Nosrat Shahsavar

Requirements and prototyping of a home health care application based on emerging java technology

IT support for home health care is an expanding area within health care IT development. Home health care differs from other in- or outpatient care delivery forms in a number of ways, and thus, the introduction of home health care applications must be based on a rigorous analysis of necessary requirements to secure safe and reliable health care. This article reports early experiences from the development of a home health care application based on emerging JAVA technologies. A prototype application for the follow-up of diabetes patients is presented and discussed in relation to a list of general requirements on home health care applications.

Predicting Metastasis in Breast Cancer: Comparing a Decision Tree with Domain Experts

Breast malignancy is the second most common cause of cancer death among women in Western countries. Identifying high-risk patients is vital in order to provide them with specialized treatment. In some situations, such as when access to experienced oncologists is not possible, decision support methods can be helpful in predicting the recurrence of cancer. Three thousand six hundred ninety-nine breast cancer patients admitted in south-east Sweden from 1986 to 1995 were studied. A decision tree was trained with all patients except for 100 cases and tested with those 100 cases. Two domain experts were asked for their opinions about the probability of recurrence of a certain outcome for these 100 patients. ROC curves, area under the ROC curves, and calibration for predictions were computed and compared. After comparing the predictions from a model built by data mining with predictions made by two domain experts, no significant differences were noted. In situations where experienced oncologists are not available, predictive models created with data mining techniques can be used to support physicians in decision making with acceptable accuracy.

Evaluation of a knowledge-based decision-support system for ventilator therapy management

Evaluation of knowledge-based systems differs from that of conventional systems in terms of verification and validation techniques. Furthermore, evaluating medical decision-support systems is difficult because the field is thus far comparatively unexplored. This paper presents an evaluation of a medical knowledge-based system called VentEx that supports decision-making in the management of ventilator therapy. Real patient data from 1300 hours of patient care involving 12 patients with 6 diagnoses are used to validate the knowledge base. The results range from 4.5% to 15.6% disagreement between the setting recommendations produced by VentEx and a gold standard, and 22.2% disagreement for recommendations for weaning. A comparison between the standard and two physicians showed that VentEx produced advice of the same quality as the physicians.

Pre-compiling medical logic modules into C++ in building medical decision support systems.

Development of medical knowledge bases is a time-consuming process, and no single medical institution can develop medical knowledge bases covering all areas of medicine. The use of medical knowledge representation standards such as the Arden Syntax is an attempt to enhance the writability and readability of computer-stored knowledge and facilitate transfer and sharing among institutions. A method for the realisation of decision support systems based on knowledge formulated according to the Arden Syntax is presented. An essential tool in this process is a medical logic module (MLM) pre-compiler, translating MLMs into an object-oriented programming language, C++. Advantages of the C++ approach compared with other alternatives are discussed.

Integrating knowledge-based technology into computer aided ventilation systems

A knowledge-based decision support system for respirator treatment, the KUSIVAR system, has been designed in cooperation between hospital, university and industry. Changes in patient data from respirator and monitoring equipment trigger a computer program that generates advice to the staff concerning e.g. therapy modes and respirator settings using expert systems and process control technology.A prototype has been built on an advanced development workstation, the Unisys Explorer, using the software Knowledge Engineering Environment (KEE). The clinical version is implemented on an Intel 80396-based microcomputer connected on-line via a data-acquisition processor to the respirator. The decision support software is implemented as a module under the Microsoft Windows multitasking environment and communicates with modules for data acquisition, database, handling and data presentation by means of message passing using the Windows Dynamic Data Exchange protocol. The modules present coherent user interfaces by conforming to Microsoft Windows standards.The knowledge base is being extensively validated by an expert group in the ICU and the system will be evaluated through animal experiments and clinical studies.

A data pre-processing method to increase efficiency and accuracy in data mining

In medicine, data mining methods such as Decision Tree Induction (DTI) can be trained for extracting rules to predict the outcomes of new patients. However, incompleteness and high dimensionality of stored data are a problem. Canonical Correlation Analysis (CCA) can be used prior to DTI as a dimension reduction technique to preserve the character of the original data by omitting non-essential data. In this study, data from 3949 breast cancer patients were analysed. Raw data were cleaned by running a set of logical rules. Missing values were replaced using the Expectation Maximization algorithm. After dimension reduction with CCA, DTI was employed to analyse the resulting dataset. The validity of the predictive model was confirmed by ten-fold cross validation and the effect of pre-processing was analysed by applying DTI to data without pre-processing. Replacing missing values and using CCA for data reduction dramatically reduced the size of the resulting tree and increased the accuracy of the prediction of breast cancer recurrence.

