Supporting decisions in medical applications: the knowledge management perspective

5K+ CT Images on Fractured Limbs: A Dataset for Medical Imaging Research

Imaging techniques widely use Computed Tomography (CT) scans for various purposes, such as screening, diagnosis, and decision-making. Of all, it holds true for bone injuries. To build fully automated Computer-Aided Detection (CADe) and Diagnosis (CADx) tools and techniques, it requires fairly large amount of data (with gold standard). Therefore, in this paper, since state-of-the-art works relied on small dataset, we introduced a CT image dataset on limbs that is designed to understand bone injuries. Our dataset is a collection of 24 patient-specific CT cases having fractures at upper and lower limbs. From upper limbs, 8 cases were collected from bones in/around the shoulder (left and right). Similarly, from lower limbs, 16 cases were collected from knees (left and right). Altogether, 5684 CT images (upper limbs: 2057 and lower limbs: 3627) were collected. Each patient-specific CT case is composed of maximum 257 scans/slices in average. Of all, clinically approved annotations were made on every 10th slices, resulting in 1787 images. Importantly, no fractured limbs were missed in our annotation. Besides, to avoid privacy and confidential issues, patient-related information were deleted. The proposed dataset could be a promising resource for the medical imaging research community, where imaging techniques are employed for various purposes. To the best of our knowledge, this is the first time 5K⁺ CT images on fractured limbs are provided for research and educational purposes.

Visual Interpretation of Convolutional Neural Network Predictions in Classifying Medical Image Modalities

Deep learning (DL) methods are increasingly being applied for developing reliable computer-aided detection (CADe), diagnosis (CADx), and information retrieval algorithms. However, challenges in interpreting and explaining the learned behavior of the DL models hinders their adoption and use in real-world systems. In this study, we propose a novel method called “Class-selective Relevance Mapping” (CRM) for localizing and visualizing discriminative regions of interest (ROI) within a medical image. Such visualizations offer improved explanation of the convolutional neural network (CNN)-based DL model predictions. We demonstrate CRM effectiveness in classifying medical imaging modalities toward automatically labeling them for visual information retrieval applications. The CRM is based on linear sum of incremental mean squared errors (MSE) calculated at the output layer of the CNN model. It measures both positive and negative contributions of each spatial element in the feature maps produced from the last convolution layer leading to correct classification of an input image. A series of experiments on a “multi-modality” CNN model designed for classifying seven different types of image modalities shows that the proposed method is significantly better in detecting and localizing the discriminative ROIs than other state of the art class-activation methods. Further, to visualize its effectiveness we generate “class-specific” ROI maps by averaging the CRM scores of images in each modality class, and characterize the visual explanation through their different size, shape, and location for our multi-modality CNN model that achieved over 98% performance on a dataset constructed from publicly available images.

Informal caregivers of older people recovering from surgery for hip fractures caused by a fall: fall prevention

The objectives of this study were to investigate the sociodemographic characteristics of informal caregivers of elderly persons who had undergone surgery for hip fractures caused by a fall, explore the level of caregiver's knowledge regarding fall prevention, and assess the relationship between this knowledge and the use of preventative measures in practice. This investigation consists of a cross-sectional study using nonprobability sampling methods conducted over a period of 12 months and involving 89 caregivers. The majority of caregivers were female (76.4%) and sons or daughters of the patients (64%). Environmental modification was the predominant preventative measure used by caregivers (88.2%). 58.1% of caregivers believed it was possible to prevent falls in the elderly and there was a significant association (p = 0,002) between believing it was possible to prevent falls and carrying out modifications in the home and/or to the daily routine of the older person. Informal caregivers with wide or partial knowledge of fall prevention put preventative measures into practice. These findings demonstrate that the number of falls among older persons could be significantly reduced if health care programmes widened their actions to include the guiding principles of the WHO falls prevention model.

