Interactive visual knowledge discovery from data-based temporal decision support system

2015 ◽  
Vol 15 (1) ◽  
pp. 31-50 ◽  
Author(s):  
Hela Ltifi ◽  
Emna Ben Mohamed ◽  
Mounir ben Ayed

The article aims to present a generic interactive visual analytics solution that provides temporal decision support using knowledge discovery from data modules together with interactive visual representations. It bases its design decisions on classification of visual representation techniques according to the criteria of temporal data type, periodicity, and dimensionality. The design proposal is applied to an existing medical knowledge discovery from data–based decision support system aiming at assisting physicians in the fight against nosocomial infections in the intensive care units. Our solution is fully implemented and evaluated.

Author(s):  
Iman Barazandeh ◽  
Mohammad Reza Gholamian

The healthcare industry is one of the most attractive domains to realize the actionable knowledge discovery objectives. This chapter studies recent researches on knowledge discovery and data mining applications in the healthcare industry and proposes a new classification of these applications. Studies show that knowledge discovery and data mining applications in the healthcare industry can be classified to three major classes, namely patient view, market view, and system view. Patient view includes papers that performed pure data mining on healthcare industry data. Market view includes papers that saw the patients as customers. System view includes papers that developed a decision support system. The goal of this classification is identifying research opportunities and gaps for researchers interested in this context.


2016 ◽  
pp. 1097-1118 ◽  
Author(s):  
Iman Barazandeh ◽  
Mohammad Reza Gholamian

The healthcare industry is one of the most attractive domains to realize the actionable knowledge discovery objectives. This chapter studies recent researches on knowledge discovery and data mining applications in the healthcare industry and proposes a new classification of these applications. Studies show that knowledge discovery and data mining applications in the healthcare industry can be classified to three major classes, namely patient view, market view, and system view. Patient view includes papers that performed pure data mining on healthcare industry data. Market view includes papers that saw the patients as customers. System view includes papers that developed a decision support system. The goal of this classification is identifying research opportunities and gaps for researchers interested in this context.


2018 ◽  
pp. 2161-2182
Author(s):  
Iman Barazandeh ◽  
Mohammad Reza Gholamian

The healthcare industry is one of the most attractive domains to realize the actionable knowledge discovery objectives. This chapter studies recent researches on knowledge discovery and data mining applications in the healthcare industry and proposes a new classification of these applications. Studies show that knowledge discovery and data mining applications in the healthcare industry can be classified to three major classes, namely patient view, market view, and system view. Patient view includes papers that performed pure data mining on healthcare industry data. Market view includes papers that saw the patients as customers. System view includes papers that developed a decision support system. The goal of this classification is identifying research opportunities and gaps for researchers interested in this context.


Author(s):  
Ахмед Магомедович Денгаев

Одним из перспективных и эффективных направлений автоматизированной диагностики заболевания является использование системы распознавания медицинских образов. Главная задача - это максимально точная интерпретация изображения. Прежде всего, необходимо правильно формализовать задачу, провести структуризацию основных условий функционирования системы. В статье составлено содержательное описание предметной области, разработано формализованная схема исследуемой системы. Обозначено, что решение задачи структуризации сводится к разработке отдельных классов, сгруппированных по общим признакам и характеристикам болезни. В этом случае точность и информативность диагноза будет зависеть от полноты базы данных конкретного класса. Приведена математическая интерпретация отношений и связей элементов системы. Применение математических моделей и алгоритмов в медицине является важной задачей. Выбор того или иного алгоритма определяется решаемой задачей. Необходимо понимать, что получаемый результат особо ценен, если он подтверждается математическими расчетами. Предложена многоуровневая архитектура системы поддержки принятия решений, где ключевое место отведено модулю автоматизированной диагностики и распознавания изображения. Отмечено, что при создании системы поддержки принятия решения в медицине специалисты сталкиваются с двумя концептуальными барьерами: первый - связан с колоссальным объемом медицинских знаний, а второй - с постоянным обновлением этих знаний и технологий их обработки. Поэтому главной задачей является правильная структуризация и формализация системы поддержки принятия решений для его эффективного применения One of the most promising and effective areas of automated diagnosis of the disease is the use of a medical image recognition system. The main task is to interpret the image as accurately as possible. First of all, it is necessary to properly formalize the task, to structure the basic conditions for the functioning of the system. The article contains a meaningful description of the subject area, and a formalized scheme of the system under study is developed. It is indicated that the solution to the problem of structuring is reduced to the development of separate classes grouped by common signs and characteristics of the disease. In this case, the accuracy and informativeness of the diagnosis will depend on the completeness of the database of a particular class. The mathematical interpretation of the relations and connections of the system elements is given. The application of mathematical models and algorithms in medicine is an important task. The choice of an algorithm is determined by the problem being solved. It is necessary to understand that the result obtained is particularly valuable if it is confirmed by mathematical calculations. A multi-level architecture of the decision support system is proposed, where the key place is given to the module of automated diagnostics and image recognition. It is noted that when creating a decision support system in medicine, specialists face two conceptual barriers: the first one is associated with a huge amount of medical knowledge, and the second one is associated with the constant updating of this knowledge and technologies for their processing. Therefore, the main task is to properly structure and formalize the decision support system for its effective application


2019 ◽  
Vol 82 (6) ◽  
pp. 775-785 ◽  
Author(s):  
Tanzila Saba ◽  
Sana Ullah Khan ◽  
Naveed Islam ◽  
Naveed Abbas ◽  
Amjad Rehman ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document