The system can be queried to display previously annotated patient images from a knowledge base of previous patient profiles for comparative studies to aid with more effective diagnosis and treatment.
Physicians use the mobile application on a PDA or a tablet PC to input, retrieve and view patient data and to quickly enter information about patient progress into electronic charts in real time. The PDA allows for improved mobility due to its reduced size and weight.
The tablet PC provides a more comprehensive user interface and additional functionality such as the ability to view and annotate medical imagery due to the larger screen size and higher processing power.
Both of the wireless devices can take advantage of any All of the information for each patient is stored as an integrated patient profile in a database and all interactions by healthcare workers are recorded by the system.
Both the PDA and the tablet PC can be used wirelessly at different locations around the hospital or in other situations where such facilities are not normally available e. They may also be used to access other resources such as online drug references or medical encyclopaedias.
The mobile devices may also be used to query the central repository of patient profiles with information specific to a particular illness to retrieve similar patient case histories that may help with a diagnosis by providing comparative assistance. Figure 1 shows the scrollable tabbed interfaces implemented for the PDA for inputting, querying and viewing textual patient data, while Figures 2—4 show the same information as displayed on the tablet PC.
Image retrieval Continuing advances in techniques for digital image capture and storage have given rise to a significant problem of information overload in the medical imagery domain. It has therefore become increasingly critical to provide intelligent application support for managing large repositories of medical imagery. The majority of current medical image retrieval techniques retrieve images by similarity of appearance, using low-level features such as shapes, or by natural language textual querying where similarity is determined by comparing words in a query string against words in semantic image metadata tags.
In order to overcome these difficulties our application aims to unite information about underlying visual data with more high-level concepts provided by healthcare professionals as they interact with medical imagery. For example, capturing a measure of human expertise and proficiency involved in making a diagnosis from an X-ray image allows us to understand why relevant information was selected e. The approach allows us to capture and reuse best practice techniques by automatically constructing a knowledge base of previous user interactions using CBR techniques.
This knowledge base can be exploited to improve future query processing by retrieving and reusing similar expert experiences, as the illness or injury of a presenting patient can now be grounded in the context of previous similar patients. The caregiver can retrieve relevant patient imagery by entering context about the current presenting patient to the retrieval system.
For example a radiologist may be viewing an X-ray image and may be having difficulty in diagnosing the problem from the particular image. The X-ray however may remind him of an image he viewed previously and he may remember some of the details of the previous patient. In this scenario the radiologist could input the details of the previous patient as search parameters to the application. Mobile decision support any similarities.
If any of the similar images had been annotated during diagnosis the radiologist may study these notes for extra information regarding the specific injury or illness. In another example, a radiologist may be diagnosing a patient from an MRI scan. The radiologist may be having difficulty in diagnosing the patient as they may not have previously encountered the particular injury or illness. In this situation the radiologist may wish to view other patient images and diagnoses to make a confident assessment so they could focus their search on the patient symptoms and retrieve information based on this parameter.
The radiologist could compare the images and profiles with the current patient, using the application as a support for his eventual decision. The resulting images are displayed in Figure 6. Image annotation tools Many new radiology applications have integrated annotation tools where radiologists can annotate patient imagery e. DICOM images in an appropriate fashion while diagnosing patients. The tools we have developed are a subset of those normally found in image processing applications and have been specifically selected and designed for specialized radiography tasks e.
DICOM, X-ray as all applied annotations are layered on top of the image and so do not alter the underlying raster. This information is collected implicitly to shield the radiographer from the burden of explicit knowledge engineering. From their perspective, the image interaction tools support them in carrying out their task e. The user can add media annotations to images as a whole or to particular highlighted aspects as depicted in Figure 7. Currently, the system supports annotation by text including a facility to upload web documents , audio and video.
All textual, audio and video annotations can be previewed before being incorporated as part of the knowledge base, and once recorded can be saved and uploaded to the image as a knowledge parcel associated with the particular patient.
The system also supports annotation by cut, copy and paste between a given image and other images in the dataset, as well as any application that supports clipboard functionality.
Once the radiologist has finished interacting with the imagery their entire work process is stored along with all other patient data as an encapsulated patient profile in the knowledge base. Mobile decision support Figure 7 Image annotation Case retrieval As the system builds up encapsulated user interactions, another type of retrieval is enabled, retrieving entire previous patient case histories.
