R.N.G. Naguib

Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa

The development of an automated algorithm for the categorization of normal and cancerous colon mucosa is reported. Six features based on texture analysis were studied. They were derived using the co-occurrence matrix and were angular second moment, entropy, contrast, inverse difference moment, dissimilarity, and correlation. Optical density was also studied. Forty-four normal images and 58 cancerous images from sections of the colon were analyzed. These two groups were split equally into two subgroups: one set was used for supervised training and the other to test the classification algorithm. A stepwise selection procedure showed that correlation and entropy were the features that discriminated most strongly between normal and cancerous tissue (P<0.0001). A parametric linear-discriminate function was used to determine the classification rule. For the training set, a sensitivity and specificity of 93.1% and 81.8%, respectively, were achieved, with an overall accuracy of 88.2%. These results mere confirmed with the test set, with a sensitivity and specificity of 93.1% and 86.4%, respectively, and an overall accuracy of 90.2%.

A fuzzy logic based-method for prognostic decision making in breast and prostate cancers

Accurate and reliable decision making in oncological prognosis can help in the planning of suitable surgery and therapy, and generally, improve patient management through the different stages of the disease. In recent years, several prognostic markers have been used as indicators of disease progression in oncology. However, the rapid increase in the discovery of novel prognostic markers resulting from the development in medical technology, has dictated the need for developing reliable methods for extracting clinically significant markers where complex and nonlinear interactions between these markers naturally exist. The aim of this paper is to investigate the fuzzy k-nearest neighbor (FK-NN) classifier as a fuzzy logic method that provides a certainty degree for prognostic decision and assessment of the markers, and to compare it with: 1) logistic regression as a statistical method and 2) multilayer feedforward backpropagation neural networks an artificial neural-network tool, the latter two techniques having been widely used for oncological prognosis. In order to achieve this aim, breast and prostate cancer data sets are considered as benchmarks for this analysis. The overall results obtained indicate that the FK-NN-based method yields the highest predictive accuracy, and that it has produced a more reliable prognostic marker model than both the statistical and artificial neural-network-based methods.

Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management

From the Publisher: The potential value of artificial neural networks (ANN) as a predictor of malignancy has begun to received increased recognition. Research and case studies can be found scattered throughout a multitude of journals. Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management brings together the work of top researchers - primarily clinicians - who present the results of their state-of-the-art work with ANNs as applied to nearly all major areas of cancer for diagnosis, prognosis, and management of the disease.The book introduces the theory of neural networks and the method of their application in oncology. It is not an exercise in ANN research, but the presentation of a new technique for diagnosing and determining the treatment of cancers. The authors have included almost all cancers for which there exists ANN applications. When the data available is ill-defined and the development of an algorithmic solution difficult, neural networks provide a non-linear approach which helps sift through the maze of information and arrive at a reasonable solution.Highly interdisciplinary in nature, this book provides comprehensive coverage of the most important materials relating to the applications of ANNs in the cancer field. With contributions from prominent research centers worldwide, it serves as an introduction to how neural networks can be used for accurate prediction or diagnosis and shows why neural networks are more accurate. Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management gives you an understanding of this new tool, its applications, and when it should be used.

Neural network analysis of combined conventional and experimental prognostic markers in prostate cancer: a pilot study.

Prostate cancer is the second most common malignancy in men in the UK. The disease is unpredictable in its behaviour and, at present, no single investigative method allows clinicians to differentiate between tumours that will progress and those that will remain quiescent. There is an increasing need for novel means to predict prognosis and outcome of the disease. The aim of this study was to assess the value of artificial neural networks in predicting outcome in prostate cancer in comparison with statistical methods, using a combination of conventional and experimental biological markers. Forty-one patients with different stages and grades of prostate cancer undergoing a variety of treatments were analysed. Artificial neural networks were used as follows: eight input neurons consisting of six conventional factors (age, stage, bone scan findings, grade, serum PSA, treatment) and two experimental markers (immunostaining for bcl-2 and p53, which are both apoptosis-regulating genes). Twenty-one patients were used for training and 20 for testing. A total of 80% of the patients were correctly classified regarding outcome using the combination of factors. When both bcl-2 and p53 immunoreactivity were excluded from the analysis, correct prediction of the outcome was achieved in only 60% of the patients (P = 0.0032). This study was able to demonstrate the value of artificial neural networks in the analysis of prognostic markers in prostate cancer. In addition, the potential for using this technology to evaluate novel markers is highlighted. Further large-scale analyses are required to incorporate this methodology into routine clinical practice.

Merger of knowledge management and information technology in healthcare: opportunities and challenges

In the last 10 years, the Information and Communication Technologies (ICTs) revolution has redefined the structure of the 21st century healthcare organization. It is clear that the 21st century healthcare organization will bring about new healthcare services and that traditional management and technological concepts would not be the appropriate conduit for disseminating these new healthcare services. The fundamental challenge faced by the 21st century clinical practitioner is to acquire proficiency in understanding and interpreting clinical information so as to attain knowledge and wisdom. An additional challenge that must be considered is that clinical practitioners make potentially life-saving decisions whilst attempting to deal with large amounts of clinical data. We focus on the emergence of telehealth as an alternative implementation for transfer of medical information using futuristic Information and Communication Technologies (ICT). We contend that current healthcare applications are being used in a static manner; futuristic applications will need to be dynamic in nature and would call for the transfer of context-based healthcare information. A Knowledge Management (KM) solution would allow healthcare institutions to give clinical data context, so as to allow knowledge derivation for more effective clinical diagnosis. It would also provide a mechanism for effective transfer of the acquired knowledge in order to aid healthcare workers as and when required Using data inputs from our collaborating organization, Applied Network Solutions (ANS), we argue that healthcare institutions that integrate KM and ICT into their main organizational processes are more likely to survive and prosper. These organizations would have a profound understanding of how to use clinical information for creating value in tangible and intangible terms.

