István Vassányi

Stress Detection Using Low Cost Heart Rate Sensors

The automated detection of stress is a central problem for ambient assisted living solutions. The paper presents the concepts and results of two studies targeted at stress detection with a low cost heart rate sensor, a chest belt. In the device validation study (n = 5), we compared heart rate data and other features from the belt to those measured by a gold standard device to assess the reliability of the sensor. With simple synchronization and data cleaning algorithm, we were able to select highly (>97%) correlated, low average error (2.2%) data segments of considerable length from the chest data for further processing. The protocol for the clinical study (n = 46) included a relax phase followed by a phase with provoked mental stress, 10 minutes each. We developed a simple method for the detection of the stress using only three time-domain features of the heart rate signal. The method produced accuracy of 74.6%, sensitivity of 75.0%, and specificity of 74.2%, which is impressive compared to the performance of two state-of-the-art methods run on the same data. Since the proposed method uses only time-domain features, it can be efficiently implemented on mobile devices.

Application of Artificial Intelligence for Weekly Dietary Menu Planning

Dietary menu planning is an important part of personalized lifestyle counseling. The chapter describes the results of an automated menu generator (MenuGene) of the web-based lifestyle counseling system Cordelia that provides personalized advice to prevent cardiovascular diseases. The menu generator uses Genetic Algorithms to prepare weekly menus for web users. The objectives are derived from personal medical data collected via forms, combined with general nutritional guidelines. The weekly menu is modeled as a multi-level structure. Results show that the Genetic Algorithm based method succeeds in planning dietary menus that satisfy strict numerical constraints on every nutritional level (meal, daily basis, weekly basis). The rule-based assessment proved capable of manipulating the mean occurrence of the nutritional components thus providing a method for adjusting the variety and harmony of the menu plans. By splitting the problem into well determined subproblems, weekly menu plans that satisfy nutritional constraints and have well assorted components can be generated with the same method that is used for daily and meal plan generation.

The impact of geographical distances to coronary angiography laboratories on the patient evaluation pathways in patients with suspected coronary artery disease. Results from a population-based study in Hungary.

Introduction Coronary artery disease (CAD) has been a leading cause of death in the western world for the last few decades, despite significant improvements in treatment and management. Diagnostic algorithms for the evaluation of patients with suspected CAD are based on available guidelines. Aim To evaluate the impact of geographical distances to coronary angiography laboratories on the patient evaluation pathways in patients with suspected CAD, from a population-based study in Hungary. Material and methods Depersonalised data of 29,202 patients identified by their pseudo-social security number were analysed. All patients underwent coronary angiography as an initial direct invasive investigation (DI) following an at least half-year-long stable period between 1 January 2004 and 31 December 2008. Results One hundred and thirty-five dominant primary cardiology centres (PCC) have been identified, from which 85 proved to have sample size more than 100 DIs in tertiary cardiology centres (TCC). The frequency of DIs showed a close correlation with PCC-TCC distances (r = –0.44, p < 0.001). A negative correlation could be demonstrated between the age of patients and PCC-TCC distances (r = –0.45, p < 0.001). Without significant change in the absolute mortality, the relative mortality increased with the increase in PCC-TCC distance (r = 0.25, p < 0.05). Conclusions The PCC-TCC distance has an important effect on patient pathways in subjects with suspected CAD.

GAME: GPU accelerated multipurpose evolutionary algorithm library

The use of genetic algorithms GAs has grown to widespread acceptance by providing an efficient way to solve complex problems lacking deterministic solvers. GAs employ a special stochastic search method based on evolutionary theory, which gives them the ability to outperform most traditional search algorithms. Also their use of independent individuals makes them an ideal candidate for parallelisation enhancing their inherently good performance even further. Their parallelisability on graphical processing units GPU had been shown multiple times, but the implementations were either single-objective GAs or just partially accelerated by GPUs, also every time they were experimental designs. The genetic algorithm library discussed in this article is the first that contains fully parallelised GPU implementations of multi-objective genetic algorithms besides the single-objective ones. Furthermore, it is organised into a ready to use framework, which provides flexible and efficient GPU accelerated GAs. Thus, enabling the user to solve complex problems faster than standard CPU-based implementations would allow and with lower overall energy cost.

Personalized Nutrition Counseling Expert System

This paper gives an overview of the MenuGene nutrition counseling expert system and its main components, focusing on home health monitoring / dietary logging. Pub- lished solutions so far can satisfy nutrient constraints, but does not take harmony rules into account. The novelty of the algo- rithm used by MenuGene is that dietetic knowledge including harmony rules can take part of the menu synthesis process. Our results show that a considerable part of dietary counseling can be extended by computer aided approach, if we provide easy to use interfaces for patients and dietetic experts. Accord- ing to our tests with volunteers an average logging accuracy of ca. 15% can be achieved with our Dietlog web interface.

