognosis for DR. The number of patients with diabetes is increasing and telemedicine, mobile handheld devices and automated solutions may alleviate the burden for healthcare. We compared the performance of 21 artificial intelligence (AI) algorithms for referable DR screening in datasets taken by handheld Optomed Aurora fundus camera in a real-world setting.Patients and methods Prospective study of 156 patients (312 eyes) attending DR screening and follow-up. Both papilla- and macula-centred 50° fundus images were taken from each eye. DR was graded by experienced ophthalmologists and 21 AI algorithms.Results Most eyes, 183 out of 312 (58.7%), had no DR and mild NPDR was noted in 21 (6.7%) of the eyes. Moderate NPDR was detected in 66 (21.2%) of the eyes, severe NPDR in 1 (0.3%), and PDR in 41 (13.1%) composing a group of 34.6% of eyes with referable DR. The AI algorithms achieved a mean agreement of 79.4% for referable DR, but the results varied from 49.4% to 92.3%. The mean sensitivity for referable DR was 77.5% (95% CI 69.1–85.8) and specificity 80.6% (95% CI 72.1–89.2). The rate for images ungradable by AI varied from 0% to 28.2% (mean 1.9%). Nineteen out of 21 (90.5%) AI algorithms resulted in grading for DR at least in 98% of the images.Conclusions Fundus images captured with Optomed Aurora were suitable for DR screening. The performance of the AI algorithms varied considerably emphasizing the need for external validation of screening algorithms in real-world settings before their clinical application.

Background: Cardiac sarcoidosis (CS) is a rare but potentially fatal inflammatory cardiomyopathy. Objectives: The authors studied temporal changes in the incidence, characteristics, and outcome of CS. Methods: A retrospective analysis was made of a 30-year nationwide cohort of CS. Results: The cohort comprised 511 patients with a median age of 52 years and female preponderance (69%). Altogether 77, 166, and 268 cases of CS were diagnosed in years 1988 to 2009, 2010 to 2014, and 2015 to 2019, respectively; the 5-year count of 2015 to 2019 was 134-fold the count of 1990 to 1994 (268/2) and 18-fold the count of 2000 to 2004 (268/15). Prior to 2010, compared with the later periods, CS presented more often with ventricular tachycardia/fibrillation (prevalence 36% vs 19% in 2010-2014 and 11% in 2015-2019, P

Abstract Deep Neural Networks (DNN’s) present some of the leading applications of Artificial Intelligence (AI) which have proven suitability on various machine-learning use cases. Forecasting demand of intermittent on-line sales is a task which needs to be carried out automatically for a large number of Stock Keeping Units (SKU’s). This paper discusses the intermittent online sales and proposes an AI-based model for forecasting demand. We provide empirical evidence by utilizing data from 17 different sellers with approximately 3000 orders in total. Our findings indicate that thanks to their multi-layered learning structure, the DNN’s can provide up to 35% better accuracy than the classic models such as Moving Average, Exponential Smoothing, Croston’s method and ARIMA. Also, it was revealed that the time between orders’ arrivals follow Exponential distribution and the order sizes also generally follow Exponential distribution. Thus, most of the time, Poisson Exponential distribution can be used for modelling intermittent sales process through online platforms. The analyses show that Poisson Exponential distribution can generate values close to real sales with less than 7% error margin with real data.

This paper aims to model and minimize transportation costs in collecting tree logs from several regions and delivering them to the nearest collection point. This paper presents agent-based modeling (ABM) that comprehensively encompasses the key elements of the pickup and delivery supply chain model and presents the units as autonomous agents communicating. The modeling combines components such as geographic information systems (GIS) routing, potential facility locations, random tree log pickup locations, fleet sizing, trip distance, and truck and train transportation. ABM models the entire pickup and delivery operation, and modeling outcomes are presented by time series charts such as the number of trucks in use, facilities inventory, and travel distance. In addition, various simulation scenarios are used to investigate potential facility locations and truck numbers and determine the optimal facility location and fleet size.

The pedagogy and practices of folk music and folk dance are firmly separate in Finland. Furthermore, the expertise in these fields focuses heavily on folk music and dance as performing arts rather than communal activities. The situation has led to the differentiation and fragmentation of professional and amateur activities. To address this gap in knowledge and practice, the KanTaMus project intends to present a pedagogical model for a joint participatory folk dance and music pedagogy devised through practice-based development work. This article explains the basic premises of the model under development. We first discuss the legacy issues crucial in Finnish folk dance and music and its pedagogy. Secondly, we outline the values, pedagogical principles, and prior development work we see as fundamental to our work. Martin Seligman's PERMA theory serves as an overall canvas for our development work. The basic elements of the theory, i.e., positive emotions, engagement, relationships, meaning, and accomplishment, work as a basis for our model, which emphasises embodied presence, inclusion, and interaction as crucial features of a shared learning situation in dance and music. Finally, we present the pairing process as a specific example of the application of the model.