Electronic health records approaches and challenges: a comparison between Malaysia and four East Asian countries

An integrated Lifetime Health Record (LHR) is fundamental for achieving seamless and continuous access to patient medical information and for the continuum of care. However, the aim has not yet been fully realised. The efforts are actively progressing around the globe. Every stage of the development of the LHR initiatives had presented peculiar challenges. The best lessons in life are those of someone elses experiences. This paper presents an overview of the development approaches undertaken by four East Asian countries in implementing a national Electronic Health Record (EHR) in the public health system. The major challenges elicited from the review including integration efforts, process reengineering, funding, people, and law and regulation will be presented, compared, discussed and used as lessons learned for the further development of the Malaysian integrated LHR.

DNA ploidy and cell cycle distribution of breast cancer aspirate cells measured by image cytometry and analyzed by artificial neural networks for their prognostic significance

Chromosomal abnormalities are commonly associated with cancer, and their importance in the pathogenesis of the disease has been well recognized. Also recognized in recent years is the possibility that, together with chromosomal abnormalities, DNA ploidy of breast cancer aspirate cells, measured by image cytometric techniques, may correlate with prognosis of the disease. Here, we have examined the use of an artificial neural network to predict: 1) subclinical metastatic disease in the regional lymph nodes and 2) histological assessment, through the analysis of data obtained by image cytometric techniques of fine needle aspirates of breast tumors. The cellular features considered were: 1) DNA ploidy measured in terms of nuclear DNA content as well as by cell cycle distribution; 2) size of the S-phase fraction; and 3) nuclear pleomorphism. A further objective of the study was to analyze individual markers in terms of impact significance on predicting outcome in both cases. DNA ploidy, indicated by cell cycle distribution, was found markedly to influence the prediction of nodal spread of breast cancer, and nuclear pleomorphism to a lesser degree. Furthermore, a comparison between histological assessment and artificial neural network prediction shows a closer correlation between the neural approach and the development of further metastases as indicated in subsequent follow-up, than does histological assessment.

Workflow management systems: the healthcare technology of the future?

In recent years, healthcare institutions have had problems accessing and maintaining the large amounts of data they deal with. This paper identifies current approaches and technologies which relate to patient administration systems. It argues that, in the near future, WWW-based multimedia patient administration systems would become the norm for healthcare institutions. The development and acceptance of web-based multimedia patient administration systems is likely to aggravate the problem of healthcare institutions being flooded with large amounts of clinical data. A large amount of clinical procedures relating to patient management are repetitive and Workflow Management Systems (WFMS) can automate these repeated activities. We believe that the introduction of WFMS would enable healthcare institutions to face this challenge of transforming large amounts of medical data into contextually relevant clinical information. The central contention of this paper is that there is a dynamic connection between healthcare, workflow and internet technologies, which is being ignored. This paper further establishes that it is possible to build a virtual electronic health record database based on the client server architecture using current internet and object-oriented (OO) technologies.

A fuzzy ambient intelligent agents approach for monitoring disease progression of dementia patients

In this paper, we discuss the development of an ambient intelligent-based system for the monitoring of dementia patients living in their own homes. Within this system groups of unobtrusive wireless sensor devices can be deployed at specific locations within a patient’s home and accessed via standardized interfaces provided through an open middleware platform. For each sensor group intelligent agents are used to learn fuzzy rules, which model the patient’s habitual behaviours in the environment. An online rule adaptation technique is applied to facilitate short-term tuning of the learnt behaviours, and long-term tracking of behaviour changes which could be due to the effects of cognitive decline caused from dementia. The proposed system reports macro level behaviour changes and micro level perception drift to care providers to enable them to make better-informed assessments of the patient’s cognitive abilities and changing care needs. We demonstrate experiments in a real pervasive computing environment, in which our intelligent agent approach can learn to model the user’s behaviours and allow online adaptation of its model to better approximate the learnt behaviours and identify long-term macro-level behaviour changes, which could be attributed to cognitive decline. We also show an example of how the user’s perceptions for thermal comfort may be captured and visualised to provide a means by which micro-level perception changes can be monitored.

A telematic system for oncology based on electronic health and patient records

The NHS in the UK recognizes six levels of IT adoption in healthcare systems. Most current healthcare systems are at Level 1 (clinical administrative data), with some notable specialized exceptions. The telematic system for oncology is at Level 6 (advanced multimedia and telematics). Oncology is a particularly complicated area, as it draws on most of the other diagnostic systems and also has a number of different treatment regimes, each of which may have their own system. Relevant information is extracted from the underlying systems on a regular basis and stored on a server that can be accessed by various parties. Regarding the electronic health record (EHR), a centralized national directory would need to be in place to show the locations of individual electronic patient records (EPRs). In order to clearly capture and specify the requirements of the telematic system for oncology, it was decided that a framework based on Ariadne, especially designed for describing computer-supported cooperative work (CSCW) should be used. The use of such a framework captures the workflow, clearly showing the tasks of each actor within the processes, as well as the resources needed by each actor. The Ariadne framework was developed as part of a European ESPRIT research project (No. 6225) which studied computational notations for representing CSCW. Ariadne can be considered as a notation for defining a multi-agent architecture for supporting articulation work among cooperating actors.