A formal domain model for dietary and physical activity counseling

Diet and physical activity planning is a complex process that usually comprises repetitive expert-patient discussions and multihour construction phases. Recent advances in artificial intelligence and improvements in CPU speeds make it now possible to enhance or even substitute the work of the dietary expert. Although research in this field began as early as the 1940s, no comprehensive domain model has been developed to date. Previous works reduced the problem to then solvable mathematical models, thus lessening the quality of the solution. Here, we present a novel domain model which can handle the multi-objective nature of the problem as well as the proper use of expert knowledge on dietary harmony. The model provides a base for the computerized planning of human-competetive solutions. An implementation of this model is employed in the nutrition and lifestyle counseling expert system Menugene.

An evolutionary divide and conquer method for long-term dietary menu planning

We present a novel Hierarchical Evolutionary Divide and Conquer method for automated, long-term planning of dietary menus. Dietary plans have to satisfy multiple numerical constraints (Reference Daily Intakes and balance on a daily and weekly basis) as well as criteria on the harmony (variety, contrast, color, appeal) of the components. Our multi-level approach solves problems via the decomposition of the search space and uses good solutions for sub-problems on higher levels of the hierarchy. Multi-Objective Genetic Algorithms are used on each level to create nutritionally adequate menus with a linear fitness combination extended with rule-based assessment. We also apply case-based initialization for starting the Genetic Algorithms from a better position of the search space. Results show that this combined strategy can cope with strict numerical constraints in a properly chosen algorithmic setup.

Correlation Clustering of Stable Angina Clinical Care Patterns for 506 Thousand Patients

Objectives Our goal was to apply statistical and network science techniques to depict how the clinical pathways of patients can be used to characterize the practices of care providers. Methods We included the data of 506,087 patients who underwent procedures related to ischemic heart disease. Patients were assigned to one of the 136 primary health-care centers using a voting scheme based on their residence. The clinical pathways were classified, and the spectrum of the pathway types was computed for each center, then a network was built with the centers as nodes and spectrum correlations as edge weights. Then Louvain clustering was used to group centers with similar pathway spectra. Results We identified 3 clusters with rather distinct characteristics that occupy quite compact spatial areas, though no geographical information was used in clustering. Network analysis and hierarchical clustering show the dominance of medical university clinics in each cluster. Conclusion Though clinical guidelines provide a uniform regulation for medical decisions, doctors have great freedom in daily clinical practice. This freedom leads to regional preferences of certain clinical pathways, the intercenter professional links, and geographical locality and coupled with quantifiable consequences in terms of care costs and periprocedural risk of patients.

Diabetesesek dietoterápiájának és önmenedzselésének támogatása mobilapplikációk használatával

Absztrakt A diabetes tobb pilleren nyugvo terapiajanak sikeressegehez a gyogyszeres, illetve az inzulinterapian, esetenkent a korhazi kezelesen tul elengedhetetlen fontossagu a helyes eletmod elsajatitasa, az eletmod-terapia. A betegseg onmenedzseleseben, a helyes eletmod, etrend kialakitasaban nyujtanak segitseget a mobilalkalmazasok. A szerzők attekintest adnak a hazai mobil- es/vagy online alkalmazasok etrendi ertekeleseről, osszehasonlitva őket nehany jellemző kulfoldi alkalmazassal. A szamos hasznos funkcio mellett a dietetikai ajanlasok alapjan tobb hianyossagot is feltartnak, amelyek kikuszobolese, illetve a hatekonysag es megbizhatosag validalasat celzo klinikai vizsgalatok az orvosi evidenciak erősiteset, valamint az ilyen jellegű alkalmazasok tovabbi terjedeset is elősegithetik. Orv. Hetil., 2016, 157(29), 1147–1153.

Combined model for diabetes lifestyle support

Treatment of diabetes mellitus is a public health related problem of modern healthcare. Surveys show that current methods to estimate the required amount of insulin are quite inefficient in practice as they are based on experience. This paper offers a new approach to predict the glucose level of people with diabetes. It combines two efficient models of the literature: one for nutrient absorption and one for glucose control. The combination of them tracks the blood sugar level considering nutrition composition, applied insulin and initial glucose level. Compared to already existing mixed meal models, the current version takes into account a more detailed nutrition composition (protein, lipid, monosaccharide, fiber and starch) supported by our expert dietary systems. Although the model gives satisfactory results even with parameter sets taken from literature, parameter training by genetic algorithms yields a better tracking of the patients.