For example, a physician may have diagnosed a patient as having a particular illness but may not be entirely sure what treatment to recommend. He may then study these patients to find those whose diagnosis is most relevant to the current patient. He may access the full treatment planning processes for each of these patients as well as any recorded outcomes.
He can also use the application to access medical reference resources about the medication prescribed as part of these treatment processes. Or in a different example a physician may have diagnosed a patient and be aware that a new drug is currently being tested on patients with the particular illness.
The physician may be interested to see if this patient qualifies for the new treatment based on information such as age and allergies. By querying the application she can view profiles of patients currently being prescribed the medication and see how they are responding to the treatment contained in up-to-date patient status reports. All of this information can be quickly accessed at any location using wireless technologies through the one integrated application, thereby reducing the time and complexity in recommending the new treatment.
An obvious application of this facility to retrieve and reuse similar patient case histories is that of medical education. Medical students preparing to work with real patients in hospital wards could have access to this rich knowledge resource that offers actual experiential advice and instruction on how to diagnose and treat patients according to many kinds of patient data including symptoms, examinations, laboratory results, and medical imagery.
Figure 9 shows an example of retrieved case histories on the tablet PC. Each row represents a patient case history and is summarized to show the most important information for that patient. It includes a matching percentage score between the current query and the similar profile, as well as the symptoms, diagnosis, applied treatments and outcomes for similar case. Our application offers several advantages over existing EHR systems. First, by reusing case histories and collective knowledge in support of similar diagnoses or treatments, the time required to diagnose and treat a new patient can be significantly reduced.
In addition, the approach facilitates knowledge sharing by retrieving potentially relevant knowledge from other patient case histories. Mobile decision support Figure 9 Retrieved patient profiles relating to particular patients, diagnoses, symptoms, treatments and outcomes may now be stored to create accessible organizational knowledge.
Calculating patient diagnoses and treatment similarity Retrieval within the system is taking place in the context of an overall workflow. Some of the most important steps in this workflow which may or may not be relevant to all patients are: entering preliminary patient details, recording results of an initial examination, inputting presenting conditions, uploading and annotating medical imagery, recording diagnoses and recommending treatments.
Most patient profiles will consist of some if not most of the information described above. Given a textual representation of these patient profiles, we can match textual queries imputed by a caregiver to patient cases in the knowledge base or case base of previous patients.
The task-based retrieval system employs indexes in separate spaces for the constituent textual segments of the patient profile. When a caregiver enters a textual query the parameters and the weights that they specify are combined and compared to existing patient cases in the case base of previous patients and a weighted average is used to compute similarity between the current patient and other patients from the central medical database.
These indices are used to calculate similarity in both retrieval of medical images and retrieval of patient case histories. Evaluation In an evaluation of our approach we conducted testing with an online dataset of encapsulated patient profiles with associated annotated medical imagery from the dermatology domain [7]. Henry Odeyinka. A short summary of this paper.
A knowledge-based decision support system for roofing materials selection. It requires synthesising a multitude of performance criteria such as initial cost, maintenance cost, thermal performance and sustainability among others.
This research aims to develop a Knowledge-based Decision support System for Material Selection KDSMS that facilitates the selection of optimal material for different sub elements of a roof design. The proposed system also has a facility for estimating roof cost based on the identified criteria. This paper presents the data modelling conceptual framework for the proposed system. This model consists of a knowledge base and a database to store different types of roofing materials with their corresponding performance characteristics and rankings.
The proposed system employs the multi criteria decision method of TOPSIS Technique of ranking Preferences by Similarity to the Ideal Solution , to resolve the materials selection and optimisation problem. High quality building with life time cost effectiveness is always preferred by the clients Schade, But the selection of materials is always a 1 Rahman-ms email.
In: Dainty, A. It is acknowledged that material selection has significant impact on the cost of a building Malin, ; Mohamed and Celik, ; however the selection of appropriate materials may reduce the energy consumption and maintenance cost of buildings Papadopoulos and Giama, Moreover, the selection of appropriate materials may impact significantly on the environment that helps to improve the decision making of green construction Castro-Lacouture et al.
It is documented that buildings are responsible for significant impact on the environment; hence eco-friendly materials are becoming popular Hymers, ; Spiegel and Meadows, Different approaches regarding materials selection have been devised for different purposes.