The role of nursing informatics on promoting quality of health care and the need for appropriate education

In today's dynamic health systems, technology plays an important role in education and nursing work. So it seems necessary to study the role of nurses and highlight the need for appropriate information technology educational programs to integrate with the ever-increasing pace of technology. A review accompanied by an extensive literature search in databases and a library search focused on the keywords were used. The criteria used for selecting studies primarily focused on nursing informatics and the importance of expertise in the effective use of information technology in all aspects of the nursing profession. In a critical assessment of emerging technologies, the key elements of nursing informatics implementation were considered as healthcare promotion, advanced systems, internet and network. In view of the nature and the development of the information age, it is required to receive necessary IT training for all categories of nurses. Due to the fast development of technology, in order to effectively take advantage of information technology in nursing outcome and quality of health care and to empower nurses; educational arrangement is recommended to set short-term and long-term specialized courses focusing on four target groups: studying, working, graduate, senior undergraduate, and graduate doctoral. The result of this study is expected to assist educational providers with program development.

E-pharmacovigilance: development and implementation of a computable knowledge base to identify adverse drug reactions

AIMS

Computer-assisted signal generation is an important issue for the prevention of adverse drug reactions (ADRs). However, due to poor standardization of patients' medical data and a lack of computable medical drug knowledge the specificity of computerized decision support systems for early ADR detection is too low and thus those systems are not yet implemented in daily clinical practice. We report on a method to formalize knowledge about ADRs based on the Summary of Product Characteristics (SmPCs) and linking them with structured patient data to generate safety signals automatically and with high sensitivity and specificity.

METHODS

A computable ADR knowledge base (ADR-KB) that inherently contains standardized concepts for ADRs (WHO-ART), drugs (ATC) and laboratory test results (LOINC) was built. The system was evaluated in study populations of paediatric and internal medicine inpatients.

RESULTS

A total of 262 different ADR concepts related to laboratory findings were linked to 212 LOINC terms. The ADR knowledge base was retrospectively applied to a study population of 970 admissions (474 internal and 496 paediatric patients), who underwent intensive ADR surveillance. The specificity increased from 7% without ADR-KB up to 73% in internal patients and from 19.6% up to 91% in paediatric inpatients, respectively.

CONCLUSIONS

This study shows that contextual linkage of patients' medication data with laboratory test results is a useful and reasonable instrument for computer-assisted ADR detection and a valuable step towards a systematic drug safety process. The system enables automated detection of ADRs during clinical practice with a quality close to intensive chart review.

Knowledge management in health: a systematic literature review

Knowledge has been used as a resource for intelligent and effective action planning in organizations. Interest in research on knowledge management processes has intensified in different areas. A systematic literature review was accomplished, based on the question: what are the contributions of Brazilian and international journal publications on knowledge management in health? The sample totaled 32 items that complied with the inclusion criteria. The results showed that 78% of journals that published on the theme are international, 77% of researchers work in higher education and 65% have a Ph.D. The texts gave rise to five thematic categories, mainly: development of knowledge management systems in health (37.5%), discussion of knowledge management application in health (28.1%) and nurses' function in knowledge management (18.7%).

A MEDICAL KNOWLEDGE SERVICE SYSTEM FOR CROSS-ORGANIZATIONAL HEALTHCARE COLLABORATION

Collaboration among healthcare organizations depends on coordination, communication and control among healthcare organizations and effective sharing of medical information and knowledge.

Medical services are knowledge-intensive activities. All information, knowledge, techniques and experience should be integrated, managed and shared using the Internet and information technology. Overall medical service quality and efficiency would be improved markedly if medical professionals and staff at different healthcare organizations could use and share medical knowledge resources. Therefore, a collaborative medical knowledge service would promote medical service quality.

This study presents a novel medical knowledge service system for cross-organizational healthcare collaboration such that all medical professionals and staff at different healthcare organizations could capture, store, manage, integrate and share medical knowledge. This system should improve medical service quality and efficiency, and promote competition in the healthcare industry. Thus, this study (i) proposes a collaborative medical knowledge service model, (ii) designs a collaborative medical knowledge service system framework, (iii) develops this proposed system, and (iv) evaluates the developed system based on user satisfaction.