Exploring cancer register data to find risk factors for recurrence of breast cancer – application of Canonical Correlation Analysis

BackgroundA common approach in exploring register data is to find relationships between outcomes and predictors by using multiple regression analysis (MRA). If there is more than one outcome variable, the analysis must then be repeated, and the results combined in some arbitrary fashion. In contrast, Canonical Correlation Analysis (CCA) has the ability to analyze multiple outcomes at the same time.One essential outcome after breast cancer treatment is recurrence of the disease. It is important to understand the relationship between different predictors and recurrence, including the time interval until recurrence. This study describes the application of CCA to find important predictors for two different outcomes for breast cancer patients, loco-regional recurrence and occurrence of distant metastasis and to decrease the number of variables in the sets of predictors and outcomes without decreasing the predictive strength of the model.MethodsData for 637 malignant breast cancer patients admitted in the south-east region of Sweden were analyzed. By using CCA and looking at the structure coefficients (loadings), relationships between tumor specifications and the two outcomes during different time intervals were analyzed and a correlation model was built.ResultsThe analysis successfully detected known predictors for breast cancer recurrence during the first two years and distant metastasis 2–4 years after diagnosis. Nottingham Histologic Grading (NHG) was the most important predictor, while age of the patient at the time of diagnosis was not an important predictor.ConclusionIn cancer registers with high dimensionality, CCA can be used for identifying the importance of risk factors for breast cancer recurrence. This technique can result in a model ready for further processing by data mining methods through reducing the number of variables to important ones.

VentEx: an on-line knowledge-based system to support ventilator management

This paper will demonstrate the clinical application of a knowledge-based decision-support system called VentEx for ventilator management. VentEx has been implemented using a knowledge-based development tool on a PC under the Microsoft Windows multitasking environment. It is integrated into a computer aided ventilator system including the Siemens Elema Servo Ventilator 900 C equipped with a Servo Computer Module 990 and the CO2 analyser 930. The system provides advanced ventilator monitoring with expert advice concerning ventilator strategy and settings based on data from on-line monitoring. The knowledge base has been primarily validated and the system has been clinically tested by the intensive care unit staff. Different approaches such as knowledge acquisition, representation and system integration have been outlined and discussed.

KAVE : a tool for knowledge acquisition to support artificial ventilation

A decision support system for artificial ventilation is being developed. One of the fundamental goals for this system is the application of the system when a domain expert is not present. Such a system requires a rich knowledge base. The knowledge acquisition process is often considered to be the bottleneck in acquiring such a complete knowledge base. Since no single available method, for example interviewing domain experts, is sufficient for removing this bottleneck, we have chosen a combination of different methods. The different backgrounds of knowledge engineers and domain experts could cause communication restrictions and difficulties between them, e.g. they might not understand each others knowledge domain and this will affect formulation of the knowledge. To solve this problem we needed a tool which supports both the knowledge engineer and the domain expert already from the initial phase of developing the knowledge base. We have developed a knowledge acquisition system called KAVE to elicit knowledge from domain experts and storing it in the knowledge base. KAVE is based on a domain specific conceptual model which is a result of cooperation between knowledge engineers and domain experts during identification, design and structuring of knowledge for this domain. KAVE includes a patient simulator to help validate knowledge in the knowledge base and a knowledge editor to facilitate refinement and maintenance of the knowledge base.

Non-compliance with a postmastectomy radiotherapy guideline: Decision tree and cause analysis

BackgroundThe guideline for postmastectomy radiotherapy (PMRT), which is prescribed to reduce recurrence of breast cancer in the chest wall and improve overall survival, is not always followed. Identifying and extracting important patterns of non-compliance are crucial in maintaining the quality of care in Oncology.MethodsAnalysis of 759 patients with malignant breast cancer using decision tree induction (DTI) found patterns of non-compliance with the guideline. The PMRT guideline was used to separate cases according to the recommendation to receive or not receive PMRT. The two groups of patients were analyzed separately. Resulting patterns were transformed into rules that were then compared with the reasons that were extracted by manual inspection of records for the non-compliant cases.ResultsAnalyzing patients in the group who should receive PMRT according to the guideline did not result in a robust decision tree. However, classification of the other group, patients who should not receive PMRT treatment according to the guideline, resulted in a tree with nine leaves and three of them were representing non-compliance with the guideline. In a comparison between rules resulting from these three non-compliant patterns and manual inspection of patient records, the following was found:In the decision tree, presence of perigland growth is the most important variable followed by number of malignantly invaded lymph nodes and level of Progesterone receptor. DNA index, age, size of the tumor and level of Estrogen receptor are also involved but with less importance. From manual inspection of the cases, the most frequent pattern for non-compliance is age above the threshold followed by near cut-off values for risk factors and unknown reasons.ConclusionComparison of patterns of non-compliance acquired from data mining and manual inspection of patient records demonstrates that not all of the non-compliances are repetitive or important. There are some overlaps between important variables acquired from manual inspection of patient records and data mining but they are not identical. Data mining can highlight non-compliance patterns valuable for guideline authors and for medical audit. Improving guidelines by using feedback from data mining can improve the quality of care in oncology.