AbstractBackground In young patients, up to 40% of ischemic strokes remain cryptogenic despite modern-day diagnostic work-up. There are limited data on blood pressure (BP) behavior in these patients. Thus, we aimed to compare ambulatory blood pressure (ABP) profiles between young patients with a recent cryptogenic ischemic stroke (CIS) and stroke-free controls.Patients and Methods In this substudy of the international multicenter case–control study SECRETO (NCT01934725), 24-hour ambulatory blood pressure monitoring (ABPM) was performed in consecutive 18–49-year-old CIS patients and stroke-free controls. The inclusion criteria were met by 132 patients (median age, 41.9 years; 56.1% males) and 106 controls (41.9 years; 56.6% males). We assessed not only 24-hour, daytime, and nighttime ABP but also hypertension phenotypes and nocturnal dipping status.Results 24-hour and daytime ABP were higher among controls. After adjusting for relevant confounders, a non-dipping pattern of diastolic blood pressure (DBP) was associated with CIS in the entire sample (odds ratio, 3.85; 95% confidence interval, 1.20–12.42), in participants without antihypertensives (4.86; 1.07–22.02), and in participants without a patent foramen ovale (PFO) (7.37; 1.47–36.81). After excluding patients in the first tertile of the delay between the stroke and ABPM, a non-dipping pattern of DBP was not associated with CIS, but a non-dipping pattern of both systolic BP and DBP was (4.85; 1.37–17.10). In participants with a PFO and in those without hypertension by any definition, no associations between non-dipping patterns of BP and CIS emerged.Conclusions Non-dipping patterns of BP were associated with CIS in the absence of a PFO but not in the absence of hypertension. This may reflect differing pathophysiology underlying CIS in patients with versus without a PFO. Due to limitations of the study, results regarding absolute ABP levels should be interpreted with caution.Key MessagesNocturnal non-dipping patterns of blood pressure were associated with cryptogenic ischemic stroke except in participants with a patent foramen ovale and in those without hypertension by any definition, which may indicate differing pathophysiology underlying cryptogenic ischemic stroke in patients with and without a patent foramen ovale.It might be reasonable to include ambulatory blood pressure monitoring in the diagnostic work-up for young patients with ischemic stroke to detect not only the absolute ambulatory blood pressure levels but also their blood pressure behavior.

Lipid-related thiamine (vitamin B1) deficiency of Baltic salmon (Salmo salar), the M74 syndrome, is generally caused by feeding on abundant young sprat (Sprattus sprattus) in the Baltic Proper, the main foraging area of these salmon. In 2014, a strong year-class of sprat was hatched in the Baltic Proper, and a strong herring (Clupea harengus) year-class was hatched in the Gulf of Bothnia, where herring is the dominant salmon prey. The fatty acid (FA) signatures of prey fish in muscle or eggs of second sea-year spawners suggested that 27% of wild River Simojoki and 68% of reared River Dal salmon remained in the Gulf of Bothnia in 2014 instead of continuing to the Baltic Proper. In 2016, 23% of the M74 females of the River Simojoki and 58% of the River Dal originated from the Gulf of Bothnia, and 13% and 16%, respectively, originated from the Baltic Proper. Some salmon from the River Neris in the southern Baltic Proper had also been feeding in the Gulf of Bothnia. In general, low free thiamine (THIAM) concentration in eggs was associated with high lipid content and high docosahexaenoic acid (DHA, 22:6n−3) and n−3 polyunsaturated FA (n−3 PUFA) concentrations in muscle but not in eggs. A higher THIAM concentration and lower proportions of DHA and n−3 PUFAs in Arctic Ocean salmon eggs, despite higher egg lipid content, indicated that their diet contained fewer fatty fish than the Baltic salmon diet. Hence, M74 originated by foraging heavily on young fatty sprat in the Baltic Proper or herring in the Gulf of Bothnia.

This paper describes the safety assessment conducted in SESAR2020 project PJ.10-W2-96 ASR on automatic speech recognition (ASR) technology implemented for air traffic control (ATC) centers. ASR already now enables the automatic recognition of aircraft callsigns and various ATC commands including command types based on controller–pilot voice communications for presentation at the controller working position. The presented safety assessment process consists of defining design requirements for ASR technology application in normal, abnormal, and degraded modes of ATC operations. A total of eight functional hazards were identified based on the analysis of four use cases. The safety assessment was supported by top-down and bottom-up modelling and analysis of the causes of hazards to derive system design requirements for the purposes of mitigating the hazards. Assessment of achieving the specified design requirements was supported by evidence generated from two real-time simulations with pre-industrial ASR prototypes in approach and en-route operational environments. The simulations, focusing especially on the safety aspects of ASR application, also validated the hypotheses that ASR reduces controllers’ workload and increases situational awareness. The missing validation element, i.e., an analysis of the safety effects of ASR in ATC, is the focus of this paper. As a result of the safety assessment activities, mitigations were derived for each hazard, demonstrating that the use of ASR does not increase safety risks and is, therefore, ready for industrialization.