Collaboration-based medical knowledge recommendation

PURPOSE

Clinicians rely on a large amount of medical knowledge when performing clinical work. In clinical environment, clinical organizations must exploit effective methods of seeking and recommending appropriate medical knowledge in order to help clinicians perform their work.

METHOD

Aiming at supporting medical knowledge search more accurately and realistically, this paper proposes a collaboration-based medical knowledge recommendation approach. In particular, the proposed approach generates clinician trust profile based on the measure of trust factors implicitly from clinicians' past rating behaviors on knowledge items. And then the generated clinician trust profile is incorporated into collaborative filtering techniques to improve the quality of medical knowledge recommendation, to solve the information-overload problem by suggesting knowledge items of interest to clinicians.

RESULTS

Two case studies are conducted at Zhejiang Huzhou Central Hospital of China. One case study is about the drug recommendation hold in the endocrinology department of the hospital. The experimental dataset records 16 clinicians' drug prescribing tracks in six months. This case study shows a proof-of-concept of the proposed approach. The other case study addresses the problem of radiological computed tomography (CT)-scan report recommendation. In particular, 30 pieces of CT-scan examinational reports about cerebral hemorrhage patients are collected from electronic medical record systems of the hospital, and are evaluated and rated by 19 radiologists of the radiology department and 7 clinicians of the neurology department, respectively. This case study provides some confidence the proposed approach will scale up.

CONCLUSION

The experimental results show that the proposed approach performs well in recommending medical knowledge items of interest to clinicians, which indicates that the proposed approach is feasible in clinical practice.

Towards case-based medical learning in radiological decision making using content-based image retrieval

BACKGROUND

Radiologists' training is based on intensive practice and can be improved with the use of diagnostic training systems. However, existing systems typically require laboriously prepared training cases and lack integration into the clinical environment with a proper learning scenario. Consequently, diagnostic training systems advancing decision-making skills are not well established in radiological education.

METHODS

We investigated didactic concepts and appraised methods appropriate to the radiology domain, as follows: (i) Adult learning theories stress the importance of work-related practice gained in a team of problem-solvers; (ii) Case-based reasoning (CBR) parallels the human problem-solving process; (iii) Content-based image retrieval (CBIR) can be useful for computer-aided diagnosis (CAD). To overcome the known drawbacks of existing learning systems, we developed the concept of image-based case retrieval for radiological education (IBCR-RE). The IBCR-RE diagnostic training is embedded into a didactic framework based on the Seven Jump approach, which is well established in problem-based learning (PBL). In order to provide a learning environment that is as similar as possible to radiological practice, we have analysed the radiological workflow and environment.

RESULTS

We mapped the IBCR-RE diagnostic training approach into the Image Retrieval in Medical Applications (IRMA) framework, resulting in the proposed concept of the IRMAdiag training application. IRMAdiag makes use of the modular structure of IRMA and comprises (i) the IRMA core, i.e., the IRMA CBIR engine; and (ii) the IRMAcon viewer. We propose embedding IRMAdiag into hospital information technology (IT) infrastructure using the standard protocols Digital Imaging and Communications in Medicine (DICOM) and Health Level Seven (HL7). Furthermore, we present a case description and a scheme of planned evaluations to comprehensively assess the system.

CONCLUSIONS

The IBCR-RE paradigm incorporates a novel combination of essential aspects of diagnostic learning in radiology: (i) Provision of work-relevant experiences in a training environment integrated into the radiologist's working context; (ii) Up-to-date training cases that do not require cumbersome preparation because they are provided by routinely generated electronic medical records; (iii) Support of the way adults learn while remaining suitable for the patient- and problem-oriented nature of medicine. Future work will address unanswered questions to complete the implementation of the IRMAdiag trainer.