Multiple criteria approach have been considered regarding material selection for different application areas, such as engineering Rao, ; Shanian and Savadogo, ; Ashby et al. Moreover, knowledge-based or expert systems have been developed to select materials for different purposes; Chen et al.
Mahmoud et al. Mohamed and Celik proposed a knowledge-based method regarding materials selection and cost estimating for a residential building where users could be able to choose their preferred one from list of materials without evaluation and synthesis of multiple design criteria and client requirements. Unlike the expert or knowledge-based system, Perera and Fernando proposed a cost modelling system for roofing material selection where several factors have been identified and considered in the selection process.
Soronis proposed an approach to the selection of roofing materials where several factors have been taken into consideration to assess durability.
It is identified that very few approaches have been developed for roofing materials selection. Some methods that have been developed for materials selection in other sectors are not suitable for the selection of building materials because every sector has its own selection criteria to meet the design requirements. This requires considering multiple criteria ranging from initial cost and maintenance cost to durability and sustainability. The information overload may exacerbate this appropriate material and technology selection.
This research aims to bridge this knowledge gap by developing a Knowledge-based Decision support System for Material Selection KDSMS that helps to optimise the selection of roofing materials and technologies. It assists the users in selecting materials according to importance of pre-defined criteria.
This system also educates the users about new materials by providing relevant information in multi-media formats and through internet. In addition, the system also assists the users in estimating the cost of roof element based on selected materials. Any knowledge-based system consists of three main components those are a user interface, knowledge base and an inference engine or a control mechanism Mockler and Dologite, The proposed knowledge-based system, KDSMS, captures knowledge from technical literature and domain experts to build the knowledge base.
It queries the knowledge base by the inference engine and provides the information to users through the user interface. Expert forum comprises of the architects and quantity surveyors who have the required knowledge about building design requirements and selection of materials. Data is collected from technical literature sources such as catalogues of manufacturers, data sheets, specification schedules, text books, price guide books and internet.
Knowledge base This consists of the material selection and cost estimating processes. As selection of materials is associated with multiple criteria, a multi criteria decision making technique, TOPSIS, is incorporated to solve decision making problem Rahman et al. It also contains building regulations and other selection factors that may influence the type of materials or technologies selected. It comprises of a decision support shell that can facilitate reaching a decision in selection of the optimal material by using TOPSIS.
Basically, a particular solution to resolve the problem of roofing materials selection under a particular circumstance is documented in the knowledge base as knowledge. For example, under the circumstances of severe exposure category of rain and when roof slope exceeds 6m in length, interlocking tiles or slates are preferred for roof covering material. Inference engine It uses IF-THEN production rule along with a forward-chaining reasoning mechanism to search design decision rules for selecting the appropriate combinations of materials based on the knowledge base and the database.
It also helps to narrow down the search space of the database. User interface It interacts with the users and processes. It accepts input from users and activates the processes to produce the output to the users. Figure 3: Roof sub elements Step 2: Knowledge elicitation The selection process is conceptualised from domain experts by conducting a series of structured interviews.
Performance criteria are identified from literature and validated through domain experts. The performance criteria for roof insulation are considered separately as it has a significant impact on internal comfort and energy consumption.
The table representing the framework for DSS is presented below. While MIS was dealing with processes like billing, inventory control and accounts and relied on accurate data that was obtained primarily from sources internal to the organisation, DSS on the other hand depended on external data as many of its applications were strategic in nature Fig 1.
This meant that the data was often ill-defined and required a different approaches. Courtney defines a more developed model of decision-making in a DSS environment in Fig. Here, the emphasis is shifted to the model development and problem analysis. Once the problem is recognised, mathematical models are built on the basis of the problem that facilitate the creation of alternate solutions, and models are then developed to analyse the various alternatives.
While no decision within this structure is clear-cut and the phases in the above process often overlap and blend together Courtney With time, DSS has further evolved to even include additional concepts and views and facilitate support of decision- making in team problem-solving.
The GSS includes brainstorming, idea evaluation and communication facilities into its mix to provide a well-rounded support to group decisions. Applications include engineering projects, development projects, scientific communities, company planning, crisis management and conflict resolution Rathwell and Burns Knowledge Management and the DSS As discussed above, the inclusion of knowledge management and its principles is what truly enables DSS to provide support for semi- and ill-structured problems.