A new integrated model of clinical reasoning: development, description and preliminary assessment in patients with stroke

PURPOSE

The main objective was the development and collection of preliminary data on the application of a new integrated clinical reasoning model (Anadysis) with patients suffering a stroke or Transient Ischemic Attack (TIA).

METHOD

Twelve healthcare professionals working in the neurological and the Accident and Emergency (A&E) units of an acute general hospital participated and experimental control was achieved by employing a pre-test post-test control group experimental design. Members of the control group used the current reasoning model of their discipline whereas the new integrated model was used by the members of the experimental group irrespective of their professions. Outcomes were measured by scoring on a protocol derived from the UK National Clinical Guidelines for Stroke divided into the three main clinical reasoning processes.

RESULTS

Collectively, data from 186 protocols based on the medical records of 49 patients showed that median percentages of correct responses in clinical reasoning were substantially higher for the experimental group by using the new integrated model.

CONCLUSIONS

This study will inform the healthcare professionals about a new effective integrated clinical reasoning model which incorporates the complex processes of diagnosis, planning and treatment as a whole. This study may also become an important consideration in the further development of clinical decision support systems within the scientific area of health informatics.

Using computer aided case based reasoning to support clinical reasoning in community occupational therapy

Community occupational therapists have long been involved in the provision of environmental control systems. Diverse electronic technologies with the potential to improve the health and quality of life of selected clients have developed rapidly in recent years. Occupational therapists employ clinical reasoning in order to determine the most appropriate technology to meet the needs of individual clients. This paper describes a number of the drivers that may increase the adoption of information and communication technologies in the occupational therapy profession. It outlines case based reasoning as understood in the domains of expert systems and knowledge management and presents the preliminary results of an ongoing investigation into the potential of a prototype computer aided case based reasoning tool to support the clinical reasoning of community occupational therapists in the process of assisting clients to choose home electronic assistive or smart house technology.

Research of Knowledge-sharing Mechanism Oriented to Hospital Management

This paper, aiming at the characteristics of hospital management in terms of knowledge management, firstly analyzes the importance of knowledge sharing and the obstacles which exist. In theory it provides knowledge sharing mechanism model and make a construction in culture, organization, motivation mechanism and technology, etc.. The paper perfects the research of knowledge management in hospital management and offers beneficial references for the improvement of service quality and efficiency.

Software and expert system for the management of chronic hepatitis B

Whereas the doubling time of overall biomedical knowledge bases has been estimated at about 19 years, the body of indexed information related to HBV has doubled in the last 8 years; the one related to HBV and antivirals has doubled in the last 5 years and the one related to Interferon and contraindications has doubled in less than 48 months. In Hepatology, as well as in other fast changing areas of medicine, the demand that clinical decision should always be based on the best verified knowledge available, is becoming more and more difficult to comply with. The Italian network of competence for hepatic diseases (Liver Unit Networks Association or LUNA) was established in 2003 with the patronage of the Italian Ministry of Health, with the primary goal of promoting advanced clinical research and real-time information exchange among the participating centres, facilitating knowledge sharing and identification of best practices. The ICT infrastructure designed for this purpose includes four sets of online accessible software tools:

Modelling a decision-support system for oncology using rule-based and case-based reasoning methodologies

In most hospital medical units, multidisciplinary committees meet weekly to discuss their patients' cases. The medical experts base their decisions on three sources of information. First, they check if their patient complies with existing guidelines. Failing these, the medical experts will base their therapeutic decisions on the cases of similar patients that they have treated in the past. We propose a multi-modal reasoning decision-support system based on both guideline and case series, which will automatically compare the patient's case to the corresponding guideline, then to other cases, and retrieve similar cases. The general structure of the system is presented here, the domain of application being oncology. As the patients' records are not currently stored in a database in a format which is directly accessible, an object-oriented model is proposed, which includes prognosis factors currently tested in clinical trials, well-established ones, and a description of the illness episodes. The system is designed to be a data warehouse. Such a system does not exist in the literature. Future work will be needed to define the similarity measures, and to connect the system to the current database.