In this section, we review the literature on Knowledge Management and investigate its connection with DSS. As defined above, Knowledge Management is essentially the process of capturing tacit knowledge and converting it into explicit knowledge. Insights, intuition, and subjective knowledge of an individual that the individual develops while being in an activity or profession are also considered tacit knowledge Nonaka and Takeuchi Explicit knowledge, on the other hand, is formal knowledge that can be expressed through language, symbols or rules etc.
It is quantifiable data that can be weighted through mathematical models or universal principles Nonaka and Takeuchi New knowledge can be created through synergising the conversion of tacit knowledge into explicit knowledge. Socialisation is the sharing of tacit knowledge. It occurs through workers exchanging with others the experiences, technical skills, mental models, and other forms of tacit knowledge.
Knowledge sharing in the workplace is often implemented with the assistance of IT, through digitised filming of the physical demonstration of a process. For example, a process might be recorded as a video and uploaded on the internet for anyone interested in learning the process to access. Such demonstration or how-to videos can facilitate the sharing of the knowledge. Artificial Intelligence AI has also been used as an innovative method that facilitates sharing of tacit knowledge Nemati, Steiger, Iyer and Herschel Externalisation or Articulation is the conversion of the tacit knowledge to explicit knowledge.
It occurs through and is largely facilitated by the DSS systems that an organisation utilises. One such example is the brainstorming of GSS. GSS brainstorming sessions enable the participants to formally state a problem and provide ideas as solutions. The ideas are then anonymously relayed without evaluative comments to the other participants.
They then provide their own enhancements and modifications and facilitate a stream of related and meaningful ideas that are directed toward solving the stated problem. After the generation of ideas, evaluation of the specific ideas usually takes place. The evaluations typically include a concise list of things the participants like and dislike about a particular idea, along with the reason why the participants thinks so. The group then addresses these concerns and works towards a valid and universally agreed solution to the stated problem that might be implemented.
The information collected from the ideas is stored formally in form of text or other data for future use. The storage of information is the catalyst to converting explicit knowledge into new knowledge. This process is called integration or leveraging. In the example of brainstorming, similar problems in the future could be directly addressed through earlier cases of successful implementations derived from the brainstorming discussions, thus generating new knowledge.
AI is often used at this stage too. GSS brainstorming sessions that are stored as text streams can be accessed and analysed through text mining software. This can enable data mining and searches based on provided keywords, related concepts, clusters of similar ideas, etc. The last stage of the Knowledge Management process is internalisation: converting explicit knowledge to implicit knowledge; here too DSS can help.
One method is by modifying the internal mental model of the knowledge worker. Such mental models are often used by knowledge workers as a performance guide in specified situations. DSS can bring about the desired change in this mental model. DSS can help in the modification of a knowledge worker method of acknowledgment of new relationships between key factors that facilitate a new discovery, thus building a model for logic where such new information is automatically internalised.
NSS are often considered a branch of GSS that involves use of computer technologies for facilitating negotiations. Rathwell and Burns define conflict resolution as one of the functions of GSS. The NSS is a system that formally addresses conflicts and provides decision- making support for negotiations. Kautish and Thapiyal classify ISS into two generations — the first one uses rule-based expert systems and the other utilises futuristic technologies like fuzzy logic, neural networks, and genetic algorithms.
The link between KM and Strategic Management is also another heavily researched among academics. In the highly competitive and global environment of modern organisations, Huang argues Knowledge to be a key asset through which competitive advantage is gained and maintained. Strategy has been often defined as the comprehensive, unified, and integrated plan that is developed to ensure the objectives of the organisation are achieved Glueck, This plan is impossible to be developed without the right information available to the strategic planners.
Strategic Planning is therefore an information-intensive process. Data regarding the internal and external factors, which are related to the organisation and the environment, and the processing of such data, are therefore vital for making strategic decisions. This means that the organisation must know what data to collect, something that is often referred to as strategic knowledge acquisition Pietrzak, Paliszkiewicz, Jalosinski and Brzozowski Pietrzak, Paliszkiewicz, Jalosinski and Brzozowski in a diagram have represented how strategic knowledge acquisition as a key element of creating superior performance Fig.
Fig: 4. Strategic knowledge acquisition as a key element of creating superior performance. The link between knowledge management and strategy is therefore considered to be very important for building an effective strategic plan. According to Pietrzak, Paliszkiewicz, Jalosinski and Brzozowski , the external environment is a key driver to the strategy.
0コメント